Development and validation of peritumoral vascular and intratumoral radiomics to predict pathologic complete responses to neoadjuvant chemotherapy in patients with triple-negative breast cancer

Development and validation of peritumoral vascular and intratumoral radiomics to predict pathologic complete responses to neoadjuvant chemotherapy in patients with triple-negative breast cancer | 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 Development and validation of peritumoral vascular and intratumoral radiomics to predict pathologic complete responses to neoadjuvant chemotherapy in patients with triple-negative breast cancer Tianwen Xie, Jing Gong, Qiufeng Zhao, Chengyue Wu, Siyu Wu, Weijun Peng, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-3960587/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 8 You are reading this latest preprint version Abstract Background To develop and validate a peritumoral vascular and intratumoral radiomics model to improve pretreatment predictions for pathologic complete responses (pCRs) to neoadjuvant chemoradiotherapy (NAC) in patients with triple-negative breast cancer (TNBC). Methods A total of 282 TNBC patients (93 in the primary cohort, 113 in the validation cohort, and 76 in The Cancer Imaging Archive [TCIA] cohort) were retrospectively included. The peritumoral vasculature on the maximum intensity projection (MIP) from pretreatment DCE-MRI was segmented by a Hessian matrix-based filter and then edited by a radiologist. Radiomics features were extracted from the tumor and peritumoral vasculature of the MIP images. The LASSO method was used for feature selection, and the k-nearest neighbor (k-NN) classifier was trained and validated to build a predictive model. The diagnostic performance was assessed using the ROC analysis. Results One hundred of the 282 patient (35.5%) with TNBC achieved pCRs after NAC. In predicting pCRs, the combined peritumoral vascular and intratumoral model (fusion model) yields a maximum AUC of 0.82 (95% confidence interval [CI]: 0.75, 0.88) in the primary cohort, a maximum AUC of 0.67 (95% CI: 0.57, 0.76) in the internal validation cohort, and a maximum AUC of 0.65 (95% CI: 0.52, 0.78) in TCIA cohort. The fusion model showed improved performance over the intratumoral model and the peritumoral vascular model, but not significantly ( p > 0.05). Conclusion This study suggested that combined peritumoral vascular and intratumoral radiomics model could provide a non-invasive tool to enable prediction of pCR in TNBC patients treated with NAC. Triple negative breast neoplasms Magnetic resonance imaging Contrast media Magnetic resonance angiography Neoadjuvant therapy Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Introduction Triple-negative breast cancer (TNBC) is characterized by the lack of the estrogen receptor (ER), progesterone receptor (PR), and human epidermal growth factor receptor 2 (HER2). TNBC, which accounts for 12–15% of all mammary tumors, has a worse outcome compared with other breast cancer subtypes [ 1 ]. Currently, neoadjuvant chemotherapy (NAC) is the standard method used to prevent systemic relapse in TNBC patients with locally advanced disease. A pathologic complete response (pCR) to NAC is considered a surrogate marker for improved disease-free survival and overall survival [ 2 ]. Although TNBC is the most chemotherapy-responsive tumor of all breast cancer subtypes, there is a high risk of recurrence and high rates of visceral and central nervous metastases in TNBC patients not achieving pCR [ 3 ]. To avoid the toxicity of ineffective treatments, it is essential to stratify patients into appropriate treatment groups before the early treatment stages. Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI), which depicts and characterizes morphologic and kinetic profiles of tumors and the disorganized, leaky vasculature, is the preferred imaging modality in the NAC setting [ 4 ]. Furthermore, radiomics analysis involving computer-based extraction of a large number of quantitative features from DCE-MRI has been shown to improve pCR prediction [ 5 ]. Most previous radiomics studies have focused on extracting features from tumor [ 6 – 8 ]. Mazurowski et al. [ 9 ] and Wang et al. [ 10 ] that evaluated features extracted from tumor-associated background parenchyma enhancement (BPE) in the context of NAC for breast cancer showed an association between this peritumoral radiomics and pCR. In addition, one published study showed that the radiomic descriptor of intratumoral and peritumoral regions on pretreatment DCE-MRI were associated with treatment responses in breast cancer [ 11 ]. These evidences indicate that valuable outcome-related information can be found outside of the tumor tissue. Angiogenesis, the biological process in which new blood vessels grow from pre-existing vasculature to provide oxygen and nutrients to tumors, plays a pivotal role in tumor responses to chemotherapy [ 12 ]. The exceptionally variable vasculature (in size, shape, and architecture) generates heterogeneous blood flow and limited perfusion throughout the tumor and is essential for cancer proliferation and likely, treatment responses. Therefore, peritumoral vascular and intratumoral features may potentially predict pCR in breast cancer. In the present study, we aimed to develop and validate a peritumoral vascular and intratumoral radiomics model from pretreatment DCE-MRI to predict pCR in patients with TNBC undergoing surgery after NAC. Materials and methods Patients The retrospective study was approved by the institutional review board of Fudan University Shanghai Cancer Center, and the need to obtain informed consent was waived. In this multicohort study, radiomics analysis was applied to three independent cohorts. A total of 328 women patients diagnosed with breast cancer histologically and TNBC immunohistochemically, and who received complete NAC with no prior treatments, underwent breast MRI before the start of NAC, and underwent surgery after NAC, were included in this study. The exclusion criteria included the following: ( a ) patients with a prior history of malignance ( n = 8), ( b ) patients without pretreatment MRI or post-operative pathology ( n = 23), ( c ) patients with poor qualities or motion artifacts on DCE-MRI ( n = 4), ( d ) patients with marked BPE on DCE-MRI ( n = 10), ( e ) and patients without obvious peritumoral vessel on DCE-MRI ( n = 1) (Fig. 1 ). Finally, the dataset from our center between February 1, 2016 and May 31, 2019 was used as the primary cohort and consisted of 93 patients (mean age, 49 years; range 26–75 years). The dataset from our center between June 1, 2019 and February 26, 2021 was used as the internal validation cohort and consisted of 113 patients (mean age, 47 years; range 25–72 years). The other dataset from “Duke-Breast-Cancer-MRI” of The Cancer Imaging Archive (TCIA) [ 13 ] was used as the external validation cohort and consisted of 76 patients (mean age, 49 years; range 24–73 years). In the primary and internal validation cohorts, ER, PR, HER2, Ki-67 index expression patterns, and axillary lymph node metastatic assessments were obtained from histopathologic reports of core biopsies performed before NAC administration. The immunohistochemical assessment of ER, PR, and HER2 was performed using the standard methods as previously reported [ 14 ]. In those tumors that were classified as 2+, HER2 genetic testing was confirmed by fluorescence in situ hybridization. Neoadjuvant chemotherapy regimen and response assessment In the primary and internal validation cohorts, the chemotherapy regimens included epirubicin/cyclophosphamide followed by docetaxel (EC followed by T), docetaxel/carboplatin (TCb), and EC. The median number of NAC cycles was six (range, 4–8). The mean interval between the end of NAC and surgery was 10 days (range, 3–27 days). There were no details of NAC regimens in TCIA cohort. pCR was determined by microscopic examination of the excised tumor and lymph nodes after the completion of NAC and defined as no invasive or noninvasive residual in breast or axillary nodes ( ypT0 ypN0 ) [ 15 ]. MRI protocols The detailed parameters of DCE-MRI acquisition of all cohorts can be found in Appendix E1 in the Supplementary Material. In the primary and internal validation cohorts, all breast MR examinations were performed within 14 days before the start of NAC. DCE-MRI was performed using a fat-suppressed T1-weighted 3D fast spoiled gradient-echo sequence before and five times continuously after a bolus injection of a gadolinium contrast agent (Magnevist, Bayer HealthCare Pharmaceuticals Inc.). The injections were performed with an automatic injector (OptiStar® Elite, Liebel-Flarsheim) at a dose of 0.1 mmol per kilogram of body weight and rate of 2 ml/sec, followed by a 20 mL saline flush. The subtraction and axial MIP images were generated automatically after acquisition. In TCIA dataset, the contrast agents included Gadavist, Magnevist, and Multihanc with the volume of 10–20 ml. The subtraction and axial MIP images were manually calculated by the radiologist (xx, 5 years of experience). Tumor Segmentation and Peritumoral Vessel Segmentation All MR images were reviewed by two breast radiologists (TX, 5 years of experience; and QZ, 11 years of experience), who were blinded to the results of the treatment outcomes. For patients with multifocal or multicentric tumors, the tumors with the largest size and the ipsilateral vessel were segmented and analyzed on the basis of the axial MIP of the first postcontrast phase. Tumor segmentation on the MIP image was conducted manually by the breast radiologist (TX, 5 years of experience). The region of interest (ROI) was delineated to include the entire tumor by using a free open-source software package (ITK-SNAP, version 3.8.0; http://itk- snap.org ). If there was overlap between the index tumor and the peritumoral vessel in the axial MIP image, the intersection was removed using the eraser tool. The illustration for tumor segmentation can be found in Appendix E2 in the Supplementary Material. The enhancement and segmentation of peritumoral vessel were performed by the eigenvalue analysis of the multiscale Hessian-based filter, which showed simultaneous noise and background suppression and vessel enhancement in MIP images [ 16 ]. The details of the multiscale Hessian-based filter method and peritumoral vessel segmentation by algorithm can be found in Appendix E3 and E4 in the Supplementary Material. The segmentation of peritumoral vessel were performed with the Python programming language (Scikit-image package, v. 3.6, Python Software Foundation, https://www.python.org/ ). Then, the peritumoral vasculature by algorithm segmentation was loaded to ITK-SNAP again, and a senior breast radiologist (xx, 11 years of experience) performed manual editing by painting missing voxels and erasing incorrect voxels to get the final peritumoral vasculature. The manual vessel editing procedure took approximately 4 minutes per case. The flowchart and illustration for the vessel segmentation procedures are shown in Fig. 2 and Fig. 3 . The final peritumoral vasculature, checked and edited by the breast radiologist (xx, 11 years of experience), represented the reference standard. To evaluate the performance of vessel detection by algorithm segmentation, the correct-detection rate, incorrect-detection rate, and missed-detection rate were computed (Appendix E5 in the Supplementary Material). Radiomic feature extraction After tumor and peritumoral vessel were segmented, the shape, statistical and textural features were extracted on MIP images using the PyRadiomics Python package [ 17 ]. For the tumor and peritumoral vessel detected on the MIP images, we extracted radiomics features, including 10 shape features, 19 first-order statistical features, and 70 texture features. Furthermore, we extracted 356 wavelet features (i.e., LL, LH, HL, HH) for each tumor. Wavelet features provide representative transformed domain information regarding intensity and textural features by decomposing the original image in low and high frequencies [ 18 ]. Finally, 455 features quantifying intratumoral characteristics and 99 features quantifying peritumoral vascular characteristics were obtained. Radiomic feature selection and model development All the radiomics features were scaled to a range of [0, 1] by using a minimum-maximum scaler. Then, the least absolute shrinkage and selection operator (LASSO) configured recursive feature elimination (RFE) method was applied to select features for the intratumoral model, peritumoral vascular model, individually. The k-nearest neighbor (k-NN) classifier was used to train and test the radiomics models for predicting pCR to NAC. The k-NN (k = 5) technique was trained based on the primary cohort, and then tested in the internal and external validation cohorts. After building the tumor features-based prediction model and vessel features-based prediction model, an information fusion method was applied to fuse the prediction scores generated by the two models to improve the model performance [ 19 ]. The information fusion method included the minimum, maximum, and weighting average of the fusion. Statistical analysis Comparisons between the patient groups were employed with the Chi-square test or Fisher’s test for qualitative variables and the Student’s t-test or Mann-Whitney U test for quantitative variables. The areas under the receiver operating characteristic (ROC) curves (AUCs) were assessed and compared among the intratumoral model, peritumoral vascular model, and fusion model using the DeLong method [ 20 ]. Statistical analyses and radiomics analyses were performed with the Python programming language (v. 3.6, Python Software Foundation, https://www.python.org/ ). p \(<\) 0.05 was considered statistically significant. Results Patients and pathologic complete responses In total, 282 patients with TNBC were finally enrolled in this study. The clinical pathologic characteristics of patients from all cohorts are listed in Table 1. A hundred of 282 patients (35.5%) achieved pCRs after NAC. The pCR rates in the primary cohort, internal validation cohort, and TCIA cohort were 36.6%, 38.9%, and 29.0%, respectively. With regard to clinicopathologic characteristics, no differences between the pCR and non-pCR groups in all cohorts were found in terms of the axillary status, Ki-67 expression, rim enhancement sign, or chemotherapy regimen ( p > 0.05). Patients who achieved pCR in the primary cohort had greater premenopausal status, and had smaller tumor sizes than those who did not ( p = 0.012, 0.022, respectively). Meanwhile, pCR was found to be significantly associated with clinical stage, tumor size and enhancement