Abstract
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.
Highlights
Cancer is a major life-threatening health problem around the world and biomedical imaging is one of the crucial data modalities in cancer research
It is evident that digital pathology is taking vast steps towards real ization in clinical work in addition to being part of research methodol ogy
Applications, both to replace conventional time-consuming work routines and the new methods are appealing to the community of pa thologists as well as researchers
Summary
Cancer is a major life-threatening health problem around the world and biomedical imaging is one of the crucial data modalities in cancer research. Radiology and Radiomics provide means of quantitative study of cancer properties at the macroscopic scale. The histopathologic ex amination of tissue, on the other hand, reveals the effects and properties of cancer at the microscopic level (Kurc et al, 2020). The new digital technologies can provide means for attaining digital images from bio logical tissue samples in a faster and more cost-effective way without compromising quality or patient care. Whole slide image analysis technology provides a way to diagnose huge numbers of medical conditions and phenomena currently studied in clinical medicine and pathology (Stathonikos et al, 2013; Al Janabi et al, 2011). Common tasks, where pa thologists locate and recognize tissue components can be automized with the aid of image analysis algorithms, such as image segmentation and recognition algorithms. Mapping and quantification of cell/nuclei in the tumor area is another significant direction
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
