TY - JOUR
T1 - A statistical 3-D pattern processing method for computer-aided detection of polyps in CT colonography
AU - Göktürk, Salih Burak
AU - Tomasi, Carlo
AU - Acar, Burak
AU - Beaulieu, Christopher F.
AU - Paik, David S.
AU - Jeffrey, R. Brooke
AU - Yee, Judy
AU - Napel, Sandy
N1 - Funding Information:
Manuscript received June 8, 2001; revised October 31, 2001. This work was supported in part by National Institutes of Health (NIH) under Grant 1R01 CA72023, in part by the Lucas Foundation, in part by the Packard Foundation, and in part by the Phil N. Allen Trust. Asterisk indicates corresponding author. *S. B. Göktürk is with the Department of Electrical Engineering, Stanford University, Robotics Laboratory, Gates Building, Stanford, CA 94305-9010 USA (e-mail: gokturkb@stanford.edu). C. Tomasi is with the Department of Computer Science, Stanford University, Stanford, CA 94305-9010 USA. B. Acar, C. F. Beaulieu, D. S. Paik, R. B. Jeffrey, Jr., and S. Napel, are with the Department of Radiology, Stanford University, Stanford, CA 94305 USA. J. Yee is with the San Francisco VA Medical Center, the University of California, San Francisco, CA 94143 USA. Publisher Item Identifier S 0278-0062(01)11212-7.
PY - 2001/12
Y1 - 2001/12
N2 - Adenomatous polyps in the colon are believed to be the precursor to colorectal carcinoma, the second leading cause of cancer deaths in United States. In this paper, we propose a new method for computer-aided detection of polyps in computed tomography (CT) colonography (virtual colonoscopy), a technique in which polyps are imaged along the wall of the air-inflated, cleansed colon with X-ray CT. Initial work with computer aided detection has shown high sensitivity, but at a cost of too many false positives. We present a statistical approach that uses support vector machines to distinguish the differentiating characteristics of polyps and healthy tissue, and uses this information for the classification of the new cases. One of the main contributions of the paper is the new three-dimensional pattern processing approach, called random orthogonal shape sections method, which combines the information from many random images to generate reliable signatures of shape. The input to the proposed system is a collection of volume data from candidate polyps obtained by a high-sensitivity, low-specificity system that we developed previously. The results of our tenfold cross-validation experiments show that, on the average, the system increases the specificity from 0.19 (0.35) to 0.69 (0.74) at a sensitivity level of 1.0 (0.95).
AB - Adenomatous polyps in the colon are believed to be the precursor to colorectal carcinoma, the second leading cause of cancer deaths in United States. In this paper, we propose a new method for computer-aided detection of polyps in computed tomography (CT) colonography (virtual colonoscopy), a technique in which polyps are imaged along the wall of the air-inflated, cleansed colon with X-ray CT. Initial work with computer aided detection has shown high sensitivity, but at a cost of too many false positives. We present a statistical approach that uses support vector machines to distinguish the differentiating characteristics of polyps and healthy tissue, and uses this information for the classification of the new cases. One of the main contributions of the paper is the new three-dimensional pattern processing approach, called random orthogonal shape sections method, which combines the information from many random images to generate reliable signatures of shape. The input to the proposed system is a collection of volume data from candidate polyps obtained by a high-sensitivity, low-specificity system that we developed previously. The results of our tenfold cross-validation experiments show that, on the average, the system increases the specificity from 0.19 (0.35) to 0.69 (0.74) at a sensitivity level of 1.0 (0.95).
KW - CT colonography
KW - Computer aided diagnosis
KW - Pattern recognition
KW - Random orthogonal shape section (ROSS) method
KW - Support vector machines classification
UR - http://www.scopus.com/inward/record.url?scp=0035544611&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0035544611&partnerID=8YFLogxK
U2 - 10.1109/42.974920
DO - 10.1109/42.974920
M3 - Article
C2 - 11811825
AN - SCOPUS:0035544611
SN - 0278-0062
VL - 20
SP - 1251
EP - 1260
JO - IEEE Transactions on Medical Imaging
JF - IEEE Transactions on Medical Imaging
IS - 12
ER -