LGCVIVMLJul 30, 2019

Confounder-Aware Visualization of ConvNets

arXiv:1907.12727v215 citations
Originality Incremental advance
AI Analysis

This addresses the issue of biased model interpretation in neuroimaging studies for researchers and clinicians, but it is incremental as it builds on existing visualization methods by adding confounder removal.

The paper tackled the problem of confounded saliency maps in ConvNets for neuroimaging, which can misinterpret disease effects by highlighting regions predictive of confounding variables like age, and proposed a two-step approach to produce confounder-free visualizations, demonstrating its potential in unbiased model interpretation on synthetic and real datasets.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes