Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
August 16, 2026Communications MedicineOpen Access

Deep learning-based quantification of collagen and associated features from H&E-stained whole slide pathology images across cancer types

View Full Paper
Ask AI
Bookmark
Share

Authors

TNTan H. NguyenCritical Path InstituteJZJun ZhangCritical Path InstituteJHJennifer HippCritical Path Institute

Discussion

Loading...

Member takes

Implication

Computational study demonstrates deep learning-based collagen profiling from routine tumor biopsies, indicating structural fiber biomarkers predict survival in pancreatic adenocarcinoma.

Key Points

  • To develop and validate a deep learning model capable of detecting and quantifying collagen fiber morphology directly from standard hematoxylin and eosin (H&E) whole-slide images across multiple cancer types.
  • Trained the inferred quantitative multimodal anisotropy imaging (iQMAI) model using polarization images of picrosirius red-stained slides as ground truth.
  • Computed morphological fiber features—including density, tortuosity, length, width, and angle—across TCGA datasets for lung adenocarcinoma, lung squamous cell carcinoma, hepatocellular carcinoma, and pancreatic adenocarcinoma.
  • iQMAI-predicted collagen metrics and fiber features closely correlated with polarization-based ground truth across diverse cancer types.
  • In pancreatic adenocarcinoma, collagen fiber density and width negatively correlated with the immunosuppressive LRRC-15 fibroblast gene expression signature.
  • Increased collagen fiber width was significantly associated with improved overall survival in pancreatic adenocarcinoma.

Cite This Study

Nguyen et al. (2026) studied this question.

synapsesocial.com/papers/6a8179bcf2fb91fc834ad0a4https://doi.org/10.1038/s43856-026-01809-x
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Abstract 4167: Virtual inference of collagen architecture from H&E to characterize stromal fiber morphology and organization in colorectal cancer2026
  2. 2Abstract 4262: AI-driven analysis of collagen characteristics in the tumor immune microenvironment predicts immune checkpoint inhibitors treatment responsiveness in gastric cancer2024
  3. 3Deep learning layer-specific collagen quantification correlates with activity and is associated with outcomes in Crohn’s disease2026
  4. 4Abstract 914: Combination analysis of tumor-associated collagen frameworks and tumor immune phenotype of lung carcinomas using virtual staining2024
  5. 5Characterization of Collagen Fiber Organization in Breast Cancer via Model-Free Multiscale pSHG Image Analysis2026