A novel segmentation approach for improving diagnostic accuracy of CAD systems for detecting lung cancer from chest computed tomography images

Abstract

Segmentation of lung tissue is an important and challenging task in any computer aided diagnosis system. The accuracy of the segmentation subsystem determines the performance of the other subsystems in any computer aided diagnosis system based on image analysis. We propose a novel technique for segmentation of lung tissue from computed tomography of the chest. Manual segmentation of lung parenchyma becomes difficult with an enormous volume of images. The goal of this work is to present an automated approach to segmentation of lung parenchyma from the rest of the chest CT image. The approach involves the conventional optimal thresholding technique and operations based on convex edge and centroid properties of the lung region. The segmentation technique proposed in this article can be used to preprocess lung images given to a computer aided diagnosis system for diagnosis of lung disorders. This improves the diagnostic performance of the system. This has been tested by using it in a computer aided diagnosis system that was used for detection of lung cancer from chest computed tomography images. The results obtained show that the lungs can be correctly segmented even in the presence of peripheral pathology bearing regions; pathology bearing regions that could not be detected using a CAD system that applies optimal thresholding could be detected using a CAD system using out proposed approach for segmentation of lungs.