Copertina

Contrastive virtual staining enhances deep learning-based PDAC subtyping from H&E-stained tissue cores

Pancreatic ductal adenocarcinoma (PDAC) subtyping typically relies on immunohistochemistry (IHC) staining for critical markers like HNF1A and KRT81, a labor-intensive manual staining process that introduces variability. Virtual staining methods offer promising alternatives by generating synthetic IH...

Descrizione completa

Salvato in:
Dettagli Bibliografici
Autori principali: Fischer, Maximilian (Autore) , Muckenhuber, Alexander (Autore) , Peretzke, Robin (Autore) , Farah, Luay (Autore) , Ulrich, Constantin (Autore) , Ziegler, Sebastian (Autore) , Schader, Philipp (Autore) , Feineis, Lorenz (Autore) , Gao, Hanno (Autore) , Xiao, Shuhan (Autore) , Götz, Michael (Autore) , Nolden, Marco (Autore) , Steiger, Katja (Autore) , Sieveke, Jens T (Autore) , Endrös, Lukas (Autore) , Braren, Rickmer (Autore) , Kleesiek, Jens Philipp (Autore) , Schüffler, Peter (Autore) , Neher, Peter (Autore) , Maier-Hein, Klaus H. (Autore)
Natura: Article (Journal)
Lingua:inglese
Pubblicazione: 2026
In: The journal of pathology
Year: 2026, Volume: 268, Fascicolo: 1, Pages: 89-98
ISSN:1096-9896
DOI:10.1002/path.6491
Accesso online:Verlag, kostenfrei, Volltext: https://doi.org/10.1002/path.6491
Verlag, kostenfrei, Volltext: https://onlinelibrary.wiley.com/doi/abs/10.1002/path.6491
Testo
Note sull'autore:Maximilian Fischer, Alexander Muckenhuber, Robin Peretzke, Luay Farah, Constantin Ulrich, Sebastian Ziegler, Philipp Schader, Lorenz Feineis, Hanno Gao, Shuhan Xiao, Michael Götz, Marco Nolden, Katja Steiger, Jens T Sieveke, Lukas Endrös, Rickmer Braren, Jens Kleesiek, Peter Schüffler, Peter Neher, Klaus Maier-Hein
Descrizione
Riassunto:Pancreatic ductal adenocarcinoma (PDAC) subtyping typically relies on immunohistochemistry (IHC) staining for critical markers like HNF1A and KRT81, a labor-intensive manual staining process that introduces variability. Virtual staining methods offer promising alternatives by generating synthetic IHC images from routine hematoxylin and eosin (H&E) slides. However, most current approaches evaluate success by image quality measures rather than assessing diagnostically relevant features. Here, we introduce a novel cycleGAN framework utilizing a contrastive-inspired approach trained on semipaired datasets derived from consecutive tissue sections. Our method significantly enhances PDAC subtyping accuracy based on synthetic IHC images generated from standard H&E inputs, improving the classification F1-score from 0.66 to 0.77 for KRT81 and from 0.61 to 0.73 for HNF1A, compared with classification directly on H&E images. This approach also substantially outperforms baseline CycleGAN models. These results underscore the clinical potential of contrastive virtual staining to streamline PDAC diagnostics and improve their robustness. © 2025 The Author(s). The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.
Descrizione del documento:Online veröffentlicht: 4. November 2025
Gesehen am 26.05.2026
Online veröffentlicht: 4. November 2025
Descrizione fisica:Online Resource
ISSN:1096-9896
DOI:10.1002/path.6491

Documenti analoghi