Vector-valued Mumford-Shah model with nonlinear statistical shape prior for image segmentation

In order to effectively segment complex medical images, the narrow band level set of shape prior was mapped into its kernel space by a nonlinear kernel function, then the Principal Component Analysis (PCA) was performed in the kernel space so as to obtain its base vectors, and nonlinear statistical shape prior can be integrated into a vector-valued Mumford-Shah model. The experimental results show that the proposed model is effective and practicable for the segmentation of the low-contrast optic disk obscured partly by blood vessels in colour optic nerve head images of early-stage glaucoma patients.