Experts outline five central barriers hampering adoption of AI in pediatric cancer imaging.
Key Details
- 1Pediatric cancers represent only about 1% of all new cancer diagnoses, resulting in very limited imaging datasets.
- 2Small and rare tumor subtypes further restrict the volume of data available for AI model training.
- 3Available pediatric imaging data are fragmented across over 200 specialized U.S. cancer centers.
- 4Lack of systematic data sharing prevents AI models from generalizing across institutions and imaging platforms.
- 5Adult oncology AI success stories have not directly translated to pediatric populations due to these barriers.
Why It Matters
Improving AI adoption in pediatric cancer imaging could enhance diagnosis and care, but requires addressing unique data and collaboration hurdles. Cross-institutional efforts and better data sharing are crucial for advancing effective AI applications in pediatric radiology.
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.
•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.
•Radiology Business
Radiology AI Devices at Elevated Risk for FDA Recalls, Study Finds
Radiology AI devices are more likely to face FDA recalls, largely due to deviations from intended use and incomplete clinical data.