# Confounder-Aware Visualization of ConvNets

arXiv: https://arxiv.org/abs/1907.12727 · HTML: https://mlsanity.com/paper/1907.12727/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 30 Jul 2019.

## Built on by (most cited first, 7 of 7)

- [TorchXRayVision: A library of chest X-ray datasets and models](https://mlsanity.com/paper/2111.00595/) (2021)
- [Representation Disentanglement for Multi-modal brain MR Analysis](https://mlsanity.com/paper/2102.11456/) (2021)
- [Metadata Normalization](https://mlsanity.com/paper/2104.09052/) (2021)
- [Metadata-Conditioned Generative Models to Synthesize Anatomically-Plausible 3D Brain MRIs](https://mlsanity.com/paper/2310.04630/) (2023)
- [Multiple Instance Neuroimage Transformer](https://mlsanity.com/paper/2208.09567/) (2022)
- [Enforcing Conditional Independence for Fair Representation Learning and Causal Image Generation](https://mlsanity.com/paper/2404.13798/) (2024)
- [Applications of interpretable deep learning in neuroimaging: a comprehensive review](https://mlsanity.com/paper/2406.17792/) (2024)

## Abstract (arXiv)

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.