Breast Cancer Detection using Explainable AI and Quantum Neural Network

Breast Cancer Detection using Explainable AI and Quantum Neural Network | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article Breast Cancer Detection using Explainable AI and Quantum Neural Network Saqqiya Waris, Javaria Amin, amina sarwar, muhammad Sharif, Mussarat Yasmeen This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4353973/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract The number one cancer type for women happens to be breast cancer. Women of any age are more likely to have this disorder because of where they live, their hormones, and the way they live. Women are more likely to be hurt by this. Many more women will have a better chance of living if breast cancer is found earlier. Computers can detect breast cancer early, improve treatment, and increase survival. Therefore, in this article, three models are proposed for the segmentation and classification of breast cancer. The DeepLabv3 model is trained on the fine-tuned hyperparameters for segmentation. The results are computed on BUSIS and DDSM datasets with the accuracy of 99% and 98% respectively. After that for classification of the breast cancer on different magnification levels. The explainable XAI model is designed on the selected fifteen layers and trained on the fine-tuned hyperparameters for breast cancer classification. This model provides the accuracy of. To analyze the classification outcomes quantum neural network is designed on the selected layers, number of Qubits, and hyperparameters. The classification results are computed on the BreakHis publicly dataset at magnification levels of 40x, 100x, 200x, and 400x. The proposed XAI model provides an accuracy of 96.67% and 100% using a quantum neural network for breast cancer classification. Qubits XAI Breast Classification Segmentation Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Figure 6 Figure 7 Figure 8 Figure 9 Figure 10 Figure 11 Figure 12 Figure 13 Figure 14 1. Introduction In women, it is diagnosed more frequently all over the world. Breast cancer can cause unhealthy lifestyles, hormonal issues, and environmental factors, which may cause high risk in women of all ages. Many women with breast cancer miss the chance to cure this disease at the initial stage. Having an early screening process is more important to improve the opportunity for survival. Early screening methods are Mammography, Magnetic Resonance Imaging (MRI), and Ultrasound to enhance women's chance of survival. These tools diagnose breast abnormalities in women [ 1 , 2 ].Ultrasound is cheaper and better at diagnosing. Manually finding breast tumors takes radiologists a long time. Computer-aided detection systems may assist medical professionals in making rapid choices thanks to recent advances in AI and Deep Learning models[ 3 ]. Computer-aided illness detection systems follow disease detection procedures. The most essential are Enhancement, segmentation, and feature extraction. The technology enhances ultrasound images during Enhancement. The technique can segment breast cancer ultrasound pictures during segmentation. The system can categorize the illness using the most essential aspects of Feature Extraction[ 4 ]. Data Augmentation will be used to make the ultrasound and mask images bigger[ 5 ]. Breast cancer is classified as benign or malignant. Benign is treatable, and patients with early identification have a good survival rate. The American Cancer Society predicts 43600 women and 530 men deaths in 2021[ 6 ]. Due to media and healthcare awareness, breast cancer mortality dropped 40% from 1989 to 2017. Mammography is the main breast cancer screening method in most countries. However, repeated procedure radiation exposure may induce additional cancers, making mammography unsafe for pregnant women. Ultrasound is widely used owing to its cost-effectiveness and diagnostic accuracy. Melanoma and benign breast cancers are difficult for radiologists to distinguish. Tumor color variation, morphological structure and form, and numerous tumors in ultrasound pictures are the main causes. Other issues include concealed tumors, poor ultrasound picture quality, and limited sensitivity in thick breast tissue. Radiologists may experience problems identifying breast cancers from healthy tissue. These worries may raise fake findings, needless tests, and women's deaths. CAD systems have been utilized in biological imaging for years as a non-invasive and flexible tool[ 3 ]. A skilled radiologist's ultrasound screening breast pictures are used by the automatic CAD system. The CAD system improved ultrasound picture clarity, medical assessment precision, and time and resource savings. Image gathering, preparation, segmentation, feature extraction, and classification are all things that most CAD systems need to do. It makes Active Contour, Thresholding, Clustering, Graph, Watershed, and deep learning. Classical methods use texture, form, color, local, global, and threshold qualities that are made by hand. Conventional methods use histogram normalization to increase the brightness of the original picture and then use a cutoff to separate the breast tumor area. With a lot of images as input, these methods don't work because they are time-consuming and need more computational power to perform task properly. Medical professionals employ segmentation algorithms to discover diseases, diagnose abnormalities, calculate tissue volume, assess anatomical structures, and treat patients. The precision of tumor segmentation and computation and the accuracy of image characteristics to classify benign or malignant tumors determine cancer diagnostic efficiency. This paper proposes a deep-learning architecture for tumor segmentation and uses machine learning (ML) techniques to classify tumors as benign or malignant. The segmentation findings help doctors decide whether a tumor is malignant or benign[ 7 ]. Many segmentation methods have been suggested recently[ 8 ]. This research examines semantic segmentation. Using GoogLeNet, a new deep learning-based segmentation architecture is developed. The 2014 Google research project Inception v1 launched the GoogLeNet[ 9 ]. DeepLabV3 + semantic segmentation and Xception depth separable convolution are used. Second, transfer learning and data augmentation increase convergence and model resilience. Third, network parameters are reduced by coding and decoding[ 10 ]. As computer vision and image processing have improved, deep learning-based neural network methods have become more common for making a good CAD system for separating breast tumors. Speckle noise, odd shapes, unclear tumor sites, and weak signals in ultrasound pictures are all problems that make it harder to identify CAD. The major contribution of the proposed research: Segmentation of breast cancer is a challenging task due to the variable size, and shape of the lesions. The DeepLabv3 + model is proposed and trained on the fine-tuned hyperparameters that more accurately segment the small lesion regions missed on the manual detection. Two models are proposed for classification of the breast cancer based on explainable XAI and quantum neural networks to analyze the result of classification. The explainable XAI-shape model is designed on the selected fifteen layers and trained on the fine-tuned hyperparameters for classification of the breast cancer. The quantum kernel provides help to learn the complex pattern as compared to the convolutional kernel. Therefore, the quantum neural network is developed on \(2\times 2\) Qubits, selected layers, and hyperparameters to provide help for more accurate classification of breast cancer. The structure of this article is such that, section 2 starts with an overview of the works of researchers that are considered related work, section 3 starts with an explanation of proposed models, section 4 starts with the discussion of results and section 5 concludes the research. 2. Related Work Breast cancer segmentation and classification have improved recently. The methodologies of ML can be included in image processing, feature extraction, selection, and classification tasks. In a rank-based ensemble method, Majumda et al.[ 11 ] compared the performance of the three CNN models named GoogleNet, VGG11, and MobileNetV3. They found that the architecture of CNN achieved an accuracy of 98.44% with 40x, 100x, 200x, and 400x magnification factors using the BreakHis dataset, which is publicly available, achieved an accuracy of 96.95% on the DDSM dataset for mammography and achieved an accuracy of 99.17% on the MIAS dataset mammograms. T. Pang et al.[ 12 ] confirmed a semi-supervised GAN breast ultrasound picture generation model. Synthetic datasets improve breast tumor classification accuracy by 90.41% and specificity by 87.94% over state-of-the-art methods. N. Toussaint et al. [ 13 ] proposed an effective model noise filter network (NF-Net) for breast tumor ultrasound image training with noisy labels. Labeling is improved by the teacher-student module. NF-Net classification models are 73% accurate and 74% F1-score. S. Kumar et al.[ 14 ] introduced a BreastNet18 model with feature fusion and a CSVM classifier that achieved 99.4% BUSI accuracy. Kowal et al.[ 15 ] used watershed algorithm (market controlled) and fully used convolutional networks for the segmentation approach. Segmentation was 90% accurate for benign and 86% for malignant. The classification model had 80.2–92.4% accuracy depending on the data type (malignant or benign). Resmini et al.[ 16 ] experimented with GA and SVM classifiers to select breast cancer models and features. Early breast cancer detection had 97.18% accuracy. Ayana et al.[ 17 ] demonstrated the different transfer learning which are using Adam, Adagrad, and SGD optimizers on the three pre-trained models which are named EfficientNetB2, InceptionV3, and ResNet50. ResNet50-Adagrad-based MSTL achieved an accuracy of 99 ± 0.612% on the dataset named Mendeley and achieved an accuracy of 98.7 ± 1.1% on the dataset named MT-Small. Rani, N et al.[ 18 ] used CBIS-DDSM and UPMC datasets to apply transfer learning with VGG16 and achieve 92%-95% accuracy. Salunkhe et al.[ 19 ] proposed Rapid Tri-Net for breast histological image classification, which achieved 99.79%, 99.8%, 99.73%, and 99.76% accuracy with the BreakHis dataset. Various models were proposed by Zerouaoui et al.[ 20 ] BreakHis with magnification factor of 40x, 100x, 200x, and 400x classified breast histological images with 93.8%, 93.4%, 93.3%, and 91.8% accuracy. 3. Methodology In a previous section, breast cancer detection literature has been reviewed. Histopathology images with low contrast and non-homogeneous intensity are difficult to detect. To overcome these limitations, this article introduces an enhanced technique for breast cancer detection. This section also discusses early BC detection methods. The proposed methodology consists of three phases. In phase 1, perform classification using Explainable AI. In phase 2 perform classification using Quantum Convolutional Neural Network (QCNN). In phase 3 perform semantic segmentation using Deeplabv3+. BC segmentation learning parameters are used to create a unique deeplabv3 + model. After segmentation, the QCNN model is developed based on the selected number of hyperparameters and performed training from scratch for the classification of the BC. Figure one shows the proposed method as a process flow diagram Figure 1 depicts the steps of segmentation and classification of SL, in which dermoscopic images are fed to the deeplabv3 + model for segmentation. The classification task for breast cancer is performed through the QCNN and XAI models to classify the different types of BC. 3.1 Segmentation using the Proposed DeepLabv3 + Model. DeepLabv3 + is an encoder-decoder model. DeepLabv3 + includes an essential but effective decoder module. Dilated convolution at various scales enhances segmentation with object boundaries, and the encoder module handles multiscale-related information. In this research work, an eight-layer segmentation model is proposed for detecting SC. The input image size is 256x256x3. Convolution blocks in the proposed model include Conv, batch-normalization (Bn), ReLU layer, and filters for the convolutional layers. Figure 2 presents the steps of the segmentation model. The model has been trained on the hyperparameters as mentioned in Table 1 . Table 1 Hyper parameter values of the proposed model for semantic segmentation Batch size 8 Filters 256 Channels 3 Classes 2 Epochs 500 Optimizer Adam Hyperparameters are evaluated after experimentation, using the three channels, 500 training epochs, two classes, and 8 batch-size for model training, and these parameters provide good results. 3.2 Classification using the XAI Model XAI methodologies explain ML model outcomes. A model-agnostic method treats the model as a black box and cannot access its underlying parameters, whereas an intrinsic approach leverages its inherent parameters to explain. Interpretable and transparent ML models are essential in healthcare to foster professional and patient trust. These models describe their decision-making process to improve confidence and understanding. Using machine learning models in healthcare requires transparency, which drives this goal. Interpretable model research is essential to address this need and increase healthcare ML use. Figure 3 shows the model architecture. The proposed XAI model utilizes Table 2 hyperparameters for training. Table 2 Hyperparameter values of the proposed model XAI for classification Batch size 8 Target size [150,150] Learning rate 0.001 Num epochs 300 The hyperparameters are seen in Table 2 ; in this experiment, parameters included a 300 epoch, an 8-batch size, a 0.001 learning rate, and fifteen transformation layers. This model contains Conv2D, MaxPooling, Dense, and Dropout layers. 