Comparison of Explainable AI Models for MRI-based Alzheimer's Disease Classification.

Autor:	Chattopadhyay T; Imaging Genetics Center, Mark and Mary Stevens Neuroimaging and Informatics Institute, Keck School of Medicine, University of Southern California, Marina del Rey, CA, United States., Joshy NA; Imaging Genetics Center, Mark and Mary Stevens Neuroimaging and Informatics Institute, Keck School of Medicine, University of Southern California, Marina del Rey, CA, United States., Jagad C; Imaging Genetics Center, Mark and Mary Stevens Neuroimaging and Informatics Institute, Keck School of Medicine, University of Southern California, Marina del Rey, CA, United States., Gleave EJ; Imaging Genetics Center, Mark and Mary Stevens Neuroimaging and Informatics Institute, Keck School of Medicine, University of Southern California, Marina del Rey, CA, United States., Thomopoulos SI; Imaging Genetics Center, Mark and Mary Stevens Neuroimaging and Informatics Institute, Keck School of Medicine, University of Southern California, Marina del Rey, CA, United States., Feng Y; Imaging Genetics Center, Mark and Mary Stevens Neuroimaging and Informatics Institute, Keck School of Medicine, University of Southern California, Marina del Rey, CA, United States., Villalón-Reina JE; Imaging Genetics Center, Mark and Mary Stevens Neuroimaging and Informatics Institute, Keck School of Medicine, University of Southern California, Marina del Rey, CA, United States., Laltoo E; Imaging Genetics Center, Mark and Mary Stevens Neuroimaging and Informatics Institute, Keck School of Medicine, University of Southern California, Marina del Rey, CA, United States., Joshi H; Multimodal Brain Image Analysis Laboratory, National Institute of Mental Health and Neuro Sciences (NIMHANS), Bengaluru, Karnataka, India., Venkatasubramanian G; Translational Psychiatry Laboratory, National Institute of Mental Health and Neuro Sciences (NIMHANS), Bengaluru, Karnataka, India., John JP; Multimodal Brain Image Analysis Laboratory, National Institute of Mental Health and Neuro Sciences (NIMHANS), Bengaluru, Karnataka, India., Ver Steeg G; University of California, Riverside, CA, United States., Ambite JL; Information Sciences Institute, University of Southern California, Marina del Rey, CA, United States., Thompson PM; Imaging Genetics Center, Mark and Mary Stevens Neuroimaging and Informatics Institute, Keck School of Medicine, University of Southern California, Marina del Rey, CA, United States.
Jazyk:	angličtina
Zdroj:	BioRxiv : the preprint server for biology [bioRxiv] 2024 Sep 17. Date of Electronic Publication: 2024 Sep 17.
DOI:	10.1101/2024.09.17.613560
Abstrakt:	Deep learning models based on convolutional neural networks (CNNs) have been used to classify Alzheimer's disease or infer dementia severity from 3D T1-weighted brain MRI scans. Here, we examine the value of adding occlusion sensitivity analysis (OSA) and gradient-weighted class activation mapping (Grad-CAM) to these models to make the results more interpretable. Much research in this area focuses on specific datasets such as the Alzheimer's Disease Neuroimaging Initiative (ADNI) or National Alzheimer's Coordinating Center (NACC), which assess people of North American, predominantly European ancestry, so we examine how well models trained on these data generalize to a new population dataset from India (NIMHANS cohort). We also evaluate the benefit of using a combined dataset to train the CNN models. Our experiments show feature localization consistent with knowledge of AD from other methods. OSA and Grad-CAM resolve features at different scales to help interpret diagnostic inferences made by CNNs.
Databáze:	MEDLINE
Externí odkaz:	Zobrazit plný text záznamu