Application of the level-set model with constraints in image segmentation
This work provides an incremental improvement to level-set segmentation by incorporating user-defined constraints, benefiting medical image analysis tasks.
The paper introduces a constrained level-set method for semi-automatic image segmentation that allows users to specify constraints on the level-set function, similar to seeds in graph-cuts methods. The method is demonstrated on artificial and cardiac MRI data, showing improved segmentation accuracy.
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.