Multi-level thresholding segmentation for pathological images: Optimal performance design of a new modified differential evolution. (September 2022)

• Record Type: Journal Article
• Authors: Ren, Lili; Zhao, Dong; Zhao, Xuehua; Chen, Weibin; Li, Lingzhi; Wu, TaiSong; Liang, Guoxi; Cai, Zhennao; Xu, Suling
• Is Part Of: Computers in biology and medicine. Volume 148(2022)
• Publication Date: 2022-09
• Subjects: Meta-heuristic -- Breast cancer -- Skin cancer -- Swarm-intelligence -- Multi-level thresholding segmentation; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2022.105910
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: The effective analytical processing of pathological images is crucial in promoting the development of medical diagnostics. Based on this matter, in this research, a multi-level thresholding segmentation (MLTS) method based on modified different evolution (MDE) is proposed. The MDE is the primary benefit offered by the suggested MLTS technique, which is a novel proposed evolutionary algorithm in this article with significant convergence accuracy and the capability to leap out of the local optimum (LO). This optimizer came into being mostly as a result of the incorporation of the movement mechanisms of white holes, black holes, and wormholes into various evolutions. Thus, the developed MLTS approach may provide high-quality segmentation results and is less susceptible to segmentation process stagnation. To validate the efficacy of the presented approaches, first, the performance of MDE is validated using 30 benchmark functions, and then the proposed segmentation method is empirically compared with other comparable methods using standard pictures. On the basis of breast cancer and skin cancer pathology images, the developed segmentation method is compared to other competing methods and experimentally validated in further detail. By analyzing experimental data, the key compensations of MDE are proven, and it is experimentally shown that the unique MDE-based MLTS approach can achieve good performance in terms of many performance assessment indices. Consequently, the proposed method may offer an efficient segmentation procedure for pathological medical images. Highlights: An improved differential evolution (MDE) is proposed for image segmentation. An effective image segmentation method based on MDE is developed. The performance of MDE is verified by comparison with some peers on test suites. The developed segmentation method is evaluated under some representative thresholds. MDE effectively optimizes segmentation process and improves segmentation results.