Causal Representation Learning with Observational Grouping for CXR Classification
This work addresses the need for more robust and generalisable diagnostic tools in medical imaging, though it appears incremental as it builds on existing causal representation learning methods.
The paper tackled the problem of learning identifiable causal representations for chest X-ray disease classification by grouping observations based on race, sex, and imaging views, resulting in improved generalisability and robustness across multiple classification tasks.
Identifiable causal representation learning seeks to uncover the true causal relationships underlying a data generation process. In medical imaging, this presents opportunities to improve the generalisability and robustness of task-specific latent features. This work introduces the concept of grouping observations to learn identifiable representations for disease classification in chest X-rays via an end-to-end framework. Our experiments demonstrate that these causal representations improve generalisability and robustness across multiple classification tasks when grouping is used to enforce invariance w.r.t race, sex, and imaging views.