9P-D-3 濃度・形状特微量を用いたスリガラス状陰影の自動識別法(D会場 大学院生・学部学生 奨励賞セッション)

抄録

Medical images are used for diagnosis of the several diseases in the medical fields. The huge number of medical images makes burden to doctors on visual screening. It is because the higher quality of digital imaging equipment improves, the more computed tomography images per case should be performed. Accordingly, development of computer aided diagnosis (CAD) system has been proposed widely to support the diagnosis of the doctors. In this paper, we propose a CAD system for automatic detecting of the ground glass opacity (GGO) shadow areas based on statistical features which are obtained density and shape features from thoracic MDCT images. The GGO areas can classified from unknown MDCT images by use of artificial neural network (ANN). The propose technique applied on 35 MDCT image sets. Some experimental results are shown along with a discussion.