Gemini-Assisted Deep Learning Classification Model for Automated Diagnosis of High-Resolution Esophageal Manometry Images

Public Deposited
Analytics

Downloadable Content

Download PDF
Request Version for Screen Reader
Creator
  • Popa, Stefan Lucian
    • Other Affiliation: Second Medical Department, “Iuliu Hatieganu” University of Medicine and Pharmacy, Cluj-Napoca, Romania
  • Surdea-Blaga, Teodora
    • Other Affiliation: Second Medical Department, “Iuliu Hatieganu” University of Medicine and Pharmacy, Cluj-Napoca, Romania
  • Dumitrascu, Dan Lucian
    • Other Affiliation: Second Medical Department, “Iuliu Hatieganu” University of Medicine and Pharmacy, Cluj-Napoca, Romania
  • Pop, Andrei Vasile
    • Other Affiliation: Second Medical Department, “Iuliu Hatieganu” University of Medicine and Pharmacy, Cluj-Napoca, Romania
  • Ismaiel, Abdulrahman
    • Other Affiliation: Second Medical Department, “Iuliu Hatieganu” University of Medicine and Pharmacy, Cluj-Napoca, Romania
  • David, Liliana
    • Other Affiliation: Second Medical Department, “Iuliu Hatieganu” University of Medicine and Pharmacy, Cluj-Napoca, Romania
  • Brata, Vlad Dumitru
    • Other Affiliation: Faculty of Medicine, “Iuliu Hatieganu” University of Medicine and Pharmacy, Cluj-Napoca, Romania
  • Turtoi, Daria Claudia
    • Other Affiliation: Faculty of Medicine, “Iuliu Hatieganu” University of Medicine and Pharmacy, Cluj-Napoca, Romania
  • Chiarioni, Giuseppe
    • School of Medicine, Department of Medicine, Division of Gastroenterology and Hepatology, UNC Center for Functional GI and Motility Disorders
  • Savarino, Edoardo Vincenzo
    • Other Affiliation: Gastroenterology Unit, Department of Surgery, Oncology and Gastroenterology, University of Padua, Padova, Italy
  • Zsigmond, Imre
    • Other Affiliation: Faculty of Mathematics and Computer Science, Babes-Bolyai University, Cluj-Napoca, Romania
  • Czako, Zoltan
    • Other Affiliation: Computer Science Department, Technical University of Cluj-Napoca, Cluj-Napoca, Romania
  • Leucuta, Daniel Corneliu
    • Other Affiliation: Department of Medical Informatics and Biostatistics, “Iuliu Hatieganu” University of Medicine and Pharmacy, Cluj-Napoca, Romania
Abstract
  • Background/Objectives: To develop a deep learning model for esophageal motility disorder diagnosis using high-resolution manometry images with the aid of Gemini. Methods: Gemini assisted in developing this model by aiding in code writing, preprocessing, model optimization, and troubleshooting. Results: The model demonstrated an overall precision of 0.89 on the testing set, with an accuracy of 0.88, a recall of 0.88, and an F1-score of 0.885. It presented better results for multiple categories, particularly in the panesophageal pressurization category, with precision = 0.99 and recall = 0.99, yielding a balanced F1-score of 0.99. Conclusions: This study demonstrates the potential of artificial intelligence, particularly Gemini, in aiding the creation of robust deep learning models for medical image analysis, solving not just simple binary classification problems but more complex, multi-class image classification tasks.
Date of publication
Keyword
DOI
Identifier
Resource type
  • Article
Rights statement
  • In Copyright
Journal title
  • Medicina
Journal volume
  • 60
Journal issue
  • 9
Page start
  • 1493
ISSN
  • 1648-9144
  • 1010-660X
Publisher
  • MDPI

Relations

Parents:

This work has no parents.

In Collection:

Items

Thumbnail Title Date Uploaded Visibility Actions
file details medicina-60-01493.pdf 2024-09-24 Public Download