Paper Info
Title
Performance optimization of differential evolution with slime mould algorithm for multilevel breast cancer image segmentation
Abstract
Breast cancer is one of the most dangerous diseases for women's health, and it is imperative to provide the necessary diagnostic assistance for it. The medical image processing technology is one of the most critical of all complementary diagnostic technologies. Image segmentation is the core step of image processing, where multilevel image segmentation is considered one of the most efficient and straightforward methods. Many multilevel image segmentation methods based on evolutionary and population-based methods have been proposed in recent years, but many have the fatal weakness of poor convergence accuracy and the tendency to fall into local optimum. Therefore, to overcome these weaknesses, this paper proposes a modified differential evolution (MDE) algorithm with a vision based on the slime mould foraging behavior, where the recently proposed slime mould algorithm (SMA) inspires it. Besides, to obtain high-quality breast cancer image segmentation results, this paper also develops an excellent MDE-based multilevel image segmentation model, the core of which is based on non-local means 2D histogram and 2D Kapur's entropy. To effectively validate the performance of the proposed method, a comparison experiment between MDE and its similar algorithms was first carried out on IEEE CEC 2014. Then, an initial validation of the MDE-based multilevel image segmentation model was performed by utilizing a reference image set. Finally, the MDE-based multilevel image segmentation model was compared with peers using breast invasive ductal carcinoma images. A series of experimental results have proved that MDE is an evolutionary algorithm with high convergence accuracy and the ability to jump out of the local optimum, as well as effectively demonstrated that the developed model is a high-quality segmentation method that can provide practical support for further research of breast invasive ductal carcinoma pathological image processing.
Year
DOI
Venue
2021
10.1016/j.compbiomed.2021.104910
COMPUTERS IN BIOLOGY AND MEDICINE
Keywords
DocType
Volume
Image segmentation, Slime mould algorithm, Differential evolution, Breast cancer, Optimization, Swarm-intelligence
Journal
138
ISSN
Citations 
PageRank 
0010-4825
1
0.35
References 
Authors
102
9
Search Limit
100102
Name
Order
Citations
PageRank
Lei Liu120.69
Dong Zhao2545.66
Fanhua Yu331.37
Ali Asghar Heidari437923.01
Jintao Ru510.35
Hui-Ling Chen665526.09
Majdi Mafarja757420.00
Hamza Turabieh851.38
Zhifang Pan931.37