pattern in the internal validation cohort ( p = 0.042, 0.024, 0.018, respectively). Feature extraction The overall performance of vessel identification was evaluated on all cohorts (Table 2). Vessel segmentation examples of 2 representative patients are shown in Fig.4. Eight tumor features and nigh peritumoral vessel features were selected from initial feature pool were included for further analysis. Detailed information on selected features is shown in Table 3. Performance of radiomics models The AUCs and ROC curves of the radiomics analyses in all cohorts are shown in Table 4. The peritumoral vascular model resulted in an AUC ranging from 0.61 to 0.77: primary cohort, 0.77 (95% confidence interval [CI]: 0.69, 0.83); internal validation cohort, 0.65 (95% CI: 0.54, 0.73); TCIA cohort, 0.61 (95% CI: 0.47, 0.73). Meantime, the intratumoral model yielded an AUC ranging from 0.61 to 0.75: primary cohort, 0.75 (95% CI: 0.66, 0.81); internal validation cohort, 0.64 (95% CI: 0.53, 0.73); TCIA cohort, 0.61 (95% CI: 0.47, 0.74). There were no statistically significant differences in each cohort of AUCs using intratumoral features or peritumoral vascular features ( p > 0.05). The fusion model yielded the highest AUC of 0.82 (95% CI: 0.75, 0.88) in the primary cohort, and the highest AUC of 0.67 (95% CI: 0.57, 0.76) in the internal cohort and the highest AUC of 0.65 (95% CI: 0.52, 0.78) in TCIA cohort (Table 5, Fig.5). The fusion model showed improved performance over the intratumoral model and the peritumoral vascular model, but not significantly ( p > 0.05). Discussion In this study, we developed and validated a radiomics model that incorporated peritumoral vascular and intratumoral features extracted from pretreatment MIP images to predict pCRs to NAC in patients with TNBC. The proposed radiomics model provides new insights into the biological characteristics of TNBC and the early prediction of its pathologic responses to NAC. Identifying patients not likely to benefit from NAC before treatment could enable tailored individual patient therapies, especially patients with TNBC, which has been known to display the highest distant metastatic rates and lowest overall survival of all breast cancer subtypes. Previous studies have shown that the prediction of pCRs to NAC varied across biological subtypes, indicating the need for specific radiomics models [3; 21]. A radiomics model dedicated to a specific biological subtype could create more reproducible and robust classification results [ 22 ]. Previous studies using intratumoral texture features extracted from DCE-MRI yielded AUCs of 0.64–0.68 for the early prediction of pCR in patients with TNBC [7; 23] and were in accordance with those in our study using texture features extracted from 2D MIP. The all intratumoral texture features selected were obtained from wavelet images, which are high-dimensional features that cannot be perceived by humans but hold more detailed information about tumors and are more sensitive when predicting pCRs [7; 24]. Although MIPs miss the proportion of tumor intensity, MIPs integrated with a DCE-MRI protocol can reveal not only the visualization of enhancing tumor but also the tumor-associated vasculature in the clinical scenario, and simplify the workflow to perform the extraction of tumor and peritumoral vasculature in the only one image. To the best of our knowledge, MIPs have never been proposed for feature extractions. The potential association between MIP-derived tumor features and pCR should be further investigated in future studies. Tumor angiogenesis is essential for the growth, invasion, and metastasis of tumors. Overexpression of vascular endothelial growth factor (VEGF) has been extensively investigated to be a key player in the formation of tumor neovasculature with many abnormal features [ 25 ]. Compared with ER-positive breast cancer, TNBC has a higher degree of VEGF, an avid stimulator of angiogenesis, which is closely correlated with the risk of distant metastases [ 26 ]. This angiogenic activity constitutes the basis for the detection and differentiation of breast cancer using DCE-MRI. MIPs from DCE-MRI can assess angiogenic activity and are considered a promising noninvasive investigational tool. Studies focusing on the use of peritumoral vessel to evaluate the response of patients with breast cancer to NAC have been reported [27; 28]. These studies assessed quantitative differences in the number and volume of peritumoral vessels before and after NAC and showed that vessel changes could serve as an early indicator to predict pathologic responses. In our study, we performed Hessian-based algorithm to segment the tumor-associated vessels from the axial MIPs of the first postcontrast phase where the greatest lesion conspicuity with the lowest background parenchymal enhancement were demonstrated, as well as the best “angiographic effect” for both arteries and veins [ 29 ]. Hessian-based algorithm showed correct-detection rates of 83.1%-89.8%, incorrect-detection rates of 20.1%-27.2%, and missed-detection rates of 10.2%-16.9%, which are similar to those in previous studies with the same algorithm [30; 31]. The incorrect-detection rates were mainly caused by linearly distributed BPE, as well as subtraction artifacts along the breast skin. The missed-detection rates were mainly due to low-signal vascular pixels identified by the radiologist but not detected by the algorithm. Furthermore, the senior radiologist checked and edited the vasculature segmented by the algorithm to get the final peritumoral vasculature for the further radiomics feature extraction. The best-performing vessel features were all from gray level dependence matrix (GLDM) quantifying gray level dependencies in an image. There features may indicate more heterogeneous of abnormal angiogenic vessels surrounding tumors demonstrating non-pCRs [ 32 ]. A higher level of abnormal vasculature and the possibility of more discontinuities in the convoluted vasculature might constrict the delivery of chemotherapeutic drugs to tumors, thereby resulting in worse treatment responses [ 33 ]. Peritumoral vascular model of TNBC on pretreatment MIP images demonstrated a similar classification performance to that of intratumoral model. Furthermore, a combined peritumoral vascular and intratumoral signature resulted in improved performance, albeit the difference was not significant. These findings suggest that peritumoral vascular radiomics based on MIP might provide a preliminary success for treatment responses in patients with TNBC. For this study, we acknowledge the following limitations. First, this study was retrospective. Second, we extracted tumor features from a single representative 2D MIP image, which consisted of projecting the voxel with the highest attenuation value onto every view throughout 2D image volume, which might not provide a comprehensive assessment of whole-tumor heterogeneity. Also, the vasculature segmented from the 2D MIP image could give distorted measures. Specifically, we used the axial MIP image to extract peritumoral vascular and intratumoral features because the MIP image revealed not only tumor enhancements but also tumor vasculature, making the interpretation and analysis simpler than when using full-study DCE-MRI images. We are currently exploring 3D tumor and vascular segmentation on 3D-subtracted postcontrast images [ 34 ]. Finally, MR contrast agent, MR scan parameters, and different phases of the menstrual cycle have effects on breast vascularization and so on the performance of peritumoral vascular radiomics analysis. Conclusions The peritumoral vascular and intratumoral radiomics based on pretreatment MIP images from DCE-MRI can be used to predict pCR to NAC in TNBC patients. This strategy of radiomics analysis could provide a potential approach to assist in understanding the biologic behavior, pretreatment planning, and response prediction of TNBC. Abbreviations AUC: areas under the curve; BPE: background parenchyma ehancement; DCE-MRI: dynamic contrast-enhanced magnetic resonance imaging; GLDM: gray level dependence matrix; k-NN: k-nearest neighbor; LASSO: least absolute shrinkage and selection operator; MIP: maximum intensity projection; NAC: neoadjuvant chemotherapy; pCR: pathologic complete response; RFE: recursive feature elimination; ROC: receiver operating characteristic; TNBC: triple-negative breast cancer. Declarations Author’s contributions TX and JG contributed to study design and manuscript editing. TX contributed to data collection and analysis. QZ contributed to imaging evaluation. SW contributed to clinical studies. CW contributed to manuscript editing. JG contributed to the study design, data analysis and manuscript editing. WP and YG contributed to the study design and imaging evaluation. All authors reviewed the manuscript. Funding This study has received funding by the National Natural Science Foundation of China (grant number, 82071878) and Clinical Research Plan of Shanghai Hospital Development Center (grant number, SHDC2020CR2008A). Ethics approval and consent to participate The study complied with the Declaration of Helsinki guidelines and declaration. The study was approved by the Ethic Committee of Fudan University Shanghai Cancer Center. Written inform consent was waived by the Ethic Committee of Fudan University Shanghai Cancer Center due to the retrospective nature of the study. Data availability The datasets used and/or analysed during the current study are available from the corresponding author upon reasonable request. Consent for publication Not applicable Competing interests The authors declare that they have no competing interests. Acknowledgements Not applicable References Dent R, Trudeau M, Pritchard KI et al (2007) Triple-negative breast cancer: clinical features and patterns of recurrence. Clin Cancer Res 13:4429-4434 Liedtke C, Mazouni C, Hess KR et al (2008) Response to neoadjuvant therapy and long-term survival in patients with triple-negative breast cancer. J Clin Oncol 26:1275-1281 Cortazar P, Zhang L, Untch M et al (2014) Pathological complete response and long-term clinical benefit in breast cancer: the CTNeoBC pooled analysis. Lancet 384:164-172 Dialani V, Chadashvili T, Slanetz PJ (2015) Role of imaging in neoadjuvant therapy for breast cancer. Ann Surg Oncol 22:1416-1424 Gillies RJ, Kinahan PE, Hricak H (2016) Radiomics: Images Are More than Pictures, They Are Data. Radiology 278:563-577 Park VY, Kim EK, Kim MJ, Yoon JH, Moon HJ (2017) Perfusion Parameters on Breast Dynamic Contrast-Enhanced MRI Are Associated With Disease-Specific Survival in Patients With Triple-Negative Breast Cancer. AJR Am J Roentgenol 208:687-694 Liu Z, Li Z, Qu J et al (2019) Radiomics of Multiparametric MRI for Pretreatment Prediction of Pathologic Complete Response to Neoadjuvant Chemotherapy in Breast Cancer: A Multicenter Study. Clin Cancer Res 25:3538-3547 Cain EH, Saha A, Harowicz MR, Marks JR, Marcom PK, Mazurowski MA (2019) Multivariate machine learning models for prediction of pathologic response to neoadjuvant therapy in breast cancer using MRI features: a study using an independent validation set. Breast Cancer Res Treat 173:455-463 Mazurowski MA, Zhang J, Grimm LJ, Yoon SC, Silber JI (2014) Radiogenomic analysis of breast cancer: luminal B molecular subtype is associated with enhancement dynamics at MR imaging. Radiology 273:365-372 Wang J, Kato F, Oyama-Manabe N et al (2015) Identifying Triple-Negative Breast Cancer Using Background Parenchymal Enhancement Heterogeneity on Dynamic Contrast-Enhanced MRI: A Pilot Radiomics Study. PLoS One 10:e0143308 Braman NM, Etesami M, Prasanna P et al (2017) Intratumoral and peritumoral radiomics for the pretreatment prediction of pathological complete response to neoadjuvant chemotherapy based on breast DCE-MRI. Breast Cancer Res 19:57 Hanahan D, Folkman J (1996) Patterns and emerging mechanisms of the angiogenic switch during tumorigenesis. Cell 86:353-364 Saha A, Harowicz MR, Grimm LJ et al (2018) A machine learning approach to radiogenomics of breast cancer: a study of 922 subjects and 529 DCE-MRI features. Br J Cancer 119:508-516 Goldhirsch A, Winer EP, Coates AS et al (2013) Personalizing the treatment of women with early breast cancer: highlights of the St Gallen International Expert Consensus on the Primary Therapy of Early Breast Cancer 2013. Ann Oncol 24:2206-2223 von Minckwitz G, Untch M, Blohmer JU et al (2012) Definition and impact of pathologic complete response on prognosis after neoadjuvant chemotherapy in various intrinsic breast cancer subtypes. J Clin Oncol 30:1796-1804 Vignati A, Giannini V, Carbonaro LA et al (2014) A new algorithm for automatic vascular mapping of DCE-MRI of the breast: Clinical application of a potential new biomarker. Comput Methods Programs Biomed 117:482-488 van Griethuysen JJM, Fedorov A, Parmar C et al (2017) Computational Radiomics System to Decode the Radiographic Phenotype. Cancer Res 77:e104-e107 Laine A, Fan J (1993) Texture classification by wavelet packet signatures. Ieee Transactions on Pattern Analysis and Machine Intelligence 15:1186-1191 Gong J, Liu JY, Jiang YJ, Sun XW, Zheng B, Nie SD (2018) Fusion of quantitative imaging features and serum biomarkers to improve performance of computer-aided diagnosis scheme for lung cancer: A preliminary study. Med Phys 45:5472-5481 DeLong ER, DeLong DM, Clarke-Pearson DL (1988) Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics 44:837-845 von Minckwitz G, Untch M, Blohmer JU et al (2012) Definition and Impact of Pathologic Complete Response on Prognosis After Neoadjuvant Chemotherapy in Various Intrinsic Breast Cancer Subtypes. Journal of Clinical Oncology 30:1796-1804 Granzier RWY, van Nijnatten TJA, Woodruff HC, Smidt ML, Lobbes MBI (2019) Exploring breast cancer response prediction to neoadjuvant systemic therapy using MRI-based radiomics: A systematic review. Eur J Radiol 121:108736 Golden DI, Lipson JA, Telli ML, Ford JM, Rubin DL (2013) Dynamic contrast-enhanced MRI-based biomarkers of therapeutic response in triple-negative breast cancer. J Am Med Inform Assoc 20:1059-1066 Nie K, Shi L, Chen Q et al (2016) Rectal Cancer: Assessment of Neoadjuvant Chemoradiation Outcome based on Radiomics of Multiparametric MRI. Clin Cancer Res 22:5256-5264 Hoeben A, Landuyt B, Highley MS, Wildiers H, Van Oosterom AT, De Bruijn EA (2004) Vascular endothelial growth factor and angiogenesis. Pharmacol Rev 56:549-580 Linderholm BK, Hellborg H, Johansson U et al (2009) Significantly higher levels of vascular endothelial growth factor (VEGF) and shorter survival times for patients with primary operable triple-negative breast cancer. Ann Oncol 20:1639-1646 Martincich L, Bertotto I, Montemurro F et al (2011) Variation of breast vascular