Journal of Bionic Engineering ›› 2023, Vol. 20 ›› Issue (5): 2240-2275.doi: 10.1007/s42235-023-00365-7

• • 上一篇    下一篇

Renal Pathology Images Segmentation Based on Improved Cuckoo Search with Difusion Mechanism and Adaptive Beta‑Hill Climbing

Jiaochen Chen1; Zhennao Cai1;Huiling Chen1; Xiaowei Chen2;José Escorcia‑Gutierrez3;Romany F. Mansour4; Mahmoud Ragab5,6   

  1. 1 College of Computer Science and Artifcial Intelligence, Wenzhou University, Wenzhou 325035, China  2 Department of Rheumatology and Immunology, The First Afliated Hospital of Wenzhou Medical University, Wenzhou 325000, China  3 Department of Computational Science and Electronics, Universidad de la Costa, CUC, 080002 Barranquilla, Colombia  4 Department of Mathematics, Faculty of Science, New Valley University, 72511, El-Kharga, Egypt  5 Information Technology Department, Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah 21589, Saudi Arabia  6 Department of Mathematics, Faculty of Science, Al-Azhar University, Naser City, Cairo 11884, Egypt
  • 出版日期:2023-08-26 发布日期:2023-09-06
  • 通讯作者: Zhennao Cai; Huiling Chen E-mail:cznao@wzu.edu.cn;chenhuiling.jlu@gmail.com
  • 作者简介:Jiaochen Chen1; Zhennao Cai1;Huiling Chen1; Xiaowei Chen2;José Escorcia?Gutierrez3;Romany F. Mansour4; Mahmoud Ragab5,6

Renal Pathology Images Segmentation Based on Improved Cuckoo Search with Difusion Mechanism and Adaptive Beta‑Hill Climbing

Jiaochen Chen1; Zhennao Cai1;Huiling Chen1; Xiaowei Chen2;José Escorcia‑Gutierrez3;Romany F. Mansour4; Mahmoud Ragab5,6   

  1. 1 College of Computer Science and Artifcial Intelligence, Wenzhou University, Wenzhou 325035, China  2 Department of Rheumatology and Immunology, The First Afliated Hospital of Wenzhou Medical University, Wenzhou 325000, China  3 Department of Computational Science and Electronics, Universidad de la Costa, CUC, 080002 Barranquilla, Colombia  4 Department of Mathematics, Faculty of Science, New Valley University, 72511, El-Kharga, Egypt  5 Information Technology Department, Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah 21589, Saudi Arabia  6 Department of Mathematics, Faculty of Science, Al-Azhar University, Naser City, Cairo 11884, Egypt
  • Online:2023-08-26 Published:2023-09-06
  • Contact: Zhennao Cai; Huiling Chen E-mail:cznao@wzu.edu.cn;chenhuiling.jlu@gmail.com
  • About author:Jiaochen Chen1; Zhennao Cai1;Huiling Chen1; Xiaowei Chen2;José Escorcia?Gutierrez3;Romany F. Mansour4; Mahmoud Ragab5,6

摘要: Lupus Nephritis (LN) is a significant risk factor for morbidity and mortality in systemic lupus erythematosus, and nephropathology is still the gold standard for diagnosing LN. To assist pathologists in evaluating histopathological images of LN, a 2D Rényi entropy multi-threshold image segmentation method is proposed in this research to apply to LN images. This method is based on an improved Cuckoo Search (CS) algorithm that introduces a Diffusion Mechanism (DM) and an Adaptive β-Hill Climbing (AβHC) strategy called the DMCS algorithm. The DMCS algorithm is tested on 30 benchmark functions of the IEEE CEC2017 dataset. In addition, the DMCS-based multi-threshold image segmentation method is also used to segment renal pathological images. Experimental results show that adding these two strategies improves the DMCS algorithm's ability to find the optimal solution. According to the three image quality evaluation metrics: PSNR, FSIM, and SSIM, the proposed image segmentation method performs well in image segmentation experiments. Our research shows that the DMCS algorithm is a helpful image segmentation method for renal pathological images.

关键词:  , Multi-threshold image segmentation , · 2D Rényi entropy , · Renal pathology , · Cuckoo search algorithm , · Swarm intelligence algorithms , · Bionic algorithm

Abstract: Lupus Nephritis (LN) is a significant risk factor for morbidity and mortality in systemic lupus erythematosus, and nephropathology is still the gold standard for diagnosing LN. To assist pathologists in evaluating histopathological images of LN, a 2D Rényi entropy multi-threshold image segmentation method is proposed in this research to apply to LN images. This method is based on an improved Cuckoo Search (CS) algorithm that introduces a Diffusion Mechanism (DM) and an Adaptive β-Hill Climbing (AβHC) strategy called the DMCS algorithm. The DMCS algorithm is tested on 30 benchmark functions of the IEEE CEC2017 dataset. In addition, the DMCS-based multi-threshold image segmentation method is also used to segment renal pathological images. Experimental results show that adding these two strategies improves the DMCS algorithm's ability to find the optimal solution. According to the three image quality evaluation metrics: PSNR, FSIM, and SSIM, the proposed image segmentation method performs well in image segmentation experiments. Our research shows that the DMCS algorithm is a helpful image segmentation method for renal pathological images.

Key words:  , Multi-threshold image segmentation , · 2D Rényi entropy , · Renal pathology , · Cuckoo search algorithm , · Swarm intelligence algorithms , · Bionic algorithm