Deep learning-based lung segmentation and automatic regional template in chest X-ray images for pediatric tuberculosis

TL;DR

This paper presents a deep learning approach for automatic lung and mediastinal region segmentation in pediatric chest X-rays to aid tuberculosis diagnosis, addressing specific challenges in pediatric imaging.

Contribution

It introduces a novel multi-view deep learning method that automatically regionalizes key areas in pediatric CXR images based on a proposed template, facilitating TB detection.

Findings

Accurate lung and mediastinal region extraction demonstrated

Potential for improved TB diagnosis in children

Code publicly available for reproducibility

Abstract

Tuberculosis (TB) is still considered a leading cause of death and a substantial threat to global child health. Both TB infection and disease are curable using antibiotics. However, most children who die of TB are never diagnosed or treated. In clinical practice, experienced physicians assess TB by examining chest X-rays (CXR). Pediatric CXR has specific challenges compared to adult CXR, which makes TB diagnosis in children more difficult. Computer-aided diagnosis systems supported by Artificial Intelligence have shown performance comparable to experienced radiologist TB readings, which could ease mass TB screening and reduce clinical burden. We propose a multi-view deep learning-based solution which, by following a proposed template, aims to automatically regionalize and extract lung and mediastinal regions of interest from pediatric CXR images where key TB findings may be present. Experimental results have shown accurate region extraction, which can be used for further analysis to confirm TB finding presence and severity assessment. Code publicly available at https://github.com/dani-capellan/pTB_LungRegionExtractor.