maps on dynamic contrast-enhanced MRI after primary chemotherapy of locally advanced breast cancer. AJR Am J Roentgenol 196:1214-1218 Wu LA, Chang RF, Huang CS et al (2015) Evaluation of the treatment response to neoadjuvant chemotherapy in locally advanced breast cancer using combined magnetic resonance vascular maps and apparent diffusion coefficient. J Magn Reson Imaging 42:1407-1420 Sardanelli F, Iozzelli A, Fausto A, Carriero A, Kirchin MA (2005) Gadobenate dimeglumine-enhanced MR imaging breast vascular maps: association between invasive cancer and ipsilateral increased vascularity. Radiology 235:791-797 Lin M, Chen JH, Nie K, Chang D, Nalcioglu O, Su MY (2009) Algorithm-based method for detection of blood vessels in breast MRI for development of computer-aided diagnosis. J Magn Reson Imaging 30:817-824 Vignati A, Giannini V, Bert A et al (2012) A fully automatic multiscale 3-dimensional Hessian-based algorithm for vessel detection in breast DCE-MRI. Invest Radiol 47:705-710 Sun C, Wee WG (1983) Neighboring gray level dependence matrix for texture classification. Computer Vision, Graphics, and Image Processing 23:341-352 Viens P, Jacquemier J, Bardou VJ et al (1999) Association of angiogenesis and poor prognosis in node-positive patients receiving anthracycline-based adjuvant chemotherapy. Breast Cancer Res Treat 54:205-212 Wu C, Pineda F, Hormuth DA, 2nd, Karczmar GS, Yankeelov TE (2019) Quantitative analysis of vascular properties derived from ultrafast DCE-MRI to discriminate malignant and benign breast tumors. Magn Reson Med 81:2147-2160 Tables Table 1 The clinicopathologic characteristics of the patients with TNBC in the three cohorts Primary cohort ( n = 93) Internal validation cohort ( n = 113) External validation cohort ( n = 76) Characteristic pCR ( n = 34) Non-pCR ( n = 59) p pCR ( n = 44) Non-pCR ( n = 69) p pCR ( n = 22) Non-pCR ( n = 54) p Age, mean ± SD, years 46.59±11.42 50.90±11.14 0.078 45.32±9.37 48.13±11.85 0.186 47.77±14.17 49.83±10.49 0.487 Menopausal status 0.012 * 0.434 0.723 Peri or Postmenopausal 11 35 19 35 8 22 Premenopausal 23 24 25 34 14 32 Clinical stage 0.946 0.042 * 0.819 I/II 25 43 32 37 17 43 III/IV 9 16 12 32 5 11 Lesion size, mean ± SD, mm 33.74±15.95 43.25±20.59 0.022 * 36.09±19.34 46.72±26.68 0.024 * 27.91±16.94 34.30±21.48 0.217 Axillary LN before NAC 0.679 0.327 0.191 Negative 9 18 11 12 13 23 Positive 25 41 33 57 9 31 Ki-67 before NAC 0.121 0.480 NA Negative 0 4 2 6 NA NA Positive 34 55 42 63 NA NA Enhancement Pattern 0.083 0.018 * 0.162 With nonmass enhancement 4 16 4 19 1 11 Mass only 30 43 40 50 21 43 Rim Enhancement 0.640 0.066 0.468 Negative 19 30 21 45 15 32 Positive 15 29 23 24 7 22 Chemotherapy regimen 0.616 0.430 NA EC-T 25 42 24 29 NA NA EC 2 7 5 10 NA NA TCb 7 10 15 30 NA NA EC epirubicin with cyclophosphamide; EC-T epirubicin with cyclophosphamide plus docetaxel; LN lymph node; NAC neoadjuvant chemotherapy; pCR pathologic complete response; SD standard deviation; TCb docetaxel with carboplatin. * p < 0.05 Table 2 Vessel detection algorithm performance Correct-detection rate (%) Incorrect-detection rate (%) Missed-detection rate (%) Primary cohort Range 60-100 0-45 0-40 Median 90.0 20.9 10.0 Mean (SD) 89.8 (5.2) 20.1 (6.5) 10.2 (5.2) Internal validation cohort Range 64-100 0-42.9 0-36 Median 86.4 25.6 13.6 Mean (SD) 85.1 (7.1) 24.9 (7.3) 14.9 (7.1) External validation cohort Range 58.3-100 0-40.0 0-41.7 Median 84.3 27.5 15.7 Mean (SD) 83.1 (9.1) 27.2 (8.2) 16.9 (9.1) SD standard deviation. Table 3 Radiomics features extracted from the tumor and peritumoral vessel were identified after feature selection Location Feature Family Feature Description Tumor (wavelet-LL) GLDM High Gray Level Emphasis Distribution of the higher gray-level values Large Dependence Emphasis Distribution of large dependencies Large Dependence High Gray Level Emphasis Joint distribution of large dependence with higher gray-level values Large Dependence Low Gray Level Emphasis Joint distribution of large dependence with lower gray-level values Low Gray Level Emphasis Distribution of low gray-level values Small Dependence Emphasis Distribution of small dependencies Small Dependence High Gray Level Emphasis Joint distribution of small dependence with higher gray-level values Small Dependence Low Gray Level Emphasis Joint distribution of small dependence with lower gray-level values Vessel GLDM Gray Level Variance Variance in grey level in the image High Gray Level Emphasis Distribution of the higher gray-level values Large Dependence Emphasis Distribution of large dependencies Large Dependence High Gray Level Emphasis Joint distribution of large dependence with higher gray-level values Large Dependence Low Gray Level Emphasis Joint distribution of large dependence with lower gray-level values Low Gray Level Emphasis Distribution of low gray-level values Small Dependence Emphasis Distribution of small dependencies Small Dependence High Gray Level Emphasis Joint distribution of small dependence with higher gray-level values Small Dependence Low Gray Level Emphasis Joint distribution of small dependence with lower gray-level values GLDM Gray Level Dependence Matrix. Table 4 Performance of the peritumoral vascular radiomics model and intratumoral radiomics model Primary cohort Internal validation cohort External validation cohort AUC 95% CI AUC 95% CI AUC 95% CI Tumor a 0.75 [0.66, 0.81] 0.64 [0.53, 0.73] 0.61 [0.47, 0.74] Vessel b 0.77 [0.69, 0.83] 0.65 [0.54, 0.73] 0.61 [0.47, 0.73] Tumor a : prediction score generated using the intratumoral features-based model; Vessel b : prediction score generated using the peritumoral vascular features-based model. AUC, area under the curve; CI, confidence interval. Table 5 A summary of the area under the curve (AUC) values obtained using different fusion methods to combine prediction scores generated by tumor features and peritumoral vessel features Primary cohort Internal validation cohort External validation cohort Model AUC 95% CI AUC 95% CI AUC 95% CI Minimum 0.81 [0.74, 0.87] 0.65 [0.54, 0.74] 0.63 [0.49, 0.76] Maximum 0.76 [0.68, 0.83] 0.65 [0.54, 0.74] 0.59 [0.44, 0.70] 0.9×Tumor a +0.1×Vessel b 0.80 [0.72, 0.86] 0.67 [0.57, 0.76] 0.64 [0.50, 0.77] 0.8×Tumor+0.2×Vessel 0.80 [0.72, 0.86] 0.67 [0.57, 0.76] 0.64 [0.50, 0.77] 0.7×Tumor+0.3×Vessel 0.81 [0.73, 0.87] 0.67 [0.56, 0.75] 0.65 [0.51, 0.77] 0.6×Tumor+0.4×Vessel 0.82 [0.75, 0.88] 0.67 [0.55, 0.75] 0.65 [0.52, 0.78] 0.5×Tumor+0.5×Vessel 0.82 [0.74, 0.88] 0.67 [0.56, 0.76] 0.64 [0.51, 0.77] 0.4×Tumor+0.6×Vessel 0.81 [0.73, 0.87] 0.66 [0.55, 0.75] 0.62 [0.48, 0.76] 0.3×Tumor+0.7×Vessel 0.81 [0.73, 0.87] 0.66 [0.55, 0.75] 0.62 [0.49, 0.76] 0.2×Tumor+0.8×Vessel 0.78 [0.70, 0.85] 0.65 [0.54, 0.74] 0.62 [0.48, 0.76] 0.1×Tumor+0.9×Vessel 0.77 [0.68, 0.83] 0.65 [0.54, 0.74] 0.61 [0.46, 0.73] Tumor a : prediction score generated using the intratumoral features-based model; Vessel b : prediction score generated using the peritumoral vascular features-based model. AUC area under the curve; CI confidence interval. Additional Declarations No competing interests reported. Supplementary Files SupplementaryMaterial.docx Cite Share Download PDF Status: Under Review Version 1 posted Editorial decision: Revision requested 09 Apr, 2024 Reviews received at journal 09 Mar, 2024 Reviewers agreed at journal 01 Mar, 2024 Reviewers invited by journal 26 Feb, 2024 Editor invited by journal 22 Feb, 2024 Submission checks completed at journal 22 Feb, 2024 Editor assigned by journal 22 Feb, 2024 First submitted to journal 16 Feb, 2024 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-3960587","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":274839482,"identity":"6c2a7b7d-300f-427d-9245-327e9d0cd524","order_by":0,"name":"Tianwen Xie","email":"","orcid":"","institution":"Fudan University Shanghai Cancer Center","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Tianwen","middleName":"","lastName":"Xie","suffix":""},{"id":274839483,"identity":"f60bb266-e421-4710-8b55-d450d20aa879","order_by":1,"name":"Jing Gong","email":"","orcid":"","institution":"Fudan University Shanghai Cancer Center","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Jing","middleName":"","lastName":"Gong","suffix":""},{"id":274839484,"identity":"11933850-9f21-4ae7-87f5-d334ae29d858","order_by":2,"name":"Qiufeng Zhao","email":"","orcid":"","institution":"Shanghai University of Traditional Chinese Medicine","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Qiufeng","middleName":"","lastName":"Zhao","suffix":""},{"id":274839485,"identity":"f4887e8a-9c33-415b-a0b9-8dc136dc9fd6","order_by":3,"name":"Chengyue Wu","email":"","orcid":"","institution":"University of Texas at Austin","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Chengyue","middleName":"","lastName":"Wu","suffix":""},{"id":274839486,"identity":"834ad4e5-d7a7-4596-aa2c-c62861c16ec3","order_by":4,"name":"Siyu Wu","email":"","orcid":"","institution":"Fudan University","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Siyu","middleName":"","lastName":"Wu","suffix":""},{"id":274839488,"identity":"1fc6530c-2086-48c9-ad8a-c2562cb69115","order_by":5,"name":"Weijun Peng","email":"","orcid":"","institution":"Fudan University Shanghai Cancer Center","correspondingAuthor":false,"submittingAuthor":false,"prefix":"","firstName":"Weijun","middleName":"","lastName":"Peng","suffix":""},{"id":274839490,"identity":"30c7d37d-9e75-4a67-a48f-ccc335fd2592","order_by":6,"name":"Yajia Gu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAu0lEQVRIiWNgGAWjYLACCQMGOTb25gOkaTHm4zmWQJpFifMkchSIUyofkWP4waLALr2NIYeB4UfFNsJaDG/kGEtIGCTntjGcPcDYc+Y2EVpm5BgAtTDntjH2JTAzthGnxfiHhEF9OhszjwFxWuQlcsyAthxOYGMjVosBz7MyCwmD44ZtPGwJB4nyi3x78ubbEn+q5eXnPz744EcFMbYc4DBgloByDhBWD7Klgf0B4weilI6CUTAKRsGIBQDZKjY1b78qYAAAAABJRU5ErkJggg==","orcid":"","institution":"Fudan University Shanghai Cancer Center","correspondingAuthor":true,"submittingAuthor":false,"prefix":"","firstName":"Yajia","middleName":"","lastName":"Gu","suffix":""}],"badges":[],"createdAt":"2024-02-16 07:19:04","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-3960587/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-3960587/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":51716230,"identity":"a6ceea45-5363-4988-86a7-f6ec05daddf1","added_by":"auto","created_at":"2024-02-27 21:05:59","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":229363,"visible":true,"origin":"","legend":"\u003cp\u003eFlowchart of the study population.\u003c/p\u003e","description":"","filename":"1.png","url":"https://assets-eu.researchsquare.com/files/rs-3960587/v1/a41cf54bf47367fd7023525e.png"},{"id":51715435,"identity":"c6261991-660f-4adf-a734-f167beec220c","added_by":"auto","created_at":"2024-02-27 20:57:59","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":91024,"visible":true,"origin":"","legend":"\u003cp\u003eFlowchart of the tumor and peritumoral vessel segmentation procedure. Tumor and peritumoral vessel segmentations were performed on the axial maximum intensity projection (MIP) of the first postcontrast phase. After breast segmentation, the lateral breast index tumor was segmented according to the tumor location. Peritumoral vessel on the MIP image was segmented using a multiscale Hessian-based filter. Additionally, the peritumoral vasculature by algorithm segmentation was generated via the intersection of the lateral tumor breast mask and the binary vessel segmentation region after reducing small gaps and filling holes. Finally, the vessel mask was identified via manual editing.\u003c/p\u003e","description":"","filename":"2.png","url":"https://assets-eu.researchsquare.com/files/rs-3960587/v1/a977a8f0d1cbf934849c4b41.png"},{"id":51715438,"identity":"2f3cc04a-6fc8-4995-a605-0c9ada9b5319","added_by":"auto","created_at":"2024-02-27 20:57:59","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":245668,"visible":true,"origin":"","legend":"\u003cp\u003eAn illusion of vessel segmentation. (a) The axial maximum intensity projection (MIP)image in one patient. After the anatomic breast segmentation was performed (b), the tumor laterality was segmented according to the tumor location (c). Peritumoral vessel in the MIP image were enhanced and segmented with a multiscale Hessian-based filter (d). After hole filling and intersection steps were performed, peritumoral vasculature by algorithm segmentation was identified (e). The final vessel mask was identified via manual editing (f).\u003c/p\u003e","description":"","filename":"3.png","url":"https://assets-eu.researchsquare.com/files/rs-3960587/v1/06c4dd841d58a49524d21f5e.png"},{"id":51715439,"identity":"e0e432d8-ac15-4e81-89c2-532eb47208cf","added_by":"auto","created_at":"2024-02-27 20:57:59","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":688457,"visible":true,"origin":"","legend":"\u003cp\u003eExamples of vessel segmentation in two representative patients are shown. The upper row shows a patient with triple-negative breast cancer (TNBC) who did not achieve a pathologic complete response (pCR); the lower row shows a patient with TNBC who achieved a pCR. (a) and (d) are maximum intensity projection (MIP) images. (b) and (e) are peritumoral vessel segmented by algorithm and intratumoral segmentation. (c) and (f) are peritumoral vessel edited by the radiologist and intratumoral segmentation.\u003c/p\u003e","description":"","filename":"4.png","url":"https://assets-eu.researchsquare.com/files/rs-3960587/v1/c42378eb5f1cac326bf598e4.png"},{"id":51716231,"identity":"7d8573fa-431a-4209-b14b-753c6bce79de","added_by":"auto","created_at":"2024-02-27 21:05:59","extension":"png","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":396392,"visible":true,"origin":"","legend":"\u003cp\u003eReceiver operating characteristic (ROC) curves generated using the three different radiomics models in the primary (a), internal validation (b), and TCIA (c) cohorts. The models included one that only used peritumoral vessel features (green), one that only used tumor features (blue), and the best fusion model (red).