- Other Title
- 3ジゲン フクブ CTゾウ オ モチイタ クローンビョウ シンダン シエン ニ オケル カイヨウ ケンシュツ シュホウ ノ カイハツ
- Development of an ulcer detection method from 3D abdominal CT images for Crohn's disease diagnostic aid
Search this article
Cronh's disease is an inflammatory disease of the digestive tract. Symptoms of Crohn's disease includes ulcers and stenosis of the intestine. An optical endoscope is used for small intestine examinations. However, endoscope cannot pass through intestinal stenosis parts in some cases. Image-based diagnosis methods of Crohn's disease are researched as alternative choice of conventional methods. This paper proposes an automated detection method of convex and concave parts on surface of ulcers from fecal tagging CT images. Ulcers on the intestinal wall cause small convex and concave parts on them. The proposed method detects the convex and the concave parts by using local intensity structure analysis technique. To reduce false positives of the detection results, we introduce a false positive reduction process using a roughness value. The roughness value evaluates the amount of concentration of the detected regions. Sensitivity of the proposed method was 88.2% with 74.1 false positives per case from experimental results using eleven cases of CT images.
IEICE Technical Report;MI2011-37
- 電子情報通信学会技術研究報告. MI, 医用画像
電子情報通信学会技術研究報告. MI, 医用画像 111 (127), 25-30, 2011-07