Related Experiment Video
Updated: Aug 16, 2025
06:09
Author Spotlight: Advancing Hepatic Fibrosis Diagnosis Using Magnetic Resonance Elastography and AI
Published on: July 21, 2023
1.3K
Automatic Diagnosis of High-Resolution Esophageal Manometry Using Artificial Intelligence
Stefan Lucian Popa1, Teodora Surdea-Blaga2, Dan Lucian Dumitrascu3
12nd Medical Department, "Iuliu Hatieganu" University of Medicine and Pharmacy, Cluj-Napoca, Romania. . popa.stefan@umfcluj.ro.
Journal of Gastrointestinal and Liver Diseases : JGLD
|December 19, 2022
Summary
Artificial intelligence (AI) can now automatically diagnose esophageal motility disorders (EMDs) using high-resolution esophageal manometry (HREM) images. This AI system achieved over 93% accuracy, offering a more efficient diagnostic approach for EMDs.
Area of Science:
- Gastroenterology
- Medical Imaging
- Artificial Intelligence
Background:
- High-resolution esophageal manometry (HREM) is the standard for diagnosing esophageal motility disorders (EMDs).
- Interpreting HREM images can be subjective, highlighting the need for objective diagnostic tools.
- Artificial intelligence (AI) offers potential for automated, accurate EMD diagnosis from HREM data.
Purpose of the Study:
- To develop and evaluate an AI-based system for the automatic diagnosis of EMDs.
- The system utilizes neural networks to analyze raw HREM images from single wet swallows.
Main Methods:
- Retrospective analysis of HREM recordings by experienced gastroenterologists to confirm diagnoses.
- Training an artificial neural network (Inception V3 CNN) on 1570 HREM images across 10 EMD categories (Chicago Classification v3.0).
- Image preprocessing included cropping, binarization, and splitting into training, testing, and validation sets.
Main Results:
- The AI algorithm achieved high accuracy in classifying HREM images.
- Overall precision of the automated diagnostic system exceeded 93%.
- The neural network successfully categorized HREM images into specific EMD diagnoses.
Conclusions:
- An AI-powered approach using HREM images enables accurate, automated diagnosis of EMDs.
- This technology has the potential to improve the efficiency and objectivity of EMD diagnosis.
