An Automated Framework for Multi-label Brain Tumor Segmentation based onKernel Sparse Representation

A novel automated framework is proposed in this paper to address the significant but challenging task of multi-label brain tumor segmentation. Kernel sparse representation, which produces discriminative sparse codes to represent features in a high-dimensional feature space, is the key component of the proposed framework. The graph-cut method is integrated into the framework to make a segmentation decision based on both the kernel sparse representation and the topological information of brain structures. A splitting technique based on principal component analysis (PCA) is adopted as an initialization component for the dictionary learning procedure, which significantly reduces the processing time without sacrificing performance. The proposed framework is evaluated on the multi-label Brain Tumor Segmentation (BRATS) Benchmark. The evaluation results demonstrate that the proposed framework is able to achieve compatible performance and better generalization ability compared to the state-of-the-art approaches.