Title
Confounder-Aware Visualization of ConvNets.
Abstract
With recent advances in deep learning, neuroimaging studies increasingly rely on convolutional networks (ConvNets) to predict diagnosis based on MR images. To gain a better understanding of how a disease impacts the brain, the studies visualize the salience maps of the ConvNet highlighting voxels within the brain majorly contributing to the prediction. However, these salience maps are generally confounded, i.e., some salient regions are more predictive of confounding variables (such as age) than the diagnosis. To avoid such misinterpretation, we propose in this paper an approach that aims to visualize confounder-free saliency maps that only highlight voxels predictive of the diagnosis. The approach incorporates univariate statistical tests to identify confounding effects within the intermediate features learned by ConvNet. The influence from the subset of confounded features is then removed by a novel partial back-propagation procedure. We use this two-step approach to visualize confounder-free saliency maps extracted from synthetic and two real datasets. These experiments reveal the potential of our visualization in producing unbiased model-interpretation.
Year
DOI
Venue
2019
10.1007/978-3-030-32692-0_38
Lecture Notes in Computer Science
Field
DocType
Volume
Voxel,Pattern recognition,Visualization,Computer science,Salience (neuroscience),Artificial intelligence,Neuroimaging,Deep learning,Univariate,Salience (language),Statistical hypothesis testing
Conference
11861
ISSN
Citations 
PageRank 
0302-9743
0
0.34
References 
Authors
0
5
Name
Order
Citations
PageRank
Qingyu Zhao122.06
Ehsan Adeli Mosabbeb226139.27
Adolf Pfefferbaum317420.61
Edith V. Sullivan411.36
Kilian Pohl557746.78