Skip to main content
SpringerLink
Log in

Evaluation of sparsity metrics and evolutionary algorithms applied for normalization of H&E histological images

  • Short Paper
  • Published:
Pattern Analysis and Applications Aims and scope Submit manuscript

Abstract

Color variations in H&E histological images can impact the segmentation and classification stages of computational systems used for cancer diagnosis. To address these variations, normalization techniques can be applied to adjust the colors of histological images. Estimates of stain color appearance matrices and stain density maps can be employed to carry out these color adjustments. This study explores these estimates by leveraging a significant biological characteristic of stain mixtures, which is represented by a sparsity parameter. Computationally estimating this parameter can be accomplished through various sparsity measures and evolutionary algorithms. Therefore, this study aimed to evaluate the effectiveness of different sparsity measures and algorithms for color normalization of H&E-stained histological images. The results obtained demonstrated that the choice of different sparsity measures significantly impacts the outcomes of normalization. The sparsity metric \(l_{\epsilon }^{0}\) proved to be the most suitable for it. Conversely, the evolutionary algorithms showed little variations in the conducted quantitative analyses. Regarding the selection of the best evolutionary algorithm, the results indicated that particle swarm optimization with a population size of 250 individuals is the most appropriate choice.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Data availability

The data that support the findings of this study are openly available in Github at https://github.com/stes/fan, reference Number [6].

References

  1. Demir C, Yener B (2005) Automated cancer diagnosis based on histopathological images: a systematic survey. Tech. Rep, Rensselaer Polytechnic Institute

    Google Scholar 

  2. Orlov NV et al (2010) Automatic classification of lymphoma images with transform-based global features. IEEE Trans Inform Technol Biomed 14(4):1003–1013

    Article  Google Scholar 

  3. Celis R, Romero E (2015) Unsupervised color normalisation for h and e stained histopathology image analysis. In: 11th international symposium on medical information processing and analysis. vol 9681, SPIE

  4. Tam A, Barker J, Rubin D (2016) A method for normalizing pathology images to improve feature extraction for quantitative pathology. Med Phys 43(1):528–537

    Article  PubMed  Google Scholar 

  5. Bilgin CC et al (2012) Digitally adjusting chromogenic dye proportions in brightfield microscopy images. J Microsc 245(3):319–330

    Article  CAS  PubMed  Google Scholar 

  6. Bug D et al (2017) Context-based normalization of histological stains using deep convolutional features. In: Stoyanov D, Taylor Z, Carneiro G, Syeda-Mahmood T, Martel A, Maier-Hein L, Tavares JMR, Bradley A, Papa JP, Belagiannis V, Nascimento JC (eds) Deep learning in medical image analysis and multimodal learning for clinical decision support. Springer, Cham, pp 135–142

    Chapter  Google Scholar 

  7. Tosta TAA et al (2019) Unsupervised method for normalization of hematoxylin-eosin stain in histological images. Comput Med Imag Graph 77:101646

    Article  ADS  Google Scholar 

  8. Li X, Plataniotis KN (2015) A complete color normalization approach to histopathology images using color cues computed from saturation-weighted statistics. IEEE Trans Biomed Eng 62(7):1862–1873

    Article  PubMed  Google Scholar 

  9. BenTaieb A, Hamarneh G (2017) Adversarial stain transfer for histopathology image analysis. IEEE Trans Med Imaging 37(3):792–802

    Article  Google Scholar 

  10. Shaban, M. Tarek, et al. (2019) Staingan: stain style transfer for digital histological images. In: 2019 IEEE16th international symposium on biomedical imaging (Isbi 2019), IEEE

  11. Salehi P, Abdolah C (2020) Pix2pix-based stain-to-stain translation: a solution for robust stain normalization in histopathology images analysis. In: 2020 international conference on machine vision and image processing (MVIP), IEEE

  12. Cho H et al. (2017) Neural stain-style transfer learning using GAN for histopathological images. arXiv:1710.08543

  13. de Bel T et al (2021) Residual Cyclegan for robust domain transformation of histopathological tissue slides. Med Image Analy 70:102004

    Article  Google Scholar 

  14. Cong C et al (2022) Colour adaptive generative networks for stain normalisation of histopathology images. Med Image Anal 82:102580

    Article  PubMed  Google Scholar 

  15. Kang H et al (2021) Stainnet: a fast and robust stain normalization network. Front Med 8:746307

    Article  Google Scholar 

  16. Jeong J et al (2023) Stain normalization using score-based diffusion model through stain separation and overlapped moving window patch strategies. Comput Biol Med 152:106335