\u003c/p\u003e","description":"","filename":"5.png","url":"https://assets-eu.researchsquare.com/files/rs-3960587/v1/a65883bd992a7cf9e0202c20.png"},{"id":51717708,"identity":"ac561820-9996-40db-89db-b951b18d1065","added_by":"auto","created_at":"2024-02-27 21:14:01","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1998413,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-3960587/v1/c53c5d07-cf55-41d6-b137-48c3e60e3491.pdf"},{"id":51715440,"identity":"d7f873af-a372-4bd9-84d2-403a289a9e47","added_by":"auto","created_at":"2024-02-27 20:58:00","extension":"docx","order_by":1,"title":"","display":"","copyAsset":false,"role":"supplement","size":189008,"visible":true,"origin":"","legend":"","description":"","filename":"SupplementaryMaterial.docx","url":"https://assets-eu.researchsquare.com/files/rs-3960587/v1/c6728e1580f3ea23044f1cfe.docx"}],"financialInterests":"No competing interests reported.","formattedTitle":"Development and validation of peritumoral vascular and intratumoral radiomics to predict pathologic complete responses to neoadjuvant chemotherapy in patients with triple-negative breast cancer","fulltext":[{"header":"Introduction","content":"\u003cp\u003eTriple-negative breast cancer (TNBC) is characterized by the lack of the estrogen receptor (ER), progesterone receptor (PR), and human epidermal growth factor receptor 2 (HER2). TNBC, which accounts for 12\u0026ndash;15% of all mammary tumors, has a worse outcome compared with other breast cancer subtypes [\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e]. Currently, neoadjuvant chemotherapy (NAC) is the standard method used to prevent systemic relapse in TNBC patients with locally advanced disease. A pathologic complete response (pCR) to NAC is considered a surrogate marker for improved disease-free survival and overall survival [\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e]. Although TNBC is the most chemotherapy-responsive tumor of all breast cancer subtypes, there is a high risk of recurrence and high rates of visceral and central nervous metastases in TNBC patients not achieving pCR [\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e]. To avoid the toxicity of ineffective treatments, it is essential to stratify patients into appropriate treatment groups before the early treatment stages.\u003c/p\u003e \u003cp\u003eDynamic contrast-enhanced magnetic resonance imaging (DCE-MRI), which depicts and characterizes morphologic and kinetic profiles of tumors and the disorganized, leaky vasculature, is the preferred imaging modality in the NAC setting [\u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e]. Furthermore, radiomics analysis involving computer-based extraction of a large number of quantitative features from DCE-MRI has been shown to improve pCR prediction [\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e]. Most previous radiomics studies have focused on extracting features from tumor [\u003cspan additionalcitationids=\"CR7\" citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e]. Mazurowski et al. [\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e] and Wang et al. [\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e] that evaluated features extracted from tumor-associated background parenchyma enhancement (BPE) in the context of NAC for breast cancer showed an association between this peritumoral radiomics and pCR. In addition, one published study showed that the radiomic descriptor of intratumoral and peritumoral regions on pretreatment DCE-MRI were associated with treatment responses in breast cancer [\u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e]. These evidences indicate that valuable outcome-related information can be found outside of the tumor tissue. Angiogenesis, the biological process in which new blood vessels grow from pre-existing vasculature to provide oxygen and nutrients to tumors, plays a pivotal role in tumor responses to chemotherapy [\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e]. The exceptionally variable vasculature (in size, shape, and architecture) generates heterogeneous blood flow and limited perfusion throughout the tumor and is essential for cancer proliferation and likely, treatment responses. Therefore, peritumoral vascular and intratumoral features may potentially predict pCR in breast cancer.\u003c/p\u003e \u003cp\u003eIn the present study, we aimed to develop and validate a peritumoral vascular and intratumoral radiomics model from pretreatment DCE-MRI to predict pCR in patients with TNBC undergoing surgery after NAC.\u003c/p\u003e"},{"header":"Materials and methods","content":"\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e \u003ch2\u003ePatients\u003c/h2\u003e \u003cp\u003e The retrospective study was approved by the institutional review board of Fudan University Shanghai Cancer Center, and the need to obtain informed consent was waived. In this multicohort study, radiomics analysis was applied to three independent cohorts. A total of 328 women patients diagnosed with breast cancer histologically and TNBC immunohistochemically, and who received complete NAC with no prior treatments, underwent breast MRI before the start of NAC, and underwent surgery after NAC, were included in this study. The exclusion criteria included the following: (\u003cem\u003ea\u003c/em\u003e) patients with a prior history of malignance (\u003cem\u003en\u003c/em\u003e\u0026thinsp;=\u0026thinsp;8), (\u003cem\u003eb\u003c/em\u003e) patients without pretreatment MRI or post-operative pathology (\u003cem\u003en\u003c/em\u003e\u0026thinsp;=\u0026thinsp;23), (\u003cem\u003ec\u003c/em\u003e) patients with poor qualities or motion artifacts on DCE-MRI (\u003cem\u003en\u003c/em\u003e\u0026thinsp;=\u0026thinsp;4), (\u003cem\u003ed\u003c/em\u003e) patients with marked BPE on DCE-MRI (\u003cem\u003en\u003c/em\u003e\u0026thinsp;=\u0026thinsp;10), (\u003cem\u003ee\u003c/em\u003e) and patients without obvious peritumoral vessel on DCE-MRI (\u003cem\u003en\u003c/em\u003e\u0026thinsp;=\u0026thinsp;1) (Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e). Finally, the dataset from our center between February 1, 2016 and May 31, 2019 was used as the primary cohort and consisted of 93 patients (mean age, 49 years; range 26\u0026ndash;75 years). The dataset from our center between June 1, 2019 and February 26, 2021 was used as the internal validation cohort and consisted of 113 patients (mean age, 47 years; range 25\u0026ndash;72 years). The other dataset from \u0026ldquo;Duke-Breast-Cancer-MRI\u0026rdquo; of The Cancer Imaging Archive (TCIA) [\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e] was used as the external validation cohort and consisted of 76 patients (mean age, 49 years; range 24\u0026ndash;73 years).\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eIn the primary and internal validation cohorts, ER, PR, HER2, Ki-67 index expression patterns, and axillary lymph node metastatic assessments were obtained from histopathologic reports of core biopsies performed before NAC administration. The immunohistochemical assessment of ER, PR, and HER2 was performed using the standard methods as previously reported [\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e]. In those tumors that were classified as 2+, HER2 genetic testing was confirmed by fluorescence in situ hybridization.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec4\" class=\"Section2\"\u003e \u003ch2\u003eNeoadjuvant chemotherapy regimen and response assessment\u003c/h2\u003e \u003cp\u003eIn the primary and internal validation cohorts, the chemotherapy regimens included epirubicin/cyclophosphamide followed by docetaxel (EC followed by T), docetaxel/carboplatin (TCb), and EC. The median number of NAC cycles was six (range, 4\u0026ndash;8). The mean interval between the end of NAC and surgery was 10 days (range, 3\u0026ndash;27 days). There were no details of NAC regimens in TCIA cohort. pCR was determined by microscopic examination of the excised tumor and lymph nodes after the completion of NAC and defined as no invasive or noninvasive residual in breast or axillary nodes (\u003cem\u003eypT0 ypN0\u003c/em\u003e) [\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e].\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec5\" class=\"Section2\"\u003e \u003ch2\u003eMRI protocols\u003c/h2\u003e \u003cp\u003eThe detailed parameters of DCE-MRI acquisition of all cohorts can be found in Appendix E1 in the Supplementary Material. In the primary and internal validation cohorts, all breast MR examinations were performed within 14 days before the start of NAC. DCE-MRI was performed using a fat-suppressed T1-weighted 3D fast spoiled gradient-echo sequence before and five times continuously after a bolus injection of a gadolinium contrast agent (Magnevist, Bayer HealthCare Pharmaceuticals Inc.). The injections were performed with an automatic injector (OptiStar\u0026reg; Elite, Liebel-Flarsheim) at a dose of 0.1 mmol per kilogram of body weight and rate of 2 ml/sec, followed by a 20 mL saline flush. The subtraction and axial MIP images were generated automatically after acquisition.\u003c/p\u003e \u003cp\u003eIn TCIA dataset, the contrast agents included Gadavist, Magnevist, and Multihanc with the volume of 10\u0026ndash;20 ml. The subtraction and axial MIP images were manually calculated by the radiologist (xx, 5 years of experience).\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec6\" class=\"Section2\"\u003e \u003ch2\u003eTumor Segmentation and Peritumoral Vessel Segmentation\u003c/h2\u003e \u003cp\u003eAll MR images were reviewed by two breast radiologists (TX, 5 years of experience; and QZ, 11 years of experience), who were blinded to the results of the treatment outcomes. For patients with multifocal or multicentric tumors, the tumors with the largest size and the ipsilateral vessel were segmented and analyzed on the basis of the axial MIP of the first postcontrast phase.\u003c/p\u003e \u003cp\u003eTumor segmentation on the MIP image was conducted manually by the breast radiologist (TX, 5 years of experience). The region of interest (ROI) was delineated to include the entire tumor by using a free open-source software package (ITK-SNAP, version 3.8.0; \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttp://itk-\u003c/span\u003e\u003cspan address=\"http://itk-\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e \u003cem\u003esnap.org\u003c/em\u003e). If there was overlap between the index tumor and the peritumoral vessel in the axial MIP image, the intersection was removed using the eraser tool. The illustration for tumor segmentation can be found in Appendix E2 in the Supplementary Material.\u003c/p\u003e \u003cp\u003eThe enhancement and segmentation of peritumoral vessel were performed by the eigenvalue analysis of the multiscale Hessian-based filter, which showed simultaneous noise and background suppression and vessel enhancement in MIP images [\u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e]. The details of the multiscale Hessian-based filter method and peritumoral vessel segmentation by algorithm can be found in Appendix E3 and E4 in the Supplementary Material. The segmentation of peritumoral vessel were performed with the Python programming language (Scikit-image package, v. 3.6, Python Software Foundation, \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://www.python.org/\u003c/span\u003e\u003cspan address=\"https://www.python.org/\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e). Then, the peritumoral vasculature by algorithm segmentation was loaded to ITK-SNAP again, and a senior breast radiologist (xx, 11 years of experience) performed manual editing by painting missing voxels and erasing incorrect voxels to get the final peritumoral vasculature. The manual vessel editing procedure took approximately 4 minutes per case. The flowchart and illustration for the vessel segmentation procedures are shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003e and Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003e.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003cp\u003eThe final peritumoral vasculature, checked and edited by the breast radiologist (xx, 11 years of experience), represented the reference standard. To evaluate the performance of vessel detection by algorithm segmentation, the correct-detection rate, incorrect-detection rate, and missed-detection rate were computed (Appendix E5 in the Supplementary Material).\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec7\" class=\"Section2\"\u003e \u003ch2\u003eRadiomic feature extraction\u003c/h2\u003e \u003cp\u003eAfter tumor and peritumoral vessel were segmented, the shape, statistical and textural features were extracted on MIP images using the PyRadiomics Python package [\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e]. For the tumor and peritumoral vessel detected on the MIP images, we extracted radiomics features, including 10 shape features, 19 first-order statistical features, and 70 texture features. Furthermore, we extracted 356 wavelet features (i.e., LL, LH, HL, HH) for each tumor. Wavelet features provide representative transformed domain information regarding intensity and textural features by decomposing the original image in low and high frequencies [\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e]. Finally, 455 features quantifying intratumoral characteristics and 99 features quantifying peritumoral vascular characteristics were obtained.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec8\" class=\"Section2\"\u003e \u003ch2\u003eRadiomic feature selection and model development\u003c/h2\u003e \u003cp\u003eAll the radiomics features were scaled to a range of [0, 1] by using a minimum-maximum scaler. Then, the least absolute shrinkage and selection operator (LASSO) configured recursive feature elimination (RFE) method was applied to select features for the intratumoral model, peritumoral vascular model, individually. The k-nearest neighbor (k-NN) classifier was used to train and test the radiomics models for predicting pCR to NAC. The k-NN (k\u0026thinsp;=\u0026thinsp;5) technique was trained based on the primary cohort, and then tested in the internal and external validation cohorts.\u003c/p\u003e \u003cp\u003eAfter building the tumor features-based prediction model and vessel features-based prediction model, an information fusion method was applied to fuse the prediction scores generated by the two models to improve the model performance [\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e]. The information fusion method included the minimum, maximum, and weighting average of the fusion.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec9\" class=\"Section2\"\u003e \u003ch2\u003eStatistical analysis\u003c/h2\u003e \u003cp\u003eComparisons between the patient groups were employed with the Chi-square test or Fisher\u0026rsquo;s test for qualitative variables and the Student\u0026rsquo;s t-test or Mann-Whitney U test for quantitative variables. The areas under the receiver operating characteristic (ROC) curves (AUCs) were assessed and compared among the intratumoral model, peritumoral vascular model, and fusion model using the DeLong method [\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e]. Statistical analyses and radiomics analyses were performed with the Python programming language (v. 3.6, Python Software Foundation, \u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://www.python.org/\u003c/span\u003e\u003cspan address=\"https://www.python.org/\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e). \u003cem\u003ep\u003c/em\u003e\u003cspan class=\"InlineEquation\"\u003e\u003cspan class=\"mathinline\"\u003e\\(\u0026lt;\\)\u003c/span\u003e\u003c/span\u003e0.05 was considered statistically significant.