An Efficient and Robust Method for Chest X-ray Rib Suppression That Improves Pulmonary Abnormality Diagnosis

• Published in: Diagnostics (Basel) 2023-05, Vol.13 (9), p.1652
• Main Authors: Xu, Di, Xu, Qifan, Nhieu, Kevin, Ruan, Dan, Sheng, Ke
• Format: Article
• Language: English
• Subjects: chest X-rays; computer aided diagnosis; Datasets; deep learning; Energy; Machine learning; Methods; rib suppression; Signal processing
• ISSN: 2075-4418; 2075-4418
• DOI: 10.3390/diagnostics13091652

Suppression of thoracic bone shadows on chest X-rays (CXRs) can improve the diagnosis of pulmonary disease. Previous approaches can be categorized as either unsupervised physical models or supervised deep learning models. Physical models can remove the entire ribcage and preserve the morphological lung details but are impractical due to the extremely long processing time. Machine learning (ML) methods are computationally efficient but are limited by the available ground truth (GT) for effective and robust training, resulting in suboptimal results. To improve bone shadow suppression, we propose a generalizable yet efficient workflow for CXR rib suppression by combining physical and ML methods. Our pipeline consists of two stages: (1) pair generation with GT bone shadows eliminated by a physical model in spatially transformed gradient fields; and (2) a fully supervised image denoising network trained on stage-one datasets for fast rib removal from incoming CXRs. For stage two, we designed a densely connected network called SADXNet, combined with a peak signal-to-noise ratio and a multi-scale structure similarity index measure as the loss function to suppress the bony structures. SADXNet organizes the spatial filters in a U shape and preserves the feature map dimension throughout the network flow. Visually, SADXNet can suppress the rib edges near the lung wall/vertebra without compromising the vessel/abnormality conspicuity. Quantitively, it achieves an RMSE of ~0 compared with the physical model generated GTs, during testing with one prediction in