Abstract
This study aims to investigate the effectiveness of the YOLOv7 computer vision algorithm in analyzing medical images to predict the four main types of heart valve regurgitation. Additionally, the overall performance of the YOLOv7 baseline model in accurately detecting and characterizing regurgitation-related lesions is compared. Through comprehensive evaluations on various datasets of heart regurgitation, the aim is to deepen understanding of the capabilities and limitations of these models, comparing, and analyzing which model offers superior accuracy and computational efficiency. The results obtained from this study are expected to guide the selection of the most suitable model to develop automated and precise diagnostic tools for heart valve regurgitation, assisting healthcare professionals in diagnosing heart valve regurgitation and improving patient outcomes.
| Original language | English |
|---|---|
| Title of host publication | ASSE 2024 - 2024 5th Asia Service Sciences and Software Engineering Conference |
| Publisher | Association for Computing Machinery |
| Pages | 126-129 |
| Number of pages | 4 |
| ISBN (Electronic) | 9798400717543 |
| DOIs | |
| State | Published - 29 12 2024 |
| Event | 2024 5th Asia Service Sciences and Software Engineering Conference, ASSE 2024 - Tokyo, Japan Duration: 11 09 2024 → 13 09 2024 |
Publication series
| Name | ACM International Conference Proceeding Series |
|---|
Conference
| Conference | 2024 5th Asia Service Sciences and Software Engineering Conference, ASSE 2024 |
|---|---|
| Country/Territory | Japan |
| City | Tokyo |
| Period | 11/09/24 → 13/09/24 |
Bibliographical note
Publisher Copyright:© 2024 Copyright held by the owner/author(s).
Keywords
- Cardiac Regurgitation
- Computer Vision Algorithm
- Deep Learning Algorithm
- Medical Images
- YOLOv7