Geodesic Active Contours with Adaptive Neighboring Influence

Automatic Thalamus Segmentation from Magnetic Resonance Images Using Multiple Atlases Level Set Framework (MALSF)

In this paper, we present an original multiple atlases level set framework (MALSF) for automatic, accurate and robust thalamus segmentation in magnetic resonance images (MRI). The contributions of the MALSF method are twofold. First, the main technical contribution is a novel label fusion strategy in the level set framework. Label fusion is achieved by seeking an optimal level set function that minimizes energy functional with three terms: label fusion term, image based term, and regularization term. This strategy integrates shape prior, image information and the regularity of the thalamus. Second, we use propagated labels from multiple registration methods with different parameters to take full advantage of the complementary information of different registration methods. Since different registration methods and different atlases can yield complementary information, multiple registration and multiple atlases can be incorporated into the level set framework to improve the segmentation performance. Experiments have shown that the MALSF method can improve the segmentation accuracy for the thalamus. Compared to ground truth segmentation, the mean Dice metrics of our method are 0.9239 and 0.9200 for left and right thalamus.

Segmentation Through Point-based Multiscale Deformable Model

We propose a local weak form formulation for the geometric deformable model (GDM) which is capable of achieving robust segmentation results for noisy and broken edges. The local weak form partial differential equation (PDE) is solved on the analysis/evolution domain which is adaptively sampled by unstructured point cloud for improved accuracy and/or reduced computational cost. The fundamental power of this strategy rests with the explicit integration of neighboring information when constructing inter-point constraint and image-derived evolution force for each front point within a local influence domain adaptively determined by geometry and image information. As a result, this local weak form GDM naturally unifies the essences of the geometric and parametric snakes through automatic local scale selection at each contour point, and exhibits their respective fundamental strengths of allowing stable boundary detection when the edge information is weak and possibly discontinuous while maintaining the abilities to handle topological changes during front evolution. In particular, this paper presents an implementation of the method through local integration of the level set function and the evolution forces. Experimental results on synthetic and real images demonstrate its superior performance.