1. Gemini-Assisted Deep Learning Classification Model for Automated Diagnosis of High-Resolution Esophageal Manometry Images.
- Author
-
Popa SL, Surdea-Blaga T, Dumitrascu DL, Pop AV, Ismaiel A, David L, Brata VD, Turtoi DC, Chiarioni G, Savarino EV, Zsigmond I, Czako Z, and Leucuta DC
- Subjects
- Humans, Image Processing, Computer-Assisted methods, Esophagus diagnostic imaging, Esophagus physiopathology, Esophagus physiology, Deep Learning, Manometry methods, Esophageal Motility Disorders diagnosis, Esophageal Motility Disorders classification, Esophageal Motility Disorders physiopathology
- 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.
- Published
- 2024
- Full Text
- View/download PDF