\u003c/p\u003e \u003c/div\u003e"},{"header":"Results","content":"\u003cp\u003e\u003cstrong\u003ePatients and pathologic complete responses\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eIn total, 282 patients with TNBC were finally enrolled in this study. The clinical pathologic characteristics of patients from all cohorts are listed in Table 1.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eA hundred of 282 patients (35.5%) achieved pCRs after NAC. The pCR rates in the primary cohort, internal validation cohort, and TCIA cohort were 36.6%, 38.9%, and 29.0%, respectively.\u0026nbsp;With regard to clinicopathologic characteristics, no differences between the pCR and non-pCR groups in all cohorts were found in terms of the axillary status, Ki-67 expression,\u0026nbsp;rim enhancement sign, or chemotherapy regimen\u0026nbsp;(\u003cem\u003ep\u003c/em\u003e \u0026gt; 0.05).\u0026nbsp;Patients who achieved pCR in the primary cohort had greater\u0026nbsp;premenopausal status, and had smaller tumor sizes than those who\u0026nbsp;did not (\u003cem\u003ep\u003c/em\u003e = 0.012, 0.022, respectively). Meanwhile, pCR was found to be significantly associated with clinical stage, tumor size and enhancement pattern in the internal validation cohort (\u003cem\u003ep\u003c/em\u003e = 0.042, 0.024, 0.018, respectively).\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eFeature extraction\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe overall performance of vessel identification was evaluated on all cohorts (Table 2).\u0026nbsp;Vessel segmentation examples of 2 representative patients are shown in Fig.4.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eEight tumor features and nigh peritumoral vessel features were selected from initial feature pool were included for further analysis. Detailed information on selected features is shown in Table 3.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003ePerformance of radiomics models\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe AUCs and ROC curves of the radiomics analyses in all cohorts are shown in Table 4.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eThe peritumoral vascular model resulted in an AUC ranging from 0.61 to 0.77: primary cohort, 0.77 (95% confidence interval [CI]: 0.69, 0.83); internal validation cohort, 0.65 (95% CI: 0.54, 0.73); TCIA cohort, 0.61 (95% CI: 0.47, 0.73). Meantime, the intratumoral model yielded an AUC ranging from 0.61 to 0.75: primary cohort, 0.75 (95% CI: 0.66, 0.81); internal validation cohort, 0.64 (95% CI: 0.53, 0.73); TCIA cohort, 0.61 (95% CI: 0.47, 0.74). There were no statistically significant differences in each cohort of AUCs using intratumoral features or peritumoral vascular features (\u003cem\u003ep\u003c/em\u003e \u0026gt; 0.05).\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eThe fusion model yielded the highest AUC of 0.82 (95% CI: 0.75, 0.88) in the primary cohort, and the highest AUC of 0.67 (95% CI: 0.57, 0.76) in the internal cohort and the highest AUC of 0.65 (95% CI: 0.52, 0.78) in TCIA cohort (Table 5, Fig.5). The fusion model showed improved performance over the intratumoral model and the peritumoral vascular model, but not significantly (\u003cem\u003ep\u003c/em\u003e \u0026gt; 0.05).\u003c/p\u003e"},{"header":"Discussion","content":"\u003cp\u003eIn this study, we developed and validated a radiomics model that incorporated peritumoral vascular and intratumoral features extracted from pretreatment MIP images to predict pCRs to NAC in patients with TNBC. The proposed radiomics model provides new insights into the biological characteristics of TNBC and the early prediction of its pathologic responses to NAC.\u003c/p\u003e \u003cp\u003eIdentifying patients not likely to benefit from NAC before treatment could enable tailored individual patient therapies, especially patients with TNBC, which has been known to display the highest distant metastatic rates and lowest overall survival of all breast cancer subtypes. Previous studies have shown that the prediction of pCRs to NAC varied across biological subtypes, indicating the need for specific radiomics models [3; 21]. A radiomics model dedicated to a specific biological subtype could create more reproducible and robust classification results [\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e].\u003c/p\u003e \u003cp\u003e Previous studies using intratumoral texture features extracted from DCE-MRI yielded AUCs of 0.64\u0026ndash;0.68 for the early prediction of pCR in patients with TNBC [7; 23] and were in accordance with those in our study using texture features extracted from 2D MIP. The all intratumoral texture features selected were obtained from wavelet images, which are high-dimensional features that cannot be perceived by humans but hold more detailed information about tumors and are more sensitive when predicting pCRs [7; 24]. Although MIPs miss the proportion of tumor intensity, MIPs integrated with a DCE-MRI protocol can reveal not only the visualization of enhancing tumor but also the tumor-associated vasculature in the clinical scenario, and simplify the workflow to perform the extraction of tumor and peritumoral vasculature in the only one image. To the best of our knowledge, MIPs have never been proposed for feature extractions. The potential association between MIP-derived tumor features and pCR should be further investigated in future studies.\u003c/p\u003e \u003cp\u003eTumor angiogenesis is essential for the growth, invasion, and metastasis of tumors. Overexpression of vascular endothelial growth factor (VEGF) has been extensively investigated to be a key player in the formation of tumor neovasculature with many abnormal features [\u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e25\u003c/span\u003e]. Compared with ER-positive breast cancer, TNBC has a higher degree of VEGF, an avid stimulator of angiogenesis, which is closely correlated with the risk of distant metastases [\u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e]. This angiogenic activity constitutes the basis for the detection and differentiation of breast cancer using DCE-MRI. MIPs from DCE-MRI can assess angiogenic activity and are considered a promising noninvasive investigational tool. Studies focusing on the use of peritumoral vessel to evaluate the response of patients with breast cancer to NAC have been reported [27; 28]. These studies assessed quantitative differences in the number and volume of peritumoral vessels before and after NAC and showed that vessel changes could serve as an early indicator to predict pathologic responses.\u003c/p\u003e \u003cp\u003eIn our study, we performed Hessian-based algorithm to segment the tumor-associated vessels from the axial MIPs of the first postcontrast phase where the greatest lesion conspicuity with the lowest background parenchymal enhancement were demonstrated, as well as the best \u0026ldquo;angiographic effect\u0026rdquo; for both arteries and veins [\u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e29\u003c/span\u003e]. Hessian-based algorithm showed correct-detection rates of 83.1%-89.8%, incorrect-detection rates of 20.1%-27.2%, and missed-detection rates of 10.2%-16.9%, which are similar to those in previous studies with the same algorithm [30; 31]. The incorrect-detection rates were mainly caused by linearly distributed BPE, as well as subtraction artifacts along the breast skin. The missed-detection rates were mainly due to low-signal vascular pixels identified by the radiologist but not detected by the algorithm. Furthermore, the senior radiologist checked and edited the vasculature segmented by the algorithm to get the final peritumoral vasculature for the further radiomics feature extraction. The best-performing vessel features were all from gray level dependence matrix (GLDM) quantifying gray level dependencies in an image. There features may indicate more heterogeneous of abnormal angiogenic vessels surrounding tumors demonstrating non-pCRs [\u003cspan citationid=\"CR32\" class=\"CitationRef\"\u003e32\u003c/span\u003e]. A higher level of abnormal vasculature and the possibility of more discontinuities in the convoluted vasculature might constrict the delivery of chemotherapeutic drugs to tumors, thereby resulting in worse treatment responses [\u003cspan citationid=\"CR33\" class=\"CitationRef\"\u003e33\u003c/span\u003e].\u003c/p\u003e \u003cp\u003ePeritumoral vascular model of TNBC on pretreatment MIP images demonstrated a similar classification performance to that of intratumoral model. Furthermore, a combined peritumoral vascular and intratumoral signature resulted in improved performance, albeit the difference was not significant. These findings suggest that peritumoral vascular radiomics based on MIP might provide a preliminary success for treatment responses in patients with TNBC.\u003c/p\u003e \u003cp\u003eFor this study, we acknowledge the following limitations. First, this study was retrospective. Second, we extracted tumor features from a single representative 2D MIP image, which consisted of projecting the voxel with the highest attenuation value onto every view throughout 2D image volume, which might not provide a comprehensive assessment of whole-tumor heterogeneity. Also, the vasculature segmented from the 2D MIP image could give distorted measures. Specifically, we used the axial MIP image to extract peritumoral vascular and intratumoral features because the MIP image revealed not only tumor enhancements but also tumor vasculature, making the interpretation and analysis simpler than when using full-study DCE-MRI images. We are currently exploring 3D tumor and vascular segmentation on 3D-subtracted postcontrast images [\u003cspan citationid=\"CR34\" class=\"CitationRef\"\u003e34\u003c/span\u003e]. Finally, MR contrast agent, MR scan parameters, and different phases of the menstrual cycle have effects on breast vascularization and so on the performance of peritumoral vascular radiomics analysis.\u003c/p\u003e"},{"header":"Conclusions","content":"\u003cp\u003eThe peritumoral vascular and intratumoral radiomics based on pretreatment MIP images from DCE-MRI can be used to predict pCR to NAC in TNBC patients. This strategy of radiomics analysis could provide a potential approach to assist in understanding the biologic behavior, pretreatment planning, and response prediction of TNBC.\u003c/p\u003e"},{"header":"Abbreviations","content":"\u003cp\u003eAUC: areas under the curve; BPE: background parenchyma ehancement; DCE-MRI: dynamic contrast-enhanced magnetic resonance imaging; GLDM: gray level dependence matrix; k-NN: k-nearest neighbor; LASSO: least absolute shrinkage and selection operator; MIP: maximum intensity projection; NAC: neoadjuvant chemotherapy; pCR: pathologic complete response; RFE: recursive feature elimination; ROC: receiver operating characteristic; TNBC: triple-negative breast cancer.\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eAuthor\u0026rsquo;s contributions\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eTX and JG contributed to study design and manuscript editing. TX contributed to data collection and analysis. QZ contributed to imaging evaluation. SW contributed to clinical studies. CW contributed to manuscript editing. JG contributed to the study design, data analysis and manuscript editing. WP and YG contributed to the study design and imaging evaluation. All authors reviewed the manuscript.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eFunding\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis study has received funding by the National Natural Science Foundation of China (grant number, 82071878) and Clinical Research Plan of Shanghai Hospital Development Center (grant number, SHDC2020CR2008A).\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eEthics approval and consent to participate\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe study complied with the Declaration of Helsinki guidelines and\u0026nbsp;\u003c/p\u003e\n\u003cp\u003edeclaration. The study was approved by the Ethic Committee of Fudan University Shanghai Cancer Center. Written inform consent was waived by the Ethic Committee of Fudan University Shanghai Cancer Center due to the retrospective nature of the study.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eData availability\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe datasets used and/or analysed during the current study are available from the corresponding author upon reasonable request.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConsent for publication\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNot applicable\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eCompeting interests\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe authors declare that they have no competing interests.