卷积神经网络
计算机科学
人工智能
互补性(分子生物学)
模式识别(心理学)
可视化
分割
水准点(测量)
灵敏度(控制系统)
视皮层
机器学习
神经科学
地图学
心理学
地理
生物
工程类
遗传学
电子工程
作者
Chengliang Yang,Anand Rangarajan,Sanjay Ranka
出处
期刊:Cornell University - arXiv
日期:2018-01-01
被引量:31
标识
DOI:10.48550/arxiv.1803.02544
摘要
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.
科研通智能强力驱动
Strongly Powered by AbleSci AI