Deep neural network heatmaps capture Alzheimer’s disease patterns reported in a large meta-analysis of neuroimaging studies

•We assessed the ability of deep networks heatmaps to capture AD effects on the brain.•SVMs, CNNs and ResNets were trained to classify 502 ADNI T1 MRIs.•GGC, integrated gradient and LRP used to produce heatmaps for the best classifiers.•Heatmaps were compared with a meta-analysis of 77 VBM studies a...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:NeuroImage (Orlando, Fla.) Jg. 269; S. 119929
Hauptverfasser: Wang, Di, Honnorat, Nicolas, Fox, Peter T., Ritter, Kerstin, Eickhoff, Simon B., Seshadri, Sudha, Habes, Mohamad
Format: Journal Article
Sprache:Englisch
Veröffentlicht: United States Elsevier Inc 01.04.2023
Elsevier Limited
Elsevier
Schlagworte:
Alliances
Alzheimer Disease
Alzheimer's disease
Artificial intelligence
Brain - physiology
Brain mapping
Brain research
Classification
Deep learning
Dementia
Explainable AI
Humans
Image processing
Immunoglobulins
Magnetic resonance imaging
Magnetic Resonance Imaging - methods
Medical imaging
Meta-analysis
Methods
Morphometry
MRI
Neural networks
Neural Networks, Computer
Neurodegenerative diseases
Neuroimaging
Neuroimaging - methods
Propagation
Deep learning
Neuroimaging
Explainable AI
Alzheimer’s disease
MRI
ISSN:1053-8119, 1095-9572, 1095-9572
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:•We assessed the ability of deep networks heatmaps to capture AD effects on the brain.•SVMs, CNNs and ResNets were trained to classify 502 ADNI T1 MRIs.•GGC, integrated gradient and LRP used to produce heatmaps for the best classifiers.•Heatmaps were compared with a meta-analysis of 77 VBM studies and SVM activations.•Integrated gradient heatmaps produced the best overlap with the meta-analysis. Deep neural networks currently provide the most advanced and accurate machine learning models to distinguish between structural MRI scans of subjects with Alzheimer’s disease and healthy controls. Unfortunately, the subtle brain alterations captured by these models are difficult to interpret because of the complexity of these multi-layer and non-linear models. Several heatmap methods have been proposed to address this issue and analyze the imaging patterns extracted from the deep neural networks, but no quantitative comparison between these methods has been carried out so far. In this work, we explore these questions by deriving heatmaps from Convolutional Neural Networks (CNN) trained using T1 MRI scans of the ADNI data set and by comparing these heatmaps with brain maps corresponding to Support Vector Machine (SVM) activation patterns. Three prominent heatmap methods are studied: Layer-wise Relevance Propagation (LRP), Integrated Gradients (IG), and Guided Grad-CAM (GGC). Contrary to prior studies where the quality of heatmaps was visually or qualitatively assessed, we obtained precise quantitative measures by computing overlap with a ground-truth map from a large meta-analysis that combined 77 voxel-based morphometry (VBM) studies independently from ADNI. Our results indicate that all three heatmap methods were able to capture brain regions covering the meta-analysis map and achieved better results than SVM activation patterns. Among them, IG produced the heatmaps with the best overlap with the independent meta-analysis.
Bibliographie:ObjectType-Article-1
ObjectType-Evidence Based Healthcare-3
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ObjectType-Article-2
ObjectType-Feature-1
content type line 23
ISSN:1053-8119
1095-9572
1095-9572
DOI:10.1016/j.neuroimage.2023.119929