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAcknowledgements\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNot applicable\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\n\u003cli\u003eDent R, Trudeau M, Pritchard KI et al (2007) Triple-negative breast cancer: clinical features and patterns of recurrence. Clin Cancer Res 13:4429-4434\u003c/li\u003e\n\u003cli\u003eLiedtke C, Mazouni C, Hess KR et al (2008) Response to neoadjuvant therapy and long-term survival in patients with triple-negative breast cancer. J Clin Oncol 26:1275-1281\u003c/li\u003e\n\u003cli\u003eCortazar P, Zhang L, Untch M et al (2014) Pathological complete response and long-term clinical benefit in breast cancer: the CTNeoBC pooled analysis. Lancet 384:164-172\u003c/li\u003e\n\u003cli\u003eDialani V, Chadashvili T, Slanetz PJ (2015) Role of imaging in neoadjuvant therapy for breast cancer. Ann Surg Oncol 22:1416-1424\u003c/li\u003e\n\u003cli\u003eGillies RJ, Kinahan PE, Hricak H (2016) Radiomics: Images Are More than Pictures, They Are Data. Radiology 278:563-577\u003c/li\u003e\n\u003cli\u003ePark VY, Kim EK, Kim MJ, Yoon JH, Moon HJ (2017) Perfusion Parameters on Breast Dynamic Contrast-Enhanced MRI Are Associated With Disease-Specific Survival in Patients With Triple-Negative Breast Cancer. AJR Am J Roentgenol 208:687-694\u003c/li\u003e\n\u003cli\u003eLiu Z, Li Z, Qu J et al (2019) Radiomics of Multiparametric MRI for Pretreatment Prediction of Pathologic Complete Response to Neoadjuvant Chemotherapy in Breast Cancer: A Multicenter Study. Clin Cancer Res 25:3538-3547\u003c/li\u003e\n\u003cli\u003eCain EH, Saha A, Harowicz MR, Marks JR, Marcom PK, Mazurowski MA (2019) Multivariate machine learning models for prediction of pathologic response to neoadjuvant therapy in breast cancer using MRI features: a study using an independent validation set. Breast Cancer Res Treat 173:455-463\u003c/li\u003e\n\u003cli\u003eMazurowski MA, Zhang J, Grimm LJ, Yoon SC, Silber JI (2014) Radiogenomic analysis of breast cancer: luminal B molecular subtype is associated with enhancement dynamics at MR imaging. Radiology 273:365-372\u003c/li\u003e\n\u003cli\u003eWang J, Kato F, Oyama-Manabe N et al (2015) Identifying Triple-Negative Breast Cancer Using Background Parenchymal Enhancement Heterogeneity on Dynamic Contrast-Enhanced MRI: A Pilot Radiomics Study. PLoS One 10:e0143308\u003c/li\u003e\n\u003cli\u003eBraman NM, Etesami M, Prasanna P et al (2017) Intratumoral and peritumoral radiomics for the pretreatment prediction of pathological complete response to neoadjuvant chemotherapy based on breast DCE-MRI. Breast Cancer Res 19:57\u003c/li\u003e\n\u003cli\u003eHanahan D, Folkman J (1996) Patterns and emerging mechanisms of the angiogenic switch during tumorigenesis. Cell 86:353-364\u003c/li\u003e\n\u003cli\u003eSaha A, Harowicz MR, Grimm LJ et al (2018) A machine learning approach to radiogenomics of breast cancer: a study of 922 subjects and 529 DCE-MRI features. Br J Cancer 119:508-516\u003c/li\u003e\n\u003cli\u003eGoldhirsch A, Winer EP, Coates AS et al (2013) Personalizing the treatment of women with early breast cancer: highlights of the St Gallen International Expert Consensus on the Primary Therapy of Early Breast Cancer 2013. Ann Oncol 24:2206-2223\u003c/li\u003e\n\u003cli\u003evon Minckwitz G, Untch M, Blohmer JU et al (2012) Definition and impact of pathologic complete response on prognosis after neoadjuvant chemotherapy in various intrinsic breast cancer subtypes. J Clin Oncol 30:1796-1804\u003c/li\u003e\n\u003cli\u003eVignati A, Giannini V, Carbonaro LA et al (2014) A new algorithm for automatic vascular mapping of DCE-MRI of the breast: Clinical application of a potential new biomarker. Comput Methods Programs Biomed 117:482-488\u003c/li\u003e\n\u003cli\u003evan Griethuysen JJM, Fedorov A, Parmar C et al (2017) Computational Radiomics System to Decode the Radiographic Phenotype. Cancer Res 77:e104-e107\u003c/li\u003e\n\u003cli\u003eLaine A, Fan J (1993) Texture classification by wavelet packet signatures. Ieee Transactions on Pattern Analysis and Machine Intelligence 15:1186-1191\u003c/li\u003e\n\u003cli\u003eGong J, Liu JY, Jiang YJ, Sun XW, Zheng B, Nie SD (2018) Fusion of quantitative imaging features and serum biomarkers to improve performance of computer-aided diagnosis scheme for lung cancer: A preliminary study. Med Phys 45:5472-5481\u003c/li\u003e\n\u003cli\u003eDeLong ER, DeLong DM, Clarke-Pearson DL (1988) Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics 44:837-845\u003c/li\u003e\n\u003cli\u003evon Minckwitz G, Untch M, Blohmer JU et al (2012) Definition and Impact of Pathologic Complete Response on Prognosis After Neoadjuvant Chemotherapy in Various Intrinsic Breast Cancer Subtypes. Journal of Clinical Oncology 30:1796-1804\u003c/li\u003e\n\u003cli\u003eGranzier RWY, van Nijnatten TJA, Woodruff HC, Smidt ML, Lobbes MBI (2019) Exploring breast cancer response prediction to neoadjuvant systemic therapy using MRI-based radiomics: A systematic review. Eur J Radiol 121:108736\u003c/li\u003e\n\u003cli\u003eGolden DI, Lipson JA, Telli ML, Ford JM, Rubin DL (2013) Dynamic contrast-enhanced MRI-based biomarkers of therapeutic response in triple-negative breast cancer. J Am Med Inform Assoc 20:1059-1066\u003c/li\u003e\n\u003cli\u003eNie K, Shi L, Chen Q et al (2016) Rectal Cancer: Assessment of Neoadjuvant Chemoradiation Outcome based on Radiomics of Multiparametric MRI. Clin Cancer Res 22:5256-5264\u003c/li\u003e\n\u003cli\u003eHoeben A, Landuyt B, Highley MS, Wildiers H, Van Oosterom AT, De Bruijn EA (2004) Vascular endothelial growth factor and angiogenesis. Pharmacol Rev 56:549-580\u003c/li\u003e\n\u003cli\u003eLinderholm BK, Hellborg H, Johansson U et al (2009) Significantly higher levels of vascular endothelial growth factor (VEGF) and shorter survival times for patients with primary operable triple-negative breast cancer. Ann Oncol 20:1639-1646\u003c/li\u003e\n\u003cli\u003eMartincich L, Bertotto I, Montemurro F et al (2011) Variation of breast vascular maps on dynamic contrast-enhanced MRI after primary chemotherapy of locally advanced breast cancer. AJR Am J Roentgenol 196:1214-1218\u003c/li\u003e\n\u003cli\u003eWu LA, Chang RF, Huang CS et al (2015) Evaluation of the treatment response to neoadjuvant chemotherapy in locally advanced breast cancer using combined magnetic resonance vascular maps and apparent diffusion coefficient. J Magn Reson Imaging 42:1407-1420\u003c/li\u003e\n\u003cli\u003eSardanelli F, Iozzelli A, Fausto A, Carriero A, Kirchin MA (2005) Gadobenate dimeglumine-enhanced MR imaging breast vascular maps: association between invasive cancer and ipsilateral increased vascularity. Radiology 235:791-797\u003c/li\u003e\n\u003cli\u003eLin M, Chen JH, Nie K, Chang D, Nalcioglu O, Su MY (2009) Algorithm-based method for detection of blood vessels in breast MRI for development of computer-aided diagnosis. J Magn Reson Imaging 30:817-824\u003c/li\u003e\n\u003cli\u003eVignati A, Giannini V, Bert A et al (2012) A fully automatic multiscale 3-dimensional Hessian-based algorithm for vessel detection in breast DCE-MRI. Invest Radiol 47:705-710\u003c/li\u003e\n\u003cli\u003eSun C, Wee WG (1983) Neighboring gray level dependence matrix for texture classification. Computer Vision, Graphics, and Image Processing 23:341-352\u003c/li\u003e\n\u003cli\u003eViens P, Jacquemier J, Bardou VJ et al (1999) Association of angiogenesis and poor prognosis in node-positive patients receiving anthracycline-based adjuvant chemotherapy. Breast Cancer Res Treat 54:205-212\u003c/li\u003e\n\u003cli\u003eWu C, Pineda F, Hormuth DA, 2nd, Karczmar GS, Yankeelov TE (2019) Quantitative analysis of vascular properties derived from ultrafast DCE-MRI to discriminate malignant and benign breast tumors. Magn Reson Med 81:2147-2160\u003c/li\u003e\n\u003c/ol\u003e"},{"header":"Tables","content":"\u003cp\u003e\u003cstrong\u003eTable 1\u0026nbsp;\u003c/strong\u003e\u003cstrong\u003eThe clinicopathologic characteristics of the patients with TNBC in the three cohorts\u003c/strong\u003e\u003c/p\u003e\n\u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"3\" valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003ePrimary cohort\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003e\u003cstrong\u003e(\u003cem\u003en\u003c/em\u003e = 93)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"5\" valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003eInternal validation cohort\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003e\u003cstrong\u003e(\u003cem\u003en\u003c/em\u003e = 113)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"3\" valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003eExternal validation cohort\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003e\u003cstrong\u003e(\u003cem\u003en\u003c/em\u003e = 76)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003eCharacteristic\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003epCR\u003c/p\u003e\n \u003cp\u003e(\u003cem\u003en\u003c/em\u003e = 34)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eNon-pCR\u003c/p\u003e\n \u003cp\u003e(\u003cem\u003en\u003c/em\u003e = 59)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u003cem\u003ep\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003epCR\u003c/p\u003e\n \u003cp\u003e(\u003cem\u003en\u003c/em\u003e = 44)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" valign=\"top\"\u003e\n \u003cp\u003eNon-pCR\u003c/p\u003e\n \u003cp\u003e(\u003cem\u003en\u003c/em\u003e = 69)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u003cem\u003ep\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003epCR\u003c/p\u003e\n \u003cp\u003e(\u003cem\u003en\u003c/em\u003e = 22)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eNon-pCR\u003c/p\u003e\n \u003cp\u003e(\u003cem\u003en\u003c/em\u003e = 54)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u003cem\u003ep\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eAge, mean \u0026plusmn; SD, years\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e46.59\u0026plusmn;11.42\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e50.90\u0026plusmn;11.14\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e0.078\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e45.32\u0026plusmn;9.37\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" valign=\"top\"\u003e\n \u003cp\u003e48.13\u0026plusmn;11.85\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" valign=\"top\"\u003e\n \u003cp\u003e0.186\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e47.77\u0026plusmn;14.17\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e49.83\u0026plusmn;10.49\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e0.487\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eMenopausal status\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e0.012\u003cem\u003e\u003csup\u003e*\u003c/sup\u003e\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" valign=\"top\"\u003e\n \u003cp\u003e0.434\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e0.723\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003ePeri or Postmenopausal\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e11\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e35\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e19\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" valign=\"top\"\u003e\n \u003cp\u003e35\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e8\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e22\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003ePremenopausal\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e23\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e24\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e25\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" valign=\"top\"\u003e\n \u003cp\u003e34\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e14\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e32\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eClinical stage\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e0.946\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" valign=\"top\"\u003e\n \u003cp\u003e0.042\u003cem\u003e\u003csup\u003e*\u003c/sup\u003e\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e0.819\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eI/II\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e25\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e43\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e32\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" valign=\"top\"\u003e\n \u003cp\u003e37\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e17\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e43\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eIII/IV\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e9\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e16\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e12\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" valign=\"top\"\u003e\n \u003cp\u003e32\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e5\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e11\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eLesion size, mean \u0026plusmn; SD, mm\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e33.74\u0026plusmn;15.95\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e43.25\u0026plusmn;20.59\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e0.022\u003cem\u003e\u003csup\u003e*\u003c/sup\u003e\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e36.09\u0026plusmn;19.34\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" valign=\"top\"\u003e\n \u003cp\u003e46.72\u0026plusmn;26.68\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" valign=\"top\"\u003e\n \u003cp\u003e0.024\u003cem\u003e\u003csup\u003e*\u003c/sup\u003e\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e27.91\u0026plusmn;16.94\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e34.30\u0026plusmn;21.48\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e0.217\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eAxillary LN before NAC\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e0.679\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" valign=\"top\"\u003e\n \u003cp\u003e0.327\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e0.191\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eNegative\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e9\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e18\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e11\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" valign=\"top\"\u003e\n \u003cp\u003e12\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e13\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e23\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003ePositive\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e25\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e41\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e33\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" valign=\"top\"\u003e\n \u003cp\u003e57\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e9\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e31\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eKi-67 before NAC\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e0.121\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" valign=\"top\"\u003e\n \u003cp\u003e0.480\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eNA\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eNegative\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e4\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" valign=\"top\"\u003e\n \u003cp\u003e6\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eNA\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eNA\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003ePositive\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e34\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e55\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e42\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" valign=\"top\"\u003e\n \u003cp\u003e63\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eNA\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eNA\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eEnhancement