Obscuration to Clarity: Bone Suppression for Enhanced Localization in Pneumothorax Segmentation of Chest Radiographs

Abstract

Chest radiography (CXR) is a primary modality for assessing cardiopulmonary conditions, but its effectiveness is limited by anatomical obstructions (e.g., ribs, clavicles) that hinder accurate pneumothorax segmentation, boundary delineation, and severity estimation. While deep learning-based bone suppression improves soft-tissue visibility, its utility for precise pixel-wise localization remains underexplored. This study investigates the downstream application of bone suppression for pneumothorax segmentation, integrating it as a preprocessing step to mitigate bony obscuration. We evaluate its impact across CNN and Vision Transformer models on two public datasets, where models trained on bone-suppressed CXRs significantly outperform (p < 0.05) non-suppressed counterparts, achieving up to 17% improvement in Mean Average Surface Distance (MASD), 4.9% in Dice Similarity Coefficient (DSC), and 5.9% in Normalized Surface Dice (NSD), alongside a 9.5% gain in Matthews Correlation Coefficient (MCC). These results demonstrate bone suppression as an architecture-independent enhancement for pneumothorax localization, improving the reliability of automated CXR interpretation.