Morphological Reconstruction Based Segmentation of Lung Fields on Digital Radiographs

Abstract

Objective To segment lung fields on digital chest radiographs automatically. Methods A morphological reconstruction filter was first applied to the original image to eliminate the local grey level extremes. Then, the Otsu-threshold method was used to segment the whole image into several connected regions, contours of which were then extracted by using a connected components labelling technique. Finally, a morphological closing operator was employed to smooth any small gaps or burrs of the lung field contours. Results Lung fields were segmented for 40 digital chest radiographs, resulting in an accurate segmentation and extraction of their lung fields for most images. Conclusion Integrating a series of algorithms, including morphological reconstruction filtering, Otsu-threshold segmentation, connected components labelling, and morphological operations for smoothing the outlines can effectively segment the lung fields on digital radiographs.