TY - JOUR
T1 - Blind color deconvolution, normalization, and classification of histological images using general super Gaussian priors and Bayesian inference
AU - Pérez-Bueno, Fernando
AU - Vega, Miguel
AU - Sales, María A.
AU - Aneiros-Fernández, José
AU - Naranjo, Valery
AU - Molina, Rafael
AU - Katsaggelos, Aggelos K.
N1 - Funding Information:
This work was sponsored in part by the Agencia Estatal de Investigación under project PID2019-105142RB-C22 / AEI / 10.13039/501100011033, Junta de Andalucía under project PY20_00286,and the work by Fernando Pérez-Bueno was sponsored by Ministerio de Economía, Industria y Competitividad under FPI contract BES-2017-081584. Funding for open access charge: Universidad de Granada / CBUA.
Publisher Copyright:
© 2021 The Author(s)
PY - 2021/11
Y1 - 2021/11
N2 - Background and Objective:Color variations in digital histopathology severely impact the performance of computer-aided diagnosis systems. They are due to differences in the staining process and acquisition system, among other reasons. Blind color deconvolution techniques separate multi-stained images into single stained bands which, once normalized, can be used to eliminate these negative color variations and improve the performance of machine learning tasks. Methods:In this work, we decompose the observed RGB image in its hematoxylin and eosin components. We apply Bayesian modeling and inference based on the use of Super Gaussian sparse priors for each stain together with prior closeness to a given reference color-vector matrix. The hematoxylin and eosin components are then used for image normalization and classification of histological images. The proposed framework is tested on stain separation, image normalization, and cancer classification problems. The results are measured using the peak signal to noise ratio, normalized median intensity and the area under ROC curve on five different databases. Results:The obtained results show the superiority of our approach to current state-of-the-art blind color deconvolution techniques. In particular, the fidelity to the tissue improves 1,27 dB in mean PSNR. The normalized median intensity shows a good normalization quality of the proposed approach on the tested datasets. Finally, in cancer classification experiments the area under the ROC curve improves from 0.9491 to 0.9656 and from 0.9279 to 0.9541 on Camelyon-16 and Camelyon-17, respectively, when the original and processed images are used. Furthermore, these figures of merits are better than those obtained by the methods compared with. Conclusions:The proposed framework for blind color deconvolution, normalization and classification of images guarantees fidelity to the tissue structure and can be used both for normalization and classification. In addition, color deconvolution enables the use of the optical density space for classification, which improves the classification performance.
AB - Background and Objective:Color variations in digital histopathology severely impact the performance of computer-aided diagnosis systems. They are due to differences in the staining process and acquisition system, among other reasons. Blind color deconvolution techniques separate multi-stained images into single stained bands which, once normalized, can be used to eliminate these negative color variations and improve the performance of machine learning tasks. Methods:In this work, we decompose the observed RGB image in its hematoxylin and eosin components. We apply Bayesian modeling and inference based on the use of Super Gaussian sparse priors for each stain together with prior closeness to a given reference color-vector matrix. The hematoxylin and eosin components are then used for image normalization and classification of histological images. The proposed framework is tested on stain separation, image normalization, and cancer classification problems. The results are measured using the peak signal to noise ratio, normalized median intensity and the area under ROC curve on five different databases. Results:The obtained results show the superiority of our approach to current state-of-the-art blind color deconvolution techniques. In particular, the fidelity to the tissue improves 1,27 dB in mean PSNR. The normalized median intensity shows a good normalization quality of the proposed approach on the tested datasets. Finally, in cancer classification experiments the area under the ROC curve improves from 0.9491 to 0.9656 and from 0.9279 to 0.9541 on Camelyon-16 and Camelyon-17, respectively, when the original and processed images are used. Furthermore, these figures of merits are better than those obtained by the methods compared with. Conclusions:The proposed framework for blind color deconvolution, normalization and classification of images guarantees fidelity to the tissue structure and can be used both for normalization and classification. In addition, color deconvolution enables the use of the optical density space for classification, which improves the classification performance.
KW - Blind color deconvolution
KW - Histopathological images
KW - Image normalization
KW - Super Gaussian
KW - Variational bayes
UR - http://www.scopus.com/inward/record.url?scp=85116921802&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85116921802&partnerID=8YFLogxK
U2 - 10.1016/j.cmpb.2021.106453
DO - 10.1016/j.cmpb.2021.106453
M3 - Article
C2 - 34649072
AN - SCOPUS:85116921802
VL - 211
JO - Computer Methods and Programs in Biomedicine
JF - Computer Methods and Programs in Biomedicine
SN - 0169-2607
M1 - 106453
ER -