Related Experiment Video
Updated: Jun 18, 2026
09:15
Creation of Patient-Specific Silicone Cardiac Models with Applications in Pre-surgical Plans and Hands-on Training
Published on: February 10, 2022
3.4K
A Real-Time End-to-End Framework with a Stacked Model Using Ultrasound Video for Cardiac Septal Defect
Siti Nurmaini1, Ria Nova2, Ade Iriani Sapitri1
1Intelligent System Research Group, Universitas Sriwijaya, Palembang 30139, Indonesia.
Journal of Imaging
|November 26, 2024
Summary
This study introduces a deep learning framework using Yolov8l for real-time diagnosis of cardiac septal defects (CSDs) in pediatric echocardiography. The model achieves high accuracy, improving efficiency and patient outcomes.
Area of Science:
- Cardiology
- Medical Imaging
- Artificial Intelligence
Background:
- Echocardiography is the standard for diagnosing cardiac septal defects (CSDs), but expert analysis is time-consuming.
- Digitization and deep learning (DL) offer potential to enhance diagnostic efficiency.
Purpose of the Study:
- To develop and evaluate a real-time, end-to-end deep learning framework for pediatric echocardiography video analysis.
- To improve the accuracy and efficiency of cardiac septal defect (CSD) diagnosis.
Main Methods:
- An advanced real-time architecture based on You Only Look Once (Yolo) techniques, specifically Yolov8l, was employed.
- The framework was trained and tested on pediatric ultrasound (US) videos for CSD decision-making.
Main Results:
- The Yolov8l model achieved a mean average precision (mAP) exceeding 89% in experiments.
- In testing with 222 US videos, the model showed 95.86% accuracy, 96.82% sensitivity, and 98.74% specificity.
- Real-time testing on 53 videos demonstrated 97.17% accuracy, 95.80% sensitivity, and 98.15% specificity.
Conclusions:
- The proposed deep learning framework demonstrates high accuracy and effectiveness for real-time CSD diagnosis in pediatric echocardiography.
- This approach shows promise for enhancing clinical decision-making and improving patient outcomes in pediatric cardiology.
