Bayesian K-SVD for H and E blind color deconvolution. Applications to stain normalization, data augmentation and cancer classification. Pérez-Bueno, F., Serra, J. G., Vega, M., Mateos, J., Molina, R., & Katsaggelos, A. K. Computerized Medical Imaging and Graphics, 97:102048, apr, 2022. ![Bayesian K-SVD for H and E blind color deconvolution. Applications to stain normalization, data augmentation and cancer classification [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper doi abstract bibtex Stain variation between images is a main issue in the analysis of histological images. These color variations, produced by different staining protocols and scanners in each laboratory, hamper the performance of computer-aided diagnosis (CAD) systems that are usually unable to generalize to unseen color distributions. Blind color deconvolution techniques separate multi-stained images into single stained bands that can then be used to reduce the generalization error of CAD systems through stain color normalization and/or stain color augmentation. In this work, we present a Bayesian modeling and inference blind color deconvolution framework based on the K-Singular Value Decomposition algorithm. Two possible inference procedures, variational and empirical Bayes are presented. Both provide the automatic estimation of the stain color matrix, stain concentrations and all model parameters. The proposed framework is tested on stain separation, image normalization, stain color augmentation, and classification problems.
@article{Fernando2022,
abstract = {Stain variation between images is a main issue in the analysis of histological images. These color variations, produced by different staining protocols and scanners in each laboratory, hamper the performance of computer-aided diagnosis (CAD) systems that are usually unable to generalize to unseen color distributions. Blind color deconvolution techniques separate multi-stained images into single stained bands that can then be used to reduce the generalization error of CAD systems through stain color normalization and/or stain color augmentation. In this work, we present a Bayesian modeling and inference blind color deconvolution framework based on the K-Singular Value Decomposition algorithm. Two possible inference procedures, variational and empirical Bayes are presented. Both provide the automatic estimation of the stain color matrix, stain concentrations and all model parameters. The proposed framework is tested on stain separation, image normalization, stain color augmentation, and classification problems.},
author = {P{\'{e}}rez-Bueno, Fernando and Serra, Juan G. and Vega, Miguel and Mateos, Javier and Molina, Rafael and Katsaggelos, Aggelos K.},
doi = {10.1016/j.compmedimag.2022.102048},
issn = {08956111},
journal = {Computerized Medical Imaging and Graphics},
keywords = {Bayesian modeling,Blind Color Deconvolution,Histological images,Stain Normalization},
month = {apr},
pages = {102048},
pmid = {35202893},
title = {{Bayesian K-SVD for H and E blind color deconvolution. Applications to stain normalization, data augmentation and cancer classification}},
url = {https://linkinghub.elsevier.com/retrieve/pii/S0895611122000210},
volume = {97},
year = {2022}
}
Downloads: 0
{"_id":"pyukgHwnrib7njSHG","bibbaseid":"prezbueno-serra-vega-mateos-molina-katsaggelos-bayesianksvdforhandeblindcolordeconvolutionapplicationstostainnormalizationdataaugmentationandcancerclassification-2022","author_short":["Pérez-Bueno, F.","Serra, J. G.","Vega, M.","Mateos, J.","Molina, R.","Katsaggelos, A. K."],"bibdata":{"bibtype":"article","type":"article","abstract":"Stain variation between images is a main issue in the analysis of histological images. These color variations, produced by different staining protocols and scanners in each laboratory, hamper the performance of computer-aided diagnosis (CAD) systems that are usually unable to generalize to unseen color distributions. Blind color deconvolution techniques separate multi-stained images into single stained bands that can then be used to reduce the generalization error of CAD systems through stain color normalization and/or stain color augmentation. In this work, we present a Bayesian modeling and inference blind color deconvolution framework based on the K-Singular Value Decomposition algorithm. Two possible inference procedures, variational and empirical Bayes are presented. Both provide the automatic estimation of the stain color matrix, stain concentrations and all model parameters. The