A Semi-Supervised Contrastive Learning Approach to Alzheimer’s Disease Diagnostics using Convolutional Autoencoders

ABSTRACT PURPOSE Alzheimer’s Disease (AD) is a neurodegenerative disease that progressively deteriorates memory and cognitive abilities. PET 18F-AV45 (florbetapir) is a common imaging modality used to characterize the distribution of beta-amyloid deposits in the brain, however interpretation may be subjective and the misdiagnosis rate of AD ranges from 12-23%. Automated algorithms for PET 18F-AV45 interpretation including those derived from deep learning may facilitate more objective and accurate AD diagnosis. MATERIALS & METHODS A total of 1232 PET AV45 scans (207 - AD; 1025 - normal) were obtained from the Alzheimer’s Disease Neuroimaging Initiative (ADNI). A semi-supervised deep learning framework was developed to differentiate AD and normal patients. The framework consists of an autoencoder (AE), a contrastive learning loss, and a categorical classification head. A contrastive learning paradigm is used to improve the discriminative properties of latent feature vectors in multidimensional space. RESULTS Upon five-fold cross-validation, the best-performing semi-supervised contrastive model achieved validation accuracy of 82% to 86%. Secondary analysis included visualization of intermediate activations, classification report verification, and principal component analysis (PCA) of latent feature vectors. The training process yielded optimal converging losses for all three loss frameworks. CONCLUSION A deep learning model can accurately diagnose AD using PET 18F-AV45 scans. Such models require large amounts of labeled data during training. The use of a semi-supervised contrastive learning objective and AE regularizer helps to improve model performance, especially when dataset sizes are constrained. Latent representations extracted by the model are visually clustered strongly with the addition of a contrastive learning mechanism. Summary Statement A semi-supervised contrastive learning deep learning system optimizes latent feature vector representations and yields strong model classification performance for larger data distributions within the Alzheimer’s Disease diagnostics domain. Key Points A common diagnostic procedure used by trained radiologists in the clinical setting is the visual analysis of PET 18F-AV45 neuroimaging scans to diagnose the different stages of Alzheimer’s Disease in a patient. Contrastive learning is a strategy that allows for the optimization of latent feature representations in multidimensional space through the use of a loss function that maximizes the distance between feature vectors of different classes and minimizes the distance of feature vectors of the same class. A semi-supervised contrastive learning approach can lead to improved performance and generalization of deep learning models optimized using small training datasets as encountered in Alzheimer’s Disease and other neurodegenerative conditions.