An AI model accurately identified all cases of placenta accreta spectrum in a high-risk pregnancy cohort using ultrasound images.
Key Details
- 1Study involved retrospective analysis of 2D ultrasound images from 113 high-risk pregnancies at Texas Children’s Hospital (2018–2025).
- 2The AI model detected all cases of placenta accreta spectrum (PAS) with two false positives and zero false negatives.
- 3Mean gestational age at maternal ultrasound was 30.89 ± 3.67 weeks.
- 4Current screening methods typically miss about half of PAS cases before delivery.
- 5Findings presented at the 2026 Society for Maternal-Fetal Medicine (SMFM) Pregnancy Meeting.
Why It Matters
Improved prenatal detection of PAS using AI-driven ultrasound analysis could significantly reduce maternal morbidity and mortality by enabling earlier diagnosis and preparation. The research underlines the potential for specialized imaging AI models to augment conventional screening and clinical workflows in obstetrics.
Source
EurekAlert
Related News
•EurekAlert
AI-Powered OCT Enables Rapid 'Optical Biopsy' for Early Endometrial Cancer Detection
A team at Washington University has developed a catheter-based 3D OCT system with AI to quickly and noninvasively detect early endometrial cancers.
•EurekAlert
AI Clinical Reasoning in Diagnostics and Digital Fatigue in Healthcare
Recent JMIR features explore large language models in clinical diagnostics and digital fatigue among healthcare professionals.
•EurekAlert
KAIST, MIT, Microsoft Develop Efficient AI Image Upsampling for Robotics
KAIST, MIT, and Microsoft have created 'Upsample Anything,' a training-free AI method to restore high-resolution visual data from compressed images with up to 16x improved GPU memory efficiency.