Abstract
Background: We propose a novel global region based method for segmentation of biomedical images with a fast level set model using Kernel Fuzzy Particles Swarm Optimization (KFPSO) clustering. In the field of medical study, segmentation of biomedical images is one of the most important approaches for the diagnosis of a patient. Segmentation of these images is still a tedious task and cumbersome due to weak contrast and poor resolution of images etc. The automatic segmentation of such images is very difficult. The main reason is a large amount of inhomogeneity present in the background and foreground of real world image. The conventional methods like C-V model and Distance Regularized Level Set (DRLS) method lead to getting improper segmentation with unconvinced results.
Methods: We proposed an efficient segmentation method for MRI biomedical images with level set approach using KFPSO clustering. In the pre-processing step, Kernel Fuzzy C- Means (KFCM) clustering is combined with PSO Initialization algorithm called KFPSO clustering for improving the clustering efficiency. In KFCM clustering algorithm, the initial cluster center is chosen randomly, and with the help of PSO, the optimal cluster centers are chosen.
Results: The Membership Function (MF) of this algorithm is less sensitive to noise and consideration of the spatial information. In the post processing step, the resulting Kernel fuzzy PSO clustering is modified to the level set model for faster and accurate segmentation.
Conclusion: The Proposed segmentation results are effective, superior and accurate compared to conventional methods. This new approach is very helpful for accurate detection of the white matter and gray matter, cancerous cells in brain and bone images.
Keywords: Biomedical images, image segmentation, KFCM clustering, level sets, PSO algorithm, DRLS.
Graphical Abstract
19
3