Article Details

Abstract

The commonly used staining method for histological images is Hematoxylin-Eosin (H&E) staining. However, due to the differences in staining raw materials, storage conditions or staining time, the color of histological images can change, which affects the performance of computer-aided histological image analysis. Therefore, in histological image analysis, it is very important to reduce the color difference between images and retain the histological information contained in the images. In this paper, a color standardization method of histological images based on skewed distribution mixture model is introduced to eliminate the color changes between histological images. Extensive experiments are carried out on three data sets, and it is compared with the commonly used color standardization methods. The experimental results show that the method has better performance in color standardization.

Keywords

skewed distribution; color standardization; EM algorithm; non-negative matrix factorization

References

1. [1] Wang Chao, Guo Ying, Cui Lei, etc Research progress in the field of deep learning assisted pathological diagnosis [J]. Modern Oncology, 2024, 32 (19): 3791-3795
2. [2] GORELICK L，VEKSLER O，GAED M，et al. Prostate Histopathology: Learning Tissue Component Histograms for Cancer Detection and Classification [J].IEEE Transactions on Medical Imaging，2013，32（10）：1804-1818.
3. [3] TABESH A，TEVEROVSKIY M，PANG H-Y，et al. Multifeature Prostate Cancer Diagnosis and Gleason Grading of Histological Images [J].IEEE Transactions on Medical Imaging，2007，26（10）：1366-1378.
4. [4] REINHARD E，ASHIKHMIN M，GOOCH B，et al. Color Transfer Between Images [J].IEEE Computer Graphics and Applications，2001，21（5）：34-41.
5. [5] MAJI P，MAHAPATRA S. Circular Clustering in Fuzzy Approximation Spaces for Color Normalization of Histological Images [J].IEEE Transactions on Medical Imaging，2020，39（5）：1735-1745.
6. [6] Tao Yehui and Zhao Shouwei Gaussian Mixture Model Image Clustering Method Based on Improved EM Algorithm [J]. Software Guide, 2022, 21 (12): 182-186
7. [7] HANBURY A，WIEN T. Circular Statistics Applied to Colour Images [J].Computer Vision Winter Workshop，2003：53-71.
8. [8] VALLE R B，BOLFARINE H，LACHOS V H. Skew-normal Linear Mixed Models [J].Journal of Data Science，2005，3（4）：415-438.
9. [9] KUMAR N，VERMA R，SHARMA S，et al. A Dataset and a Technique for Generalized Nuclear Segmentation for Computational Pathology [J].IEEE Transactions on Medical Imaging，2017，36（7）：1550-1560.
10. [10] GELASCA E D，BYUN J，OBARA B，et al. Evaluation and Benchmark for Biological Image Segmentation [C]//2008 15th IEEE International Conference on Image Processing.San Diego：IEEE，2008：1816-1819.
11. [11] KRUK M，KUREK J，OSOWSKI S，et al. Ensemble of Classifiers and Wavelet Transformation for Improved Recognition of Fuhrman Grading in Clear-Cell Renal carcinoma [J].Biocybernetics and Biomedical Engineering，2017，37（3）：357-364.
12. [12] MACENKO M，NIETHAMMER M，MARRON J，et al. A Method for Normalizing Histology Slides for Quantitative Analysis [C]//2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro.Boston：IEEE，2009：1107-1110.
13. [13] VAHADANE A，PENG T Y，ALBARQOUNI S，et al. Structure-Preserving Color Normalization and Sparse Stain Separation for Histological Images [C]//2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI).Brooklyn：IEEE，2016，35（8）：1012-1015.
14. [14] MAJI P，MAHAPATRA S. Rough-Fuzzy Circular Clustering for Color Normalization of Histological Images [J].Fundamenta Informaticae，2019，164（1）：103-117.
15. [15] ZANJANI F G，ZINGER S，DE WITH P H N. Deep Convolutional Gaussian Mixture Model for Stain-Color Normalization of Histopathological Images [C]//Medical Image Computing and Computer Assisted Intervention-MICCAI 2018（MICCAI 2018）.Granada：Springer，2018：274-282.

About the authors

Fan Xiaoyan (1995-), female, Han ethnicity, from Luoyang, Henan, teaching assistant, master's student, research direction: medical image processing.