Fully Automatic Blind Color Deconvolution of Histological Images Using Super Gaussians

In digital pathology blind color deconvolution techniques separate multi-stained images into single stained bands. These band images are then used for image analysis and classification purposes. This paper proposes the use of Super Gaussian priors for each stain band together with the similarity to a given reference matrix for the color vectors. Variational inference and an evidence lower bound are then utilized to automatically estimate the latent variables and model parameters. The proposed methodology is tested on real images and compared to classical and state-of-the-art methods for histopathological blind image color deconvolution. Its use as a preprocessing step in prostate cancer classification is also analysed.

[1]  A. Ruifrok,et al.  Quantification of histochemical staining by color deconvolution. , 2001, Analytical and quantitative cytology and histology.

[2]  Peter H. N. de With,et al.  Stain normalization of histopathology images using generative adversarial networks , 2018, 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018).

[3]  Nasir M. Rajpoot,et al.  Stain deconvolution of histology images via independent component analysis in the wavelet domain , 2016, 2016 IEEE 13th International Symposium on Biomedical Imaging (ISBI).

[4]  Egor Krivov,et al.  Ensembling Neural Networks for Digital Pathology Images Classification and Segmentation , 2018, ICIAR.

[5]  Nassir Navab,et al.  Staingan: Stain Style Transfer for Digital Histological Images , 2018, 2019 IEEE 16th International Symposium on Biomedical Imaging (ISBI 2019).

[6]  Kaisa Liimatainen,et al.  Metastasis detection from whole slide images using local features and random forests , 2017, Cytometry. Part A : the journal of the International Society for Analytical Cytology.

[7]  Aggelos K. Katsaggelos,et al.  Bayesian Blind Deconvolution with General Sparse Image Priors , 2012, ECCV.

[8]  Aggelos K. Katsaggelos,et al.  Fully Automated Blind Color Deconvolution of Histopathological Images , 2018, MICCAI.

[9]  Jelena Kovacevic,et al.  Algorithm and benchmark dataset for stain separation in histology images , 2014, 2014 IEEE International Conference on Image Processing (ICIP).

[10]  Nasir M. Rajpoot,et al.  Stain Deconvolution Using Statistical Analysis of Multi-Resolution Stain Colour Representation , 2017, PloS one.

[11]  Evgueni A. Haroutunian,et al.  Information Theory and Statistics , 2011, International Encyclopedia of Statistical Science.

[12]  Nassir Navab,et al.  Structure-Preserving Color Normalization and Sparse Stain Separation for Histological Images , 2016, IEEE Transactions on Medical Imaging.

[13]  Aggelos K. Katsaggelos,et al.  Variational Bayes Color Deconvolution with a Total Variation Prior , 2019, 2019 27th European Signal Processing Conference (EUSIPCO).

[14]  丸山 徹.  Convex Analysisの二,三の進展について , 1977 .

[15]  Zhiguo Jiang,et al.  Adaptive color deconvolution for histological WSI normalization , 2019, Comput. Methods Programs Biomed..

[16]  Jan Larsen,et al.  Unmixing of Hyperspectral Images using Bayesian Non-negative Matrix Factorization with Volume Prior , 2011, J. Signal Process. Syst..

[17]  Xu Zhou,et al.  Fast Bayesian blind deconvolution with Huber Super Gaussian priors , 2017, Digit. Signal Process..

[18]  J. S. Marron,et al.  A method for normalizing histology slides for quantitative analysis , 2009, 2009 IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[19]  Christopher K. I. Williams,et al.  Gaussian Processes for Machine Learning (Adaptive Computation and Machine Learning) , 2005 .

[20]  Aggelos K. Katsaggelos,et al.  Blind Color Deconvolution of Histopathological Images Using a Variational Bayesian Approach , 2018, 2018 25th IEEE International Conference on Image Processing (ICIP).

[21]  Serge J. Belongie,et al.  Unsupervised Color Decomposition Of Histologically Stained Tissue Samples , 2003, NIPS.

[22]  Aggelos K. Katsaggelos,et al.  A TV-based image processing framework for blind color deconvolution and classification of histological images , 2020, Digit. Signal Process..

[23]  Shyam Lal,et al.  A study about color normalization methods for histopathology images. , 2018, Micron.

[24]  Miguel Vega,et al.  Variational Bayesian Blind Color Deconvolution of Histopathological Images , 2020, IEEE Transactions on Image Processing.

[25]  Neil D. Lawrence,et al.  Deep Gaussian Processes , 2012, AISTATS.

[26]  Zhenhua Guo,et al.  Rotation invariant texture classification using LBP variance (LBPV) with global matching , 2010, Pattern Recognit..

[27]  Adrián Colomer,et al.  A new optical density granulometry-based descriptor for the classification of prostate histological images using shallow and deep Gaussian processes , 2019, Comput. Methods Programs Biomed..