Towards better interpretable and generalizable AD detection using collective artificial intelligence

Huy-Dung Nguyen, Michaël Clément, Boris Mansencal, Pierrick Coupé

Abstract: Highlights•Our novel deep grading biomarker enables to improve the interpretability of deep model outputs for Alzheimer’s Disease (AD) classification.•The extension of collective artificial intelligence strategy enables to improve the model performance across domains.•The use of graph convolutional network enables to obtain state-of-the-art in performance for both AD diagnosis and prognosis.