Shape prior constrained PSO model for bladder wall MRI segmentation

Bladder wall segmentation from Magnetic Resonance (MR) images plays an important role in diagnosis. Since the thickness of the bladder wall is a key indication of bladder cancer. There are several methods that have been used for bladder wall segmentation, such as level sets and Active Shape Model (ASM). However, the weak boundaries, the artifacts inside bladder lumen and the complex background outside the bladder wall make the bladder wall segmentation very challenging. To overcome these difficulties and obtain accurate bladder walls, in this paper, a shape prior constrained particle swarm optimization (SPC-PSO) model is proposed to segment the inner and outer boundaries of the bladder wall. The bladder walls are divided into two categories: strong boundaries and weak boundaries by the proposed model. For the strong boundaries, the proposed model can reserve it. For the weak boundaries, the model applies the shape prior to guide the process of segmentation. Compared with some state-of-the-art methods, better results were obtained on bladder MR images from 11 patients by our proposed method.