Segmentation of lung area and extraction of abnormal area on CT images of the thorax

摘要

In the recent years, various imaging techniques have been introduced into medical fields such as ultrasound images, magnetic resonance images, CT images, etc. In this paper, we propose a new technique for segmentation of lung area and extraction of its abnormal area on the CT image set of the thorax. In the first stage, we extract the ROI based on image preprocessing techniques. In the final stage, the abnormal area is extracted by comparing the density profile. In the experiment, nine lung CT image sets of the thorax are employed in the proposed technique and some of results are shown.