3.3 Classification using Quantum Neural Network Machine learning using neural networks has made great strides in several practical applications as of late. One clear use is in the investigation of quantum many-body systems, where theoretical analysis is challenging due to the complexity of the states. Several recent articles employ machine learning to study quantum systems, use physical concepts to understand machine learning or use quantum computers to improve machine learning tasks. Quantum computers are solving challenges traditional computers can't. Quantum computers work differently from classical ones. By parallelizing qubits, quantum computers may leverage superposition and entanglement, which conventional computers cannot, and they can be incredibly fast [ 21 ]. The convolution layer finds hidden data using linear region pixel combinations. Feature map compression via the pooling layer reduces learning resources and model fit. Applying these layers repeatedly reduces data size sufficiently for the fully linked layer to classify. Gradient descent or other optimizers may train the model using the difference in loss between the learned and actual labels for improved outcomes. Traditional machine learning methods can't solve many real-world situations. Data must be translated to standard computer data for machine learning on the many-body Hilbert space quantum physics problem set. Data grows quickly with the system. The challenge is difficult for machine learning. Computer settings that can't handle data and models have alternatives. Much research has employed the Quantum Convolutional Neural Network (QCNN), which combines CNN with quantum computing, to solve these challenges. [ 22 ]. CNNs on quantum systems can solve quantum physics issues fast. CNN can improve things by adding a quantum system to the issues it previously addressed. Image categorization often uses CNN-style neural networks. Quantum computers are superposition and parallel computing experts. Henderson recommended boosting CNN using quantum settings. CNN investigated quantum computing after these revelations. Quantum convolution layers operate like convolution layers. Quantum convolution filters input feature maps to build new ones. Unlike convolution, quantum convolution filters in quantum computing. Traditional computers lack quantum superposition and parallel computation. Quantum convolution processes visual maps in filter size increments. The quantum convolution layer may be developed with small quantum computers [ 23 ]. As illustrated in Fig. 4 , the quantum convolution layer is capable of construction. The notion is developed as follows: The filter size-specific pixel data is encoded in qubits. Quantum circuits that utilize filters to identify the hidden state from the input state. The decoding process measures fresh classical data. Repeat 1)–3) until the new feature map is ready. Figure 4 shows how these Layers are added to the network. Define the quantum circuit using Google's quantum circuit design framework. Embed this static model section. Show a rectangle quantum circuit and specify the layers of the model in Fig. 4 (a), a two-qubit unitary circuit in Fig. 4 (b), and a two-qubit pooling circuit in Fig. 4 (c). In a proposed quantum neural network, \(2\times 2\) square region is embedded in the quantum circuit through parameterized rotations employed to qubits that are initiated in the ground state. The unitary operations are performed through the variational quantum circuit. The quantum circuit measured the list of the raw expectation values that are mapped to the channels of the single pixel of output. This process is repeated in different parts until scan whole image. The model contains flattened input, output layers with different activation units, and a Dense layer with ReLU activation of the softmax layer. The proposed model architecture is provided in Fig. 5 . The model approach uses Table 3 the hyperparameters for training purposes. Table 3 Hyperparameter values of the proposed model QCNN for classification Batch size 16 Learning rate 0.002 Num epochs 20 The hyperparameters are seen in Table 3 ; in this experiment, parameters included a 20 epoch, a 16-batch size, and a 0.002 learning rate. 4. Results and Discussion The segmentation and classification models are tested on several datasets. For segmentation, BUSIS[ 24 ] and DDSM [ 25 ] datasets are utilized. For classification, Histopathology [ 26 ] and BreakHis [ 27 , 28 ] datasets are utilized. MATLAB-2023B, Google Colab, and Jupyter Notebook with Windows OS and RTX 3070 graphic card do the studies. This research tests the suggested technique with two experiments. The recommended techniques are assessed using sensitivity, accuracy specificity, and F1 score. We abbreviate these as Sn, Acc, SP, and f1 respectively. The dataset is described in Table 4 These BC detection databases are public. Table 4 Dataset detail used in research. Ref # Years Datasets Classes No of Images [ 24 ] 2021 BUSIS 2 1,578 [ 25 ] 2021 DDSM 2 13,140 [ 26 ] 2018 Histopathology 2 271,404 [ 27 ] 2019 BreakHis 2 16,143 [ 28 ] 2020 BreakHis 8 196,868 Table 4 displays the number of input images that are applied for training and testing. The detail of the publicly available dataset is described as follows: BreakHis dataset contains two classes of BC such as malignant and benign with 16,143 images. BreakHis dataset contains 196,868 images with eight classes including AD, FB, PT, TA, DC, LC, MC, and PC lesions. The DDSM dataset contains 2 classes such as malignant and benign with 13,140 images. The BUSIS contains 1,578 images with 2 classes. The Histopathology contains 271,404 images for 2 classes such as malignant and benign. One experiment is performed on segmentation of the breast lesions and two models are proposed for classification of the breast lesions. 4.1. Experiment#1: Segmentation of the Breast Cancer (BC) The proposed segmentation model's performance is computed using mean and weighted IoU as M-IoU and W-IoU, global (G-Accuracy) as G-Acc and mean (M-Accuracy) as M-Acc, mean BF score as M-BF-Score from BUSIS and DDSM datasets in Tables 5 – 6 . Table 5 Performance of the segmentation model using the BUSIS dataset. G-Acc 0.991 M-IoU 0.990 M-Acc 0.989 W-IoU 0.988 M-BF-Score 0.979 Table 5 shows the suggested segmentation model's 0.989 and 0.991 BUSIS M- and G-Accuracy. BUSIS and DDSM breast cancer segmentation findings are shown in Figs. 6 and 7 . Using the BUSIS dataset, segmented BC is overlaid on original input pictures to highlight breast cancer locations in Fig. 6 . Table 6 Performance of the segmentation model using the DDSM dataset. G-Acc 0.989 M-IoU 0. 987 M-Acc 0. 986 W-IoU 0. 989 M-BF-Score 0. 987 Table 6 summarizes the results of the segmentation proposed earlier; the model achieved M-Acc and G-Acc of 0.986 and 0.989 on the DDSM dataset. Figure 7 presents segmented breast cancer and maps it to the source images to demonstrate diseased breast areas using the DDSM dataset. The achieved segmentation results are compared to existing methods as given in Table 7 . Table 7 Proposed model for segmentation result compared with existing work. Ref # Year Datasets Result (ACC) [ 29 ] 2020 CBIS-DDSM 84.40% [ 30 ] 2021 91.99% [ 31 ] 2022 92.86% [ 32 ] 2023 86.71% [ 18 ] 2024 92.00% Proposed Method 98.00% [ 33 ] 2021 BUSIS 94.12% [ 34 ] 2022 89.73% [ 35 ] 2023 96.52%,93.18% [ 36 ] 2024 96.99% Proposed Method 99% For automatic breast segmentation, use Atreus neural semantic segmentation. This DeepLabv3 + investigation discovered malignancies on CBIS-DDSM and BUSIS datasets 98% of the time. The intended VGG16 network is 0.844 CBIS-DDSM accurate[ 29 ]. The two-view classifier showed 0.9199 ± 0.0623 accuracy in 5-fold cross-validation, identifying malignant and non-cancerous breast images using one model and no additional data[ 30 ]. INbreast scored 96.34% for Connected-SegNets, CBIS-DDSM 92.86%, and private 92.25% [ 31 ]. The method achieved 86.71% CBIS-DDSM dataset accuracy[ 32 ]. Transfer learning using the VGG16 model was 92–95% accurate. VGG16 transfer learning benefits CBIS-DDSM and UPMC[ 18 ]. The public BUS dataset gave the SHA-MTL model 94.12% accuracy[ 33 ]. CNN model MIAS accuracy was 96.55%. The DDSM dataset showed 90.68%. INbreast showed 91.28% [ 34 ]. ShuffleNet-ResNet finds 99.17% abnormalities and 98.00% malignancies in mini-DDSM and 96.52% and 93.18% in BUSI datasets[ 35 ]. The triple decoder + multi-attention model was 96.99% accurate on BUSI and 97.69% on UDIAT. Jaccard index testing is 83.40% in UDIAT and 82.31% in BUSI [ 36 ]. 4.2. Experiment#2: XAI Model Classification of BC The XAI model is used for the classification of BC. The BC is classified into two classes: malignant and benign. Table 8 demonstrates the BreakHis dataset's results using our approach to the classification problem. The training and testing outcomes of the proposed method are provided in Fig. 8 . Accuracy as ACC, F1 Score as F1, Recall as Re, and Precision as Pr. The classification results on BreakHis are presented in the form of a confusion matrix in Fig. 9 . Table 8 Proposed classification result on BreakHis Dataset with magnification factors. Magnification Factor ACC F1 Re Pr 40X 1.00 1.00 1.00 1.00 100X 1.00 1.00 1.00 1.00 200X 1.00 1.00 1.00 1.00 400X 1.00 1.00 1.00 1.00 Table 8 shows 100% accuracy in the BreakHis dataset for classification. Table 9 compares the proposed classification model to current studies. In Fig. 10 , computed results on eight classes present the ratio of true positive/negative and false positive/negative. The training and validation accuracy with the number of epochs is presented graphically where a pink line for training and a green line for validation. The quantitative results on eight classes using the BreakHis dataset with a 40x magnification factor are given in Table 9 and the 100x magnification factor is given in Table 10 . Table 9 Classification results on BreakHis with 40x magnification factor Classes Precision% Recall% F1-score% AD 1.00 0.91 0.95 DC 1.00 1.00 1.00 FB 0.86 1.00 1.00 LC 1.00 1.00 1.00 MC 0.92 1.00 0.96 PC 1.00 0.81 1.00 PT 1.00 0.81 0.89 TA 0.94 1.00 0.97 Accuracy 0.96 Misclassification rate 0.03 Macro-F1 0.96 Weighted-F1 0.96 Table 9 , provides the classification outcomes on 40x magnification factor on eight classes such as AD, FB, PT, TA, DC, LC, MC, and PC. In which 96.27% accuracy and 0 misclassification rate is achieved. Table 10 Classification results on BreakHis with 100x magnification factor Classes Precision% Recall% F1-score% AD 1.00 0.98 0.99 DC 1.00 1.00 1.00 FB 1.00 0.51 0.68 LC 0.89 1.00 0.94 MC 0.96 0.70 0.81 PC 1.00 1.00 1.00 PT 0.44 1.00 0.61 TA 1.00 0.95 0.97 Accuracy 0.85 Misclassification rate 0.14 Macro-F1 0.87 Weighted-F1 0.85 Table 10 , provides the classification outcomes on 100x magnification factor on eight classes such as AD, FB, PT, TA, DC, LC, MC, and PC. In which 85.03% accuracy and 0 misclassification rate is achieved. In Fig. 11 , computed results on eight classes present the ratio of true positive/negative and false positive/negative. The training and validation accuracy with the number of epochs is presented graphically where a pink line for training and a green line for validation. The quantitative results on eight classes using the BreakHis dataset with a 40x magnification factor are given in Table 11 and the 100x magnification factor is given in Table 12 . Table 11 Classification results on BreakHis with 200x magnification factor Classes Precision% Recall% F1-score% AD 0.97 1.00 0.98 DC 1.00 1.00 1.00 FB 1.00 0.95 0.97 LC 1.00 1.00 1.00 MC 1.00 1.00 1.00 PC 1.00 1.00 1.00 PT 0.95 1.00 0.97 TA 1.00 0.97 0.98 Accuracy 0.99 Misclassification rate 0.00 Macro-F1 0.99 Weighted-F1 0.99 Table 11 , provides the classification outcomes on 100x magnification factor on eight classes such as AD, FB, PT, TA, DC, LC, MC, and PC. In which 99.10% accuracy and 0 misclassification rate is achieved. Table 12 Classification results on BreakHis with 400x magnification factor Classes Precision% Recall% F1-score% AD 0.91 1.00 0.95 DC 1.00 1.00 1.00 FB 1.00 0.98 0.99 LC 1.00 0.98 0.99 MC 1.00 0.92 0.96 PC 1.00 1.00 1.00 PT 1.00 1.00 0.99 TA 1.00 1.00 1.00 Accuracy 0.98 Misclassification rate 0.01 Macro-F1 0.98 Weighted-F1 0.98 Table 12 , provides the classification outcomes on 100x magnification factor on eight classes such as AD, FB, PT, TA, DC, LC, MC, and PC. In which 98.62% accuracy and 0 misclassification rate is achieved. 4.3. Experiment#3: Classification of the BC using the QNN Model The QNN model is used for the classification of BC. The BC is classified into two classes: malignant and benign. Figure 10 shows the classification result on the publicly available BreakHis dataset. Figure 12 , presents the classification results on different magnification levels such as 40x, 100x, and 200x. The performance of classification is measured in terms of the confusion matrix and training and validation accuracy for the number of epochs. In the confusion matrix, 0 denotes the benign class and 1 is the malignant class. The quantitative assessment in terms of ACC, F1, Re, and Pr. Table 13 classification result on BreakHis Dataset with magnification factors. Magnification Factor ACC% F1 Re Pr 40x 1.00 1.00 1.00 1.00 100x 0.97 0.97 1.00 0.95 200x 0.97 0.97 1.00 0.94 In Table 13 , the achieved results in terms of accuracy based on the binary classification are 100% on 40x, 97.92% on 100x, and 200x. The classification results are computed on eight classes of breast cancer and are presented in Fig. 11 . In Fig. 13 , computed results on eight classes present the ratio of true positive/negative and false positive/negative. The training and validation accuracy with the number of epochs is presented graphically where a pink line for training and a green line for validation. The quantitative results on eight classes using the BreakHis dataset with a 40x magnification factor are given in Table 14 . Table 14 Classification results on BreakHis with 40x magnification factor Classes Precision% Recall% F1-score% AD 1.00 1.00 1.00 FB 1.00 1.00 1.00 PT 1.00 1.00 1.00 TA 1.00 1.00 1.00 DC 1.00 1.00 1.00 LC 1.00 1.00 1.00 MC 1.00 1.00 1.00 PC 1.00 1.00 1.00 Accuracy 1.00 Misclassification rate 0.00 Macro-F1 1.00 Weighted-F1 1.00 Table 14 , provides the classification outcomes on 40x magnification factor on eight classes such as AD, FB, PT, TA, DC, LC, MC, and PC. In which 100% accuracy and 0 misclassification rate is achieved. Table 15 Classification results on BreakHis with 100x magnification factor Class name Precision Recall F1-score AD 1.00 1.00 1.00 FB 1.00 1.00 1.00 PT 1.00 1.00 1.00 TA 1.00 1.00 1.00 DC 1.00 1.00 1.00 LC 1.00 1.00 1.00 MC 1.00 1.00 1.00 PC 1.00 1.00 1.00 Accuracy 1.00 Misclassification rate 0.00 Macro-F1 1.00 Weighted-F1 1.00 Table 15 provides the classification outcomes on the 100x magnification factor. The achieved outcomes are compared to the existing methods as given in Table 16 . Table 16 Proposed model for classification result compared with existing work Ref # Year Datasets ACC% [ 37 ] 2021 BreakHis 2 classes 96.75 [ 38 ] 2022 94.67 [ 39 ] 2022 96.35 [ 40 ] 2023 96.30 [ 41 ] 2024 99.16 [ 19 ] 2024 99.76 Proposed Method with XAI 96.87 Proposed Method with QNN 1.00 [ 42 ] 2021 BreakHis 8 classes 95.00 [ 43 ] 2023 89.00 [ 41 ] 2024 98.27 Proposed Method with XAI 98.62 Proposed Method with QNN 1.00 XAI and QCNN models classify BC with 96.87% and 100% accuracy on BreakHis with 2 and 8 classes, respectively, according to Table 16 . Model accuracy is 96.75%, 96.7%, 95.78%, and 93.86% for benign and malignant binary classification [ 37 ]. Classify BreakHis with pretrained models. The highest classifier is VGG16 with a precision of 92.60% and an f1- score of 85.21%. The model achieved an accuracy of 94.67% and a recall of 80.52% [ 38 ]. The proposed model has a maximum accuracy of 96.35%. The network architectures tested include VGG16, ResNet50, and a proposed model [ 39 ]. On the BreakHis dataset, pretrained models had 92%, 87%, 90%, 79%, and 92% accuracy. Data features were retrieved using ResNet 50. To 96.3%, accuracy has substantially increased [ 40 ]. AlexNet convolutional neural network diagnoses breast cancer using BreakHis dataset features. The proposed method has 99.36% AUC, 95% accuracy, as well as 97% sensitivity with 90% specificity [ 42 ]. Deep learning cancer classifiers VGG, ResNet, Xception, Inception. Top performance Xception is 0.9 F1 and 89% accurate. Inception and ResNet are 87% accurate [ 43 ]. The Swin-Transformer V2 architecture classified eight-class BC histopathological images with multiple labels with 98.27%, 97.95%, 98.97%, and 99.16% accuracy on Break-His [ 41 ]. Rapid Tri-Net with Aquila Optimization (Rapid Tri-Net) on BreakHis and BACH datasets achieved 99.79%, 99.8%, 99.73%, and 99.76% accuracy at 40x, 100x, 200x, and 400x [ 20 ]. 5. Conclusion Statistically speaking, for the worldwide population of women breast cancer is the number one cancer type in terms of the number of patients. Poor health, hormone issues, and environmental factors may make it more probable for women of any age to have it. Breast cancer early detection helps more women survive. This approach's efficiency is verified by comparing the findings to the newest work in this field. The segmentation of the breast lesion is a challenging task due to the variable shape, size, and texture of the lesion region. To overcome this challenge, the Deeplabv3 model is used with optimal hyperparameters for segmentation. This method's results are evaluated on BUSIS and DDSM datasets with the accuracy of 99.0% and 98.0% respectively. Furthermore, the classification of different types of lesion regions is still a great challenge, to overcome this two models are proposed such as XAI and quantum neural network. These models are designed on the selected number of layers and optimal hyperparameters and evaluated on the different types of magnification factors such as 40x, 100x, and 200x. The classification results are computed on BreakHis's publically available dataset. The XAI model classifies breast cancer achieved an accuracy of 96.87% and achieved an accuracy of 98.62% with 8 classes such as AD, FB, PT , TA, DC, LC, MC, and PC, quantum neural network models classify breast cancer achieved an accuracy of 100% on binary classes such as benign and malignant and achieved an accuracy of 100% with 8 classes such as AD, FB, PT , TA, DC, LC, MC and PCon BreakHis dataset with magnification factors 40x, 100x, 200x, and 400x. As per the results of the strategy and experiments outlined above, we outperformed the published results on the metrics defined herein. Declarations Funding Declaration We received no funding regarding this article. Competing Interest declaration No competing interest regarding this article Author Contribution declaration Saqqiya Waris : Implementation, Draft writing Javaria Amin: Implementation, Algorithm designing, Draft Writing, Proofreading, Data Collection, Supervision Amina Sarwar: Formating Muhammad Sharif and Mussarat Yasmeen: Proof-reading Author Contribution Funding DeclarationWe received no funding regarding this article.Competing Interest declarationNo competing interest regarding this articleAuthor Contribution declarationSaqqiya Waris: Implementation, Draft writingJavaria Amin: Implementation, Algorithm designing, Draft Writing, Proofreading, Data Collection, SupervisionAmina Sarwar: FormatingMuhammad Sharif and Mussarat Yasmeen: Proof-reading References Cheng H-D, Shan J, Ju W, Guo Y, Zhang L. Automated breast cancer detection and classification using ultrasound images: A survey. Pattern Recogn. 