Segmentation of thoracic CT image based on FCM clustering

To develop a computer aided detection system that improves diagnostic accuracy of lung cancer on thoracic CT. A novel method for CT image segmentation of lung is proposed, with which, several regions that are suspicious of cancer can be segmented rapidly and effectively. Algorithm of extracting pulmonary parenchyma was introduced firstly to extract pulmonary parenchyma. Secondly, FCM was employed twice, we named it with TFCM. FCM was first employed to identify areas of lung cancer. Finally, FCM was employed to segment the cancers. Experimental results on real medical images demonstrate the efficiency and effectiveness of the proposed algorithm.