A nonlinear mapping approach to stain normalization in digital histopathology images using image-specific color deconvolution - PubMed (original) (raw)
A nonlinear mapping approach to stain normalization in digital histopathology images using image-specific color deconvolution
Adnan Mujahid Khan et al. IEEE Trans Biomed Eng. 2014 Jun.
Abstract
Histopathology diagnosis is based on visual examination of the morphology of histological sections under a microscope. With the increasing popularity of digital slide scanners, decision support systems based on the analysis of digital pathology images are in high demand. However, computerized decision support systems are fraught with problems that stem from color variations in tissue appearance due to variation in tissue preparation, variation in stain reactivity from different manufacturers/batches, user or protocol variation, and the use of scanners from different manufacturers. In this paper, we present a novel approach to stain normalization in histopathology images. The method is based on nonlinear mapping of a source image to a target image using a representation derived from color deconvolution. Color deconvolution is a method to obtain stain concentration values when the stain matrix, describing how the color is affected by the stain concentration, is given. Rather than relying on standard stain matrices, which may be inappropriate for a given image, we propose the use of a color-based classifier that incorporates a novel stain color descriptor to calculate image-specific stain matrix. In order to demonstrate the efficacy of the proposed stain matrix estimation and stain normalization methods, they are applied to the problem of tumor segmentation in breast histopathology images. The experimental results suggest that the paradigm of color normalization, as a preprocessing step, can significantly help histological image analysis algorithms to demonstrate stable performance which is insensitive to imaging conditions in general and scanner variations in particular.
Similar articles
- A study about color normalization methods for histopathology images.
Roy S, Kumar Jain A, Lal S, Kini J. Roy S, et al. Micron. 2018 Nov;114:42-61. doi: 10.1016/j.micron.2018.07.005. Epub 2018 Aug 1. Micron. 2018. PMID: 30096632 Review. - A Complete Color Normalization Approach to Histopathology Images Using Color Cues Computed From Saturation-Weighted Statistics.
Li X, Plataniotis KN. Li X, et al. IEEE Trans Biomed Eng. 2015 Jul;62(7):1862-73. doi: 10.1109/TBME.2015.2405791. Epub 2015 Feb 19. IEEE Trans Biomed Eng. 2015. PMID: 25706507 - Stain Color Adaptive Normalization (SCAN) algorithm: Separation and standardization of histological stains in digital pathology.
Salvi M, Michielli N, Molinari F. Salvi M, et al. Comput Methods Programs Biomed. 2020 Sep;193:105506. doi: 10.1016/j.cmpb.2020.105506. Epub 2020 Apr 17. Comput Methods Programs Biomed. 2020. PMID: 32353672 - Circular Mixture Modeling of Color Distribution for Blind Stain Separation in Pathology Images.
Li X, Plataniotis KN. Li X, et al. IEEE J Biomed Health Inform. 2017 Jan;21(1):150-161. doi: 10.1109/JBHI.2015.2503720. Epub 2015 Nov 25. IEEE J Biomed Health Inform. 2017. PMID: 26625434 - Optimized detection and segmentation of nuclei in gastric cancer images using stain normalization and blurred artifact removal.
Martos O, Hoque MZ, Keskinarkaus A, Kemi N, Näpänkangas J, Eskuri M, Pohjanen VM, Kauppila JH, Seppänen T. Martos O, et al. Pathol Res Pract. 2023 Aug;248:154694. doi: 10.1016/j.prp.2023.154694. Epub 2023 Jul 16. Pathol Res Pract. 2023. PMID: 37494804 Review.
Cited by
- Impact of Stain Variation and Color Normalization for Prognostic Predictions in Pathology.
Lin SS, Zhou H, Cote RJ, Watson M, Govindan R, Yang C. Lin SS, et al. ArXiv [Preprint]. 2024 Sep 12:arXiv:2409.08338v1. ArXiv. 2024. PMID: 39314500 Free PMC article. Preprint. - Improving performance in colorectal cancer histology decomposition using deep and ensemble machine learning.
Prezja F, Annala L, Kiiskinen S, Lahtinen S, Ojala T, Ruusuvuori P, Kuopio T. Prezja F, et al. Heliyon. 2024 Sep 10;10(18):e37561. doi: 10.1016/j.heliyon.2024.e37561. eCollection 2024 Sep 30. Heliyon. 2024. PMID: 39309850 Free PMC article. - EpidermaQuant: Unsupervised Detection and Quantification of Epidermal Differentiation Markers on H-DAB-Stained Images of Reconstructed Human Epidermis.
Zamojski D, Gogler A, Scieglinska D, Marczyk M. Zamojski D, et al. Diagnostics (Basel). 2024 Aug 29;14(17):1904. doi: 10.3390/diagnostics14171904. Diagnostics (Basel). 2024. PMID: 39272688 Free PMC article. - Stain SAN: simultaneous augmentation and normalization for histopathology images.
Kim T, Li Y, Calhoun BC, Thennavan A, Carey LA, Symmans WF, Troester MA, Perou CM, Marron JS. Kim T, et al. J Med Imaging (Bellingham). 2024 Jul;11(4):044006. doi: 10.1117/1.JMI.11.4.044006. Epub 2024 Aug 23. J Med Imaging (Bellingham). 2024. PMID: 39185474 - Computational methods and biomarker discovery strategies for spatial proteomics: a review in immuno-oncology.
Mi H, Sivagnanam S, Ho WJ, Zhang S, Bergman D, Deshpande A, Baras AS, Jaffee EM, Coussens LM, Fertig EJ, Popel AS. Mi H, et al. Brief Bioinform. 2024 Jul 25;25(5):bbae421. doi: 10.1093/bib/bbae421. Brief Bioinform. 2024. PMID: 39179248 Free PMC article. Review.
Publication types
MeSH terms
Substances
LinkOut - more resources
Full Text Sources
Other Literature Sources