2010;43(1):299–317. Cheng H-D, Shi X, Min R, Hu L, Cai X, Du H. Approaches for automated detection and classification of masses in mammograms, Pattern recognition , vol. 39, no. 4, pp. 646–668, 2006. Castellino RA. Computer aided detection (CAD): an overview, Cancer Imaging, vol. 5, no. 1, p. 17, 2005. Xian M, et al. A benchmark for breast ultrasound image segmentation (BUSIS). Infinite Study; 2018. Huang Q, Huang Y, Luo Y, Yuan F, Li X. Segmentation of breast ultrasound image with semantic classification of superpixels. Med Image Anal. 2020;61:101657. Siegel RL, Miller KD, Fuchs HE, Jemal A. Cancer statistics, 2022, CA: a cancer journal for clinicians, 72, 1, 2022. Yassin NI, Omran S, El EM, Houby, Allam H. Machine learning techniques for breast cancer computer aided diagnosis using different image modalities: A systematic review, Computer methods and programs in biomedicine, vol. 156, pp. 25–45, 2018. Amrane M, Oukid S, Gagaoua I, Ensari T. Breast cancer classification using machine learning. 2018 electric electronics, computer science, biomedical engineerings' meeting (EBBT). IEEE; 2018. pp. 1–4. Szegedy C et al. Going deeper with convolutions, in Proceedings of the IEEE conference on computer vision and pattern recognition, 2015, pp. 1–9. Salpea N, Tzouveli P, Kollias D. Medical image segmentation: A review of modern architectures, in European Conference on Computer Vision, 2022: Springer, pp. 691–708. Majumdar S, Pramanik P, Sarkar R. Gamma function based ensemble of CNN models for breast cancer detection in histopathology images. Expert Syst Appl. 2023;213:119022. Pang T, Wong JHD, Ng WL, Chan CS. Semi-supervised GAN-based radiomics model for data augmentation in breast ultrasound mass classification, Computer Methods and Programs in Biomedicine, 203, p. 106018, 2021. Toussaint N et al. Weakly supervised localisation for fetal ultrasound images, in Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support: 4th International Workshop, DLMIA 2018, and 8th International Workshop, ML-CDS 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, September 20, 2018, Proceedings 4, 2018: Springer, pp. 192–200. Kumar S, Parthasarathi P, Hogo MA, Masud M, Al-Amri JF, Abouhawwash M. Breast Cancer Detection Using Breastnet-18 Augmentation with Fine-Tuned VGG-16, Intelligent Automation and Soft Computing, 36, 2, pp. 2363–78, 2023. Kowal M, Skobel M, Gramacki A, Korbicz J. Breast cancer nuclei segmentation and classification based on a deep learning approach. Int J Appl Math Comput Sci. 2021;31(1):85–106. Resmini R, Silva L, Araujo AS, Medeiros P, Muchaluat-Saade D, Conci A. Combining genetic algorithms and SVM for breast cancer diagnosis using infrared thermography, Sensors, 21, 14, p. 4802, 2021. Ayana G, Park J, Jeong J-W, Choe S-w. A novel multistage transfer learning for ultrasound breast cancer image classification, Diagnostics, 12, 1, p. 135, 2022. Rani N, Gupta DK, Singh S. Multi-class classification of breast cancer abnormality using transfer learning, Multimedia Tools and Applications, pp. 1–16, 2024. Salunkhe PB, Patil PS. Rapid tri-net: breast cancer classification from histology images using rapid tri-attention network, Multimedia Tools and Applications, pp. 1–31, 2024. Zerouaoui H, Alaoui OE, Idri A. New design strategies of deep heterogenous convolutional neural networks ensembles for breast cancer diagnosis. Multimedia Tools Appl, pp. 1–32, 2024. Farhi E, Neven H. Classification with quantum neural networks on near term processors, arXiv preprint arXiv:1802.06002, 2018. Bokhan D, Mastiukova AS, Boev AS, Trubnikov DN, Fedorov AK. Multiclass classification using quantum convolutional neural networks with hybrid quantum-classical learning. Front Phys. 2022;10:1069985. Jia ZA, Yi B, Zhai R, Wu YC, Guo GC, Guo GP. Quantum neural network states: A brief review of methods and applications, Advanced Quantum Technologies, 2, no. 7–8, p. 1800077, 2019. A. shah. Breast Ultrasound Images Dataset. Kaggle. https://www.kaggle.com/datasets/aryashah2k/breast-ultrasound-images-dataset (accessed 2024). Awsaf. CBIS-DDSM: Breast Cancer Image Dataset. https://www.kaggle.com/datasets/awsaf49/cbis-ddsm-breast-cancer-image-dataset (accessed. Mooney P. Breast Histopathology Images. Kaggle. https://www.kaggle.com/datasets/paultimothymooney/breast-histopathology-images (accessed 2024). AnuKritika. Breast Cancer Dataset from BreakHis. Kaggle. https://www.kaggle.com/datasets/kritika397/breast-cancer-dataset-from-breakhis (accessed 2023). Bukun. accessed. BreakHis. Kaggle. https://www.kaggle.com/datasets/ambarish/breakhis (2024). Falconi LG, Perez M, Aguilar WG, Conci A. Transfer learning and fine tuning in breast mammogram abnormalities classification on CBIS-DDSM database. Adv Sci Technol Eng Syst J. 2020;5(2):154–65. Petrini DG et al. End-to-end training of convolutional network for breast cancer detection in two-view mammography, Cancer Research, vol. 81, no. 13_Supplement, pp. 183–183, 2021. Alkhaleefah M et al. Connected-segNets: A deep learning model for breast tumor segmentation from X-ray images, Cancers, vol. 14, no. 16, p. 4030, 2022. Bouzar-Benlabiod L, Harrar K, Yamoun L, Khodja MY, Akhloufi MA. A novel breast cancer detection architecture based on a CNN-CBR system for mammogram classification. Comput Biol Med. 2023;163:107133. Zhang G, Zhao K, Hong Y, Qiu X, Zhang K, Wei B. SHA-MTL: soft and hard attention multi-task learning for automated breast cancer ultrasound image segmentation and classification. Int J Comput Assist Radiol Surg. 2021;16:1719–25. Muduli D, Dash R, Majhi B. Automated diagnosis of breast cancer using multi-modal datasets: A deep convolution neural network based approach. Biomed Signal Process Control. 2022;71:102825. Sahu A, Das PK, Meher S. High accuracy hybrid CNN classifiers for breast cancer detection using mammogram and ultrasound datasets. Biomed Signal Process Control. 2023;80:104292. Umer MJ, Sharif M, Raza M. A Multi-attention Triple Decoder Deep Convolution Network for Breast Cancer Segmentation Using Ultrasound Images, Cognitive Computation, 16, 2, pp. 581–94, 2024. Zewdie ET, Tessema AW, Simegn GL. Classification of breast cancer types, sub-types and grade from histopathological images using deep learning technique. Health Technol. 2021;11(6):1277–90. Agarwal P, Yadav A, Mathur P. Breast cancer prediction on breakhis dataset using deep cnn and transfer learning model, in Data Engineering for Smart Systems: Proceedings of SSIC 2021, 2022: Springer, pp. 77–88. Dalke R. Neural Network Based Diagnosis of Breast Cancer Using the Breakhis Dataset. California Polytechnic State University; 2022. Singh UP, Sahu M. A Hybrid Approach for Improving the Classification performance of Imbalanced Breast Cancer data, in 2023 International Conference on Communication, Circuits, and Systems (IC3S), 2023: IEEE, pp. 1–6. Kolla B, Venugopal P. An integrated approach for magnification independent breast cancer classification. Biomed Signal Process Control. 2024;88:105594. Senan EM, Alsaade FW, Al-Mashhadani MIA, Theyazn H, Al-Adhaileh MH. Classification of histopathological images for early detection of breast cancer using deep learning. J Appl Sci Eng. 2021;24(3):323–9. İ, Sayın et al. Comparative Analysis of Deep Learning Architectures for Breast Cancer Diagnosis Using the BreaKHis Dataset, arXiv preprint arXiv:2309.01007, 2023. Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-4353973","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":300209647,"identity":"866d097b-42a3-47ef-ae73-95d9f797135e","order_by":0,"name":"Saqqiya Waris","email":"","orcid":"","institution":"University of Wah","correspondingAuthor":false,"prefix":"","firstName":"Saqqiya","middleName":"","lastName":"Waris","suffix":""},{"id":300209648,"identity":"40ce6ddf-ce8e-4574-96ff-545120df5677","order_by":1,"name":"Javaria Amin","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA9klEQVRIiWNgGAWjYBACxgYQaQBlfoAIgrgJxGlhnEGMFhTAzEOMFub2M4aPKwrsGPinHW57bNtmk9jA3rxNgnFHGm6H9eQYG54xSGaQuJ3YbpzblpbYwHOsTILxTA4ev6SlSTYYMDMw3E5sk85tO5zbIJFjJsHYVoFbS/+z9J8NBvUM8iAtliAt8m8IaJmRfIyxweAwgwFICyPYFh6QFjwOm/H4MNBhx3kMgVoke86l1bfxpBVbJJ7B7X3D/sTGjw1/quXkbqc/k/hRZmPMz354442PO5Jxa2mA0DxwETYQkdiAUweDPA734tEyCkbBKBgFIw4AAKElUQTGD+/4AAAAAElFTkSuQmCC","orcid":"","institution":"University of Wah","correspondingAuthor":true,"prefix":"","firstName":"Javaria","middleName":"","lastName":"Amin","suffix":""},{"id":300209649,"identity":"c258b459-3941-4614-881a-7a9a2297f59e","order_by":2,"name":"amina sarwar","email":"","orcid":"","institution":"University of Wah","correspondingAuthor":false,"prefix":"","firstName":"amina","middleName":"","lastName":"sarwar","suffix":""},{"id":300209650,"identity":"fec5f118-5d2c-402b-bbc1-82eafc4c8674","order_by":3,"name":"muhammad Sharif","email":"","orcid":"","institution":"COMSATS University Islamabad","correspondingAuthor":false,"prefix":"","firstName":"muhammad","middleName":"","lastName":"Sharif","suffix":""},{"id":300209651,"identity":"4e6cd86f-4b00-46f0-b748-618a378e82e5","order_by":4,"name":"Mussarat Yasmeen","email":"","orcid":"","institution":"COMSATS University Islamabad","correspondingAuthor":false,"prefix":"","firstName":"Mussarat","middleName":"","lastName":"Yasmeen","suffix":""}],"badges":[],"createdAt":"2024-05-01 11:24:49","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4353973/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4353973/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":56168982,"identity":"4c6cd7e1-986a-4fc0-97b4-c31e1a1cbdf0","added_by":"auto","created_at":"2024-05-09 11:15:28","extension":"jpg","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":61500,"visible":true,"origin":"","legend":"\u003cp\u003eProposed method architecture\u003c/p\u003e","description":"","filename":"Picture1.jpg","url":"https://assets-eu.researchsquare.com/files/rs-4353973/v1/97bb2fc34ea260c0c74d14f8.jpg"},{"id":56169975,"identity":"5a92e75a-12a0-4af5-8048-f673623011a4","added_by":"auto","created_at":"2024-05-09 11:31:28","extension":"jpg","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":40952,"visible":true,"origin":"","legend":"\u003cp\u003eDeepLabv3+ model for breast cancer segmentation\u003c/p\u003e","description":"","filename":"Picture2.jpg","url":"https://assets-eu.researchsquare.com/files/rs-4353973/v1/479aba306c658c7a1ec9c316.jpg"},{"id":56168976,"identity":"953c6c84-8520-4ce8-aa2b-29475b6c8e29","added_by":"auto","created_at":"2024-05-09 11:15:25","extension":"jpg","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":94179,"visible":true,"origin":"","legend":"\u003cp\u003eProposed XAI method for breast cancer identification\u003c/p\u003e","description":"","filename":"Picture3.jpg","url":"https://assets-eu.researchsquare.com/files/rs-4353973/v1/0bd156a79cb0dded46811e9d.jpg"},{"id":56168971,"identity":"7fa61f16-dbc1-40f0-bdcd-da1eb8f515d9","added_by":"auto","created_at":"2024-05-09 11:15:24","extension":"jpg","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":60138,"visible":true,"origin":"","legend":"\u003cp\u003eQuantum layers (a) quantum circuit (b) two-qubit unitary circuit (c) two-qubit pooling circuit\u003c/p\u003e","description":"","filename":"Picture4.jpg","url":"https://assets-eu.researchsquare.com/files/rs-4353973/v1/91d7ef7cace08bd4cd65ffef.jpg"},{"id":56169187,"identity":"6c55d0e8-5f60-4db1-b62f-7c44911a7df3","added_by":"auto","created_at":"2024-05-09 11:23:25","extension":"jpg","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":56702,"visible":true,"origin":"","legend":"\u003cp\u003eProposed quantum convolutional neural network\u003c/p\u003e","description":"","filename":"Picture5.jpg","url":"https://assets-eu.researchsquare.com/files/rs-4353973/v1/7e121166fc56d85667beafb9.jpg"},{"id":56169192,"identity":"72572e92-5dc1-4367-9dd3-3cf624140ea1","added_by":"auto","created_at":"2024-05-09 11:23:29","extension":"jpg","order_by":6,"title":"Figure 6","display":"","copyAsset":false,"role":"figure","size":137526,"visible":true,"origin":"","legend":"\u003cp\u003eSegmentation result of BC (a) original image (b) original mask (c) predicted mask (d) overlapped prediction (e) Grad CAM\u003c/p\u003e","description":"","filename":"Picture6.jpg","url":"https://assets-eu.researchsquare.com/files/rs-4353973/v1/6a4c3c95e195bce1247817cb.jpg"},{"id":56170317,"identity":"ca64d97d-8280-47d1-a3c6-30a22bd5ccb5","added_by":"auto","created_at":"2024-05-09 11:39:28","extension":"jpg","order_by":7,"title":"Figure 7","display":"","copyAsset":false,"role":"figure","size":37547,"visible":true,"origin":"","legend":"\u003cp\u003eSegmentation of breast cancer on DDSM dataset (a) input images (b) segmentation (c) overlaps segmented region into input image.\u003c/p\u003e","description":"","filename":"Picture7.jpg","url":"https://assets-eu.researchsquare.com/files/rs-4353973/v1/d431b610147d415d3af5b4a5.jpg"},{"id":56168968,"identity":"a92d6065-2fe5-4eef-9663-cd3ef5d63f1a","added_by":"auto","created_at":"2024-05-09 11:15:22","extension":"jpg","order_by":8,"title":"Figure 8","display":"","copyAsset":false,"role":"figure","size":72770,"visible":true,"origin":"","legend":"\u003cp\u003eProposed classification accuracy on BreakHis (a) 40x, (b) 100x, (c) 200x and (d) 400x.\u003c/p\u003e","description":"","filename":"Picture8.jpg","url":"https://assets-eu.researchsquare.com/files/rs-4353973/v1/64d13bb6c904a178a85578d7.jpg"},{"id":56168973,"identity":"4c183a6a-db7e-4284-8959-83dccd4b38cf","added_by":"auto","created_at":"2024-05-09 11:15:24","extension":"jpg","order_by":9,"title":"Figure 9","display":"","copyAsset":false,"role":"figure","size":56363,"visible":true,"origin":"","legend":"\u003cp\u003eConfusion matrix of classification model on BreakHis dataset, (a) 40x, (b) 100x (c) 200x, and (d) 400x magnification factor.\u003c/p\u003e","description":"","filename":"Picture9.jpg","url":"https://assets-eu.researchsquare.com/files/rs-4353973/v1/f3ea2820aa3d97437d39f647.jpg"},{"id":56168986,"identity":"4c0f1e69-4e1d-4ca2-b6c6-bf28b9c0266b","added_by":"auto","created_at":"2024-05-09 11:15:29","extension":"jpg","order_by":10,"title":"Figure 10","display":"","copyAsset":false,"role":"figure","size":73703,"visible":true,"origin":"","legend":"\u003cp\u003eClassification results of Breast Cancer (a) (b) confusion matrix on 40x and 100x \u0026nbsp;magnification levels respectively.