Deep learning-based quantitative histopathology of endoscopic biopsies in Crohn’s disease: a retrospective cross-sectional validation study - Report - MDSpire

Deep learning-based quantitative histopathology of endoscopic biopsies in Crohn’s disease: a retrospective cross-sectional validation study

  • By

  • Xin Jiang

  • Pan Li

  • Zhaojing Chen

  • Hui Yao

  • Hao Jia

  • Taiping Wang

  • Xuefeng Tang

  • June 5, 2026

  • 0 min

Share

Clinical Report: Quantitative Histopathological Analysis of Endoscopic Biopsies in Crohn's Disease

Overview

Expand on the specific AI-derived metrics and their implications for diagnostic accuracy.

Background

Crohn's disease is characterized by significant histopathological variability, complicating diagnosis and treatment. Conventional histologic assessments rely heavily on subjective visual evaluations, which can lead to inconsistencies and misdiagnoses. The integration of AI in histopathological analysis offers a promising solution to enhance objectivity and reproducibility in evaluating CD.

Data Highlights

MetricConcordance with Pathologist Assessment (CCC)
Crypt Abscess RatioGood
Cryptitis RatioGood
Submucosal Plasma Cell DensityWeak (0.376)

Key Findings

  • The deep learning framework achieved Dice coefficients and AUC values exceeding 0.95 for segmentation and classification tasks.
  • AI-derived crypt abscess and cryptitis ratios showed good concordance with pathologist assessments.
  • Submucosal plasma cell density demonstrated weaker agreement with pathologist evaluations (CCC = 0.376).
  • AI-derived features correlated with clinical activity indicators, albeit weakly to moderately.
  • Greater submucosal inflammatory infiltration was observed in CD biopsies compared to non-CD inflammatory colitis.

Clinical Implications

The AI-based framework can enhance the accuracy and reproducibility of histopathological assessments in Crohn's disease, potentially leading to better patient management. Clinicians should consider integrating these quantitative metrics into routine evaluations to improve diagnostic confidence.

Conclusion

The study presents a robust AI-driven approach for histopathological analysis in Crohn's disease, which may complement traditional methods and support standardized evaluations. Further validation in clinical settings is warranted to fully realize its potential.

Related Resources & Content

  1. Author(s)/Org, Source, Year -- Title
  2. Author(s)/Org, Source, Year -- Title
  3. Author(s)/Org, Source, Year -- Title
  4. Author(s)/Org, Source, Year -- Title
  5. Official journal of the American College of Gastroenterology | ACG, 2025 -- Clinical Guideline on Management of Crohn's Disease
  6. Efficacy and safety of mirikizumab in patients with moderately-to-severely active Crohn's disease, PubMed, 2023 -- Phase 3 Study
  7. Official journal of the American College of Gastroenterology | ACG
  8. Efficacy and safety of mirikizumab in patients with moderately-to-severely active Crohn's disease: a phase 3, multicentre, randomised, double-blind, placebo-controlled and active-controlled, treat-through study - PubMed

Original Source(s)

Related Content