Multi-Resolution Texture-Based 3D Level Set Segmentation

This paper presents a novel three-dimensional level set method for the segmentation of textured volumes. The algorithm combines sparse and multi-resolution schemes to speed up computations and utilise the multi-scale nature of extracted texture features. The method's performance is also enhanced by graphics processing unit (GPU) acceleration. The segmentation process starts with an initial surface at the coarsest resolution of the input volume and moves to progressively higher scales. The surface evolution is driven by a generalised data term that can consider multiple feature types and is not tied to specific descriptors. The proposed implementation of this approach uses features based on grey level co-occurrence matrices and discrete wavelet transform. Quantitative results from experiments performed on synthetic volumes showed a significant improvement in segmentation quality over traditional methods. Qualitative validation using real-world medical datasets, and comparison with other similar GPU-based algorithms, were also performed. In all cases, the proposed implementation provided good segmentation accuracy while maintaining competitive performance.