AI-powered post-processing improves handheld ultrasound detection of small or faint carotid plaques in community screening.
Key Details
- 1AI model developed in China sharpens handheld carotid ultrasound images.
- 2Tested in adults 40+ in a community screening program; 153 plaques in 117 participants.
- 3AI-enhanced images detected 94.8% of plaques (145/153), versus 87.6% (134/153) with standard images.
- 4AI enhancement highlighted 11 additional small or low-contrast plaques.
- 5Correctly flagged unstable plaques 63.2% of the time, up from 47.4% using unenhanced images.
- 6Still missed over one-third of unstable plaques; not reliable as sole risk stratification tool.
Why It Matters
AI post-processing may extend the clinical value of handheld ultrasound in primary and community care, aiding triage for confirmatory imaging or stroke risk management. Caution is warranted as the tool cannot replace comprehensive diagnostic assessment.
Source
EurekAlert
Related News
•EurekAlert
Sydney Team Reveals Fractal Limits to Predictability in AI Training
University of Sydney researchers discover that deep learning models may remain unpredictable due to deep-rooted mathematical properties, even under controlled training conditions.
•EurekAlert
Machine Learning Tool Maps Alzheimer’s Risk on fMRI Spectrum
Researchers developed an AI framework using resting-state fMRI to assess Alzheimer's risk along a continuum from SuperAgers to AD patients.
•EurekAlert
AI Model MANTIS Improves Risk Stratification in Pediatric Brain Tumors
Dana-Farber Cancer Institute has developed an AI model, MANTIS, that uses DNA methylation profiling to individualize prognosis and guide therapy for children with brain tumors.