A deep learning late-fusion model using sagittal T2 MRI predicts postpartum hemorrhage risk with high accuracy.
Key Details
- 1Study involved 581 pregnant women with suspected placenta accreta who underwent placental MRI from May 2018 to June 2024.
- 2Models compared: 2D and 3D deep learning, radiomics, clinical, and ensemble fusion models.
- 3Best performance: late-fusion deep learning model (validation set AUC: 0.90, sensitivity: 92%, specificity: 91%).
- 4MRI remains crucial for evaluating placental abnormalities; AI enhances risk prediction.
- 5Earlier identification enables tailored delivery planning and preparedness for hemorrhage risk.
Why It Matters
Effective AI-driven risk prediction could enable earlier intervention and resource planning for postpartum hemorrhage, a leading cause of maternal mortality. This study demonstrates the potential for integrating advanced imaging AI into women's imaging protocols to directly impact patient outcomes.
Source
AuntMinnie
Related News
•AuntMinnie
Stanford Team Introduces Real-Time AI Safety Monitoring for Radiology
Stanford researchers introduced an ensemble monitoring model to provide real-time confidence assessments for FDA-cleared radiology AI tools.
•AuntMinnie
Head-to-Head Study Evaluates AI Accuracy in Fracture Detection on X-Ray
A prospective study compared three commercial AI tools for fracture detection on x-ray, showing moderate-to-high accuracy for simple cases but weaker performance in complex scenarios.
•AuntMinnie
AI Boosts Agreement in CAD-RADS Classification on Cardiac CT
Deep learning AI improves interreader agreement in CAD-RADS assessments on coronary CT angiography.