Instrumental Variable Learning for Chest X-ray Classification
This work addresses the problem of improving diagnostic accuracy in medical imaging for healthcare applications, but it appears incremental as it builds on existing deep learning methods with a causal approach.
The paper tackled the challenge of accurate automatic diagnosis from chest X-rays by addressing confounding factors like image resolution and noise, proposing an interpretable instrumental variable learning framework that achieved competitive results on datasets such as MIMIC-CXR, NIH ChestX-ray 14, and CheXpert.
The chest X-ray (CXR) is commonly employed to diagnose thoracic illnesses, but the challenge of achieving accurate automatic diagnosis through this method persists due to the complex relationship between pathology. In recent years, various deep learning-based approaches have been suggested to tackle this problem but confounding factors such as image resolution or noise problems often damage model performance. In this paper, we focus on the chest X-ray classification task and proposed an interpretable instrumental variable (IV) learning framework, to eliminate the spurious association and obtain accurate causal representation. Specifically, we first construct a structural causal model (SCM) for our task and learn the confounders and the preliminary representations of IV, we then leverage electronic health record (EHR) as auxiliary information and we fuse the above feature with our transformer-based semantic fusion module, so the IV has the medical semantic. Meanwhile, the reliability of IV is further guaranteed via the constraints of mutual information between related causal variables. Finally, our approach's performance is demonstrated using the MIMIC-CXR, NIH ChestX-ray 14, and CheXpert datasets, and we achieve competitive results.