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

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.

Authors

Institutions

Publication Details

Published
2024-11-13
DOI
https://doi.org/10.1109/sipaim62974.2024.10783631
Citations
5
Primary Topic
Medical Imaging and Analysis
Type
article
Field-Weighted Citation Impact
0.92

Funders

Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

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

Chirag Jagad, Himanshu Joshi, Sophia I. Thomopoulos, José Luis Ambite et al.
5 citations
Medical Imaging and Analysis
0.92
article

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

Chirag Jagad, Himanshu Joshi, Sophia I. Thomopoulos, José Luis Ambite, Neha Ann Joshy, Ganesan Venkatasubramanian, Emily Laltoo, Yixue Feng, John P. John, Julio E. Villalón‐Reina, Tamoghna Chattopadhyay, Greg Ver Steeg, Paul M. Thompson, Emma J. Gleave
article en
5 citations

Abstract

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.

University of California, Riverside (US), University of Southern California (US), National Institute of Mental Health and Neurosciences (IN)
National Institutes of Health, National Institute on Aging, Fogarty International Center
Openalex Percentile: Top 27%
Medical Imaging and Analysis
0.92
DOISourceOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.