\u003c/p\u003e","description":"","filename":"Picture10.jpg","url":"https://assets-eu.researchsquare.com/files/rs-4353973/v1/3b6f9d51c648b56ea8d83e3d.jpg"},{"id":56169972,"identity":"f107290e-c66b-47f7-aad2-85c6bb4f79b2","added_by":"auto","created_at":"2024-05-09 11:31:26","extension":"jpg","order_by":11,"title":"Figure 11","display":"","copyAsset":false,"role":"figure","size":74120,"visible":true,"origin":"","legend":"\u003cp\u003eClassification results of Breast Cancer (a) (b) confusion matrix on 200x and 400x magnification levels respectively\u003c/p\u003e","description":"","filename":"Picture11.jpg","url":"https://assets-eu.researchsquare.com/files/rs-4353973/v1/31d505c9352a0da85bad5ec5.jpg"},{"id":56169193,"identity":"eb7ce701-d823-4e3d-a2d4-b363e68d1c83","added_by":"auto","created_at":"2024-05-09 11:23:30","extension":"jpg","order_by":12,"title":"Figure 12","display":"","copyAsset":false,"role":"figure","size":91880,"visible":true,"origin":"","legend":"\u003cp\u003eClassification results of Breast Cancer (a) (c) (e) confusion matrix on 40x, 100x, and 200x magnification levels respectively (b) (d) (f) Training/Validation on a matrix on 40x, 100x, and 200x magnification levels respectively\u003c/p\u003e","description":"","filename":"Picture12.jpg","url":"https://assets-eu.researchsquare.com/files/rs-4353973/v1/d691c2e5710c8c86600ac71b.jpg"},{"id":56168980,"identity":"de150814-e46f-43e8-b7e4-93677d4c1be2","added_by":"auto","created_at":"2024-05-09 11:15:27","extension":"jpg","order_by":13,"title":"Figure 13","display":"","copyAsset":false,"role":"figure","size":79950,"visible":true,"origin":"","legend":"\u003cp\u003eClassification results of Breast Cancer on BreakHis-40x dataset (a) confusion matrix of Quantum CNN (b) Training/Validation accuracy of Quantum CNN (c) Training/Validation loss of Quantum CNN\u003c/p\u003e","description":"","filename":"Picture13.jpg","url":"https://assets-eu.researchsquare.com/files/rs-4353973/v1/6a1d8b98b80425eda7807f7d.jpg"},{"id":56169190,"identity":"347fc142-722d-46d8-a3cb-107609ca0a9c","added_by":"auto","created_at":"2024-05-09 11:23:27","extension":"jpg","order_by":14,"title":"Figure 14","display":"","copyAsset":false,"role":"figure","size":90465,"visible":true,"origin":"","legend":"\u003cp\u003eClassification results of Breast Cancer on BreakHis-100x dataset (a) confusion matrix of Quantum CNN (b) Training/Validation accuracy of Quantum CNN (c) Training/Validation loss of Quantum CNN\u003c/p\u003e","description":"","filename":"Picture14.jpg","url":"https://assets-eu.researchsquare.com/files/rs-4353973/v1/6c808bc19cb62a5ca78d0c40.jpg"},{"id":68628174,"identity":"60cda64e-8d17-4df6-9903-8d6c325f111b","added_by":"auto","created_at":"2024-11-09 17:46:18","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":2051035,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4353973/v1/83dc1a5f-4ed1-4f6f-a759-14a57ea61b29.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Breast Cancer Detection using Explainable AI and Quantum Neural Network","fulltext":[{"header":"1. Introduction","content":"\u003cp\u003eIn women, it is diagnosed more frequently all over the world. Breast cancer can cause unhealthy lifestyles, hormonal issues, and environmental factors, which may cause high risk in women of all ages. Many women with breast cancer miss the chance to cure this disease at the initial stage. Having an early screening process is more important to improve the opportunity for survival. Early screening methods are Mammography, Magnetic Resonance Imaging (MRI), and Ultrasound to enhance women's chance of survival. These tools diagnose breast abnormalities in women [\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e, \u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e].Ultrasound is cheaper and better at diagnosing. Manually finding breast tumors takes radiologists a long time. Computer-aided detection systems may assist medical professionals in making rapid choices thanks to recent advances in AI and Deep Learning models[\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e]. Computer-aided illness detection systems follow disease detection procedures. The most essential are Enhancement, segmentation, and feature extraction. The technology enhances ultrasound images during Enhancement. The technique can segment breast cancer ultrasound pictures during segmentation. The system can categorize the illness using the most essential aspects of Feature Extraction[\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e]. Data Augmentation will be used to make the ultrasound and mask images bigger[\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e]. Breast cancer is classified as benign or malignant. Benign is treatable, and patients with early identification have a good survival rate. The American Cancer Society predicts 43600 women and 530 men deaths in 2021[\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e]. Due to media and healthcare awareness, breast cancer mortality dropped 40% from 1989 to 2017. Mammography is the main breast cancer screening method in most countries. However, repeated procedure radiation exposure may induce additional cancers, making mammography unsafe for pregnant women. Ultrasound is widely used owing to its cost-effectiveness and diagnostic accuracy. Melanoma and benign breast cancers are difficult for radiologists to distinguish. Tumor color variation, morphological structure and form, and numerous tumors in ultrasound pictures are the main causes. Other issues include concealed tumors, poor ultrasound picture quality, and limited sensitivity in thick breast tissue. Radiologists may experience problems identifying breast cancers from healthy tissue. These worries may raise fake findings, needless tests, and women's deaths. CAD systems have been utilized in biological imaging for years as a non-invasive and flexible tool[\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e]. A skilled radiologist's ultrasound screening breast pictures are used by the automatic CAD system. The CAD system improved ultrasound picture clarity, medical assessment precision, and time and resource savings. Image gathering, preparation, segmentation, feature extraction, and classification are all things that most CAD systems need to do. It makes Active Contour, Thresholding, Clustering, Graph, Watershed, and deep learning. Classical methods use texture, form, color, local, global, and threshold qualities that are made by hand. Conventional methods use histogram normalization to increase the brightness of the original picture and then use a cutoff to separate the breast tumor area. With a lot of images as input, these methods don't work because they are time-consuming and need more computational power to perform task properly. Medical professionals employ segmentation algorithms to discover diseases, diagnose abnormalities, calculate tissue volume, assess anatomical structures, and treat patients. The precision of tumor segmentation and computation and the accuracy of image characteristics to classify benign or malignant tumors determine cancer diagnostic efficiency. This paper proposes a deep-learning architecture for tumor segmentation and uses machine learning (ML) techniques to classify tumors as benign or malignant. The segmentation findings help doctors decide whether a tumor is malignant or benign[\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eMany segmentation methods have been suggested recently[\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e]. This research examines semantic segmentation. Using GoogLeNet, a new deep learning-based segmentation architecture is developed. The 2014 Google research project Inception v1 launched the GoogLeNet[\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e]. DeepLabV3\u0026thinsp;+\u0026thinsp;semantic segmentation and Xception depth separable convolution are used. Second, transfer learning and data augmentation increase convergence and model resilience. Third, network parameters are reduced by coding and decoding[\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e]. As computer vision and image processing have improved, deep learning-based neural network methods have become more common for making a good CAD system for separating breast tumors. Speckle noise, odd shapes, unclear tumor sites, and weak signals in ultrasound pictures are all problems that make it harder to identify CAD.\u003c/p\u003e \u003cp\u003eThe major contribution of the proposed research:\u003c/p\u003e \u003cp\u003e \u003cul\u003e \u003cli\u003e \u003cp\u003eSegmentation of breast cancer is a challenging task due to the variable size, and shape of the lesions. The DeepLabv3\u0026thinsp;+\u0026thinsp;model is proposed and trained on the fine-tuned hyperparameters that more accurately segment the small lesion regions missed on the manual detection.\u003c/p\u003e \u003c/li\u003e \u003cli\u003e \u003cp\u003eTwo models are proposed for classification of the breast cancer based on explainable XAI and quantum neural networks to analyze the result of classification.\u003c/p\u003e \u003c/li\u003e \u003cli\u003e \u003cp\u003eThe explainable XAI-shape model is designed on the selected fifteen layers and trained on the fine-tuned hyperparameters for classification of the breast cancer.\u003c/p\u003e \u003c/li\u003e \u003cli\u003e \u003cp\u003eThe quantum kernel provides help to learn the complex pattern as compared to the convolutional kernel. Therefore, the quantum neural network is developed on \u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\(2\\times 2\\)\u003c/span\u003e\u003c/span\u003e Qubits, selected layers, and hyperparameters to provide help for more accurate classification of breast cancer.\u003c/p\u003e \u003c/li\u003e \u003c/ul\u003e \u003c/p\u003e \u003cp\u003eThe structure of this article is such that, section 2 starts with an overview of the works of researchers that are considered related work, section 3 starts with an explanation of proposed models, section 4 starts with the discussion of results and section 5 concludes the research.\u003c/p\u003e"},{"header":"2. Related Work","content":"\u003cp\u003eBreast cancer segmentation and classification have improved recently. The methodologies of ML can be included in image processing, feature extraction, selection, and classification tasks. In a rank-based ensemble method, Majumda et al.[\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e] compared the performance of the three CNN models named GoogleNet, VGG11, and MobileNetV3. They found that the architecture of CNN achieved an accuracy of 98.44% with 40x, 100x, 200x, and 400x magnification factors using the BreakHis dataset, which is publicly available, achieved an accuracy of 96.95% on the DDSM dataset for mammography and achieved an accuracy of 99.17% on the MIAS dataset mammograms. T. Pang et al.[\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e] confirmed a semi-supervised GAN breast ultrasound picture generation model. Synthetic datasets improve breast tumor classification accuracy by 90.41% and specificity by 87.94% over state-of-the-art methods. N. Toussaint et al. [\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e] proposed an effective model noise filter network (NF-Net) for breast tumor ultrasound image training with noisy labels. Labeling is improved by the teacher-student module. NF-Net classification models are 73% accurate and 74% F1-score. S. Kumar et al.[\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e] introduced a BreastNet18 model with feature fusion and a CSVM classifier that achieved 99.4% BUSI accuracy. Kowal et al.[\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e] used watershed algorithm (market controlled) and fully used convolutional networks for the segmentation approach. Segmentation was 90% accurate for benign and 86% for malignant. The classification model had 80.2\u0026ndash;92.4% accuracy depending on the data type (malignant or benign).\u003c/p\u003e \u003cp\u003eResmini et al.[\u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e] experimented with GA and SVM classifiers to select breast cancer models and features. Early breast cancer detection had 97.18% accuracy. Ayana et al.[\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e] demonstrated the different transfer learning which are using Adam, Adagrad, and SGD optimizers on the three pre-trained models which are named EfficientNetB2, InceptionV3, and ResNet50. ResNet50-Adagrad-based MSTL achieved an accuracy of 99\u0026thinsp;\u0026plusmn;\u0026thinsp;0.612% on the dataset named Mendeley and achieved an accuracy of 98.7\u0026thinsp;\u0026plusmn;\u0026thinsp;1.1% on the dataset named MT-Small.\u003c/p\u003e \u003cp\u003eRani, N et al.[\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e] used CBIS-DDSM and UPMC datasets to apply transfer learning with VGG16 and achieve 92%-95% accuracy. Salunkhe et al.[\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e] proposed Rapid Tri-Net for breast histological image classification, which achieved 99.79%, 99.8%, 99.73%, and 99.76% accuracy with the BreakHis dataset. Various models were proposed by Zerouaoui et al.[\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e] BreakHis with magnification factor of 40x, 100x, 200x, and 400x classified breast histological images with 93.8%, 93.4%, 93.3%, and 91.8% accuracy.\u003c/p\u003e"},{"header":"3. Methodology","content":"\u003cp\u003eIn a previous section, breast cancer detection literature has been reviewed. Histopathology images with low contrast and non-homogeneous intensity are difficult to detect. To overcome these limitations, this article introduces an enhanced technique for breast cancer detection. This section also discusses early BC detection methods. The proposed methodology consists of three phases. In phase 1, perform classification using Explainable AI. In phase 2 perform classification using Quantum Convolutional Neural Network (QCNN). In phase 3 perform semantic segmentation using Deeplabv3+. BC segmentation learning parameters are used to create a unique deeplabv3\u0026thinsp;+\u0026thinsp;model. After segmentation, the QCNN model is developed based on the selected number of hyperparameters and performed training from scratch for the classification of the BC. Figure one shows the proposed method as a process flow diagram\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eFigure \u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e depicts the steps of segmentation and classification of SL, in which dermoscopic images are fed to the deeplabv3\u0026thinsp;+\u0026thinsp;model for segmentation. The classification task for breast cancer is performed through the QCNN and XAI models to classify the different types of BC.\u003c/p\u003e \u003cdiv id=\"Sec4\" class=\"Section2\"\u003e \u003ch2\u003e3.1 Segmentation using the Proposed DeepLabv3\u0026thinsp;+\u0026thinsp;Model.\u003c/h2\u003e \u003cp\u003eDeepLabv3\u0026thinsp;+\u0026thinsp;is an encoder-decoder model. DeepLabv3\u0026thinsp;+\u0026thinsp;includes an essential but effective decoder module. Dilated convolution at various scales enhances segmentation with object boundaries, and the encoder module handles multiscale-related information. In this research work, an eight-layer segmentation model is proposed for detecting SC. The input image size is 256x256x3. Convolution blocks in the proposed model include Conv, batch-normalization (Bn), ReLU layer, and filters for the convolutional layers. Figure\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003e presents the steps of the segmentation model.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eThe model has been trained on the hyperparameters as mentioned in Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab1\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eHyper parameter values of the proposed model for semantic segmentation\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"2\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eBatch size\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003e8\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eFilters\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e256\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eChannels\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e3\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eClasses\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eEpochs\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e500\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eOptimizer\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eAdam\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003eHyperparameters are evaluated after experimentation, using the three channels, 500 training epochs, two classes, and 8 batch-size for model training, and these parameters provide good results.