An Efficient and Robust Method for Chest X-Ray Rib Suppression that Improves Pulmonary Abnormality Diagnosis

TL;DR

This paper introduces a fast, robust deep learning method for suppressing rib shadows in chest X-rays, improving pulmonary disease diagnosis by enhancing image clarity and supporting downstream diagnostic tasks.

Contribution

It presents a novel two-stage workflow combining physical model-generated training data with a densely connected neural network, SADXNet, for efficient rib suppression in chest X-rays.

Findings

Achieves near-zero RMSE in rib suppression during testing.

Reduces false positives in lung nodule detection and disease localization.

Speeds up rib removal to under 1 second per image.

Abstract

Suppression of thoracic bone shadows on chest X-rays (CXRs) has been indicated to improve the diagnosis of pulmonary disease. Previous approaches can be categorized as unsupervised physical and supervised deep learning models. Nevertheless, with physical models able to preserve morphological details but at the cost of extremely long processing time, existing DL methods face challenges of gathering sufficient/qualitative ground truth (GT) for robust training, thus leading to failure in maintaining clinically acceptable false positive rates. We hereby propose a generalizable yet efficient workflow of two stages: (1) training pairs generation with GT bone shadows eliminated in by a physical model in spatially transformed gradient fields. (2) fully supervised image denoising network training on stage-one datasets for fast rib removal on incoming CXRs. For step two, we designed a densely connected network called SADXNet, combined with peak signal to noise ratio and multi-scale structure similarity index measure objective minimization to suppress bony structures. The SADXNet organizes spatial filters in U shape (e.g., X=7; filters = 16, 64, 256, 512, 256, 64, 16) and preserves the feature map dimension throughout the network flow. Visually, SADXNet can suppress the rib edge and that near the lung wall/vertebra without jeopardizing the vessel/abnormality conspicuity. Quantitively, it achieves RMSE of ~0 during testing with one prediction taking <1s. Downstream tasks including lung nodule detection as well as common lung disease classification and localization are used to evaluate our proposed rib suppression mechanism. We observed 3.23% and 6.62% area under the curve (AUC) increase as well as 203 and 385 absolute false positive decrease for lung nodule detection and common lung disease localization, separately.