Md. Ziaul Hoque, Anja Keskinarkaus, Pia Nyberg, Tapio Seppänen, Retinex model based stain normalization technique for whole slide image analysis, Computerized Medical Imaging and Graphics, Volume 90, 2021, 101901, ISSN 0895-6111, https://doi.org/10.1016/j.compmedimag.2021.101901
Retinex model based stain normalization technique for whole slide image analysis
|Author:||Hoque, Md. Ziaul1,2; Keskinarkaus, Anja1,2; Nyberg, Pia3,4;|
1Physiological Signal Analysis Group, Center for Machine Vision and Signal Analysis, University of Oulu, Finland
2Faculty of Information Technology and Electrical Engineering, University of Oulu, Finland
3Biobank Borealis of Northern Finland, Oulu University Hospital, Finland
4Translational & Cancer Research Unit, Medical Research Center Oulu, Faculty of Medicine, University of Oulu, Finland
|Online Access:||PDF Full Text (PDF, 6.9 MB)|
|Persistent link:|| http://urn.fi/urn:nbn:fi-fe2021050428669
|Publish Date:|| 2021-05-04
Medical imaging provides the means for diagnosing many of the medical phenomena currently studied in clinical medicine and pathology. The variations of color and intensity in stained histological slides affect the quantitative analysis of the histopathological images. Moreover, stain normalization utilizing color for the classification of pixels into different stain components is challenging. The staining also suffers from variability, which complicates the automatization of tissue area segmentation with different staining and the analysis of whole slide images. We have developed a Retinex model based stain normalization technique in terms of area segmentation from stained tissue images to quantify the individual stain components of the histochemical stains for the ideal removal of variability. The performance was experimentally compared to reference methods and tested on organotypic carcinoma model based on myoma tissue and our method consistently has the smallest standard deviation, skewness value, and coefficient of variation in normalized median intensity measurements. Our method also achieved better quality performance in terms of Quaternion Structure Similarity Index Metric (QSSIM), Structural Similarity Index Metric (SSIM), and Pearson Correlation Coefficient (PCC) by improving robustness against variability and reproducibility. The proposed method could potentially be used in the development of novel research as well as diagnostic tools with the potential improvement of accuracy and consistency in computer aided diagnosis in biobank applications.
Computerized medical imaging and graphics
|Type of Publication:||
A1 Journal article – refereed
|Field of Science:||
113 Computer and information sciences
213 Electronic, automation and communications engineering, electronics
The research work of this paper was conducted with Physiological Signal Analysis Group at Center for Machine Vision and Signal Analysis (CMVS) in the Faculty of Information Technology and Electrical Engineering (ITEE) at University of Oulu, Finland. This research has been financially supported by Academy of Finland 6 Genesis Flagship (Grant 318927) and Academy of Finland Identifying trajectories of healthy aging via integration of birth cohorts and biobank data (Grant 309112). We are thankful to Professor Tuula Salo group (University of Oulu and University of Helsinki) for selction and access to the myoma organotypic slides. We thank Sanna Juntunen, Eeva-Maija Kiljander, Maija-Leena Lehtonen, and Merja Tyynismaa for technical assistance in preparing the organotypic cultures and slides.
|Academy of Finland Grant Number:||
318927 (Academy of Finland Funding decision)
309112 (Academy of Finland Funding decision)
© 2021 The Author(s). Published by Elsevier Ltd. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).