# Benchmarking Dependence Measures to Prevent Shortcut Learning in Medical Imaging

arXiv: https://arxiv.org/abs/2407.18792 · HTML: https://mlsanity.com/paper/2407.18792/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 20 references that are in the map.
- First posted on arXiv 26 Jul 2024.

## Builds on (most cited first, 12 of 12)

- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison](https://mlsanity.com/paper/1901.07031/) (2019)
- [MINE: Mutual Information Neural Estimation](https://mlsanity.com/paper/1801.04062/) (2018)
- [Causality matters in medical imaging](https://mlsanity.com/paper/1912.08142/) (2019)
- [Unsupervised domain adaptation in brain lesion segmentation with adversarial networks](https://mlsanity.com/paper/1612.08894/) (2016)
- [Morpho-MNIST: Quantitative Assessment and Diagnostics for Representation Learning](https://mlsanity.com/paper/1809.10780/) (2018)
- [On the Versatile Uses of Partial Distance Correlation in Deep Learning](https://mlsanity.com/paper/2207.09684/) (2022)
- [MI^2GAN: Generative Adversarial Network for Medical Image Domain Adaptation using Mutual Information Constraint](https://mlsanity.com/paper/2007.11180/) (2020)
- [Right for the Wrong Reason: Can Interpretable ML Techniques Detect Spurious Correlations?](https://mlsanity.com/paper/2307.12344/) (2023)
- [Measuring the Biases and Effectiveness of Content-Style Disentanglement](https://mlsanity.com/paper/2008.12378/) (2020)
- [Disentangling representations of retinal images with generative models](https://mlsanity.com/paper/2402.19186/) (2024)

## Built on by (most cited first, 2 of 2)

- [MIMM-X: Disentangling Spurious Correlations for Medical Image Analysis](https://mlsanity.com/paper/2511.22990/) (2025)
- [Mitigating Shortcut Learning via Feature Disentanglement in Medical Imaging: A Benchmark Study](https://mlsanity.com/paper/2602.18502/) (2026)

## Abstract (arXiv)

Medical imaging cohorts are often confounded by factors such as acquisition devices, hospital sites, patient backgrounds, and many more. As a result, deep learning models tend to learn spurious correlations instead of causally related features, limiting their generalizability to new and unseen data. This problem can be addressed by minimizing dependence measures between intermediate representations of task-related and non-task-related variables. These measures include mutual information, distance correlation, and the performance of adversarial classifiers. Here, we benchmark such dependence measures for the task of preventing shortcut learning. We study a simplified setting using Morpho-MNIST and a medical imaging task with CheXpert chest radiographs. Our results provide insights into how to mitigate confounding factors in medical imaging.