GPU-Based Level Set Method for MRI Brain Tumor Segmentation using Modified Probabilistic Clustering
Ram Kumar, Sweta Rani, Abahan Sarkar, Fazal Ahmed Talukdar · Advances in medical technologies and clinical practice book series · 2016
The level set method (LSM) has been widely used in image segmentation due to its intrinsic nature which allows handling complex shapes and topological changes easily. We propose a new level set algorithm, which is based on probabilistic c mean objective function which incorporates intensity inhomogeneity in image and robust to noise. The computational complexity of the proposed LSM is greatly reduced by using highly parallelizable lattice Boltzmann method (LBM). So the proposed algorithm is effective and highly parallelizable. The proposed LSM is implemented using Experimental results demonstrate the performance of the proposed method.