Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Differences in time to drug initiation and inactive disease achievement by insurance type in patients with nonsystemic juvenile idiopathic arthritis.

Drugs & therapy perspectives : for rational drug selection and use·2026

Same author

Tasty&Healthy exclusive whole food diet in asymptomatic children and young adults with biologically active Crohn's disease: the TASTI-E randomized controlled trial.

Clinical gastroenterology and hepatology : the official clinical practice journal of the American Gastroenterological Association·2026

Same author

β-Glucan and Inulin Estimated Intake Are Associated With Reduced Risk of Crohn's Disease, Improved Gut Barrier and Systemic Inflammation Markers, and Multi-Omic Signatures in a High-Risk Cohort.

Gastroenterology·2026

Same author

Interleukin23 Receptor Genetic Variants Associate With Crohn's Disease Risk and Microbiome Changes in Healthy First-Degree Relatives.

Clinical gastroenterology and hepatology : the official clinical practice journal of the American Gastroenterological Association·2026

Same author

A comparative analysis of corticosteroids and exclusive enteral nutrition induction therapy in children with small bowel Crohn's disease: results of two prospective cohorts.

European journal of pediatrics·2026

Same author

Serum thiol redox-related alterations in asymptomatic first-degree relatives are associated with future Crohn's disease.

Redox biology·2026

Same journal

Response to Jamalinia and Lonardo.

Clinical and translational gastroenterology·2026

Same journal

The impact of obesity on inflammatory cytokines and 90- and 180-day survival in patients with alcohol-associated hepatitis.

Clinical and translational gastroenterology·2026

Same journal

Serum IFABP level as an index of mucosal health in celiac disease: a small intestinal morphometry study.

Clinical and translational gastroenterology·2026

Same journal

Global, regional and national burden of liver cancer in middle-aged and older adults from 1990 to 2021: a comprehensive analysis with cross-country inequality, decomposition, and frontier analysis.

Clinical and translational gastroenterology·2026

Same journal

Correction to: Serum and Urinary Metabolomics Reflect the Early Stages of De Novo Metabolic Syndrome After Liver Transplant: A 2-Center Longitudinal Study.

Clinical and translational gastroenterology·2026

Same journal

A Novel Endoscopic Biopsy Technique for Translational Research in Patients with Inflammatory Bowel Disease.

Clinical and translational gastroenterology·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Apr 29, 2026

Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis

Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis

Published on: June 18, 2020

Automated Eosinophil Quantification Using Deep Learning to Predict Therapy Escalation in Pediatric Ulcerative

James Reigle¹, Xiaoxuan Liu^1,2,3, Oscar Lopez-Nunez^4,5

¹Division of Gastroenterology, Hepatology and Nutrition, Cincinnati Children's Hospital Medical Center, Cincinnati, Ohio, USA.

Clinical and Translational Gastroenterology

|April 27, 2026

Summary

This summary is machine-generated.

Deep learning accurately quantifies eosinophils in pediatric ulcerative colitis (UC), identifying patients likely to respond to treatment or require escalation to anti-TNFα therapy.

Keywords:

U-Net artificial intelligence deep learning model eosinophils histopathology predictive modeling ulcerative colitis

More Related Videos

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

Automated Image-Based Quantification of Neutrophil Extracellular Traps Using NETQUANT

Automated Image-Based Quantification of Neutrophil Extracellular Traps Using NETQUANT

Published on: November 27, 2019

Related Experiment Videos

Last Updated: Apr 29, 2026

Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis

Supervised Machine Learning for Semi-Quantification of Extracellular DNA in Glomerulonephritis

Published on: June 18, 2020

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

Automated Image-Based Quantification of Neutrophil Extracellular Traps Using NETQUANT

Automated Image-Based Quantification of Neutrophil Extracellular Traps Using NETQUANT

Published on: November 27, 2019

Area of Science:

Gastroenterology
Computational Pathology
Pediatric Inflammatory Bowel Disease

Background:

Eosinophils are increasingly recognized as key players in ulcerative colitis (UC) disease activity and treatment response.
Manual eosinophil counting is labor-intensive and prone to variability.
Automated image analysis offers a scalable and reproducible method for eosinophil evaluation.

Purpose of the Study:

To develop and validate a deep learning (DL) model for automated eosinophil detection in pediatric UC.
To assess the association of eosinophil metrics with clinical, histologic, and endoscopic features.
To evaluate the predictive value of eosinophil counts for treatment outcomes.

Main Methods:

A U-Net-based DL model was trained on pathologist-annotated whole-slide images.
Model performance was benchmarked against other DL models and evaluated using AUROC, precision, recall, and F1 score.
The validated algorithm was applied to rectal biopsies from 221 treatment-naïve pediatric UC patients in the PROTECT cohort.

Main Results:

The DL model achieved high accuracy (AUROC=0.94, F1=0.86) and strong concordance with expert counts (ρ=0.87-0.89).
Higher eosinophil density correlated with basal lymphoid aggregates and predicted corticosteroid-free remission.
Lower eosinophil counts predicted the need for anti-TNFα therapy escalation.

Conclusions:

Automated eosinophil quantification using DL is a highly accurate and reproducible method.
Eosinophil metrics can serve as valuable biomarkers for risk stratification in pediatric UC.
This approach has the potential to guide therapeutic decisions and improve patient care.