Virtual IHC Staining From H&E in Breast Cancer: A Benchmark of Deep Generative Models for HER2, ER, PgR and Ki-67
This review and benchmark evaluates deep generative models that virtually produce immunohistochemistry images for key breast cancer biomarkers (HER2, PgR, ER, Ki-67) directly from H&E-stained slides. Tested on public datasets, the study provides a practical comparison of state-of-the-art virtual staining techniques and serves as a resource for researchers and clinicians exploring cost-effective alternatives to physical IHC.
The original study
H&E to IHC virtual staining methods in breast cancer: an overview and benchmarking.
- Authors
- Klöckner P, Teixeira J, Montezuma D, Fraga J, Horlings HM, Cardoso JS, et al.
- Journal
- NPJ digital medicine
- Type
- Journal Article, Review
- PMID
- 40603634
Original abstract
Immunohistochemistry (IHC) is crucial for the clinical categorisation of breast cancer cases. Deep generative models may offer a cost-effective alternative by virtually generating IHC images from hematoxylin and eosin samples. This review explores the state-of-the-art in virtual staining for breast cancer biomarkers (HER2, PgR, ER and Ki-67) and benchmarks several models on public datasets. It serves as a resource for researchers and clinicians interested in applying or developing virtual staining techniques.