Improving diagnosis of congenital heart disease using deep learning
Toward efficient performance for deep learning on medical imaging
['FUNDING_R01'] · UNIVERSITY OF CALIFORNIA, SAN FRANCISCO · NIH-11051061
This study is working on using advanced computer technology to help doctors better spot congenital heart disease in unborn babies by looking at ultrasound images, making it easier to catch any issues early on during pregnancy.
Quick facts
| Phase | ['FUNDING_R01'] |
|---|---|
| Study type | Nih_funding |
| Sex | All |
| Sponsor | UNIVERSITY OF CALIFORNIA, SAN FRANCISCO (nih funded) |
| Locations | 1 site (SAN FRANCISCO, UNITED STATES) |
| Trial ID | NIH-11051061 on ClinicalTrials.gov |
What this research studies
This research focuses on enhancing the diagnosis and clinical decision-making for congenital heart disease (CHD) through advanced deep learning techniques. By analyzing a vast collection of imaging data from tens of thousands of patients across multiple clinical centers, the project aims to address the current challenges in prenatal detection of CHD, which is often underdiagnosed. The team is developing and optimizing deep learning models to improve the accuracy of fetal ultrasound interpretations, thereby increasing the detection rate of CHD during the second trimester. This innovative approach seeks to bridge the gap between theoretical detection capabilities and actual clinical outcomes.
Who could benefit from this research
Good fit: Ideal candidates for this research include pregnant individuals undergoing routine fetal ultrasounds during the second trimester.
Not a fit: Patients who are not pregnant or those whose fetuses do not have any risk factors for congenital heart disease may not benefit from this research.
Why it matters
Potential benefit: If successful, this research could significantly improve the early detection of congenital heart disease, leading to better clinical outcomes for affected infants.
How similar studies have performed: Previous research has demonstrated success in using deep learning for medical imaging, particularly in improving diagnostic accuracy in various conditions, indicating a promising potential for this approach.
Where this research is happening
SAN FRANCISCO, UNITED STATES
- UNIVERSITY OF CALIFORNIA, SAN FRANCISCO — SAN FRANCISCO, UNITED STATES (ACTIVE)
Researchers
- Principal investigator: ARNAOUT, RIMA — UNIVERSITY OF CALIFORNIA, SAN FRANCISCO
- Study coordinator: ARNAOUT, RIMA
About this research
- This is an active NIH-funded research project — typically early-stage science, not a clinical trial accepting patient enrollment.
- Some NIH-funded labs run parallel clinical studies or seek volunteers for related work. To check, contact the principal investigator or institution listed above.
- For full project details, budget, and progress reports, visit the official NIH RePORTER page below.