Related Experiment Video
Updated: Aug 10, 2026
08:05
Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
Published on: December 19, 2020
Automatic segmentation of lung fields on chest radiographic images
M J Carreira1, D Cabello, A Mosquera
1Department of Electronics and Computer Science, University of Santiago de Compostela, Santiago de Compostela, E-15706, Spain.
Summary
This study presents an automated system for segmenting lung fields in chest X-rays. The progressive segmentation approach achieved an 87% overlap with radiologist-drawn contours, improving diagnostic accuracy.
Area of Science:
- Medical Imaging
- Computer-Aided Diagnosis
- Radiology
Background:
- Accurate lung field segmentation is crucial for diagnosing respiratory diseases from chest radiographs.
- Manual segmentation is time-consuming and subject to inter-observer variability.
Purpose of the Study:
- To develop and evaluate an automated system for segmenting lung fields in posteroanterior (PA) chest radiographs.
- To assess the system's performance against expert annotations.
Main Methods:
- A three-level image analysis system employing progressive segmentation.
- Domain-independent operations, implicit knowledge, and explicit production rules were utilized.
- A hybrid control structure guided by region models was implemented.
Main Results:
- The automated system achieved a mean overlap of 87% with radiologist-drawn contours.
- The system demonstrated high accuracy in segmenting lung fields across 45 PA chest radiographs.
Conclusions:
- The developed system offers an effective and automated solution for lung field segmentation in chest radiography.
- This technology has the potential to enhance the efficiency and consistency of radiological image analysis.