    Article  PubMed  Google Scholar 

  17. Lei G et al (2020) StainCNNs: an efficient stain feature learning method. Neurocomputing 406:267–273

    Article  Google Scholar 

  18. Vahadane A et al (2016) Structure-preserving color normalization and sparse stain separation for histological images. IEEE Trans Med Imaging 35(8):1962–1971

    Article  PubMed  Google Scholar 

  19. Maji P, Mahapatra S (2019) Rough-fuzzy circular clustering for color normalization of histological images. Fund Inform 164(1):103–117

    MathSciNet  Google Scholar 

  20. Aswathy MA, Jagannath M (2020) Dual stage normalization approach towards classification of breast cancer. IETE J Res 68(4):3074–3085

    Article  Google Scholar 

  21. Zheng Y et al (2019) Adaptive color deconvolution for histological WSI normalization. Comput Methods Progr Biomed 170:107–120

    Article  Google Scholar 

  22. Pérez-Bueno F et al (2022) Bayesian K-SVD for H and E blind color deconvolution. Applications to stain normalization, data augmentation and cancer classification. Comput Med Imaging Graph 97:102048

    Article  PubMed  Google Scholar 

  23. McCann, MT et al (2014) Algorithm and benchmark dataset for stain separation in histology images. In: 2014 IEEE international conference on image processing (ICIP), IEEE

  24. Lu C, Shi J, Jia J (2013) Online robust dictionary learning. In: Proceedings of the IEEE conference on computer vision and pattern recognition

  25. Mairal J et al (2010) Online learning for matrix factorization and sparse coding. J Mach Learn Res 11(1):19–60

    MathSciNet  Google Scholar 

  26. Tang Y et al (2011) A fast recursive algorithm based on fuzzy 2-partition entropy approach for threshold selection. Neurocomputing 74(17):3072–3078

    Article  Google Scholar 

  27. Bose A, Mali K (2016) Fuzzy-based artificial bee colony optimization for gray image segmentation. SIViP 10(6):1089–1096

    Article  Google Scholar 

  28. Bhandari AK, Kumar A, Singh GK (2015) Tsallis entropy based multilevel thresholding for colored satellite image segmentation using evolutionary algorithms. Expert Syst Appl 42(22):8707–8730

    Article  Google Scholar 

  29. Cuevas E, Zaldívar D, Perez-Cisneros M (2016) Image segmentation based on differential evolution optimization. In: Applications of evolutionary computation in image processing and pattern recognition. Springer, Cham. pp 9-22

  30. Tosta TAA, et al (2017) Computational method for unsupervised segmentation of lymphoma histological images based on fuzzy 3-partition entropy and genetic algorithm. Expert Syst Appl 81:223–243

    Article  Google Scholar 

  31. Remamany KP et al (2015) Brain tumor segmentation in MRI images using integrated modified PSO-fuzzy approach. Int. Arab J. Inf. Technol. 12(6):797–805

    Google Scholar 

  32. Bayraktar, Z, Komurcu M, Douglas HW (2010) Wind Driven Optimization (WDO): A novel nature-inspired optimization algorithm and its application to electromagnetics. In: 2010 IEEE antennas and propagation society international symposium. IEEE,

  33. Zhang S, Jiang W, Satoh S (2018) Multilevel thresholding color image segmentation using a modified artificial bee colony algorithm. IEICE Trans Inf Syst 101(8):2064–2071

    Article  Google Scholar 

  34. Yin S et al (2014) Efficient multilevel image segmentation through fuzzy entropy maximization and graph cut optimization. Pattern Recognit 47(9):2894–2907

    Article  ADS  Google Scholar 

  35. Bhandari AK et al (2014) Cuckoo search algorithm and wind driven optimization based study of satellite image segmentation for multilevel thresholding using Kapur’s entropy. Exp Syst Appl 41(7):3538–3560

    Article  Google Scholar 

  36. Walkowski S, Szymas J (2011) Quality evaluation of virtual slides using methods based on comparing common image areas. In: Diagnostic pathology. Vol. 6. No. 1. BioMed Central

  37. Hammouche K, Diaf M, Siarry P (2008) A multilevel automatic thresholding method based on a genetic algorithm for a fast image segmentation. Comput Vis Image Underst 109(2):163–175

    Article  Google Scholar 

  38. Hoyer PO (2004) Non-negative matrix factorization with sparseness constraints. J Mach Learn Res 5(9):1457–1469

    MathSciNet  Google Scholar 

  39. Hurley N, Rickard S (2009) Comparing measures of sparsity. IEEE Trans Inf Theory 55(10):4723–4741

    Article  MathSciNet  Google Scholar 

  40. Mosquera-Lopez C, Escobar R, Agaian S (2015) Modeling human-perceived quality for the assessment of digitized histopathology color standardization. In: 2015 IEEE international conference on imaging systems and techniques (IST). IEEE

