StainGAN: Stain Style Transfer for Digital Histological Images

04/04/2018

∙

by   M Tarek Shaban, et al.

∙

0

∙

share

Digitized Histological diagnosis is in increasing demand. However, color variations due to various factors are imposing obstacles to the diagnosis process. The problem of stain color variations is a well-defined problem with many proposed solutions. Most of these solutions are highly dependent on a reference template slide. We propose a deep-learning solution inspired by CycleGANs that is trained end-to-end, eliminating the need for an expert to pick a representative reference slide. Our approach showed superior results quantitatively and qualitatively against the state of the art methods (10 improvement visually using SSIM). We further validated our method on a clinical use-case, namely Breast Cancer tumor classification, showing 12 AUC. The code will be made publicly available.