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec5\" class=\"Section2\"\u003e \u003ch2\u003e3.2 Classification using the XAI Model\u003c/h2\u003e \u003cp\u003eXAI methodologies explain ML model outcomes. A model-agnostic method treats the model as a black box and cannot access its underlying parameters, whereas an intrinsic approach leverages its inherent parameters to explain. Interpretable and transparent ML models are essential in healthcare to foster professional and patient trust. These models describe their decision-making process to improve confidence and understanding. Using machine learning models in healthcare requires transparency, which drives this goal. Interpretable model research is essential to address this need and increase healthcare ML use. Figure\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e shows the model architecture.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eThe proposed XAI model utilizes Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e hyperparameters for training.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab2\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eHyperparameter values of the proposed model XAI for classification\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"2\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eBatch size\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003e8\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTarget size\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e[150,150]\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLearning rate\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.001\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNum epochs\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e300\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003eThe hyperparameters are seen in Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e; in this experiment, parameters included a 300 epoch, an 8-batch size, a 0.001 learning rate, and fifteen transformation layers. This model contains Conv2D, MaxPooling, Dense, and Dropout layers.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec6\" class=\"Section2\"\u003e \u003ch2\u003e3.3 Classification using Quantum Neural Network\u003c/h2\u003e \u003cp\u003eMachine learning using neural networks has made great strides in several practical applications as of late. One clear use is in the investigation of quantum many-body systems, where theoretical analysis is challenging due to the complexity of the states. Several recent articles employ machine learning to study quantum systems, use physical concepts to understand machine learning or use quantum computers to improve machine learning tasks. Quantum computers are solving challenges traditional computers can't. Quantum computers work differently from classical ones. By parallelizing qubits, quantum computers may leverage superposition and entanglement, which conventional computers cannot, and they can be incredibly fast [\u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eThe convolution layer finds hidden data using linear region pixel combinations. Feature map compression via the pooling layer reduces learning resources and model fit. Applying these layers repeatedly reduces data size sufficiently for the fully linked layer to classify. Gradient descent or other optimizers may train the model using the difference in loss between the learned and actual labels for improved outcomes. Traditional machine learning methods can't solve many real-world situations. Data must be translated to standard computer data for machine learning on the many-body Hilbert space quantum physics problem set. Data grows quickly with the system. The challenge is difficult for machine learning. Computer settings that can't handle data and models have alternatives. Much research has employed the Quantum Convolutional Neural Network (QCNN), which combines CNN with quantum computing, to solve these challenges. [\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e]. CNNs on quantum systems can solve quantum physics issues fast. CNN can improve things by adding a quantum system to the issues it previously addressed. Image categorization often uses CNN-style neural networks. Quantum computers are superposition and parallel computing experts. Henderson recommended boosting CNN using quantum settings. CNN investigated quantum computing after these revelations. Quantum convolution layers operate like convolution layers. Quantum convolution filters input feature maps to build new ones. Unlike convolution, quantum convolution filters in quantum computing. Traditional computers lack quantum superposition and parallel computation. Quantum convolution processes visual maps in filter size increments. The quantum convolution layer may be developed with small quantum computers [\u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e]. As illustrated in Fig.\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e4\u003c/span\u003e, the quantum convolution layer is capable of construction. The notion is developed as follows:\u003c/p\u003e \u003cp\u003e \u003cul\u003e \u003cli\u003e \u003cp\u003eThe filter size-specific pixel data is encoded in qubits.\u003c/p\u003e \u003c/li\u003e \u003cli\u003e \u003cp\u003eQuantum circuits that utilize filters to identify the hidden state from the input state.\u003c/p\u003e \u003c/li\u003e \u003cli\u003e \u003cp\u003eThe decoding process measures fresh classical data.\u003c/p\u003e \u003c/li\u003e \u003cli\u003e \u003cp\u003eRepeat 1)\u0026ndash;3) until the new feature map is ready.\u003c/p\u003e \u003c/li\u003e \u003c/ul\u003e \u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eFigure \u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e4\u003c/span\u003e shows how these Layers are added to the network. Define the quantum circuit using Google's quantum circuit design framework. Embed this static model section. Show a rectangle quantum circuit and specify the layers of the model in Fig.\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e4\u003c/span\u003e(a), a two-qubit unitary circuit in Fig.\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e4\u003c/span\u003e(b), and a two-qubit pooling circuit in Fig.\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e4\u003c/span\u003e(c).\u003c/p\u003e \u003cp\u003eIn a proposed quantum neural network, \u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\(2\\times 2\\)\u003c/span\u003e\u003c/span\u003e square region is embedded in the quantum circuit through parameterized rotations employed to qubits that are initiated in the ground state. The unitary operations are performed through the variational quantum circuit. The quantum circuit measured the list of the raw expectation values that are mapped to the channels of the single pixel of output. This process is repeated in different parts until scan whole image. The model contains flattened input, output layers with different activation units, and a Dense layer with ReLU activation of the softmax layer. The proposed model architecture is provided in Fig.\u0026nbsp;\u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e5\u003c/span\u003e.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eThe model approach uses Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e the hyperparameters for training purposes.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab3\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 3\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eHyperparameter values of the proposed model QCNN for classification\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"2\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eBatch size\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003e16\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLearning rate\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.002\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNum epochs\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e20\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003eThe hyperparameters are seen in Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e; in this experiment, parameters included a 20 epoch, a 16-batch size, and a 0.002 learning rate.\u003c/p\u003e \u003c/div\u003e"},{"header":"4. Results and Discussion","content":"\u003cp\u003eThe segmentation and classification models are tested on several datasets. For segmentation, BUSIS[\u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e24\u003c/span\u003e] and DDSM [\u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e25\u003c/span\u003e] datasets are utilized. For classification, Histopathology [\u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e] and BreakHis [\u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e, \u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e28\u003c/span\u003e] datasets are utilized. MATLAB-2023B, Google Colab, and Jupyter Notebook with Windows OS and RTX 3070 graphic card do the studies. This research tests the suggested technique with two experiments. The recommended techniques are assessed using sensitivity, accuracy specificity, and F1 score. We abbreviate these as Sn, Acc, SP, and f1 respectively. The dataset is described in Table\u0026nbsp;\u003cspan refid=\"Tab4\" class=\"InternalRef\"\u003e4\u003c/span\u003e These BC detection databases are public.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab4\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 4\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eDataset detail used in research.\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"5\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRef #\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eYears\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eDatasets\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eClasses\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003eNo of Images\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e[\u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e24\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e2021\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eBUSIS\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e1,578\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e[\u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e25\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e2021\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eDDSM\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e13,140\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e[\u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e2018\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eHistopathology\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e271,404\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e[\u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e2019\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eBreakHis\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e16,143\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e[\u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e28\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e2020\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eBreakHis\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e \u003cp\u003e8\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e \u003cp\u003e196,868\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003eTable\u0026nbsp;\u003cspan refid=\"Tab4\" class=\"InternalRef\"\u003e4\u003c/span\u003e displays the number of input images that are applied for training and testing. The detail of the publicly available dataset is described as follows: BreakHis dataset contains two classes of BC such as malignant and benign with 16,143 images. BreakHis dataset contains 196,868 images with eight classes including AD, FB, PT, TA, DC, LC, MC, and PC lesions. The DDSM dataset contains 2 classes such as malignant and benign with 13,140 images. The BUSIS contains 1,578 images with 2 classes. The Histopathology contains 271,404 images for 2 classes such as malignant and benign. One experiment is performed on segmentation of the breast lesions and two models are proposed for classification of the breast lesions.\u003c/p\u003e \u003cdiv id=\"Sec8\" class=\"Section2\"\u003e \u003ch2\u003e4.1. Experiment#1: Segmentation of the Breast Cancer (BC)\u003c/h2\u003e \u003cp\u003eThe proposed segmentation model's performance is computed using mean and weighted IoU as M-IoU and W-IoU, global (G-Accuracy) as G-Acc and mean (M-Accuracy) as M-Acc, mean BF score as M-BF-Score from BUSIS and DDSM datasets in Tables\u0026nbsp;\u003cspan refid=\"Tab5\" class=\"InternalRef\"\u003e5\u003c/span\u003e\u0026ndash;\u003cspan refid=\"Tab6\" class=\"InternalRef\"\u003e6\u003c/span\u003e.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab5\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 5\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003ePerformance of the segmentation model using the BUSIS dataset.\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"2\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eG-Acc\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.991\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eM-IoU\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.990\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eM-Acc\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.989\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eW-IoU\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.988\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eM-BF-Score\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e0.979\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003eTable\u0026nbsp;\u003cspan refid=\"Tab5\" class=\"InternalRef\"\u003e5\u003c/span\u003e shows the suggested segmentation model's 0.989 and 0.991 BUSIS M- and G-Accuracy. BUSIS and DDSM breast cancer segmentation findings are shown in Figs.\u0026nbsp;\u003cspan refid=\"Fig6\" class=\"InternalRef\"\u003e6\u003c/span\u003e and \u003cspan refid=\"Fig7\" class=\"InternalRef\"\u003e7\u003c/span\u003e.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eUsing the BUSIS dataset, segmented BC is overlaid on original input pictures to highlight breast cancer locations in Fig.\u0026nbsp;\u003cspan refid=\"Fig6\" class=\"InternalRef\"\u003e6\u003c/span\u003e.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab6\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 6\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003ePerformance of the segmentation model using the DDSM dataset.\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"2\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eG-Acc\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.989\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eM-IoU\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0. 987\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eM-Acc\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0. 986\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eW-IoU\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0. 989\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eM-BF-Score\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0. 987\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003eTable\u0026nbsp;\u003cspan refid=\"Tab6\" class=\"InternalRef\"\u003e6\u003c/span\u003e summarizes the results of the segmentation proposed earlier; the model achieved M-Acc and G-Acc of 0.986 and 0.989 on the DDSM dataset. Figure\u0026nbsp;\u003cspan refid=\"Fig7\" class=\"InternalRef\"\u003e7\u003c/span\u003e presents segmented breast cancer and maps it to the source images to demonstrate diseased breast areas using the DDSM dataset.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eThe achieved segmentation results are compared to existing methods as given in Table\u0026nbsp;\u003cspan refid=\"Tab7\" class=\"InternalRef\"\u003e7\u003c/span\u003e.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab7\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 7\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eProposed model for segmentation result compared with existing work.