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
Toronto Study: LLMs Must Cite Sources for Radiology Decision Support
University of Toronto researchers found that large language models (LLMs) such as DeepSeek V3 and GPT-4o offer promising support for radiology decision-making in pancreatic cancer when their recommendations cite guideline sources.
•AuntMinnie
AI Model Using Mammograms Enhances Five-Year Breast Cancer Risk Assessment
A new image-only AI model more accurately predicts five-year breast cancer risk than breast density alone, according to multinational research presented at RSNA 2025.
•Radiology Business
AI Model Uses CT Scans to Reveal Biomarker for Chronic Stress
Researchers developed an AI model to measure chronic stress using adrenal gland volume on routine CT scans.