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
•Radiology Business
Framework Assesses Real-World Financial Impact of Radiology AI Adoption
A new analysis presents a financial calculator for objectively assessing the return on investment (ROI) of implementing radiology AI solutions.
•Radiology Business
AI Technique Unveils Previously Hidden MS Gray Matter Lesions on MRI
Researchers developed an AI-enhanced method to detect previously invisible gray matter lesions in multiple sclerosis using MRI.
•Radiology Business
Majority of Patients Want Disclosure When AI Used in Imaging
A new survey finds that nearly all patients want to be informed when AI is utilized in medical imaging interpretation.