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
•Radiology Business
Study Highlights Limitations of AI in Prostate MRI Screening
New research points to several shortcomings in implementing AI for MRI-based prostate cancer screening.
•AuntMinnie
Deep Learning Model Predicts Brain Tumor MRI Enhancement Without Gadolinium
German researchers developed a deep learning approach to predict MRI contrast enhancement in brain tumors without the need for gadolinium-based agents.
•AuntMinnie
Multimodal LLMs Achieve High Accuracy Detecting Scoliosis on X-rays
Multimodal LLMs achieved up to 94% accuracy for scoliosis detection on spine x-rays, but struggled with lumbar stenosis on MRI.