Computer-aided detection of polyps in CT colonography: performance evaluation in comparison with human readers based on large multicenter clinical trial cases

Authors:
H. Yoshida;J. Näppi;Wenli Cai
Affiliations:
Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, MA;Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, MA;Department of Radiology, Massachusetts General Hospital and Harvard Medical School, Boston, MA
Venue:
ISBI'09 Proceedings of the Sixth IEEE international conference on Symposium on Biomedical Imaging: From Nano to Macro
Year:
2009

Citing 2
Cited 0

Solid shape

Solid shape
A Pipeline for Computer Aided Polyp Detection

IEEE Transactions on Visualization and Computer Graphics

Quantified Score

Hi-index	0.01

Visualization

Abstract

CT colonography (CTC), also known as virtual colonoscopy, is a promising alternative technique for providing mass screening for colorectal carcinoma. In this study, we developed a high-performance CAD scheme that automatically detects suspicious polyps in CTC data, and retrospectively compared its performance with that of prospective unaided human CTC reading in the detection of clinically significant adenomas/carcinomas by use of CTC database consisting of cases from two large multicenter clinical trials.