Segmenting the endocardial border of the left ventricle in cardiac magnetic resonance images

The proposed method is composed of two phases: Segmentation phase: uses a bottom-up multi-scale analysis, based mainly on taking the advantage of using the morphological scale-space by decomposing the image into a number of scales of different structure size. As a result of the decomposition, the gray level appearance structures adjacent to the endocardial border are located, and finally an estimated boundary is obtained regardless of those structures. Refinement phase: Asserts prior information about local structure around defined points along the shape boundary. Our approach is able to correctly locate and classify the inner structures in 91% of the tested 220 MR images from different cases (imaged on 1.5 T whole body scanner). The estimated boundary converges correctly to the main endocardial border. In conclusion, this new approach represents a step towards automatic left ventricle segmentation.