A Brain Tumor Image Segmentation Method Based on Quantum Entanglement and Wormhole Behaved Particle Swarm Optimization

Abstract

PurposeAlthough classical techniques for image segmentation may work well for some images, they may perform poorly or not work at all for others. It often depends on the properties of the particular image segmentation task under study. The reliable segmentation of brain tumors in medical images represents a particularly challenging and essential task. For example, some brain tumors may exhibit complex so-called “bottle-neck” shapes which are essentially circles with long indistinct tapering tails, known as a “dual tail.” Such challenging conditions may not be readily segmented, particularly in the extended tail region or around the so-called “bottle-neck” area. In those cases, existing image segmentation techniques often fail to work well.MethodsExisting research on image segmentation using wormhole and entangle theory is first analyzed. Next, a random positioning search method that uses a quantum-behaved particle swarm optimization (QPSO) approach is improved by using a hyperbolic wormhole path measure for seeding and linking particles. Finally, our novel quantum and wormhole-behaved particle swarm optimization (QWPSO) is proposed.ResultsExperimental results show that our QWPSO algorithm can better cluster complex “dual tail” regions into groupings with greater adaptability than conventional QPSO. Experimental work also improves operational efficiency and segmentation accuracy compared with current competing reference methods.ConclusionOur QWPSO method appears extremely promising for isolating smeared/indistinct regions of complex shape typical of medical image segmentation tasks. The technique is especially advantageous for segmentation in the so-called “bottle-neck” and “dual tail”-shaped regions appearing in brain tumor images.

Multi Level Approach for Segmentation of Interstitial Lung Disease (ILD) Patterns Classification Based on Superpixel Processing and Fusion of K-Means Clusters: SPFKMC

“…In the literature, there are many types of segmentation algorithms applied to medical images, such as thresholding [ 10 , 11 ], region growing [ 12 , 13 ], machine learning [ 14 , 15 ], deep-learning [ 16 , 17 ], active contour [ 18 , 19 ], quantum-inspired computing [ 20 , 21 ], and computational intelligence [ 22 , 23 ]. Therefore, this section sequentially and individually reviews the related recent developments in unsupervised and supervised categories.…”

A Novel Approach for Hybrid Image Segmentation GCPSO: FCM Techniques for MRI Brain Tumour Identification and Classification

“…Segmentation. An enhanced EDPSO (Darwinian particle swarm optimization) and Quantum Entanglement and Wormhole Behaved Particle Swarm Optimization Techniques [12][13][14] were proposed to segment a tumour image which overcomes this existing method of GCPSO (Guaranteed Convergence Particle Swarm Optimization). We propose, a new Hybrid GCPSO (Guaranteed Convergence Particle Swarm Optimization)-FCM (Fuzzy C-Mean) algorithm use to each particle to every number of generations/iterations so the ftness value of all the particles to improve.…”

Short‐term and long‐term memory self‐attention network for segmentation of tumours in 3D medical images

“…There are many traditional segmentation algorithms, such as thresholding [5,6], region growing [7,8], machine learning [9,10], active contour [11,12], quantum-inspired computing [13,14], and computational intelligence [15,16]. These algorithms are mostly based on the differences in edge and grayscale distribution.…”