DASGAN trains a segmentation network on semi-automatically labeled CK images via unpaired translation to PD-L1, enabling epithelium segmentation and TC score estimation without serial sections.
StainGAN: Stain Style Transfer for Digital Histological Images
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
abstract
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% increase in AUC. The code will be made publicly available.
fields
eess.IV 2years
2019 2verdicts
UNVERDICTED 2representative citing papers
Domain adaptation via stain normalization and unpaired translation generates synthetic labeled target images to train nuclei detection networks, reported superior to fully supervised intra-domain baselines.
citing papers explorer
-
DASGAN -- Joint Domain Adaptation and Segmentation for the Analysis of Epithelial Regions in Histopathology PD-L1 Images
DASGAN trains a segmentation network on semi-automatically labeled CK images via unpaired translation to PD-L1, enabling epithelium segmentation and TC score estimation without serial sections.
-
Domain Adaptation-based Augmentation for Weakly Supervised Nuclei Detection
Domain adaptation via stain normalization and unpaired translation generates synthetic labeled target images to train nuclei detection networks, reported superior to fully supervised intra-domain baselines.