\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"4\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRef #\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eYear\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eDatasets\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eResult \u003c/p\u003e \u003cp\u003e(ACC)\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e[\u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e29\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2020\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\" morerows=\"5\" rowspan=\"6\"\u003e \u003cp\u003eCBIS-DDSM\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e84.40%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e[\u003cspan citationid=\"CR30\" class=\"CitationRef\"\u003e30\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2021\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e91.99%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e[\u003cspan citationid=\"CR31\" class=\"CitationRef\"\u003e31\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2022\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e92.86%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e[\u003cspan citationid=\"CR32\" class=\"CitationRef\"\u003e32\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2023\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e86.71%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e[\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2024\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e92.00%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003e\u003cb\u003eProposed Method\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e98.00%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e[\u003cspan citationid=\"CR33\" class=\"CitationRef\"\u003e33\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2021\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\" morerows=\"4\" rowspan=\"5\"\u003e \u003cp\u003eBUSIS\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e94.12%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e[\u003cspan citationid=\"CR34\" class=\"CitationRef\"\u003e34\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2022\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e89.73%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e[\u003cspan citationid=\"CR35\" class=\"CitationRef\"\u003e35\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2023\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e96.52%,93.18%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e[\u003cspan citationid=\"CR36\" class=\"CitationRef\"\u003e36\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2024\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e96.99%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003e\u003cb\u003eProposed Method\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e99%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003eFor automatic breast segmentation, use Atreus neural semantic segmentation. This DeepLabv3\u0026thinsp;+\u0026thinsp;investigation discovered malignancies on CBIS-DDSM and BUSIS datasets 98% of the time. The intended VGG16 network is 0.844 CBIS-DDSM accurate[\u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e29\u003c/span\u003e]. The two-view classifier showed 0.9199\u0026thinsp;\u0026plusmn;\u0026thinsp;0.0623 accuracy in 5-fold cross-validation, identifying malignant and non-cancerous breast images using one model and no additional data[\u003cspan citationid=\"CR30\" class=\"CitationRef\"\u003e30\u003c/span\u003e]. INbreast scored 96.34% for Connected-SegNets, CBIS-DDSM 92.86%, and private 92.25% [\u003cspan citationid=\"CR31\" class=\"CitationRef\"\u003e31\u003c/span\u003e]. The method achieved 86.71% CBIS-DDSM dataset accuracy[\u003cspan citationid=\"CR32\" class=\"CitationRef\"\u003e32\u003c/span\u003e]. Transfer learning using the VGG16 model was 92\u0026ndash;95% accurate. VGG16 transfer learning benefits CBIS-DDSM and UPMC[\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e]. The public BUS dataset gave the SHA-MTL model 94.12% accuracy[\u003cspan citationid=\"CR33\" class=\"CitationRef\"\u003e33\u003c/span\u003e]. CNN model MIAS accuracy was 96.55%. The DDSM dataset showed 90.68%. INbreast showed 91.28% [\u003cspan citationid=\"CR34\" class=\"CitationRef\"\u003e34\u003c/span\u003e]. ShuffleNet-ResNet finds 99.17% abnormalities and 98.00% malignancies in mini-DDSM and 96.52% and 93.18% in BUSI datasets[\u003cspan citationid=\"CR35\" class=\"CitationRef\"\u003e35\u003c/span\u003e]. The triple decoder\u0026thinsp;+\u0026thinsp;multi-attention model was 96.99% accurate on BUSI and 97.69% on UDIAT. Jaccard index testing is 83.40% in UDIAT and 82.31% in BUSI [\u003cspan citationid=\"CR36\" class=\"CitationRef\"\u003e36\u003c/span\u003e].\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec9\" class=\"Section2\"\u003e \u003ch2\u003e4.2. Experiment#2: XAI Model Classification of BC\u003c/h2\u003e \u003cp\u003eThe XAI model is used for the classification of BC. The BC is classified into two classes: malignant and benign. Table\u0026nbsp;\u003cspan refid=\"Tab8\" class=\"InternalRef\"\u003e8\u003c/span\u003e demonstrates the BreakHis dataset's results using our approach to the classification problem. The training and testing outcomes of the proposed method are provided in Fig.\u0026nbsp;\u003cspan refid=\"Fig8\" class=\"InternalRef\"\u003e8\u003c/span\u003e. Accuracy as ACC, F1 Score as F1, Recall as Re, and Precision as Pr.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eThe classification results on BreakHis are presented in the form of a confusion matrix in Fig.\u0026nbsp;\u003cspan refid=\"Fig9\" class=\"InternalRef\"\u003e9\u003c/span\u003e.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab8\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 8\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eProposed classification result on BreakHis Dataset with magnification factors.\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"5\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMagnification Factor\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eACC\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eF1\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eRe\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003ePr\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e40X\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e100X\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e200X\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e400X\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003eTable\u0026nbsp;\u003cspan refid=\"Tab8\" class=\"InternalRef\"\u003e8\u003c/span\u003e shows 100% accuracy in the BreakHis dataset for classification. Table\u0026nbsp;\u003cspan refid=\"Tab9\" class=\"InternalRef\"\u003e9\u003c/span\u003e compares the proposed classification model to current studies.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eIn Fig.\u0026nbsp;\u003cspan refid=\"Fig10\" class=\"InternalRef\"\u003e10\u003c/span\u003e, computed results on eight classes present the ratio of true positive/negative and false positive/negative. The training and validation accuracy with the number of epochs is presented graphically where a pink line for training and a green line for validation. The quantitative results on eight classes using the BreakHis dataset with a 40x magnification factor are given in Table\u0026nbsp;\u003cspan refid=\"Tab9\" class=\"InternalRef\"\u003e9\u003c/span\u003e and the 100x magnification factor is given in Table\u0026nbsp;\u003cspan refid=\"Tab10\" class=\"InternalRef\"\u003e10\u003c/span\u003e.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab9\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 9\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eClassification results on BreakHis with 40x magnification factor\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"4\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eClasses\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePrecision%\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eRecall%\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eF1-score%\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eAD\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.91\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.95\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eDC\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eFB\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.86\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eLC\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eMC\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.92\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.96\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003ePC\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.81\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003ePT\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.81\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.89\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eTA\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.94\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.97\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eAccuracy\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"3\" nameend=\"c4\" namest=\"c2\"\u003e \u003cp\u003e0.96\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eMisclassification rate\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"3\" nameend=\"c4\" namest=\"c2\"\u003e \u003cp\u003e0.03\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eMacro-F1\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"3\" nameend=\"c4\" namest=\"c2\"\u003e \u003cp\u003e0.96\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eWeighted-F1\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"3\" nameend=\"c4\" namest=\"c2\"\u003e \u003cp\u003e0.96\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003eTable\u0026nbsp;\u003cspan refid=\"Tab9\" class=\"InternalRef\"\u003e9\u003c/span\u003e, provides the classification outcomes on 40x magnification factor on eight classes such as AD, FB, PT, TA, DC, LC, MC, and PC. In which 96.27% accuracy and 0 misclassification rate is achieved.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab10\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 10\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eClassification results on BreakHis with 100x magnification factor\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"4\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eClasses\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePrecision%\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eRecall%\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eF1-score%\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eAD\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.98\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.99\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eDC\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eFB\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.51\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.68\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eLC\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.89\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.94\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eMC\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.96\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.70\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.81\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003ePC\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003ePT\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.44\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.61\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eTA\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.95\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.97\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eAccuracy\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"3\" nameend=\"c4\" namest=\"c2\"\u003e \u003cp\u003e0.85\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eMisclassification rate\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"3\" nameend=\"c4\" namest=\"c2\"\u003e \u003cp\u003e0.14\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eMacro-F1\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"3\" nameend=\"c4\" namest=\"c2\"\u003e \u003cp\u003e0.87\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eWeighted-F1\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"3\" nameend=\"c4\" namest=\"c2\"\u003e \u003cp\u003e0.85\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003eTable\u0026nbsp;\u003cspan refid=\"Tab10\" class=\"InternalRef\"\u003e10\u003c/span\u003e, provides the classification outcomes on 100x magnification factor on eight classes such as AD, FB, PT, TA, DC, LC, MC, and PC. In which 85.03% accuracy and 0 misclassification rate is achieved.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eIn Fig.\u0026nbsp;\u003cspan refid=\"Fig11\" class=\"InternalRef\"\u003e11\u003c/span\u003e, computed results on eight classes present the ratio of true positive/negative and false positive/negative. The training and validation accuracy with the number of epochs is presented graphically where a pink line for training and a green line for validation. The quantitative results on eight classes using the BreakHis dataset with a 40x magnification factor are given in Table\u0026nbsp;\u003cspan refid=\"Tab11\" class=\"InternalRef\"\u003e11\u003c/span\u003e and the 100x magnification factor is given in Table\u0026nbsp;\u003cspan refid=\"Tab12\" class=\"InternalRef\"\u003e12\u003c/span\u003e.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab11\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 11\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eClassification results on BreakHis with 200x magnification factor\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"4\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eClasses\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePrecision%\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eRecall%\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eF1-score%\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eAD\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.97\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.98\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eDC\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eFB\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.95\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.97\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eLC\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eMC\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003ePC\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003ePT\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.95\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.97\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eTA\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.97\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.98\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eAccuracy\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"3\" nameend=\"c4\" namest=\"c2\"\u003e \u003cp\u003e0.99\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eMisclassification rate\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"3\" nameend=\"c4\" namest=\"c2\"\u003e \u003cp\u003e0.00\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eMacro-F1\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"3\" nameend=\"c4\" namest=\"c2\"\u003e \u003cp\u003e0.99\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eWeighted-F1\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"3\" nameend=\"c4\" namest=\"c2\"\u003e \u003cp\u003e0.99\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003eTable\u0026nbsp;\u003cspan refid=\"Tab11\" class=\"InternalRef\"\u003e11\u003c/span\u003e, provides the classification outcomes on 100x magnification factor on eight classes such as AD, FB, PT, TA, DC, LC, MC, and PC. In which 99.10% accuracy and 0 misclassification rate is achieved.