A study evaluates generative AI's performance in interpreting chest X-rays for tuberculosis screening in low-resource settings.
Key Details
- 1Researchers trained a generative AI model using two public TB chest radiograph datasets.
- 2The AI generated free-text reports and labeled images as showing presence/absence and laterality of TB-related abnormalities.
- 3Radiologists compared the model's reports to their own interpretations and judged report acceptability.
- 4Two additional radiologists established the reference standard for evaluation.
- 5Generative AI shows promise but still needs significant oversight before clinical deployment.
Why It Matters
Automating TB screening with generative AI could address radiologist shortages, especially in high-prevalence, low-resource settings. However, the need for oversight highlights ongoing challenges around accuracy, reliability, and safe adoption in clinical workflows.
Source
Health Imaging
Related News
•AuntMinnie
Toronto Study: LLMs Must Cite Sources for Radiology Decision Support
University of Toronto researchers found that large language models (LLMs) such as DeepSeek V3 and GPT-4o offer promising support for radiology decision-making in pancreatic cancer when their recommendations cite guideline sources.
•AuntMinnie
AI Model Using Mammograms Enhances Five-Year Breast Cancer Risk Assessment
A new image-only AI model more accurately predicts five-year breast cancer risk than breast density alone, according to multinational research presented at RSNA 2025.
•Radiology Business
AI Model Uses CT Scans to Reveal Biomarker for Chronic Stress
Researchers developed an AI model to measure chronic stress using adrenal gland volume on routine CT scans.