In this section
@article{Yeung:2026:10.1109/OJEMB.2026.3687108,
author = {Yeung, M and Watts, T and Tan, SYW and Jing, P and Ferreira, PF and Scott, AD and Nielles-Vallespin, S and Yang, G},
doi = {10.1109/OJEMB.2026.3687108},
journal = {IEEE Open Journal of Engineering in Medicine and Biology},
title = {Stain consistency learning: handling stain variation for automatic digital pathology segmentation},
url = {http://dx.doi.org/10.1109/OJEMB.2026.3687108},
year = {2026}
}
TY - JOUR
AB - Stain variation poses a major challenge for automated digital pathology. Numerous techniques address this issue, yet show limited success, especially outside H&E stains and classification tasks. We propose Stain Consistency Learning (SCL), combining stain-specific augmentation and a novel consistency loss to learn stain-invariant features. We conduct the first large-scale evaluation of ten methods on Masson's trichrome and H&E datasets for segmentation. Our results demonstrate that traditional stain normalization offers little benefit, while stain augmentation and adversarial learning significantly improve performance. SCL consistently outperforms all other methods. Code is available at:https://github.com/mlyg/stain_consistency_learning.
AU - Yeung,M
AU - Watts,T
AU - Tan,SYW
AU - Jing,P
AU - Ferreira,PF
AU - Scott,AD
AU - Nielles-Vallespin,S
AU - Yang,G
DO - 10.1109/OJEMB.2026.3687108
PY - 2026///
SN - 2644-1276
TI - Stain consistency learning: handling stain variation for automatic digital pathology segmentation
T2 - IEEE Open Journal of Engineering in Medicine and Biology
UR - http://dx.doi.org/10.1109/OJEMB.2026.3687108
ER -
For enquiries about the MRI Physics Collective, please contact:
Mary Finnegan
Senior MR Physicist at the Imperial College Healthcare NHS Trust
Pete Lally
Assistant Professor in Magnetic Resonance (MR) Physics at Imperial College
Jan Sedlacik
MR Physicist at the Robert Steiner MR Unit, Hammersmith Hospital Campus