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab12\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 12\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eClassification results on BreakHis with 400x magnification factor\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"4\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eClasses\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePrecision%\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eRecall%\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eF1-score%\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eAD\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.91\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.95\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eDC\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eFB\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.98\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.99\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eLC\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.98\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.99\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eMC\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.92\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.96\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003ePC\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003ePT\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e0.99\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eTA\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eAccuracy\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"3\" nameend=\"c4\" namest=\"c2\"\u003e \u003cp\u003e0.98\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eMisclassification rate\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"3\" nameend=\"c4\" namest=\"c2\"\u003e \u003cp\u003e0.01\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eMacro-F1\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"3\" nameend=\"c4\" namest=\"c2\"\u003e \u003cp\u003e0.98\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eWeighted-F1\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"3\" nameend=\"c4\" namest=\"c2\"\u003e \u003cp\u003e0.98\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003eTable\u0026nbsp;\u003cspan refid=\"Tab12\" class=\"InternalRef\"\u003e12\u003c/span\u003e, provides the classification outcomes on 100x magnification factor on eight classes such as AD, FB, PT, TA, DC, LC, MC, and PC. In which 98.62% accuracy and 0 misclassification rate is achieved.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec10\" class=\"Section2\"\u003e \u003ch2\u003e4.3. Experiment#3: Classification of the BC using the QNN Model\u003c/h2\u003e \u003cp\u003eThe QNN model is used for the classification of BC. The BC is classified into two classes: malignant and benign. Figure\u0026nbsp;\u003cspan refid=\"Fig10\" class=\"InternalRef\"\u003e10\u003c/span\u003e shows the classification result on the publicly available BreakHis dataset.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eFigure \u003cspan refid=\"Fig12\" class=\"InternalRef\"\u003e12\u003c/span\u003e, presents the classification results on different magnification levels such as 40x, 100x, and 200x. The performance of classification is measured in terms of the confusion matrix and training and validation accuracy for the number of epochs. In the confusion matrix, 0 denotes the benign class and 1 is the malignant class. The quantitative assessment in terms of ACC, F1, Re, and Pr.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab13\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 13\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eclassification result on BreakHis Dataset with magnification factors.\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"5\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMagnification Factor\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eACC%\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eF1\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eRe\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003ePr\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e40x\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e100x\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.97\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.97\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.95\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e200x\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e0.97\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e0.97\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e0.94\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003eIn Table\u0026nbsp;\u003cspan refid=\"Tab13\" class=\"InternalRef\"\u003e13\u003c/span\u003e, the achieved results in terms of accuracy based on the binary classification are 100% on 40x, 97.92% on 100x, and 200x. The classification results are computed on eight classes of breast cancer and are presented in Fig.\u0026nbsp;\u003cspan refid=\"Fig11\" class=\"InternalRef\"\u003e11\u003c/span\u003e.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eIn Fig.\u0026nbsp;\u003cspan refid=\"Fig13\" class=\"InternalRef\"\u003e13\u003c/span\u003e, computed results on eight classes present the ratio of true positive/negative and false positive/negative. The training and validation accuracy with the number of epochs is presented graphically where a pink line for training and a green line for validation. The quantitative results on eight classes using the BreakHis dataset with a 40x magnification factor are given in Table\u0026nbsp;\u003cspan refid=\"Tab14\" class=\"InternalRef\"\u003e14\u003c/span\u003e.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab14\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 14\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eClassification results on BreakHis with 40x magnification factor\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"4\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eClasses\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePrecision%\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eRecall%\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eF1-score%\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eAD\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eFB\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003ePT\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eTA\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eDC\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eLC\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eMC\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003ePC\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eAccuracy\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"3\" nameend=\"c4\" namest=\"c2\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eMisclassification rate\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"3\" nameend=\"c4\" namest=\"c2\"\u003e \u003cp\u003e0.00\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eMacro-F1\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"3\" nameend=\"c4\" namest=\"c2\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eWeighted-F1\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"3\" nameend=\"c4\" namest=\"c2\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003eTable\u0026nbsp;\u003cspan refid=\"Tab14\" class=\"InternalRef\"\u003e14\u003c/span\u003e, provides the classification outcomes on 40x magnification factor on eight classes such as AD, FB, PT, TA, DC, LC, MC, and PC. In which 100% accuracy and 0 misclassification rate is achieved.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab15\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 15\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eClassification results on BreakHis with 100x magnification factor\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"4\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eClass name\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003ePrecision\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eRecall\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eF1-score\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eAD\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eFB\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003ePT\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eTA\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eDC\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eLC\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eMC\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003ePC\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eAccuracy\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"3\" nameend=\"c4\" namest=\"c2\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eMisclassification rate\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"3\" nameend=\"c4\" namest=\"c2\"\u003e \u003cp\u003e0.00\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eMacro-F1\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"3\" nameend=\"c4\" namest=\"c2\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e\u003cb\u003eWeighted-F1\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colspan=\"3\" nameend=\"c4\" namest=\"c2\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003eTable\u0026nbsp;\u003cspan refid=\"Tab15\" class=\"InternalRef\"\u003e15\u003c/span\u003e provides the classification outcomes on the 100x magnification factor. The achieved outcomes are compared to the existing methods as given in Table\u0026nbsp;\u003cspan refid=\"Tab16\" class=\"InternalRef\"\u003e16\u003c/span\u003e.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab16\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 16\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eProposed model for classification result compared with existing work\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"4\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRef #\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eYear\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eDatasets\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eACC%\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e[\u003cspan citationid=\"CR37\" class=\"CitationRef\"\u003e37\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2021\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\" morerows=\"7\" rowspan=\"8\"\u003e \u003cp\u003eBreakHis\u003c/p\u003e \u003cp\u003e2 classes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e96.75\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e[\u003cspan citationid=\"CR38\" class=\"CitationRef\"\u003e38\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2022\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e94.67\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e[\u003cspan citationid=\"CR39\" class=\"CitationRef\"\u003e39\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2022\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e96.35\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e[\u003cspan citationid=\"CR40\" class=\"CitationRef\"\u003e40\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2023\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e96.30\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e[\u003cspan citationid=\"CR41\" class=\"CitationRef\"\u003e41\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2024\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e99.16\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e[\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2024\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e99.76\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003e\u003cb\u003eProposed Method with XAI\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e96.87\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003e\u003cb\u003eProposed Method with QNN\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e[\u003cspan citationid=\"CR42\" class=\"CitationRef\"\u003e42\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2021\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\" morerows=\"4\" rowspan=\"5\"\u003e \u003cp\u003eBreakHis\u003c/p\u003e \u003cp\u003e8 classes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e95.00\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e[\u003cspan citationid=\"CR43\" class=\"CitationRef\"\u003e43\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2023\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e89.00\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003e[\u003cspan citationid=\"CR41\" class=\"CitationRef\"\u003e41\u003c/span\u003e]\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003e2024\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e98.27\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003e\u003cb\u003eProposed Method with XAI\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e98.62\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colspan=\"2\" nameend=\"c2\" namest=\"c1\"\u003e \u003cp\u003e\u003cb\u003eProposed Method with QNN\u003c/b\u003e\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003e1.00\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003eXAI and QCNN models classify BC with 96.87% and 100% accuracy on BreakHis with 2 and 8 classes, respectively, according to Table\u0026nbsp;\u003cspan refid=\"Tab16\" class=\"InternalRef\"\u003e16\u003c/span\u003e. Model accuracy is 96.75%, 96.7%, 95.78%, and 93.86% for benign and malignant binary classification [\u003cspan citationid=\"CR37\" class=\"CitationRef\"\u003e37\u003c/span\u003e]. Classify BreakHis with pretrained models. The highest classifier is VGG16 with a precision of 92.60% and an f1- score of 85.21%. The model achieved an accuracy of 94.67% and a recall of 80.52% [\u003cspan citationid=\"CR38\" class=\"CitationRef\"\u003e38\u003c/span\u003e]. The proposed model has a maximum accuracy of 96.35%. The network architectures tested include VGG16, ResNet50, and a proposed model [\u003cspan citationid=\"CR39\" class=\"CitationRef\"\u003e39\u003c/span\u003e]. On the BreakHis dataset, pretrained models had 92%, 87%, 90%, 79%, and 92% accuracy. Data features were retrieved using ResNet 50. To 96.3%, accuracy has substantially increased [\u003cspan citationid=\"CR40\" class=\"CitationRef\"\u003e40\u003c/span\u003e]. AlexNet convolutional neural network diagnoses breast cancer using BreakHis dataset features. The proposed method has 99.36% AUC, 95% accuracy, as well as 97% sensitivity with 90% specificity [\u003cspan citationid=\"CR42\" class=\"CitationRef\"\u003e42\u003c/span\u003e]. Deep learning cancer classifiers VGG, ResNet, Xception, Inception. Top performance Xception is 0.9 F1 and 89% accurate. Inception and ResNet are 87% accurate [\u003cspan citationid=\"CR43\" class=\"CitationRef\"\u003e43\u003c/span\u003e]. The Swin-Transformer V2 architecture classified eight-class BC histopathological images with multiple labels with 98.27%, 97.95%, 98.97%, and 99.16% accuracy on Break-His [\u003cspan citationid=\"CR41\" class=\"CitationRef\"\u003e41\u003c/span\u003e]. Rapid Tri-Net with Aquila Optimization (Rapid Tri-Net) on BreakHis and BACH datasets achieved 99.79%, 99.8%, 99.73%, and 99.76% accuracy at 40x, 100x, 200x, and 400x [\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e].