Skip to content
DraconiticResearch
Search Sources API
201,683 studies31 sourcesUpdated 30 min ago
Peer-reviewedCC BY 4.0The Journal of Pathology

DUCK‐Net: automated deep learning segmentation of ductular reactions in murine liver injury captures multicellular niche dynamics from H&E morphology

  • Nathalie Feeley1
  • Kai Williams1
  • Caitlin McCaffrey1,2
  • Daniel Field1
  • Kyle Davies1
  • Hugh Warden1
  • Luke Boulter1
  • Steve Thorn1,2
  • Tak Yung Man3
  • Wei‐Yu Lu3
  • Stephen J Wigmore4,5
  • Ewen M Harrison4,5
4 more authors
  • Stuart J Forbes3
  • Ian P Tomlinson2
  • Timothy J Kendall3,6
  • Rachel V Guest1,4
6 affiliations
  1. 1Institute of Genetics and Cancer University of Edinburgh Edinburgh UK
  2. 2Department of Oncology University of Oxford Oxford UK
  3. 3Institute of Regeneration and Repair University of Edinburgh Edinburgh UK
  4. 4Department of Clinical Surgery University of Edinburgh Edinburgh UK
  5. 5Centre for Medical Informatics, Usher Institute University of Edinburgh Edinburgh UK
  6. 6Edinburgh Pathology University of Edinburgh Edinburgh UK
Read full textDOICite

Abstract

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.

Related

  1. A morphology-driven workflow to decipher 3D electron microscopy segmentation in diatoms
    Clarisse Uwizeye, Serena Flori, Joanell Angulo +4
    Cell Reports MethodsPeer-reviewedCC BY 4.0Full textBiophysicsHAL
  2. SpaCut: Transcript-Aware Morphology Fusion for Robust Cell Segmentation in Subcellular Spatial Transcriptomics.
    Yongheng Li, Fangfang Zhu, Wenwen Min
    Advanced science (Weinheim, Baden-Wurttemberg, Germany)Peer-reviewedCC BYFull textMolecular biology & gene regulationEurope PMCPMC
  3. Physics and Morphology Constrained Quantitative Susceptibility Based Segmentation of Cerebral Veins
    Y. C. Al-Khoury, A. Rezaei, V. Raspa +5
    bioRxivPreprintCC BYFull textBiophysicsbioRxiv
  4. Deepweed: automated individual segmentation and tracking for duckweed lineage analysis
    Tolulope Oyeniran, Bukola Akindipe, Tasmia Islam +3
    BioinformaticsPeer-reviewedCC BY 4.0Full textBiophysicsCrossrefPMC
  5. Improving Molecular-Morphology Contrastive Pretraining using Deep-Learning-based Morphology Profiles
    Jie Li, Kathryn E. Kirchoff, Dante A. Pertusi +1
    arXivPreprintCC BY 4.0Full textBiophysicsarXiv

Cite

BibTeXRIS
BibTeX
@article{feeley2026ducknet,
  title = {{DUCK‐Net: automated deep learning segmentation of ductular reactions in murine liver injury captures multicellular niche dynamics from H&E morphology}},
  author = {Nathalie Feeley and Kai Williams and Caitlin McCaffrey and Daniel Field and Kyle Davies and Hugh Warden and Luke Boulter and Steve Thorn and Tak Yung Man and Wei‐Yu Lu and Stephen J Wigmore and Ewen M Harrison and Stuart J Forbes and Ian P Tomlinson and Timothy J Kendall and Rachel V Guest},
  journal = {The Journal of Pathology},
  year = {2026},
  month = sep,
  doi = {10.1002/path.70113},
  url = {https://doi.org/10.1002/path.70113},
  note = {CC BY 4.0},
}
RIS
TY  - JOUR
TI  - DUCK‐Net: automated deep learning segmentation of ductular reactions in murine liver injury captures multicellular niche dynamics from H&E morphology
AU  - Nathalie Feeley
AU  - Kai Williams
AU  - Caitlin McCaffrey
AU  - Daniel Field
AU  - Kyle Davies
AU  - Hugh Warden
AU  - Luke Boulter
AU  - Steve Thorn
AU  - Tak Yung Man
AU  - Wei‐Yu Lu
AU  - Stephen J Wigmore
AU  - Ewen M Harrison
AU  - Stuart J Forbes
AU  - Ian P Tomlinson
AU  - Timothy J Kendall
AU  - Rachel V Guest
PY  - 2026
DA  - 2026/09/08
JO  - The Journal of Pathology
DO  - 10.1002/path.70113
UR  - https://doi.org/10.1002/path.70113
AB  - 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.
SN  - 0022-3417
SN  - 1096-9896
ER  -