Abstract
The colorless biopsied tissue samples are usually stained in order to visualize different microscopic structures for diagnostic purposes. But color variations associated with the process of sample preparation, usage of raw materials, diverse staining protocols, and using different slide scanners may adversely influence both visual inspection and computer-aided image analysis. As a result, many methods are proposed for histopathology image stain normalization in recent years. In this study, we introduce a novel approach for stain normalization based on learning a mixture of multivariate skew-normal distributions for stain clustering and parameter estimation alongside a stain transformation technique. The proposed method, labeled "Class-Agnostic Weighted Normalization" (short CLAW normalization), has the ability to normalize a source image by learning the color distribution of both source and target images within an expectation-maximization framework. The novelty of this approach is its flexibility to quantify the underlying both symmetric and nonsymmetric distributions of the different stain components while it is considering the spatial information. The performance of this new stain normalization scheme is tested on several publicly available digital pathology datasets to compare it against state-of-the-art normalization algorithms in terms of ability to preserve the image structure and information. All in all, our proposed method performed superior more consistently in comparison with existing methods in terms of information preservation, visual quality enhancement, and boosting computer-aided diagnosis algorithm performance.
Highlights
T HE pathologist’s diagnosis is generally considered as the final decision in critical diseases such as cancer
The rest of the experiments are dedicated to evaluating the performance of our stain normalization method against state-of-the-art methods, using 1, 537 histopathology images
We have introduced an automated stain normalization framework based on a mixture of SN distributions, to capture both symmetric and nonsymmetric observations
Summary
T HE pathologist’s diagnosis is generally considered as the final decision in critical diseases such as cancer. The advent of digital pathology has created opportunities to harness the power of the computer vision algorithms in this sensitive field. The digital pathology aims to infer meaningful representations from digitized glass slides for the subsequent decision-making steps. Stain, as a fundamental visual property of the input image, highly influences either the performance of an image analysis algorithm or the outcome of the clinician assessment. Most cells and tissue samples are colorless originally These transparent specimens are stained to make tissue patterns visible. Due to several factors such as sample preparation, dye substance, staining, and scanning procedures, color variations may be introduced to the digitization process of the glass slide with the biopsy sample [1]. The stain variation may cause confusion and uncertainty in the result of any utilized image processing approach or clinician evaluation result. Several stain normalization methods are proposed in the literature in order to enhance color in pathology images
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.
