Automated lung segmentation and computer-aided diagnosis for thoracic CT scans

Abstract

Automated segmentation of the lungs in thoracic computed tomography (CT) scans represents an essential process in the development of computer-aided diagnostic (CAD) methods and computer-assisted quantification techniques. A core segmentation process may be developed for general application; however, modifications may be required for specific clinical tasks. We have developed such an automated lung segmentation method based on gray-level thresholding techniques and have applied this method (1) as a pre-processing step for automated lung nodule detection and (2) as the foundation for a computer-assisted technique to measure the extent of pleural mesothelioma. In the automated detection of lung nodules, we have developed a method that has achieved 71% nodule detection sensitivity with an average of 0.4 false-positive detections per section on a database of 38 CT scans. Our method for the computer-assisted quantification of mesothelioma achieved a correlation coefficient of 0.97 with the average manual measurements of four observers based on 134 measurement sites in 22 CT scans. Important differences exist in the specific approaches to automated lung segmentation required for these two clinical tasks.