Automated Knowledge Guided Segmentation of Colonic Walls for Computerized Detection of Polyps in CT Colonography英文文献.pdfVIP

Journal of Computer Assisted Tomography 26(4):493–504 © 2002 Lippincott Williams Wilkins, Inc., Philadelphia Automated Knowledge-Guided Segmentation of Colonic Walls for Computerized Detection of Polyps in CT Colonography Janne Näppi, Abraham H. Dachman, Peter MacEneaney, and Hiroyuki Yoshida Purpose: We have developed a novel automated technique for segmenting colonic walls for the application of computer-aided polyp detection in CT colonography. In particular, the technique was designed to minimize the presence of extracolonic com- ponents, such as small bowel, in the segmented colon. Methods: The segmentation technique combines an improved version of our pre- viously reported anatomy-oriented colon segmentation technique with a colon-based analysis step that performs self-adjusting volume-growing within the colonic lumen. Extracolonic components are eliminated by intersecting of the resulting two segmen- tations, so that the colonic walls remain in the intersection. The technique was evalu- ated on 88 CT colonography datasets. The colon segmentations were evaluated sub- jectively by four radiologists, as well as objectively by performance of a n automated polyp detection on the segmentation. For comparison, the tests were also performed for the anatomy-oriented colon segmentation technique. Results: On average, the technique covered 98% of the visible colonic walls. Ap- proximately 50% of the extracolonic components remaining in the anatomy-oriented segmentation were removed, but 10–15% of the s