Image Segmentation With Adaptive Edge-Region Collaborated Level-Set Method

Hybrid level-set method merging edge-region terms has been widely investigated for image segmentation. Nevertheless, the existing models usually meet the issue that each coefficient of edge and region information is tough to choose. It is often determined empirically lacking reliable theory foundation. To alleviate this issue, in this letter, an adaptive edge-region collaborated level-set method is presented, where the internal and external parameters can be selected automatically. For internal parameters, we adopt the local intensity information entropy to overcome the difference in gray-level distribution between target and background. For external parameters, the iterative process of energy function is optimized in terms of the global collaboration of edge-region information. Five representative and recent models are selected as benchmarks to indicate the generalization of our method, which validates that the adaptive parameters can improve the Dice similarity coefficient (DSC) by 0.7%–1.3% with only a small increase in computation time. As a limitation, the proposed method is restricted to applications for single-phase level-set models.