Empirical comparison of color normalization methods for epithelial-stromal classification in H and E images - PubMed (original) (raw)
Empirical comparison of color normalization methods for epithelial-stromal classification in H and E images
Amit Sethi et al. J Pathol Inform. 2016.
Abstract
Context: Color normalization techniques for histology have not been empirically tested for their utility for computational pathology pipelines.
Aims: We compared two contemporary techniques for achieving a common intermediate goal - epithelial-stromal classification.
Settings and design: Expert-annotated regions of epithelium and stroma were treated as ground truth for comparing classifiers on original and color-normalized images.
Materials and methods: Epithelial and stromal regions were annotated on thirty diverse-appearing H and E stained prostate cancer tissue microarray cores. Corresponding sets of thirty images each were generated using the two color normalization techniques. Color metrics were compared for original and color-normalized images. Separate epithelial-stromal classifiers were trained and compared on test images. Main analyses were conducted using a multiresolution segmentation (MRS) approach; comparative analyses using two other classification approaches (convolutional neural network [CNN], Wndchrm) were also performed.
Statistical analysis: For the main MRS method, which relied on classification of super-pixels, the number of variables used was reduced using backward elimination without compromising accuracy, and test - area under the curves (AUCs) were compared for original and normalized images. For CNN and Wndchrm, pixel classification test-AUCs were compared.
Results: Khan method reduced color saturation while Vahadane reduced hue variance. Super-pixel-level test-AUC for MRS was 0.010-0.025 (95% confidence interval limits ± 0.004) higher for the two normalized image sets compared to the original in the 10-80 variable range. Improvement in pixel classification accuracy was also observed for CNN and Wndchrm for color-normalized images.
Conclusions: Color normalization can give a small incremental benefit when a super-pixel-based classification method is used with features that perform implicit color normalization while the gain is higher for patch-based classification methods for classifying epithelium versus stroma.
Keywords: Color normalization; computational pathology; epithelial-stromal classification.
Figures
Figure 1
Diversity of H and E stained images illustrated using four prostate cancer samples with Gleason Grade 3. The first two samples show range of epithelial brightness, and the last two show the range of stromal brightness
Figure 2
Preparation of the training and testing sets using original and color-normalized images
Figure 3
Color normalization illustrated using inter-image standard deviation (error bars) of mean (bars) hue, saturation, and intensity for epithelium and stroma. Continuous color bars between epithelium and stroma illustrate the hue, saturation, and intensity range holding the other two at their means
Figure 4
Contribution of color to epithelial-stromal classification illustrated using mean intra-image standard deviation (error bars) around mean (bars) hue, saturation, and intensity. Color bars between epithelium and stroma illustrate the full range of hue, saturation, and intensity while holding the other two constant
Figure 5
Selected sub-images and their normalized versions
Figure 6
An example H and E stained tissue image (left), its super-pixel boundaries (center, green), and detected dark sub-objects (right, black)
Figure 7
Test - area under the curve for the three sets of images for logistic regression models using different number of variables
Figure 8
Receiver operating characteristic curves for pixel-level accuracy for twenty-feature models for ten test images for the three models for thresholds 0.75, 0.5, 0.25, 0.15, and 0.1 on the logistic regression output
Figure 9
Two examples of cores whose pixels have been classified into epithelium (green) and stroma (red) based on original images as well as normalized images using Vahadane and Khan methods
Similar articles
- Influence of normalization and color features on super-pixel classification: application to cytological image segmentation.
Bechar MEA, Settouti N, Daho MEH, Adel M, Chikh MA. Bechar MEA, et al. Australas Phys Eng Sci Med. 2019 Jun;42(2):427-441. doi: 10.1007/s13246-019-00735-8. Epub 2019 Mar 4. Australas Phys Eng Sci Med. 2019. PMID: 30830650 - Automatic normalized digital color staining in the recognition of abnormal blood cells using generative adversarial networks.
Barrera K, Rodellar J, Alférez S, Merino A. Barrera K, et al. Comput Methods Programs Biomed. 2023 Oct;240:107629. doi: 10.1016/j.cmpb.2023.107629. Epub 2023 May 30. Comput Methods Programs Biomed. 2023. PMID: 37301181 - Blind color deconvolution, normalization, and classification of histological images using general super Gaussian priors and Bayesian inference.
Pérez-Bueno F, Vega M, Sales MA, Aneiros-Fernández J, Naranjo V, Molina R, Katsaggelos AK. Pérez-Bueno F, et al. Comput Methods Programs Biomed. 2021 Nov;211:106453. doi: 10.1016/j.cmpb.2021.106453. Epub 2021 Oct 5. Comput Methods Programs Biomed. 2021. PMID: 34649072 - Psoriasis skin biopsy image segmentation using Deep Convolutional Neural Network.
