Visual Explanations From Deep 3D Convolutional Neural Networks for Alzheimer's Disease Classification

Abstract

We develop three efficient approaches for generating visual explanations from 3D convolutional neural networks (3D-CNNs) for Alzheimer's disease classification. One approach conducts sensitivity analysis on hierarchical 3D image segmentation, and the other two visualize network activations on a spatial map. Visual checks and a quantitative localization benchmark indicate that all approaches identify important brain parts for Alzheimer's disease diagnosis. Comparative analysis show that the sensitivity analysis based approach has difficulty handling loosely distributed cerebral cortex, and approaches based on visualization of activations are constrained by the resolution of the convolutional layer. The complementarity of these methods improves the understanding of 3D-CNNs in Alzheimer's disease classification from different perspectives.

arXiv commentAccepted by 2018 American Medical Informatics Association Annual Symposium (AMIA2018)

References in corpus (4)

• Adam: A Method for Stochastic Optimization
• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Alzheimer's Disease Diagnostics by a Deeply Supervised Adaptable 3D Convolutional Network
• Global Model Interpretation via Recursive Partitioning

Cited by in corpus (9)

• Layer-Wise Relevance Propagation for Explaining Deep Neural Network Decisions in MRI-Based Alzheimer's Disease Classification
• An Explainable 3D Residual Self-Attention Deep Neural Network FOR Joint Atrophy Localization and Alzheimer's Disease Diagnosis using Structural MRI
• Visualizing Convolutional Networks for MRI-based Diagnosis of Alzheimer's Disease
• Global Model Interpretation via Recursive Partitioning
• Biomarker Investigation using Multiple Brain Measures from MRI through XAI in Alzheimer's Disease Classification
• Deep Learning Development Environment in Virtual Reality
• IMFNet: Interpretable Multimodal Fusion for Point Cloud Registration
• Deep Learning for Regularization Prediction in Diffeomorphic Image Registration
• Understanding Patch-Based Learning by Explaining Predictions