  41. Khan N et al (2021) SD-Net: understanding overcrowded scenes in real-time via an efficient dilated convolutional neural network. J Real Time Image Process 18:1729–1743

    Article  Google Scholar 

  42. Roy S et al (2018) A study about color normalization methods for histopathology images. Micron 114:42–61

    Article  PubMed  Google Scholar 

  43. Pérez-Bueno F et al (2021) Blind color deconvolution, normalization, and classification of histological images using general super Gaussian priors and Bayesian inference. Comput Methods Progr Biomed 211:106453

    Article  Google Scholar 

  44. Zhao B et al (2022) RestainNet: a self-supervised digital re-stainer for stain normalization. Comput Electric Eng 103:108304

    Article  Google Scholar 

  45. Azzeh J, Zahran B, Alqadi Z (2018) Salt and pepper noise: effects and removal. Int J Inform Vis 24:252–256

    Google Scholar 

  46. Yang Y, Wen J, Chen X (2015) Improvements on particle swarm optimization algorithm for velocity calibration in microseismic monitoring. Earthq Sci 28:263–273

    Article  ADS  Google Scholar 

  47. Rodrigues F et al (2021) Simultaneous tuning of the AVR and PSS parameters using particle swarm optimization with oscillating exponential decay. Int J Electri Power Energy Syst 133:107215

    Article  Google Scholar 

  48. Du K-L, et al (2016) Particle swarm optimization. Search and optimization by metaheuristics: techniques and algorithms inspired by nature pp 153-173

  49. Kumlu D, Erer I, Paker S (2022) Non-negative matrix factorization based approaches for wall mitigation in TWRI. Signal Image Video Process 16:889–896

    Article  Google Scholar 

Download references

Acknowledgements

This study was financed in part by the Coordenação de Aperfeiçoamento de Pessoal de Nível Superior - Brazil (CAPES) - Finance Code 001. The authors gratefully acknowledge the financial support of National Council for Scientific and Technological Development CNPq (Grants 311404/2021-9 and 313643/2021-0) and the State of Minas Gerais Research Foundation - FAPEMIG (Grants APQ-00578-18 and APQ-01129-21), CAPES (Grant \#1575210) and São Paulo Research Foundation - FAPESP (Grant \#2022/03020-1).

Funding

Funding was provided by Conselho Nacional de Desenvolvimento Científico e Tecnológico (Grant No 311404/2021-9 and 313643/2021-0), Fundação de Amparo à Pesquisa do Estado de Minas Gerais (Grant No. APQ-00578-18 and APQ-01129-21), Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (Grant No. 1575210) and Fundação de Amparo à Pesquisa do Estado de São Paulo (Grant No. 2022/03020-1).

Author information

Authors and Affiliations

  1. Institute of Science and Technology, Federal University of São Paulo, Av. Cesare Mansueto Giulio Lattes, 1201, São José dos Campos, São Paulo, 12247014, Brazil

    Thaína A. Azevedo Tosta

  2. Department of Histology and Morphology, Institute of Biomedical Science, Federal University of Uberlândia, Av. Amazonas, S/N, Uberlândia, Minas Gerais, 38405320, Brazil

    Paulo Rogério de Faria

  3. Department of Computer Science and Statistics, São Paulo State University, R. Cristóvão Colombo, 2265, São José do Rio Preto, São Paulo, 15054000, Brazil

    Leandro Alves Neves

  4. Federal Institute of Triângulo Mineiro, R. Belarmino Vilela Junqueira S/N, Ituiutaba, Minas Gerais, 38305-200, Brazil

    Alessandro Santana Martins

  5. Chitkara University Institute of Engineering and Technology, Chitkara University, Jansla, Rajpura, Punjab, 140401, India

    Chetna Kaushal

  6. Faculty of Computer Science, Federal University of Uberlândia, Av. João Naves de Ávila, 2121, Uberlândia, Minas Gerais, 38400902, Brazil

    Marcelo Zanchetta do Nascimento

Authors
  1. Thaína A. Azevedo Tosta
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Paulo Rogério de Faria
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Leandro Alves Neves
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Alessandro Santana Martins
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Chetna Kaushal
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Marcelo Zanchetta do Nascimento
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Thaína A. Azevedo Tosta.

Ethics declarations

Conflicts of interest

The authors have no conflicts of interest to declare that are relevant to the content of this article.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Tosta, T.A.A., de Faria, P.R., Neves, L.A. et al. Evaluation of sparsity metrics and evolutionary algorithms applied for normalization of H&E histological images. Pattern Anal Applic 27, 11 (2024). https://doi.org/10.1007/s10044-024-01218-7

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s10044-024-01218-7

Keywords

Search

Navigation