A coupled level-set framework for bladder wall segmentation with application to MRI-based virtual cystoscopy

In this paper, we propose a coupled level-set framework for segmentation of bladder wall using T1-weighted magnetic resonance (MR) images. The segmentation results will be used for non-invasive MR-based virtual cystoscopy (VCys). The framework uses two level-set functions to segment inner and outer borders of the bladder wall respectively. Based on Chan-Vese (C-V) model, a local adaptive fitting (LAF) image energy is introduced to capture local intensity contrast. Comparing with previous work, our method has the following advantages. First of all, unlike most other work which only segments the boundary of the bladder but not inner border and outer border respectively, our method extracts the inner border as well as the outer border of bladder wall automatically. Secondly, we focus on T1-weighted MR images which decrease the image intensity of the urine and therefore minimize the partial volume effect (PVE) on the bladder wall for detection of abnormalities on the mucosa layer in contrast to others' work on CT images and T2-weighted MR images which enhance the intensity of the urine and encounter the PVE. In addition, T1-weighted MR images provide the best tissue contrast for detection of the outer border of the bladder wall. Since MR images tend to be inhomogeneous and have ghost artifacts due to motion and other causes as compared to computer tomography (CT)-based VCys, our framework is easy to control the geometric property of level-set functions to mitigate the influences of inhomogeneity and ghosts. Finally, a variety of geometric parameters, such as the thickness of bladder wall, etc, can be measured easily under the level-set framework. These parameters are clinically important for VCys. The segmentation results were evaluated by experienced radiologists, whose feedback strongly demonstrated the usefulness of such coupled level-set framework for VCys.