A novel approach for liver steatosis assessment in ultrasound images using an adapted Vision-Language Foundation Model.
A new AI tool analyzes ultrasound images with 95% accuracy to detect fatty liver disease, potentially enabling faster diagnosis without invasive testing.
Metabolic dysfunction-associated steatotic liver disease (MASLD) is among the most prevalent chronic liver diseases worldwide. At the feature level, the VLM achieved 95.1% accuracy (κ=0.90-0.96), outperforming image-only baselines on clinically relevant tasks.
What the study was
- Study design
- Cohort study
- Population
- patients
- Sample size
- 1925
- Category
- Other
- Maturity
- Exploratory
- Journal
- Computers in biology and medicine
Why it surfaced
Score 7/10 [PROMISING_PRELIMINARY]: Cohort study (Journal Article) matched 'AI/ML in clinical diagnostics and imagin'. Components — novelty:2/3, relevance:2/3, design:1/2, population:2/2. Confidence: high. Conservative scoring applied per v1.3 rubric.
A plain-language summary of published research — not medical advice. Talk to a clinician about your own care.