Bayesian K-SVD for H and E blind color deconvolution. Applications to stain normalization, data augmentation and cancer classification. (April 2022)

• Record Type: Journal Article
• Authors: Pérez-Bueno, Fernando; Serra, Juan G.; Vega, Miguel; Mateos, Javier; Molina, Rafael; Katsaggelos, Aggelos K.
• Is Part Of: Computerized medical imaging and graphics. Volume 97(2022)
• Publication Date: 2022-04
• Subjects: Bayesian modeling -- Histological images -- Blind Color Deconvolution -- Stain Normalization; Diagnostic imaging -- Periodicals; Imaging systems in medicine -- Periodicals; Diagnosis, Radioscopic -- Data processing -- Periodicals; Diagnostic Imaging -- Periodicals; Imagerie pour le diagnostic -- Périodiques; Diagnostic imaging; Periodicals; Electronic journals; Electronic journals; 616.0754
• DOI: 10.1016/j.compmedimag.2022.102048
• Languages: English
• ISSNs: 0895-6111

Abstract

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. Highlights: Stain variation is a critical issue in histopathological image analysis. Blind Color Deconvolution is used to deal with stain variation using different techniques. Bayesian K-SVD decomposition identifies the stain color and produces an accurate stain separation. Application to gigapixel whole-slide images is challenging and requires domain-specific adaptation.