Application of the level-set model with constraints in image segmentation

TL;DR

This paper introduces a constrained level-set model for semi-automatic image segmentation that incorporates prior information through constraints, improving segmentation accuracy on artificial and real medical images.

Contribution

It presents a novel constrained level-set approach with a specific numerical scheme, enhancing prior segmentation methods by integrating explicit constraints.

Findings

Effective segmentation on artificial images

Successful application to cardiac MRI data

Improved accuracy with prior constraints

Abstract

We propose and analyze a constrained level-set method for semi-automatic image segmentation. Our level-set model with constraints on the level-set function enables us to specify which parts of the image lie inside respectively outside the segmented objects. Such a-priori information can be expressed in terms of upper and lower constraints prescribed for the level-set function. Constraints have the same conceptual meaning as initial seeds of the popular graph-cuts based methods for image segmentation. A numerical approximation scheme is based on the complementary-finite volumes method combined with the Projected successive over-relaxation method adopted for solving constrained linear complementarity problems. The advantage of the constrained level-set method is demonstrated on several artificial images as well as on cardiac MRI data.