Polyps Flagging in Virtual Colonoscopy
Computer tomographic colonography, combined with computer-aided detection, is a promising emerging technique for colonic polyp analysis. We present a complete pipeline for polyp detection, starting with a simple colon segmentation technique that enhances polyps, followed by an adaptive-scale candidate polyp delineation and classification based on new texture and geometric features that consider both the information in the candidate polyp and its immediate surrounding area. The proposed system is tested with ground truth data, including challenging flat and small polyps. For polyps larger than 6mm in size we achieve 100% sensitivity with just 0.9 false positives per case, and for polyps larger than 3mm in size we achieve 93% sensitivity with 2.8 false positives per case.
KeywordsTexture Feature Shape Index Virtual Colonoscopy Optical Colonoscopy Polyp Detection
- 2.Fiori, M., Musé, P., Sapiro, G.: A complete system for candidate polyps detection in virtual colonoscopy (2012), http://arxiv.org/abs/1209.6525
- 4.Koenderink, J.J.: Solid Shape. MIT Press, Cambridge (1990)Google Scholar
- 5.Fiori, M., Musé, P., Aguirre, S., Sapiro, G.: Automatic colon polyp flagging via geometric and texture features. In: IEEE EMBS, pp. 3170–3173 (2010)Google Scholar
- 8.Pickhardt, P., Choi, J., Hwang, I., Butler, J., Puckett, M., Hildebrandt, H., Wong, R., Nugent, P., Mysliwiec, P., Schindler, W.: Computed tomographic virtual colonoscopy to screen for colorectal neoplasia in asymptomatic adults. New England Journal of Medicine 349(23), 2191–2200 (2003)CrossRefGoogle Scholar