Deep vision transformers in neurodegenerative disease diagnosis using 18F-fluorodeoxyglucose positron emission tomography scans and anatomical brain atlas

This research explores adapting vision transformers (ViTs) to classify neurodegenerative diseases while ensuring their decision-making process is interpretable. We developed a model to classify 18F-fluorodeoxyglucose (18F-FDG) positron emission tomography (PET) brain scans into three categories: cognitively normal, mild cognitive impairment, and Alzheimer’s disease (AD). The dataset utilized in this research contains 580 samples of 18F-FDG PET scans obtained from the AD neuroimaging initiative. The proposed model obtained an F1 score of 81% (macro-average of all classes) on the test dataset, a significant performance improvement compared to the literature. Furthermore, we combined the model’s attention maps with the Automated Anatomical Atlas 3, which represents a digital brain map, to identify the most influential areas on the model’s predictions and to conduct a regions’ importance study as a step toward explainability. We demonstrated that ViTs can achieve competitive performance compared to convolutional neural networks while enabling the development of explainable models without extra computations due to the attention mechanism.