Enhanced Cycle-Consistent Generative Adversarial Network for Color Normalization of H&E Stained Images

Due to differences in tissue preparations, staining protocols and scanner models, stain colors of digitized histological images are excessively diverse. Color normalization is almost a necessary procedure for quantitative digital pathology analysis. Though several color normalization methods have been proposed, most of them depend on selection of representative templates and may fail in regions not matching the templates. We propose an enhanced cycle-GAN based method with a novel auxiliary input for the generator by computing a stain color matrix for every H&E image in the training set. The matrix guides the translation in the generator, and thus stabilizes the cycle consistency loss. We applied our proposed method as a pre-processing step for a breast metastasis classification task on a dataset from five medical centers and achieved the highest performance compared to other color normalization methods. Furthermore, our method is template-free and may be applied to other datasets without finetuning.

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

[2]  Joakim Lindblad,et al.  Blind Color Decomposition of Histological Images , 2013, IEEE Transactions on Medical Imaging.

[3]  Li Fei-Fei,et al.  Perceptual Losses for Real-Time Style Transfer and Super-Resolution , 2016, ECCV.

[4]  Nasir M. Rajpoot,et al.  A Nonlinear Mapping Approach to Stain Normalization in Digital Histopathology Images Using Image-Specific Color Deconvolution , 2014, IEEE Transactions on Biomedical Engineering.

[5]  Andrew Janowczyk,et al.  Stain Normalization using Sparse AutoEncoders (StaNoSA): Application to digital pathology , 2017, Comput. Medical Imaging Graph..

[6]  Alexei A. Efros,et al.  Image-to-Image Translation with Conditional Adversarial Networks , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[7]  Erik Reinhard,et al.  Color Transfer between Images , 2001, IEEE Computer Graphics and Applications.

[8]  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.

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

[10]  Ghassan Hamarneh,et al.  Adversarial Stain Transfer for Histopathology Image Analysis , 2018, IEEE Transactions on Medical Imaging.

[11]  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).

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

[13]  Tomas Pfister,et al.  Learning from Simulated and Unsupervised Images through Adversarial Training , 2016, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).