New research finds increased patient BMI can negatively impact AI performance on low-dose CT scans.
Key Details
- 1Study published in the European Journal of Radiology examines BMI impact on chest LDCTs.
- 2Higher BMI causes increased X-ray attenuation and image noise, degrading image quality.
- 3Researchers compared AI and human lung nodule detection in cohorts with highest and lowest BMI (top and bottom 1.5%).
- 4AI's diagnostic accuracy is limited by the diversity of its training datasets, particularly in BMI distribution.
- 5Prior literature shows conflicting findings about BMI influence on human performance; data on AI's vulnerability to BMI-related artifacts is growing.
Why It Matters
This study highlights a potential bias and limitation of current imaging AI tools, especially those trained on less diverse patients. Understanding performance differences across BMI ranges is essential for ensuring equitable and accurate lung cancer screening in clinical settings.
Source
Radiology Business
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.