Topology-Preserving 3D Image Segmentation Based On Hyperelastic Regularization

TL;DR

This paper introduces a novel 3D topology-preserving image segmentation model using hyperelastic regularization, capable of handling both 2D and 3D images, with proven solution existence and effective numerical results.

Contribution

It extends topology-preserving segmentation to 3D images with hyperelastic regularization and provides a convergent iterative solution scheme.

Findings

Effective segmentation on synthetic images

Successful application to real images

Model guarantees solution existence

Abstract

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.