Multi-pathology Chest X-ray Classification with Rejection Mechanisms

Overconfidence in deep learning models poses a significant risk in high - stakes medical imaging tasks, particularly in multi - label classification of chest X - rays, where multiple co - occurring pathologies must be detected simultaneously. This study introduces an uncertainty - aware framework for chest X - ray diagnosis based on a DenseNet - 121 backbone, enhanced with two selective prediction mechanisms: entropy - based rejection and confidence interval - based rejection. Both methods enable the model to abstain from un certain predictions, improving reliability by deferring ambiguous cases to clinical experts. A quantile - based calibration procedure is employed to tune rejection thresholds using either global or class - specific strategies. Experiments conducted on three la rge public datasets (PadChest, NIH ChestX - ray14, and MIMIC - CXR) demonstrate that selective rejection improves the trade - off between diagnostic accuracy and coverage, with entropy - based rejection yielding the highest average A U C across all pathologies. Thes e results support the integration of selective prediction into AI - assisted diagnostic workflows, providing a practical step toward safer, uncertainty - aware deployment of deep learning in clinical settings. Automating medical diagnosis with deep learning has shown great potential, particularly in medical imaging domains such as chest X - ray analysis. Convolutional neural networks, including architectures like DenseNet - 121, have demonstrated strong performance in detecting a range of thoracic pathologies [1],[2] . However, successfully integrating such models into clinical workflows requires more than high classification accuracy . I t demands robust mechanisms for managing uncertainty and ensuring patient safety. 2 Figure 1: Overview of the proposed selective chest X - ray classification framework .