Researchers demonstrated an AI model's strong accuracy in measuring fetal lung maturity from ultrasound images.
Key Details
- 1The AI model was developed using convolutional neural networks (CNNs) to analyze fetal lung ultrasound images.
- 2The model measured a 'heterogeneity index' to distinguish pre-term from term lung development.
- 3It was trained and validated on a dataset of 543 images (156 pre-term, 387 term), using five-fold cross-validation.
- 4The AI achieved a validation accuracy of 92% and a training accuracy of 88%, with stable training loss.
- 5The research was presented at the 2026 AIUM annual meeting by Nicole Adelson from Hofstra University.
- 6The team's future plans include expanding the dataset, optimizing the model with advanced methods, and developing a portable, real-time assessment system.
Why It Matters
This AI-driven approach could replace current invasive or less accurate methods for fetal lung maturity assessment, potentially improving outcomes for pre-term infants. Adoption of such portable, real-time AI tools could enhance clinical decision-making in obstetrics and beyond.
Source
AuntMinnie
Related News
•AuntMinnie
Study: Computer Vision Models Best LLMs in Chest CT Breast Abnormality Detection
Computer vision models (CVMs) surpass large language models (LLMs) in accurately labeling incidental breast abnormalities on chest CT scans.
•Cardiovascular Business
Radiology Maintains Lead in FDA-Cleared AI Algorithms, Cardiology Follows
Radiology remains the top specialty for FDA-cleared AI, with cardiology as a strong second, particularly in cardiovascular imaging.
•AuntMinnie
Deep Learning Models Rival Radiologists for Pancreatic Cancer Detection on CT
Deep-learning models achieved comparable or superior accuracy to experienced radiologists in detecting pancreatic cancer on CT scans, especially for small tumors.