A medical analytical system using intelligent fuzzy level set brain image segmentation based on improved quantum particle swarm optimization

Medical image segmentation demonstrates a significant part in curative image exploration and dispensation, is a multifaceted and perplexing assignment for reckoning efficiency and dissection precision. Segmenting an image is essential to dissection different components of the image, which is prominent fact to identify region of defect accurately. An Intelligent Fuzzy Level Set Method (IFLSM) along with an over-all search proficiency of Improved Quantum Particle Swarm Optimization (IQPSO) for image segmentation is proposed to improve the steadiness and meticulousness thus aiming at reduction of opening sensitivity. The proposed algorithm aims at optimizing the opening contours by utilizing the IQPSO method in addition with intelligent fuzzy clustering method, and segments the image using enhanced Level Set Method (LSM). A stable cluster head is identified using the comprehensive quest aptitude of IQPSO. The iteration period will also provide a pre-segmentation contour which is nearer to Region of Interest (ROI). The implementation of the proposed work for segmenting brain tissues through Magnetic Image Resonance (MRI) images provides an optimized result which is 15% more than the original FLSM algorithm. The obtained contours from the proposed work shows more stability than the original FLSM. The proposed work shows a promising significant improvement in the image segmentation process.