ReinhardGAN Hybrid Strategic Light optimization for Normalization of H E Stained Colorectal Cancer
DOI:
https://doi.org/10.4108/eetpht.11.10445Keywords:
Arithmetic Optimization Algorithm, Hematoxylin and Eosin, Normalization, Reinhard Stain Normalization, War Strategy OptimizationAbstract
Stain normalization is a crucial pre-processing process for the accurate interpretation of Haematoxylin and Eosin (H&E) stained histopathology images based on colorectal cancer. Effective normalization improves classification accuracy by reducing computational complexity, addressing inter- variability in background colors across a dataset, and minimizing data loss. This paper proposes a novel approach that combines Reinhard normalization with a Generative Adversarial Network (ReinhardGAN) to enhance image color properties, such as consistency, contrast, and luminance. To further optimize the normalization process, a Hybrid Strategic Light Optimization (HSLO) algorithm is introduced, minimizing the loss and computational cost during the H&E-stained image normalization. The experimental results demonstrate that the proposed ReinhardGAN-HSLO provided outstanding performance over conventional color normalization methods in terms of colour consistency and normalization as indicated by qualitative and quantitative assessments
Downloads
References
[1] Oboma YI, et al. Histopathological, cytological and radiological correlations in allergy and public health concerns: a comprehensive review. J Asthma Allergy. 2024;17:1333–1354.
[2] Cong C. Computer Vision in Histopathology Image Analysis: Preprocessing and Classification [dissertation]. University of New South Wales; 2024. Available from: http://hdl.handle.net/1959.4/102394
[3] Dibal NI, Garba SH, Jacks TW. Histological stains and their application in teaching and research. Asian J Health Sci. 2022;8(2):ID43.
[4] Franchet C, et al. Bias reduction using combined stain normalization and augmentation for AI-based classification of histological images. Comput Biol Med. 2024;171:108130.
[5] Martinez-Del-Rio-Ortega R, et al. Brain tumor detection using magnetic resonance imaging and convolutional neural networks. Big Data Cogn Comput. 2024;8(9):123.
[6] Uchikov P, et al. Artificial intelligence in the diagnosis of colorectal cancer: a literature review. Diagnostics. 2024;14(5):528.
[7] Rehman ZU, et al. Comprehensive review on computational in-situ hybridization digital pathology using image analysis techniques: principles and applications.
[8] Faizal, Abas FS, Cheah PL, Looi LM, Toh YF. Comprehensive review on computational in-situ hybridization digital pathology using image analysis techniques: principles and applications.
[9] Reinhard E, Adhikhmin M, Gooch B, Shirley P. Colour transfer between images. IEEE Comput Graph Appl. 2001;21(5):34–41.
[10] Guo Y, Shahin AI, Garg H. An indeterminacy fusion of encoder-decoder network based on neutrosophic set for white blood cells segmentation. Expert Syst Appl. 2024;246:123156.
[11] Roy S, Panda S, Jangid M. Modified reinhard algorithm for color normalization of colorectal cancer histopathology images. In: Proc 29th Eur Signal Process Conf (EUSIPCO); 2021. p. 1020–1024.
[12] Piorkowski A, Gertych A. Color normalization approach to adjust nuclei segmentation in images of hematoxylin and eosin stained tissue. In: International Conference on Information Technologies in Biomedicine. Cham: Springer; 2018. p. 253–262.
[13] Roy S, Lal S, Kini JR. Novel color normalization method for hematoxylin eosin stained histopathology images. IEEE Access. 2019;7:28982–28998.
[14] Rabeya RA, et al. An experimental comparison and quantitative analysis on conventional stain normalization for histopathology images. 2024;27(11):1268–1288.
[15] Yengec-Tasdemir SB, et al. Improved classification of colorectal polyps on histopathological images with ensemble learning and stain normalization. Comput Methods Programs Biomed. 2023;232:107441.
[16] Lee J, et al. Unsupervised machine learning for identifying important visual features through bag-of-words using histopathology data from chronic kidney disease. Sci Rep. 2022;12(1).
[17] Hetz MJ, Bucher TC, Brinker TJ. Multi-domain stain normalization for digital pathology: a cycle-consistent adversarial network for whole slide images. Med Image Anal. 2024;94:103149.
[18] Alhassan AM. A generative adversarial network to Reinhard stain normalization for histopathology image analysis. Ain Shams Eng J. 2024;15(10):102955.
[19] Rehman ZU, et al. Comprehensive analysis of color normalization methods for HER2-SISH histopathology images. J Eng Sci Technol. 2024;19:146–159.
[20] Kausar T, et al. SA-GAN: stain acclimation generative adversarial network for histopathology image analysis. Appl Sci. 2021;12(1):288.
[21] Hoque MZ, et al. Stain normalization methods for histopathology image analysis: a comprehensive review and experimental comparison. Inf Fusion. 2024;102:101997.
[22] Moghadam AZ, et al. Stain transfer using generative adversarial networks and disentangled features. Comput Biol Med. 2022;142:105219.
[23] Wagner SJ, et al. Structure-preserving multi-domain stain color augmentation using style-transfer with disentangled representations. In: Int Conf Med Image Comput Assist Interv. Cham: Springer; 2021. p. 323–332.
[24] Wong IHM, et al. Slide-free histological imaging by microscopy with ultraviolet surface excitation using speckle illumination. Photonics Res. 2021;10(1):120– 125.
[25] Nazki H, et al. MultiPathGAN: Structure preserving stain normalization using unsupervised multi-domain adversarial network with perception loss. In: Proc 38th ACM/SIGAPP Symp Appl Comput; 2023. p. 1450–1457.
[26] Abdel-Basset M, et al. Light spectrum optimizer: A novel physics-inspired metaheuristic optimization algorithm. Mathematics. 2022;10(19):3466.
[27] Ayyarao TSLV, et al. War strategy optimization algorithm: a new effective metaheuristic algorithm for global optimization. IEEE Access. 2022;10:25073–25105.
[28] Cong C, et al. Colour adaptive generative networks for stain normalisation of histopathology images. Med Image Anal. 2022;82:102580. 17
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Shubhajit Panda, Mahesh Jangid, Ashish Jain
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This is an open access article distributed under the terms of the CC BY-NC-SA 4.0, which permits copying, redistributing, remixing, transformation, and building upon the material in any medium so long as the original work is properly cited.