\u003c/p\u003e \u003c/div\u003e"},{"header":"5. Conclusion","content":"\u003cp\u003eStatistically speaking, for the worldwide population of women breast cancer is the number one cancer type in terms of the number of patients. Poor health, hormone issues, and environmental factors may make it more probable for women of any age to have it. Breast cancer early detection helps more women survive. This approach\u0026apos;s efficiency is verified by comparing the findings to the newest work in this field. \u0026nbsp;\u003c/p\u003e\n\u003cp\u003eThe segmentation of the breast lesion is a challenging task due to the variable shape, size, and texture of the lesion region. To overcome this challenge, the Deeplabv3 model is used with optimal hyperparameters for segmentation. This method\u0026apos;s results are evaluated on BUSIS and DDSM datasets with the accuracy of 99.0% and 98.0% respectively. \u0026nbsp;Furthermore, the classification of different types of lesion regions is still a great challenge, to overcome this two models are proposed such as XAI and quantum neural network. These models are designed on the selected number of layers and optimal hyperparameters and evaluated on the different types of magnification factors such as 40x, 100x, and 200x.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eThe classification results are computed on BreakHis\u0026apos;s publically available dataset. The XAI model classifies breast cancer achieved an accuracy of 96.87% and achieved an accuracy of 98.62% with 8 classes such as AD, FB, PT , TA, DC, LC, MC, and PC, quantum neural network models classify breast cancer achieved an accuracy of 100% on binary classes such as benign and malignant and achieved an accuracy of 100% with 8 classes such as AD, FB, PT , TA, DC, LC, MC and PCon BreakHis dataset with magnification factors 40x, 100x, 200x, and 400x. \u0026nbsp;As per the results of the strategy and experiments outlined above, we outperformed the published results on the metrics defined herein.\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eFunding Declaration\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eWe received no funding regarding this article.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eCompeting Interest declaration\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNo competing interest regarding this article\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAuthor Contribution declaration\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eSaqqiya Waris\u003c/strong\u003e: Implementation, Draft writing\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eJavaria Amin:\u003c/strong\u003e Implementation, Algorithm designing, Draft Writing, Proofreading, Data Collection, Supervision\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAmina Sarwar:\u003c/strong\u003e Formating\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eMuhammad Sharif and Mussarat Yasmeen:\u003c/strong\u003e Proof-reading\u003c/p\u003e\u003ch2\u003eAuthor Contribution\u003c/h2\u003e\u003cp\u003eFunding DeclarationWe received no funding regarding this article.Competing Interest declarationNo competing interest regarding this articleAuthor Contribution declarationSaqqiya Waris: Implementation, Draft writingJavaria Amin: Implementation, Algorithm designing, Draft Writing, Proofreading, Data Collection, SupervisionAmina Sarwar: FormatingMuhammad Sharif and Mussarat Yasmeen: Proof-reading\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eCheng H-D, Shan J, Ju W, Guo Y, Zhang L. Automated breast cancer detection and classification using ultrasound images: A survey. Pattern Recogn. 2010;43(1):299\u0026ndash;317.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCheng H-D, Shi X, Min R, Hu L, Cai X, Du H. Approaches for automated detection and classification of masses in mammograms, \u003cem\u003ePattern recognition\u003c/em\u003e, vol. 39, no. 4, pp. 646\u0026ndash;668, 2006.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCastellino RA. Computer aided detection (CAD): an overview, Cancer Imaging, vol. 5, no. 1, p. 17, 2005.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eXian M, et al. A benchmark for breast ultrasound image segmentation (BUSIS). Infinite Study; 2018.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHuang Q, Huang Y, Luo Y, Yuan F, Li X. Segmentation of breast ultrasound image with semantic classification of superpixels. Med Image Anal. 2020;61:101657.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSiegel RL, Miller KD, Fuchs HE, Jemal A. Cancer statistics, 2022, CA: a cancer journal for clinicians, 72, 1, 2022.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eYassin NI, Omran S, El EM, Houby, Allam H. Machine learning techniques for breast cancer computer aided diagnosis using different image modalities: A systematic review, Computer methods and programs in biomedicine, vol. 156, pp. 25\u0026ndash;45, 2018.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAmrane M, Oukid S, Gagaoua I, Ensari T. Breast cancer classification using machine learning. 2018 electric electronics, computer science, biomedical engineerings' meeting (EBBT). IEEE; 2018. pp. 1\u0026ndash;4.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSzegedy C et al. Going deeper with convolutions, in Proceedings of the IEEE conference on computer vision and pattern recognition, 2015, pp. 1\u0026ndash;9.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSalpea N, Tzouveli P, Kollias D. Medical image segmentation: A review of modern architectures, in European Conference on Computer Vision, 2022: Springer, pp. 691\u0026ndash;708.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMajumdar S, Pramanik P, Sarkar R. Gamma function based ensemble of CNN models for breast cancer detection in histopathology images. Expert Syst Appl. 2023;213:119022.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePang T, Wong JHD, Ng WL, Chan CS. Semi-supervised GAN-based radiomics model for data augmentation in breast ultrasound mass classification, Computer Methods and Programs in Biomedicine, 203, p. 106018, 2021.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eToussaint N et al. Weakly supervised localisation for fetal ultrasound images, in Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support: 4th International Workshop, DLMIA 2018, and 8th International Workshop, ML-CDS 2018, Held in Conjunction with MICCAI 2018, Granada, Spain, September 20, 2018, Proceedings 4, 2018: Springer, pp. 192\u0026ndash;200.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKumar S, Parthasarathi P, Hogo MA, Masud M, Al-Amri JF, Abouhawwash M. Breast Cancer Detection Using Breastnet-18 Augmentation with Fine-Tuned VGG-16, Intelligent Automation and Soft Computing, 36, 2, pp. 2363\u0026ndash;78, 2023.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKowal M, Skobel M, Gramacki A, Korbicz J. Breast cancer nuclei segmentation and classification based on a deep learning approach. Int J Appl Math Comput Sci. 2021;31(1):85\u0026ndash;106.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eResmini R, Silva L, Araujo AS, Medeiros P, Muchaluat-Saade D, Conci A. Combining genetic algorithms and SVM for breast cancer diagnosis using infrared thermography, Sensors, 21, 14, p. 4802, 2021.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAyana G, Park J, Jeong J-W, Choe S-w. A novel multistage transfer learning for ultrasound breast cancer image classification, Diagnostics, 12, 1, p. 135, 2022.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRani N, Gupta DK, Singh S. Multi-class classification of breast cancer abnormality using transfer learning, Multimedia Tools and Applications, pp. 1\u0026ndash;16, 2024.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSalunkhe PB, Patil PS. Rapid tri-net: breast cancer classification from histology images using rapid tri-attention network, Multimedia Tools and Applications, pp. 1\u0026ndash;31, 2024.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZerouaoui H, Alaoui OE, Idri A. New design strategies of deep heterogenous convolutional neural networks ensembles for breast cancer diagnosis. Multimedia Tools Appl, pp. 1\u0026ndash;32, 2024.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eFarhi E, Neven H. Classification with quantum neural networks on near term processors, arXiv preprint arXiv:1802.06002, 2018.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBokhan D, Mastiukova AS, Boev AS, Trubnikov DN, Fedorov AK. Multiclass classification using quantum convolutional neural networks with hybrid quantum-classical learning. Front Phys. 2022;10:1069985.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eJia ZA, Yi B, Zhai R, Wu YC, Guo GC, Guo GP. Quantum neural network states: A brief review of methods and applications, Advanced Quantum Technologies, 2, no. 7\u0026ndash;8, p. 1800077, 2019.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eA. shah. Breast Ultrasound Images Dataset. Kaggle. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://www.kaggle.com/datasets/aryashah2k/breast-ultrasound-images-dataset\u003c/span\u003e\u003cspan address=\"https://www.kaggle.com/datasets/aryashah2k/breast-ultrasound-images-dataset\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (accessed 2024).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAwsaf. CBIS-DDSM: Breast Cancer Image Dataset. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://www.kaggle.com/datasets/awsaf49/cbis-ddsm-breast-cancer-image-dataset\u003c/span\u003e\u003cspan address=\"https://www.kaggle.com/datasets/awsaf49/cbis-ddsm-breast-cancer-image-dataset\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (accessed.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMooney P. Breast Histopathology Images. Kaggle. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://www.kaggle.com/datasets/paultimothymooney/breast-histopathology-images\u003c/span\u003e\u003cspan address=\"https://www.kaggle.com/datasets/paultimothymooney/breast-histopathology-images\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (accessed 2024).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAnuKritika. Breast Cancer Dataset from BreakHis. Kaggle. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://www.kaggle.com/datasets/kritika397/breast-cancer-dataset-from-breakhis\u003c/span\u003e\u003cspan address=\"https://www.kaggle.com/datasets/kritika397/breast-cancer-dataset-from-breakhis\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (accessed 2023).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBukun. accessed. BreakHis. Kaggle. \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://www.kaggle.com/datasets/ambarish/breakhis\u003c/span\u003e\u003cspan address=\"https://www.kaggle.com/datasets/ambarish/breakhis\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e (2024).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eFalconi LG, Perez M, Aguilar WG, Conci A. Transfer learning and fine tuning in breast mammogram abnormalities classification on CBIS-DDSM database. Adv Sci Technol Eng Syst J. 2020;5(2):154\u0026ndash;65.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePetrini DG et al. End-to-end training of convolutional network for breast cancer detection in two-view mammography, Cancer Research, vol. 81, no. 13_Supplement, pp. 183\u0026ndash;183, 2021.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAlkhaleefah M et al. Connected-segNets: A deep learning model for breast tumor segmentation from X-ray images, Cancers, vol. 14, no. 16, p. 4030, 2022.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBouzar-Benlabiod L, Harrar K, Yamoun L, Khodja MY, Akhloufi MA. A novel breast cancer detection architecture based on a CNN-CBR system for mammogram classification. Comput Biol Med. 2023;163:107133.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZhang G, Zhao K, Hong Y, Qiu X, Zhang K, Wei B. SHA-MTL: soft and hard attention multi-task learning for automated breast cancer ultrasound image segmentation and classification. Int J Comput Assist Radiol Surg. 2021;16:1719\u0026ndash;25.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMuduli D, Dash R, Majhi B. Automated diagnosis of breast cancer using multi-modal datasets: A deep convolution neural network based approach. Biomed Signal Process Control. 2022;71:102825.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSahu A, Das PK, Meher S. High accuracy hybrid CNN classifiers for breast cancer detection using mammogram and ultrasound datasets. Biomed Signal Process Control. 2023;80:104292.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eUmer MJ, Sharif M, Raza M. A Multi-attention Triple Decoder Deep Convolution Network for Breast Cancer Segmentation Using Ultrasound Images, Cognitive Computation, 16, 2, pp. 581\u0026ndash;94, 2024.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZewdie ET, Tessema AW, Simegn GL. Classification of breast cancer types, sub-types and grade from histopathological images using deep learning technique. Health Technol. 2021;11(6):1277\u0026ndash;90.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAgarwal P, Yadav A, Mathur P. Breast cancer prediction on breakhis dataset using deep cnn and transfer learning model, in Data Engineering for Smart Systems: Proceedings of SSIC 2021, 2022: Springer, pp. 77\u0026ndash;88.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDalke R. Neural Network Based Diagnosis of Breast Cancer Using the Breakhis Dataset. California Polytechnic State University; 2022.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSingh UP, Sahu M. A Hybrid Approach for Improving the Classification performance of Imbalanced Breast Cancer data, in 2023 International Conference on Communication, Circuits, and Systems (IC3S), 2023: IEEE, pp. 1\u0026ndash;6.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKolla B, Venugopal P. An integrated approach for magnification independent breast cancer classification. Biomed Signal Process Control. 2024;88:105594.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSenan EM, Alsaade FW, Al-Mashhadani MIA, Theyazn H, Al-Adhaileh MH. Classification of histopathological images for early detection of breast cancer using deep learning. J Appl Sci Eng. 2021;24(3):323\u0026ndash;9.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eİ, Sayın et al. Comparative Analysis of Deep Learning Architectures for Breast Cancer Diagnosis Using the BreaKHis Dataset, arXiv preprint arXiv:2309.01007, 2023.\u003c/span\u003e\u003c/li\u003e\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Qubits, XAI, Breast, Classification, Segmentation","lastPublishedDoi":"10.21203/rs.3.rs-4353973/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4353973/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe number one cancer type for women happens to be breast cancer. Women of any age are more likely to have this disorder because of where they live, their hormones, and the way they live. Women are more likely to be hurt by this. Many more women will have a better chance of living if breast cancer is found earlier. Computers can detect breast cancer early, improve treatment, and increase survival. Therefore, in this article, three models are proposed for the segmentation and classification of breast cancer. The DeepLabv3 model is trained on the fine-tuned hyperparameters for segmentation. The results are computed on BUSIS and DDSM datasets with the accuracy of 99% and 98% respectively. After that for classification of the breast cancer on different magnification levels. The explainable XAI model is designed on the selected fifteen layers and trained on the fine-tuned hyperparameters for breast cancer classification. This model provides the accuracy of. To analyze the classification outcomes quantum neural network is designed on the selected layers, number of Qubits, and hyperparameters. The classification results are computed on the BreakHis publicly dataset at magnification levels of 40x, 100x, 200x, and 400x. The proposed XAI model provides an accuracy of 96.67% and 100% using a quantum neural network for breast cancer classification.\u003c/p\u003e","manuscriptTitle":"Breast Cancer Detection using Explainable AI and Quantum Neural Network","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-05-09 11:15:04","doi":"10.21203/rs.3.rs-4353973/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"1fcf4ca7-c92b-4a1e-b1ac-88cfcb5513c6","owner":[],"postedDate":"May 9th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2024-11-09T17:38:07+00:00","versionOfRecord":[],"versionCreatedAt":"2024-05-09 11:15:04","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4353973","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4353973","identity":"rs-4353973","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}