AUTOMATIC DETECTION OF GGO CANDIDATE REGIONS BY USING DENSITY AND SHAPE FEATURES

Various imaging equipments have been introduced into medicalelds. Es- pecially, high resolution helical computed tomography (HRCT) is one of the most useful diagnosis systems because it provides a high resolution image to medical doctors as a clear image. Radiologist can easily detect abnormalities by use of the clear images. Detection of abnormal areas such as lung nodule, ground glass opacity on multi detector computed tomography images is a difficult task for radiologists. It is because subtle lesions such as small lung nodules tend to be low in contras, and a large number of computed tomogra- phy images require a long visual screening times. To detect the abnormalities by use of computer aided diagnosis (CAD) system, some technical methods for detecting the ab- normalities have been proposed in medicaleld. Despite of these efforts, their approach did not succeed because of difficulty of image processing in detecting the ground glass opacity (GGO) areas exactly. Thus they did not reach to the stage of automatic detec- tion employing unknown thoracic MDCT data sets. In this paper, we develop a CAD system for automatic detecting of GGO areas from thoracic MDCT images by use ofve statistical features which are obtained four density features and one shape feature. The proposed technique applied on 31 MDCT image sets. 79.4 (%) of recognition rates and 1.07 of false positive rates was achieved. Some experimental results are shown along with a discussion. Keywords: Ground glass opacity, Computer aided diagnosis, MDCT