Share Email Print

Proceedings Paper

A CAD utilizing 3D massive-training ANNs for detection of flat lesions in CT colonography: preliminary results
Author(s): Kenji Suzuki; Ivan Sheu; Don C. Rockey M.D.; Abraham H. Dachman M.D.
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Our purpose was to develop a computer-aided diagnostic (CAD) scheme for detection of flat lesions (also known as superficial elevated or depressed lesions) in CT colonography (CTC), which utilized 3D massive-training artificial neural networks (MTANNs) for false-positive (FP) reduction. Our CAD scheme consisted of colon segmentation, polyp candidate detection, linear discriminant analysis, and MTANNs. To detect flat lesions, we developed a precise shape analysis in the polyp detection step to accommodate the analysis to include a flat shape. With our MTANN CAD scheme, 68% (19/28) of flat lesions, including six lesions "missed" by radiologists in a multicenter clinical trial, were detected correctly, with 10 (249/25) FPs per patient.

Paper Details

Date Published: 27 February 2009
PDF: 7 pages
Proc. SPIE 7260, Medical Imaging 2009: Computer-Aided Diagnosis, 72601A (27 February 2009); doi: 10.1117/12.811073
Show Author Affiliations
Kenji Suzuki, The Univ. of Chicago (United States)
Ivan Sheu, The Univ. of Chicago (United States)
Don C. Rockey M.D., The Univ. of Texas Southwestern Medical Ctr. (United States)
Abraham H. Dachman M.D., The Univ. of Chicago (United States)

Published in SPIE Proceedings Vol. 7260:
Medical Imaging 2009: Computer-Aided Diagnosis
Nico Karssemeijer; Maryellen L. Giger, Editor(s)

© SPIE. Terms of Use
Back to Top
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?