Pattern\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e0.083\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" valign=\"top\"\u003e\n \u003cp\u003e0.018\u003cem\u003e\u003csup\u003e*\u003c/sup\u003e\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e0.162\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eWith nonmass enhancement\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e4\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e16\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e4\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e19\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e11\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eMass only\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e30\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e43\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e40\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e50\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e21\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e43\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eRim Enhancement\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e0.640\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e0.066\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e0.468\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eNegative\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e19\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e30\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e21\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e45\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e15\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e32\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003ePositive\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e15\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e29\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e23\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e24\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e7\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e22\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eChemotherapy regimen\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e0.616\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e0.430\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eNA\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eEC-T\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e25\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e42\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e24\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e29\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eNA\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eNA\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eEC\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e2\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e7\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e5\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e10\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eNA\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eNA\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eTCb\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e7\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e10\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e15\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e30\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eNA\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003eNA\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"14.655172413793103%\"\u003e\u003cbr\u003e\u003c/td\u003e\n \u003ctd width=\"10.83743842364532%\"\u003e\u003cbr\u003e\u003c/td\u003e\n \u003ctd width=\"10.83743842364532%\"\u003e\u003cbr\u003e\u003c/td\u003e\n \u003ctd width=\"6.403940886699507%\"\u003e\u003cbr\u003e\u003c/td\u003e\n \u003ctd width=\"10.83743842364532%\"\u003e\u003cbr\u003e\u003c/td\u003e\n \u003ctd width=\"10.83743842364532%\"\u003e\u003cbr\u003e\u003c/td\u003e\n \u003ctd width=\"0.8620689655172413%\"\u003e\u003cbr\u003e\u003c/td\u003e\n \u003ctd width=\"0.8620689655172413%\"\u003e\u003cbr\u003e\u003c/td\u003e\n \u003ctd width=\"6.403940886699507%\"\u003e\u003cbr\u003e\u003c/td\u003e\n \u003ctd width=\"10.83743842364532%\"\u003e\u003cbr\u003e\u003c/td\u003e\n \u003ctd width=\"10.83743842364532%\"\u003e\u003cbr\u003e\u003c/td\u003e\n \u003ctd width=\"5.788177339901478%\"\u003e\u003cbr\u003e\u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003e\u003cem\u003eEC\u003c/em\u003e epirubicin with cyclophosphamide; \u003cem\u003eEC-T\u003c/em\u003e epirubicin with cyclophosphamide plus docetaxel; \u003cem\u003eLN\u003c/em\u003e lymph node; \u003cem\u003eNAC\u003c/em\u003e neoadjuvant chemotherapy;\u003cem\u003e\u0026nbsp;pCR\u003c/em\u003e pathologic complete response; \u003cem\u003eSD\u003c/em\u003e standard deviation; \u003cem\u003eTCb\u003c/em\u003e docetaxel with carboplatin.\u003c/p\u003e\n\u003cp\u003e\u003cem\u003e\u003csup\u003e*\u003c/sup\u003e\u003c/em\u003e\u003cem\u003e\u0026nbsp;p \u0026lt; 0.05\u003c/em\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eTable 2 Vessel detection algorithm performance\u003c/strong\u003e\u003c/p\u003e\n\u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e\u003cstrong\u003eCorrect-detection rate\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003e\u003cstrong\u003e(%)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e\u003cstrong\u003eIncorrect-detection rate\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003e\u003cstrong\u003e(%)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e\u003cstrong\u003eMissed-detection rate\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003e\u003cstrong\u003e(%)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003e\n \u003cp\u003ePrimary cohort\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003e\n \u003cp\u003e\u0026nbsp; Range\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e60-100\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0-45\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0-40\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003e\n \u003cp\u003e\u0026nbsp; Median\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e90.0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e20.9\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e10.0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003e\n \u003cp\u003e\u0026nbsp; Mean (SD)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e89.8 (5.2)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e20.1 (6.5)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e10.2 (5.2)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003e\n \u003cp\u003eInternal validation cohort\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003e\n \u003cp\u003e\u0026nbsp; Range\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e64-100\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0-42.9\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e0-36\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003e\n \u003cp\u003e\u0026nbsp; Median\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e86.4\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e25.6\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e13.6\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003e\n \u003cp\u003e\u0026nbsp; Mean (SD)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e85.1 (7.1)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e24.9 (7.3)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e14.9 (7.1)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003e\n \u003cp\u003eExternal validation cohort\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003e\n \u003cp\u003e\u0026nbsp; Range\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e58.3-100\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e0-40.0\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e0-41.7\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003e\n \u003cp\u003e\u0026nbsp; Median\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e84.3\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e27.5\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e15.7\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003e\n \u003cp\u003e\u0026nbsp; Mean (SD)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e83.1 (9.1)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e27.2 (8.2)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e16.9 (9.1)\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003e\u003cem\u003eSD\u003c/em\u003e standard deviation.\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eTable 3 Radiomics features extracted from the tumor and peritumoral vessel were identified after feature selection\u003c/strong\u003e\u003c/p\u003e\n\u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\" width=\"931\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd width=\"8.16326530612245%\" valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003eLocation\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"15.467239527389903%\" valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003eFeature Family\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"38.66809881847476%\" valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003eFeature\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"37.70139634801289%\" valign=\"top\"\u003e\n \u003cp\u003e\u003cstrong\u003eDescription\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"8.16326530612245%\" rowspan=\"8\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003cp\u003eTumor\u0026nbsp;(wavelet-LL)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"15.467239527389903%\" rowspan=\"8\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003cp\u003eGLDM\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"38.66809881847476%\" valign=\"top\"\u003e\n \u003cp\u003eHigh Gray Level Emphasis\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"37.70139634801289%\" valign=\"top\"\u003e\n \u003cp\u003eDistribution of the higher gray-level values\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"50.63291139240506%\" valign=\"top\"\u003e\n \u003cp\u003eLarge Dependence Emphasis\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"49.36708860759494%\" valign=\"top\"\u003e\n \u003cp\u003eDistribution of large dependencies\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"50.63291139240506%\" valign=\"top\"\u003e\n \u003cp\u003eLarge Dependence High Gray Level Emphasis\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"49.36708860759494%\" valign=\"top\"\u003e\n \u003cp\u003eJoint distribution of large dependence with higher gray-level values\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"50.63291139240506%\" valign=\"top\"\u003e\n \u003cp\u003eLarge Dependence Low Gray Level Emphasis\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"49.36708860759494%\" valign=\"top\"\u003e\n \u003cp\u003eJoint distribution of large dependence with lower gray-level values\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"50.63291139240506%\" valign=\"top\"\u003e\n \u003cp\u003eLow Gray Level Emphasis\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"49.36708860759494%\" valign=\"top\"\u003e\n \u003cp\u003eDistribution of low gray-level values\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"50.63291139240506%\" valign=\"top\"\u003e\n \u003cp\u003eSmall Dependence Emphasis\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"49.36708860759494%\" valign=\"top\"\u003e\n \u003cp\u003eDistribution of small dependencies\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"50.63291139240506%\" valign=\"top\"\u003e\n \u003cp\u003eSmall Dependence High Gray Level Emphasis\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"49.36708860759494%\" valign=\"top\"\u003e\n \u003cp\u003eJoint distribution of small dependence with higher gray-level values\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"50.63291139240506%\" valign=\"top\"\u003e\n \u003cp\u003eSmall Dependence Low Gray Level Emphasis\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"49.36708860759494%\" valign=\"top\"\u003e\n \u003cp\u003eJoint distribution of small dependence with lower gray-level values\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"8.16326530612245%\" rowspan=\"9\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003cp\u003eVessel\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"15.467239527389903%\" rowspan=\"9\" valign=\"top\"\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003cp\u003eGLDM\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"38.66809881847476%\" valign=\"top\"\u003e\n \u003cp\u003eGray Level Variance\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"37.70139634801289%\" valign=\"top\"\u003e\n \u003cp\u003eVariance in grey level in the image\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"50.63291139240506%\" valign=\"top\"\u003e\n \u003cp\u003eHigh Gray Level Emphasis\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"49.36708860759494%\" valign=\"top\"\u003e\n \u003cp\u003eDistribution of the higher gray-level values\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"50.63291139240506%\" valign=\"top\"\u003e\n \u003cp\u003eLarge Dependence\u0026nbsp;Emphasis\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"49.36708860759494%\" valign=\"top\"\u003e\n \u003cp\u003eDistribution of large dependencies\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"50.63291139240506%\" valign=\"top\"\u003e\n \u003cp\u003eLarge Dependence High Gray Level Emphasis\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"49.36708860759494%\" valign=\"top\"\u003e\n \u003cp\u003eJoint distribution of large dependence with higher gray-level values\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"50.63291139240506%\" valign=\"top\"\u003e\n \u003cp\u003eLarge Dependence Low Gray Level Emphasis\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"49.36708860759494%\" valign=\"top\"\u003e\n \u003cp\u003eJoint distribution of large dependence with lower gray-level values\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"50.63291139240506%\" valign=\"top\"\u003e\n \u003cp\u003eLow Gray Level Emphasis\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"49.36708860759494%\" valign=\"top\"\u003e\n \u003cp\u003eDistribution of low gray-level values\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"50.63291139240506%\" valign=\"top\"\u003e\n \u003cp\u003eSmall Dependence Emphasis\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"49.36708860759494%\" valign=\"top\"\u003e\n \u003cp\u003eDistribution of small dependencies\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"50.63291139240506%\" valign=\"top\"\u003e\n \u003cp\u003eSmall Dependence High Gray Level Emphasis\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"49.36708860759494%\" valign=\"top\"\u003e\n \u003cp\u003eJoint distribution of small dependence with higher gray-level values\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd width=\"50.63291139240506%\" valign=\"top\"\u003e\n \u003cp\u003eSmall Dependence Low Gray Level Emphasis\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd width=\"49.36708860759494%\" valign=\"top\"\u003e\n \u003cp\u003eJoint distribution of small dependence with lower gray-level values\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003e\u003cem\u003eGLDM\u003c/em\u003e Gray Level Dependence Matrix.