Automatic detection of ground glass opacity from the thoracic MDCT images by using density features

Abstract

Automatic detection of abnormal shadow area on a multi detector CT image is important task under developing a computer aided diagnosis system. Ground glass opacity is one of the important features in lung cancer diagnosis of computer aided diagnosis. It may be seen as diffuse or more often as patchy in distribution taking sometimes a geographic or mosaic distribution. A large number of diseases can be associated with GGO on CT image. We propose a technique for automatic detection of ground glass opacity from the segmented lung regions by computer based on a set of the thoracic CT images. In this paper, we segment the lung region for extraction of the region of interest employing binarization and labeling process from the inputted each slices images. The region having the largest area is regarded as the tentative lung regions. Furthermore, the ground glass opacity is classified by correlation distribution on the successive slice from the extracted lung region with respect to the thoracic CT images. Experiment is performed employing 32 thoracic CT image sets and 71.7% of recognition rates were achieved. Obtained results are shown along with a discussion.