Pediatric Inflammatory Bowel Disease Tissue Classification From Pathology Slide Images: Detecting Phenotypes Using Computer Vision

Authors

• Chloe Martin-King, Children’s Health Orange County (CHOC)
• Ali Nael, Children’s Health Orange County (CHOC)
• Louis Ehwerhemuepha, Children’s Health Orange County (CHOC)
• Blake Calvo, Children’s Health Orange County (CHOC)
• Quinn Gates, Children’s Health Orange County (CHOC)
• Jamie Janchoi, Children’s Health Orange County (CHOC)
• Elisa Ornelas, Children’s Health Orange County (CHOC)
• Melissa Perez, Children’s Health Orange County (CHOC)
• Andrea Venderby, Children’s Health Orange County (CHOC)
• John Miklavcic, Chapman UniversityFollow
• Peter Chang, University of California, Irvine
• Aaron Sassoon, Children’s Health Orange County (CHOC)
• Brian Rubio, California State University, Fullerton
• Ghislaine Barrigan, University of San Diego
• Kenneth Grant, Children’s Health Orange County (CHOC)

Document Type

Article

Publication Date

2-14-2026

Abstract

Background and Aims

With the advent of computer vision algorithms, we hypothesize that histopathology images from endoscopic biopsies may be utilized for automated classification of histologic phenotypes, thus guiding Crohn’s disease and ulcerative colitis diagnosis and treatment. The aim of our study is to assess whether artificial intelligence can be used to improve pediatric inflammatory bowel disease outcomes by aiding pathologists with accurate detection of abnormal tissue sections.

Methods

Three two-dimensional (2D) convolutional neural networks with multiple instance learning were developed to classify histopathology tissue sections as normal vs abnormal and as containing active inflammation and/or chronic changes/architectural distortion.

Results

The abnormal vs normal classification model achieved an accuracy of 0.84, an area under the receiver operating characteristic curve (AUC-ROC) of 0.91, and an F1-score of 0.79. Precision, sensitivity, and specificity were 0.85, 0.74, and 0.91, respectively. The accuracy for predicting active inflammation was 0.85, AUC-ROC was 0.92, and F1-score was 0.78. The accuracy for predicting chronic changes/architectural distortion was 0.86, with an AUC-ROC of 0.93 and an F1-score of 0.76. All 3 models achieved a Matthews correlation coefficient of 0.67.

Conclusion

The findings resulting from this study are significant primarily because they indicate that there is a strong artificial intelligence–interpretable signal present in endoscopic whole slide imaging, even with the necessary, weakly supervised method of multiple instance learning.

Comments

This article was originally published in Gastro Hep Advances, volume 5, issue 5, in 2026. https://doi.org/10.1016/j.gastha.2026.100899

Recommended Citation

Martin-King C, Nael A, Ehwerhemuepha L, et al. Pediatric inflammatory bowel disease tissue classification from pathology slide images: detecting phenotypes using computer vision. Gastro Hep Advances 2026;5:100899. https://doi.org/10.1016/j.gastha.2026.100899

Peer Reviewed

1

Copyright

The Authors. Published by Elsevier Inc. on behalf of the AGA Institute

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 License.