\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eTable 4 Performance of the peritumoral vascular radiomics model and intratumoral radiomics model\u003c/strong\u003e\u003c/p\u003e\n\u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\"\u003e\n \u003cp\u003e\u003cstrong\u003ePrimary cohort\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\"\u003e\n \u003cp\u003e\u003cstrong\u003eInternal validation cohort\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\"\u003e\n \u003cp\u003e\u003cstrong\u003eExternal validation cohort\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e\u003cstrong\u003eAUC\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e\u003cstrong\u003e95% CI\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e\u003cstrong\u003eAUC\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e\u003cstrong\u003e95% CI\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e\u003cstrong\u003eAUC\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e\u003cstrong\u003e95% CI\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003e\n \u003cp\u003eTumor\u003csup\u003ea\u003c/sup\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e0.75\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[0.66, 0.81]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e0.64\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[0.53, 0.73]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e0.61\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[0.47, 0.74]\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003e\n \u003cp\u003eVessel\u003csup\u003eb\u003c/sup\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e0.77\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[0.69, 0.83]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e0.65\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[0.54, 0.73]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e0.61\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[0.47, 0.73]\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003eTumor\u003csup\u003ea\u003c/sup\u003e: prediction score generated using the intratumoral features-based model; Vessel\u003csup\u003eb\u003c/sup\u003e: prediction score generated using the peritumoral vascular features-based model.\u003c/p\u003e\n\u003cp\u003eAUC,\u0026nbsp;area under the curve; CI,\u0026nbsp;confidence interval.\u003cstrong\u003e\u003c/strong\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eTable 5 A summary of the area under the curve (AUC) values obtained using different fusion methods to combine prediction scores generated by tumor features and peritumoral vessel features\u003c/strong\u003e\u003c/p\u003e\n\u003cdiv align=\"\"\u003e\n \u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd\u003e\n \u003cp\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\"\u003e\n \u003cp\u003e\u003cstrong\u003ePrimary cohort\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\"\u003e\n \u003cp\u003e\u003cstrong\u003eInternal validation cohort\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\"\u003e\n \u003cp\u003e\u003cstrong\u003eExternal validation cohort\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003e\n \u003cp\u003e\u003cstrong\u003eModel\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e\u003cstrong\u003eAUC\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e\u003cstrong\u003e95% CI\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e\u003cstrong\u003eAUC\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e\u003cstrong\u003e95% CI\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e\u003cstrong\u003eAUC\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd\u003e\n \u003cp\u003e\u003cstrong\u003e95% CI\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003e\n \u003cp\u003eMinimum\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e0.81\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[0.74, 0.87]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e0.65\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[0.54, 0.74]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e0.63\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[0.49, 0.76]\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003e\n \u003cp\u003eMaximum\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e0.76\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[0.68, 0.83]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e0.65\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[0.54, 0.74]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e0.59\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[0.44, 0.70]\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003e\n \u003cp\u003e0.9\u0026times;Tumor\u003csup\u003ea\u003c/sup\u003e+0.1\u0026times;Vessel\u003csup\u003eb\u003c/sup\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e0.80\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[0.72, 0.86]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e0.67\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[0.57, 0.76]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e0.64\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[0.50, 0.77]\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003e\n \u003cp\u003e0.8\u0026times;Tumor+0.2\u0026times;Vessel\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e0.80\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[0.72, 0.86]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e0.67\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[0.57, 0.76]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e0.64\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[0.50, 0.77]\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003e\n \u003cp\u003e0.7\u0026times;Tumor+0.3\u0026times;Vessel\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e0.81\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[0.73, 0.87]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e0.67\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[0.56, 0.75]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e0.65\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[0.51, 0.77]\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003e\n \u003cp\u003e0.6\u0026times;Tumor+0.4\u0026times;Vessel\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e0.82\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[0.75, 0.88]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e0.67\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[0.55, 0.75]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e0.65\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[0.52, 0.78]\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003e\n \u003cp\u003e0.5\u0026times;Tumor+0.5\u0026times;Vessel\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e0.82\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[0.74, 0.88]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e0.67\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[0.56, 0.76]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e0.64\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[0.51, 0.77]\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003e\n \u003cp\u003e0.4\u0026times;Tumor+0.6\u0026times;Vessel\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e0.81\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[0.73, 0.87]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e0.66\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[0.55, 0.75]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e0.62\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[0.48, 0.76]\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003e\n \u003cp\u003e0.3\u0026times;Tumor+0.7\u0026times;Vessel\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e0.81\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[0.73, 0.87]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e0.66\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[0.55, 0.75]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e0.62\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[0.49, 0.76]\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003e\n \u003cp\u003e0.2\u0026times;Tumor+0.8\u0026times;Vessel\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e0.78\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[0.70, 0.85]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e0.65\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[0.54, 0.74]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e0.62\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[0.48, 0.76]\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd\u003e\n \u003cp\u003e0.1\u0026times;Tumor+0.9\u0026times;Vessel\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e0.77\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[0.68, 0.83]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e0.65\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[0.54, 0.74]\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e0.61\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\"\u003e\n \u003cp\u003e[0.46, 0.73]\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n \u003c/table\u003e\n\u003c/div\u003e\n\u003cp\u003eTumor\u003csup\u003ea\u003c/sup\u003e: prediction score generated using the intratumoral features-based model; Vessel\u003csup\u003eb\u003c/sup\u003e: prediction score generated using the peritumoral vascular features-based model.\u003c/p\u003e\n\u003cp\u003e\u003cem\u003eAUC\u003c/em\u003e area under the curve; \u003cem\u003eCI\u003c/em\u003e confidence interval.\u003c/p\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"bmc-medical-imaging","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"bmim","sideBox":"Learn more about [BMC Medical Imaging](http://bmcmedimaging.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/bmim/default.aspx","title":"BMC Medical Imaging","twitterHandle":"BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Triple negative breast neoplasms, Magnetic resonance imaging, Contrast media, Magnetic resonance angiography, Neoadjuvant therapy","lastPublishedDoi":"10.21203/rs.3.rs-3960587/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-3960587/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eBackground\u003c/h2\u003e \u003cp\u003eTo develop and validate a peritumoral vascular and intratumoral radiomics model to improve pretreatment predictions for pathologic complete responses (pCRs) to neoadjuvant chemoradiotherapy (NAC) in patients with triple-negative breast cancer (TNBC).\u003c/p\u003e\u003ch2\u003eMethods\u003c/h2\u003e \u003cp\u003eA total of 282 TNBC patients (93 in the primary cohort, 113 in the validation cohort, and 76 in The Cancer Imaging Archive [TCIA] cohort) were retrospectively included. The peritumoral vasculature on the maximum intensity projection (MIP) from pretreatment DCE-MRI was segmented by a Hessian matrix-based filter and then edited by a radiologist. Radiomics features were extracted from the tumor and peritumoral vasculature of the MIP images. The LASSO method was used for feature selection, and the k-nearest neighbor (k-NN) classifier was trained and validated to build a predictive model. The diagnostic performance was assessed using the ROC analysis.\u003c/p\u003e\u003ch2\u003eResults\u003c/h2\u003e \u003cp\u003eOne hundred of the 282 patient (35.5%) with TNBC achieved pCRs after NAC. In predicting pCRs, the combined peritumoral vascular and intratumoral model (fusion model) yields a maximum AUC of 0.82 (95% confidence interval [CI]: 0.75, 0.88) in the primary cohort, a maximum AUC of 0.67 (95% CI: 0.57, 0.76) in the internal validation cohort, and a maximum AUC of 0.65 (95% CI: 0.52, 0.78) in TCIA cohort. The fusion model showed improved performance over the intratumoral model and the peritumoral vascular model, but not significantly (\u003cem\u003ep\u003c/em\u003e\u0026thinsp;\u0026gt;\u0026thinsp;0.05).\u003c/p\u003e\u003ch2\u003eConclusion\u003c/h2\u003e \u003cp\u003eThis study suggested that combined peritumoral vascular and intratumoral radiomics model could provide a non-invasive tool to enable prediction of pCR in TNBC patients treated with NAC.\u003c/p\u003e","manuscriptTitle":"Development and validation of peritumoral vascular and intratumoral radiomics to predict pathologic complete responses to neoadjuvant chemotherapy in patients with triple-negative breast cancer","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-02-27 20:57:54","doi":"10.21203/rs.3.rs-3960587/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2024-04-09T11:00:08+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2024-03-09T15:07:39+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"d6ea9253-80e2-4a66-91cd-ad8548fc6d61","date":"2024-03-01T06:12:21+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2024-02-26T12:37:50+00:00","index":"","fulltext":""},{"type":"editorInvited","content":"","date":"2024-02-22T20:00:11+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2024-02-22T19:36:44+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2024-02-22T19:36:44+00:00","index":"","fulltext":""},{"type":"submitted","content":"BMC Medical Imaging","date":"2024-02-16T07:17:48+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"bmc-medical-imaging","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"bmim","sideBox":"Learn more about [BMC Medical Imaging](http://bmcmedimaging.biomedcentral.com/)","snPcode":"","submissionUrl":"https://www.editorialmanager.com/bmim/default.aspx","title":"BMC Medical Imaging","twitterHandle":"BMC_series","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"em","reportingPortfolio":"BMC Series","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"34131eb1-d264-40e5-955e-5fe99c48056e","owner":[],"postedDate":"February 27th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2024-05-27T06:38:04+00:00","versionOfRecord":[],"versionCreatedAt":"2024-02-27 20:57:54","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-3960587","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-3960587","identity":"rs-3960587","version":["v1"]},"buildId":"-HB7Z8yhvgn0wM9Nzuekk","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}