Topology-Preserving 3D Image Segmentation Based On Hyperelastic Regularization
This work addresses segmentation challenges for degraded 3D medical or scientific images, offering an incremental extension from 2D to 3D with topology preservation.
The authors tackled the problem of 3D image segmentation under degradation by proposing a novel model that preserves topology using hyperelastic regularization, establishing solution existence and demonstrating effectiveness through numerical experiments on synthetic and real images.
Image segmentation is to extract meaningful objects from a given image. For degraded images due to occlusions, obscurities or noises, the accuracy of the segmentation result can be severely affected. To alleviate this problem, prior information about the target object is usually introduced. In [10], a topology-preserving registration-based segmentation model was proposed, which is restricted to segment 2D images only. In this paper, we propose a novel 3D topology-preserving registration-based segmentation model with the hyperelastic regularization, which can handle both 2D and 3D images. The existence of the solution of the proposed model is established. We also propose a converging iterative scheme to solve the proposed model. Numerical experiments have been carried out on the synthetic and real images, which demonstrate the effectiveness of our proposed model.