proposed framework is tested on stain separation, image normalization, stain color augmentation, and classification problems.","author":[{"propositions":[],"lastnames":["Pérez-Bueno"],"firstnames":["Fernando"],"suffixes":[]},{"propositions":[],"lastnames":["Serra"],"firstnames":["Juan","G."],"suffixes":[]},{"propositions":[],"lastnames":["Vega"],"firstnames":["Miguel"],"suffixes":[]},{"propositions":[],"lastnames":["Mateos"],"firstnames":["Javier"],"suffixes":[]},{"propositions":[],"lastnames":["Molina"],"firstnames":["Rafael"],"suffixes":[]},{"propositions":[],"lastnames":["Katsaggelos"],"firstnames":["Aggelos","K."],"suffixes":[]}],"doi":"10.1016/j.compmedimag.2022.102048","issn":"08956111","journal":"Computerized Medical Imaging and Graphics","keywords":"Bayesian modeling,Blind Color Deconvolution,Histological images,Stain Normalization","month":"apr","pages":"102048","pmid":"35202893","title":"Bayesian K-SVD for H and E blind color deconvolution. Applications to stain normalization, data augmentation and cancer classification","url":"https://linkinghub.elsevier.com/retrieve/pii/S0895611122000210","volume":"97","year":"2022","bibtex":"@article{Fernando2022,\nabstract = {Stain variation between images is a main issue in the analysis of histological images. These color variations, produced by different staining protocols and scanners in each laboratory, hamper the performance of computer-aided diagnosis (CAD) systems that are usually unable to generalize to unseen color distributions. Blind color deconvolution techniques separate multi-stained images into single stained bands that can then be used to reduce the generalization error of CAD systems through stain color normalization and/or stain color augmentation. In this work, we present a Bayesian modeling and inference blind color deconvolution framework based on the K-Singular Value Decomposition algorithm. Two possible inference procedures, variational and empirical Bayes are presented. Both provide the automatic estimation of the stain color matrix, stain concentrations and all model parameters. The proposed framework is tested on stain separation, image normalization, stain color augmentation, and classification problems.},\nauthor = {P{\\'{e}}rez-Bueno, Fernando and Serra, Juan G. and Vega, Miguel and Mateos, Javier and Molina, Rafael and Katsaggelos, Aggelos K.},\ndoi = {10.1016/j.compmedimag.2022.102048},\nissn = {08956111},\njournal = {Computerized Medical Imaging and Graphics},\nkeywords = {Bayesian modeling,Blind Color Deconvolution,Histological images,Stain Normalization},\nmonth = {apr},\npages = {102048},\npmid = {35202893},\ntitle = {{Bayesian K-SVD for H and E blind color deconvolution. Applications to stain normalization, data augmentation and cancer classification}},\nurl = {https://linkinghub.elsevier.com/retrieve/pii/S0895611122000210},\nvolume = {97},\nyear = {2022}\n}\n","author_short":["Pérez-Bueno, F.","Serra, J. G.","Vega, M.","Mateos, J.","Molina, R.","Katsaggelos, A. K."],"key":"Fernando2022","id":"Fernando2022","bibbaseid":"prezbueno-serra-vega-mateos-molina-katsaggelos-bayesianksvdforhandeblindcolordeconvolutionapplicationstostainnormalizationdataaugmentationandcancerclassification-2022","role":"author","urls":{"Paper":"https://linkinghub.elsevier.com/retrieve/pii/S0895611122000210"},"keyword":["Bayesian modeling","Blind Color Deconvolution","Histological images","Stain Normalization"],"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://sites.northwestern.edu/ivpl/files/2023/06/IVPL_Updated_publications-1.bib","dataSources":["KTWAakbPXLGfYseXn","ePKPjG8C6yvpk4mEK","ya2CyA73rpZseyrZ8","zFPgsTDAW8aDnb5iN","E6Bth2QB5BYjBMZE7","nbnEjsN7MJhurAK9x","PNQZj6FjzoxxJk4Yi","7FpDWDGJ4KgpDiGfB","bod9ms4MQJHuJgPpp","QR9t5P2cLdJuzhfzK","D8k2SxfC5dKNRFgro","7Dwzbxq93HWrJEhT6","qhF8zxmGcJfvtdeAg","fvDEHD49E2ZRwE3fb","H7crv8NWhZup4d4by","DHqokWsryttGh7pJE","vRJd4wNg9HpoZSMHD","sYxQ6pxFgA59JRhxi","w2WahSbYrbcCKBDsC","XasdXLL99y5rygCmq","3gkSihZQRfAD2KBo3","t5XMbyZbtPBo4wBGS","bEpHM2CtrwW2qE8FP","teJzFLHexaz5AQW5z"],"keywords":["bayesian modeling","blind color deconvolution","histological images","stain normalization"],"search_terms":["bayesian","svd","blind","color","deconvolution","applications","stain","normalization","data","augmentation","cancer","classification","pérez-bueno","serra","vega","mateos","molina","katsaggelos"],"title":"Bayesian K-SVD for H and E blind color deconvolution. Applications to stain normalization, data augmentation and cancer classification","year":2022}