TY - JOUR
T1 - Variational Bayesian Blind Color Deconvolution of Histopathological Images
AU - Hidalgo-Gavira, Natalia
AU - Mateos, Javier
AU - Vega, Miguel
AU - Molina, Rafael
AU - Katsaggelos, Aggelos K.
N1 - Funding Information:
Manuscript received March 14, 2019; revised September 1, 2019; accepted September 28, 2019. Date of publication October 15, 2019; date of current version December 30, 2019. This work was supported in part by the Spanish Min-isterio de Economía y Competitividad under Grant DPI2016-77869-C2-2-R and the Visiting Scholar Program at the University of Granada. The associate editor coordinating the review of this manuscript and approving it for publication was Dr. Christophoros Nikou. (Corresponding author: Javier Mateos.) N. Hidalgo-Gavira, J. Mateos, and R. Molina are with the Departamento de Ciencias de la Computación e I. A., Universidad de Granada, 18071 Granada, Spain (e-mail: jmd@decsai.ugr.es).
Publisher Copyright:
© 2019 IEEE.
PY - 2020
Y1 - 2020
N2 - Most whole-slide histological images are stained with two or more chemical dyes. Slide stain separation or color deconvolution is a crucial step within the digital pathology workflow. In this paper, the blind color deconvolution problem is formulated within the Bayesian framework. Starting from a multi-stained histological image, our model takes into account both spatial relations among the concentration image pixels and similarity between a given reference color-vector matrix and the estimated one. Using Variational Bayes inference, three efficient new blind color deconvolution methods are proposed which provide automated procedures to estimate all the model parameters in the problem. A comparison with classical and current state-of-the-art color deconvolution algorithms using real images has been carried out demonstrating the superiority of the proposed approach.
AB - Most whole-slide histological images are stained with two or more chemical dyes. Slide stain separation or color deconvolution is a crucial step within the digital pathology workflow. In this paper, the blind color deconvolution problem is formulated within the Bayesian framework. Starting from a multi-stained histological image, our model takes into account both spatial relations among the concentration image pixels and similarity between a given reference color-vector matrix and the estimated one. Using Variational Bayes inference, three efficient new blind color deconvolution methods are proposed which provide automated procedures to estimate all the model parameters in the problem. A comparison with classical and current state-of-the-art color deconvolution algorithms using real images has been carried out demonstrating the superiority of the proposed approach.
KW - Bayesian modeling and inference
KW - Blind color deconvolution
KW - histopathological images
KW - variational Bayes
UR - http://www.scopus.com/inward/record.url?scp=85077739541&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85077739541&partnerID=8YFLogxK
U2 - 10.1109/TIP.2019.2946442
DO - 10.1109/TIP.2019.2946442
M3 - Article
C2 - 31634128
AN - SCOPUS:85077739541
SN - 1057-7149
VL - 29
SP - 2026
EP - 2036
JO - IEEE Transactions on Image Processing
JF - IEEE Transactions on Image Processing
IS - 1
M1 - 8870230
ER -