Adopting transfer learning for neuroimaging: a comparative analysis with a custom 3D convolution neural network model.

BACKGROUND: In recent years, neuroimaging with deep learning (DL) algorithms have made remarkable advances in the diagnosis of neurodegenerative disorders. However, applying DL in different medical domains is usually challenged by lack of labeled data. To address this challenge, transfer learning (TL) has been applied to use state-of-the-art convolution neural networks pre-trained on natural images. Yet, there are differences in characteristics between medical and natural images, also image classification and targeted medical diagnosis tasks. The purpose of this study is to investigate the performance of specialized and TL in the classification of neurodegenerative disorders using 3D volumes of 18F-FDG-PET brain scans. RESULTS: Results show that TL models are suboptimal for classification of neurodegenerative disorders, especially when the objective is to separate more than two disorders. Additionally, specialized CNN model provides better interpretations of predicted diagnosis. CONCLUSIONS: TL can indeed lead to superior performance on binary classification in timely and data efficient manner, yet for detecting more than a single disorder, TL models do not perform well. Additionally, custom 3D model performs comparably to TL models for binary classification, and interestingly perform better for diagnosis of multiple disorders. The results confirm the superiority of the custom 3D-CNN in providing better explainable model compared to TL adopted ones.

The bvFTD phenocopy syndrome: a case study supported by repeated MRI, [18F]FDG-PET and pathological assessment.

A clinical syndrome with neuropsychiatric features of bvFTD without neuroimaging abnormalities and a lack of decline is a phenocopy of bvFTD (phFTD). Growing evidence suggests that psychological, psychiatric and environmental factors underlie phFTD. We describe a patient diagnosed with bvFTD prior to the revision of the diagnostic guidelines of FTD. Repeated neuroimaging was normal and there was no FTD pathology at autopsy, rejecting the diagnosis. We hypothesize on etiological factors that on hindsight might have played a role. This case report contributes to the understanding of phFTD and adds to the sparse literature of the postmortem assessment of phFTD.