Towards Robust Lung Segmentation in Chest Radiographs with Deep Learning

TL;DR

This paper introduces a robust deep learning model for lung segmentation in chest X-ray images, effectively handling challenges like rib edges and shape variability, achieving high accuracy on public datasets.

Contribution

The paper presents a novel deep learning model that focuses on ignoring irrelevant regions to improve lung segmentation robustness in chest radiographs.

Findings

Achieved a DICE score of 98.6% on public datasets.

Demonstrated robustness across different datasets and patient variations.

Outperformed existing methods in lung segmentation accuracy.

Abstract

Automated segmentation of Lungs plays a crucial role in the computer-aided diagnosis of chest X-Ray (CXR) images. Developing an efficient Lung segmentation model is challenging because of difficulties such as the presence of several edges at the rib cage and clavicle, inconsistent lung shape among different individuals, and the appearance of the lung apex. In this paper, we propose a robust model for Lung segmentation in Chest Radiographs. Our model learns to ignore the irrelevant regions in an input Chest Radiograph while highlighting regions useful for lung segmentation. The proposed model is evaluated on two public chest X-Ray datasets (Montgomery County, MD, USA, and Shenzhen No. 3 People's Hospital in China). The experimental result with a DICE score of 98.6% demonstrates the robustness of our proposed lung segmentation approach.