Adult-trained radiology AI models often underperform when applied to pediatric imaging data, according to a systematic review.
Key Details
- 1Researchers reviewed over 2,000 articles but only 15 met inclusion criteria for full-text analysis.
- 2Studied AI tasks included segmentation, object detection, and classification.
- 3Only 2 adult-trained models (organ segmentation on CT) showed similar accuracy between adults and children.
- 4Most models performed worse on pediatric data, with variable degrees of performance drop.
- 5Fine-tuning with limited pediatric data led to improvements in 5 out of 6 studies, but none outperformed the original adult-trained models.
- 6Findings highlight the need for dedicated pediatric imaging datasets for AI model development.
Why It Matters
Reliable AI model performance for pediatric imaging cannot be assumed based on adult-trained models alone. This underscores a critical demand for collecting pediatric-specific data to develop safe and effective AI tools for children.
Source
AuntMinnie
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.