DUCK ‐Net: automated deep learning segmentation of ductular reactions in murine liver injury captures multicellular niche dynamics from H&E morphology
The Journal of Pathology · 2026-12 · 270 (4) · 441-454
DOI: 10.1002/path.70113 ↗At a glance
Journal article in The Journal of Pathology, published online on 2026-09-08. Written by Nathalie Feeley and 15 co-authors. Institution: Institute of Genetics and Cancer, University of Edinburgh, Edinburgh, UK. Major MEDLINE topics: Deep Learning, Liver, Chemical and Drug Induced Liver Injury, Cholestasis. 49 references. The full text is freely available (open access, CC BY 4.0). Funded by: AMMF The Cholangiocarcinoma Charity, IGC Langmuir Talent Development Fund (CRUK Scotland Centre), Wellcome Trust.
Abstract (original language)
Ductular reactions (DRs) are dynamic and complex multicellular responses that occur as a result of various hepatic injuries. Precise identification and quantification of the extent of DRs is a cornerstone of pre‐clinical modelling of liver disease, with links to inflammation, fibrosis, regeneration, and disease severity. Here, we apply a deep learning model, Deep Understanding Convolutional Kernel (DUCK‐Net), to the automated detection and segmentation of DRs in whole‐slide histopathological images of murine models of liver damage. Following annotation of a training dataset by a specialist liver histopathologist, we demonstrate accelerated performance and accurate detection, achieving a mean Dice coefficient (model‐expert segmentation overlap) of 85.4% and a specificity of 98%, indicating minimal false positives. Evaluation of model validity and utility was achieved with a histological time course of cholestatic injury and recovery using 3,5‐diethoxycarbonyl‐1,4‐dihydrocollidine diet (DDC) in mice. When assessed against a multiple linear regression model incorporating core epithelial and stromal components of the DR as quantified using immunohistochemistry (IHC), DUCK‐Net predicted the spatiotemporal response to injury and repair/resolution with a coefficient of determination ( R 2 ) of 0.88. Moreover, DUCK‐Net kinetics strongly correlated with published spatial transcriptomic (Stereo‐seq) analysis of the DDC model, demonstrating that H&E‐based segmentation captured molecular DR dynamics comparable to or exceeding that of individual IHC markers without the need for immunostaining. DUCK‐Net provides a novel and accessible platform for rapid, accurate histological quantification of liver injury reflective of the matrix‐rich, multicellular regenerative niche observed in DRs. © 2026 The Author(s). The Journal of Pathology published by John Wiley & Sons Ltd on behalf of The Pathological Society of Great Britain and Ireland.
Subjects
MeSH terms (MEDLINE)
Author keywords
Substances
Authors and institutions
- Institute of Genetics and Cancer, University of Edinburgh, Edinburgh, UK.
- Department of Oncology, University of Oxford, Oxford, UK.
- Institute of Regeneration and Repair, University of Edinburgh, Edinburgh, UK.
- Department of Clinical Surgery, University of Edinburgh, Edinburgh, UK.
- Centre for Medical Informatics, Usher Institute, University of Edinburgh, Edinburgh, UK.
- Edinburgh Pathology, University of Edinburgh, Edinburgh, UK.
ORCID profiles: Nathalie Feeley, Daniel Field, Steve Thorn, Wei-Yu Lu, Stephen J Wigmore, Timothy J Kendall, Rachel V Guest
Funding
- AMMF The Cholangiocarcinoma Charity
- IGC Langmuir Talent Development Fund (CRUK Scotland Centre)
- Wellcome Trust
Cite
APA
Feeley, N., Williams, K., McCaffrey, C., Field, D., Davies, K., Warden, H., Boulter, L., Thorn, S., Man, T. Y., Lu, W. Y., Wigmore, S. J., Harrison, E. M., Forbes, S. J., Tomlinson, I. P., Kendall, T. J., & Guest, R. V. (2026). DUCK ‐Net: automated deep learning segmentation of ductular reactions in murine liver injury captures multicellular niche dynamics from H&E morphology. The Journal of Pathology, 270(4), 441-454. https://doi.org/10.1002/path.70113
Vancouver
Feeley N, Williams K, McCaffrey C, Field D, Davies K, Warden H, et al. DUCK ‐Net: automated deep learning segmentation of ductular reactions in murine liver injury captures multicellular niche dynamics from H&E morphology. The Journal of Pathology. 2026;270(4):441-454. doi:10.1002/path.70113
BibTeX
@article{Feeley2026,
author = {Feeley, Nathalie and Williams, Kai and McCaffrey, Caitlin and Field, Daniel and Davies, Kyle and Warden, Hugh and Boulter, Luke and Thorn, Steve and Man, Tak Yung and Lu, Wei-Yu and Wigmore, Stephen J and Harrison, Ewen M and Forbes, Stuart J and Tomlinson, Ian P and Kendall, Timothy J and Guest, Rachel V},
title = {DUCK ‐Net: automated deep learning segmentation of ductular reactions in murine liver injury captures multicellular niche dynamics from H&E morphology},
journal = {The Journal of Pathology},
year = {2026},
volume = {270},
number = {4},
pages = {441--454},
doi = {10.1002/path.70113}
}
EUVIMED