Benchmarking Dependence Measures to Prevent Shortcut Learning in Medical Imaging
This addresses the challenge of improving model generalizability in medical imaging by reducing shortcut learning, though it is incremental as it benchmarks existing methods rather than introducing new ones.
The paper tackled the problem of deep learning models learning spurious correlations in medical imaging due to confounding factors, by benchmarking dependence measures like mutual information and distance correlation to prevent shortcut learning, with results providing insights for mitigating these issues in datasets such as Morpho-MNIST and CheXpert.
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.