Related Experiment Video
Updated: Jan 12, 2026
Hemodynamic Precision in the Neonatal Intensive Care Unit using Targeted Neonatal Echocardiography
Published on: January 27, 2023
Artificial Intelligence-Assisted Image Extraction in Neonatal Echocardiography for Congenital Heart Disease Diagnosis
Aminkeng Zawuo Leke1, Lionel Landry Sop Deffo1, Yunkavi Sabastian Wirsiy1
1Digital Technology and Innovation Hub, Health Research Foundation Buea, Buea, Cameroon.
Insights
This study develops an AI-assisted echocardiography system to improve congenital heart disease (CHD) diagnosis in Sub-Saharan Africa. The AI tool empowers nonexpert healthcare workers to capture accurate cardiac images for remote specialist interpretation, aiming to reduce under-5 mortality.
Area of Science:
- Medical Technology
- Artificial Intelligence in Healthcare
- Pediatric Cardiology
Background:
- Sub-Saharan Africa faces the highest global burden of under-5 mortality, with congenital heart disease (CHD) as a significant contributor.
- Limited diagnostic capacity and a shortage of specialized personnel hinder effective CHD diagnosis and care in resource-limited settings.
- Existing diagnostic methods like echocardiography require expert interpretation, posing a challenge in areas with scarce medical specialists.
Purpose of the Study:
- To develop an artificial intelligence (AI)-assisted echocardiography system for nonexpert operators.
- To enable nurses, midwives, and doctors to perform basic cardiac ultrasound sweeps on neonates with suspected CHD.
- To facilitate the extraction of accurate cardiac images for remote interpretation by pediatric cardiologists.
Main Methods:
- A 2-phase deep learning approach for real-time cardiac view detection in neonatal echocardiography.
- Utilizing diverse datasets from Cameroon and South Africa, with pretraining on retrospective data and fine-tuning on prospective data.
- Employing convolutional neural networks and long short-term memory layers, with reinforcement learning for dynamic feature extraction.
Main Results:
- Retrospective data collection initiated in September 2024, with 308 neonates' data collected and labeled to date.
- An initial AI model framework has been developed, and training has commenced.
- The project is in its intensive execution phase, with all objectives progressing in parallel and final results anticipated within 10 months.
Conclusions:
- The developed AI-assisted echocardiography model shows significant promise for enhancing early CHD diagnosis.
- This technology can improve CHD care in Sub-Saharan Africa and other low-resource settings.
- The system aims to bridge the diagnostic gap, reduce mortality, and increase access to expert cardiac interpretation.
Background:
Sub-Saharan Africa (SSA) bears the highest global burden of under-5 mortality, with congenital heart disease (CHD) as a major contributor. Despite advancements in high-income countries, CHD-related mortality in SSA remains largely unchanged due to limited diagnostic capacity and centralized health care. While pulse oximetry aids early detection, confirmation typically relies on echocardiography, a procedure constrained by a shortage of specialized personnel. Artificial intelligence (AI) offers a promising solution to bridge this diagnostic gap.
Objective:
This study aims to develop an AI-assisted echocardiography system that enables nonexpert operators, such as nurses, midwives, and medical doctors, to perform basic cardiac ultrasound sweeps on neonates suspected of CHD and extract accurate cardiac images for remote interpretation by a pediatric cardiologist.
Methods:
The study will use a 2-phase approach to develop a deep learning model for real-time cardiac view detection in neonatal echocardiography, utilizing data from St. Padre Pio Hospital in Cameroon and the Red Cross War Memorial Children's Hospital in South Africa to ensure demographic diversity. In phase 1, the model will be pretrained on retrospective data from nearly 500 neonates (0-28 days old). Phase 2 will fine-tune the model using prospective data from 1000 neonates, which include background elements absent in the retrospective dataset, enabling adaptation to local clinical environments. The datasets will consist of short and continuous echocardiographic video clips covering 10 standard cardiac views, as defined by the American Society of Echocardiography. The model architecture will leverage convolutional neural networks and convolutional long short-term memory layers, inspired by the interleaved visual memory framework, which integrates fast and slow feature extractors via a shared temporal memory mechanism. Video preprocessing, annotation with predefined cardiac view codes using Labelbox, and training with TensorFlow and PyTorch will be performed. Reinforcement learning will guide the dynamic use of feature extractors during training. Iterative refinement, informed by clinical input, will ensure that the model effectively distinguishes correct from incorrect views in real time, enhancing its usability in resource-limited settings.
Results:
Retrospective data collection for the project began in September 2024, and to date, data from 308 babies have been collected and labeled. In parallel, the initial model framework has been developed and training initiated using a subset of the labeled data. The project is currently in the intensive execution phase, with all objectives progressing in parallel and final results expected within 10 months.
Conclusions:
The AI-assisted echocardiography model developed in this project holds promise for improving early CHD diagnosis and care in SSA and other low-resource settings.
International Registered Report Identifier (Irrid):
DERR1-10.2196/75270.
