A New Medical Analytical Framework for Automated Detection of MRI Brain Tumor Using Evolutionary Quantum Inspired Level Set Technique

Segmenting brain tumors in 3D magnetic resonance imaging (3D-MRI) accurately is critical for easing the diagnostic and treatment processes. In field of energy functional theory-based methods image segmentation analysis, level set have emerged as a potent computational approach that has greatly aided advancement geometric active contour model. An important factor reducing error number required iterations when using technique choice initial points, both which are dealing with wide range sizes, shapes, structures may take. To define velocity function, conventional simply use gradient, edge strength, region intensity. This article suggests clustering method influenced by Quantum Inspired Dragonfly Algorithm (QDA), metaheuristic optimizer inspired swarming behaviors dragonflies, to extract points. The proposed model employs quantum-inspired computing paradigm stabilize trade-off between exploitation exploration, thereby compensating any shortcomings DA-based method, such slow convergence or falling into local optimum. begin, quantum rotation gate concept can be used relocate colony agents location where they better achieve optimum value. main then given robust search capacity adopting mutation procedure enhance swarm’s realize its variety. After preliminary phase cranium disembodied from brain, tumor contours (edges) determined help QDA. MRI series will derived these extracted edges. final step isolate area across all volume segments. When applied 3D-MRI images BraTS’ 2019 dataset, outperformed state-of-the-art approaches segmentation, shown obtained results.