Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Sep 28;14(1):22454.
doi: 10.1038/s41598-024-73335-6.

Improved genetic algorithm for multi-threshold optimization in digital pathology image segmentation

Affiliations

Improved genetic algorithm for multi-threshold optimization in digital pathology image segmentation

Tangsen Huang et al. Sci Rep. .

Abstract

This paper presents an improved genetic algorithm focused on multi-threshold optimization for image segmentation in digital pathology. By innovatively enhancing the selection mechanism and crossover operation, the limitations of traditional genetic algorithms are effectively addressed, significantly improving both segmentation accuracy and computational efficiency. Experimental results demonstrate that the improved genetic algorithm achieves the best balance between precision and recall within the threshold range of 0.02 to 0.05, and it significantly outperforms traditional methods in terms of segmentation performance. Segmentation quality is quantified using metrics such as precision, recall, and F1 score, and statistical tests confirm the superior performance of the algorithm, especially in its global search capabilities for complex optimization problems. Although the algorithm's computation time is relatively long, its notable advantages in segmentation quality, particularly in handling high-precision segmentation tasks for complex images, are highly pronounced. The experiments also show that the algorithm exhibits strong robustness and stability, maintaining reliable performance under different initial conditions. Compared to general segmentation models, this algorithm demonstrates significant advantages in specialized tasks, such as pathology image segmentation, especially in resource-constrained environments. Therefore, this improved genetic algorithm offers an efficient and precise multi-threshold optimization solution for image segmentation, providing valuable reference for practical applications.

Keywords: Global search capability; Image segmentation; Improved genetic algorithm; Multi-threshold optimization; Robustness and stability.

PubMed Disclaimer

Conflict of interest statement

The authors declare no competing interests.

Figures

None
Algorithm 1: Extracting Pixel Ratio Sequence of Epithelial and Stromal Regions
Fig. 1
Fig. 1
Comparison of model performance on different datasets.
Fig. 2
Fig. 2
Performance comparison between the improved GA and the original GA.
Fig. 3
Fig. 3
Box plots comparing computation time and segmentation quality.
Fig. 4
Fig. 4
Bar graphs displaying average computation time and segmentation quality.
Fig. 5
Fig. 5
Performance changes and convergence speed during iteration.
Fig. 6
Fig. 6
Comparison of final performance across.
Fig. 7
Fig. 7
Comparison of performance fluctuations with different initializations and random seeds.
Fig. 8
Fig. 8
The 3D plot of the time complexity analysis of the improved genetic algorithm.
Fig. 9
Fig. 9
Performance comparison of algorithm variants.
Fig. 10
Fig. 10
Total running time vs. number of generations.
Fig. 11
Fig. 11
Rate of convergence of the genetic algorithm.
Fig. 12
Fig. 12
Impact of mutation rates on convergence.
Fig. 13
Fig. 13
Representative samples of original pathology images from the dataset.
Fig. 14
Fig. 14
Segmentation results using the improved genetic algorithm.

References

    1. Liron, P. & Bui, M. Digital pathology: An overview. Surg. Pathol. Clin. 14(3), 407–421 (2021).
    1. Metin, N., Gurcan & Tomaszewski, J. E. Introduction to digital pathology. Annu. Rev. Biomed. Eng. 22(1), 313–326 (2020).
    1. Ravikanth Papineni, S., Ghosh & Viswanath, K. Applications of digital pathology: An overview. Biomolecules 12 (3), 416 (2022). - PubMed
    1. Khang, A. & Sivaraman, K. A. Big data, cloud computing and IoT: Tools and applications/edited. J. Future Revol. Comput. Sci. Commun. Eng. 4(4), 599–602 (2023).
    1. Gharehchopogh, F. et al. Slime mould algorithm: A comprehensive survey of its variants and applications. Arch. Comput. Methods Eng. 30(4), 2683–2723 (2023). - PMC - PubMed

LinkOut - more resources