A novel colon wall flattening model for computed tomographic colonography: method and validation

Abstract

Computed tomographic colonography (CTC) has been developed for screening of colon cancer. Flattening the three-dimensional (3D) colon wall into two-dimensional (2D) image is believed to (1) provide supplementary information to the endoscopic views and further (2) facilitate colon registration, taenia coli (TC) detection and haustral fold segmentation. Although the previously used conformal mapping-based flattening methods can preserve the angular geometry, they have the limitations in providing accurate information of the 3D inner colon wall due to the lack of undulating topography. In this paper, we present a novel colon-wall flattening method using a strategy of 2.5D approach. Coupling with the conformal flattening model, the presented new approach builds an elevation distance map to depict the neighbouring characteristics of the inner colon wall. We validated the new method via two CTC applications: TC detection and haustral fold segmentation. Experimental results demonstrated the effectiveness of our strategy for CTC studies.