Pal A, Garain U, Chandra A, Chatterjee R, Senapati S. Pal A, et al. Comput Methods Programs Biomed. 2018 Jun;159:59-69. doi: 10.1016/j.cmpb.2018.01.027. Epub 2018 Feb 6. Comput Methods Programs Biomed. 2018. PMID: 29650319 - Computational normalization of H&E-stained histological images: Progress, challenges and future potential.
Azevedo Tosta TA, de Faria PR, Neves LA, do Nascimento MZ. Azevedo Tosta TA, et al. Artif Intell Med. 2019 Apr;95:118-132. doi: 10.1016/j.artmed.2018.10.004. Epub 2018 Nov 9. Artif Intell Med. 2019. PMID: 30420242 Review.
Cited by
- Computational pathology: A survey review and the way forward.
Hosseini MS, Bejnordi BE, Trinh VQ, Chan L, Hasan D, Li X, Yang S, Kim T, Zhang H, Wu T, Chinniah K, Maghsoudlou S, Zhang R, Zhu J, Khaki S, Buin A, Chaji F, Salehi A, Nguyen BN, Samaras D, Plataniotis KN. Hosseini MS, et al. J Pathol Inform. 2024 Jan 14;15:100357. doi: 10.1016/j.jpi.2023.100357. eCollection 2024 Dec. J Pathol Inform. 2024. PMID: 38420608 Free PMC article. Review. - Deep Learning Methodologies Applied to Digital Pathology in Prostate Cancer: A Systematic Review.
Rabilloud N, Allaume P, Acosta O, De Crevoisier R, Bourgade R, Loussouarn D, Rioux-Leclercq N, Khene ZE, Mathieu R, Bensalah K, Pecot T, Kammerer-Jacquet SF. Rabilloud N, et al. Diagnostics (Basel). 2023 Aug 14;13(16):2676. doi: 10.3390/diagnostics13162676. Diagnostics (Basel). 2023. PMID: 37627935 Free PMC article. Review. - Artificial intelligence and digital pathology: clinical promise and deployment considerations.
Zarella MD, McClintock DS, Batra H, Gullapalli RR, Valante M, Tan VO, Dayal S, Oh KS, Lara H, Garcia CA, Abels E. Zarella MD, et al. J Med Imaging (Bellingham). 2023 Sep;10(5):051802. doi: 10.1117/1.JMI.10.5.051802. Epub 2023 Jul 31. J Med Imaging (Bellingham). 2023. PMID: 37528811 Free PMC article. Review. - Stain normalization in digital pathology: Clinical multi-center evaluation of image quality.
Michielli N, Caputo A, Scotto M, Mogetta A, Pennisi OAM, Molinari F, Balmativola D, Bosco M, Gambella A, Metovic J, Tota D, Carpenito L, Gasparri P, Salvi M. Michielli N, et al. J Pathol Inform. 2022 Sep 24;13:100145. doi: 10.1016/j.jpi.2022.100145. eCollection 2022. J Pathol Inform. 2022. PMID: 36268060 Free PMC article. - Breast histopathological image analysis using image processing techniques for diagnostic puposes: A methodological review.
Rashmi R, Prasad K, Udupa CBK. Rashmi R, et al. J Med Syst. 2021 Dec 3;46(1):7. doi: 10.1007/s10916-021-01786-9. J Med Syst. 2021. PMID: 34860316 Free PMC article. Review.
References
- Tabesh A, Teverovskiy M, Pang HY, Kumar VP, Verbel D, Kotsianti A, et al. Multifeature prostate cancer diagnosis and Gleason grading of histological images. IEEE Trans Med Imaging. 2007;26:1366–78. - PubMed
- Beck AH, Sangoi AR, Leung S, Marinelli RJ, Nielsen TO, van de Vijver MJ, et al. Systematic analysis of breast cancer morphology uncovers stromal features associated with survival. Sci Transl Med. 2011;3:108. - PubMed
- Vahadane A, Peng T, Albarqouni S, Baust M, Steiger K, Schlitter AM, et al. Structure-Preserved Color Normalization for Histological Images. International Symposium on Biomedical Imaging (ISBI): From Nano to Macro, New York, USA; April. 2015
- Khan AM, Rajpoot N, Treanor D, Magee D. A nonlinear mapping approach to stain normalization in digital histopathology images using image-specific color deconvolution. IEEE Trans Biomed Eng. 2014;61:1729–38. - PubMed
LinkOut - more resources
Full Text Sources
Other Literature Sources