Author:

Keywords:

PSI_MIC, Science & Technology, Technology, Life Sciences & Biomedicine, Computer Science, Interdisciplinary Applications, Computer Science, Theory & Methods, Medicine, Research & Experimental, Radiology, Nuclear Medicine & Medical Imaging, Computer Science, Research & Experimental Medicine

Abstract:

The paper presents a system for Computer Aided Detection in Virtual Colonography based on geometric modeling. We label locations in the CT volume data, which have a high probability of being colonic polyps, and present them in a user-friendly way. We introduce a method for fast colonic wall elimination and then model polyps based on Slope Density Functions, to be able to reduce the number of false positive cases. The method was tested on a study group of 50 data sets. Using normal colonoscopy as standard of reference, true positive and false positive findings were determined. The detection rate for polyps larger than 6mm was above 85%. Initial results show that Computer Aided Diagnosis is feasible and that our method holds potential for screening purposes.