Washington, D.C.-based Children’s National Hospital and Children’s Hospital of Philadelphia have helped launch what they describe as the first large-scale, open-access benchmark dataset designed specifically for pediatric brain tumor segmentation and analysis, according to a May 12 report published in Radiology: Artificial Intelligence.
The dataset, called “Brain Tumor Segmentation in Pediatrics,” or BraTS-PEDs, includes MRI data from 457 pediatric patients with high-grade gliomas collected through multiple institutions and international research consortia. Researchers said the dataset was developed to address a lack of standardized pediatric imaging data for AI development in radiology and precision medicine.
Each case includes multiple MRI sequences, including pre- and postcontrast T1-weighted, T2-weighted and T2-fluid-attenuated inversion recovery scans. Researchers said the dataset is structured with training, validation and hidden testing subsets to support reproducible benchmarking and evaluation across institutions.
Pediatric brain tumors are the most common solid tumors in children and the leading cause of cancer-related mortality in the pediatric population, according to the report. Researchers said the dataset could support development of AI tools aimed at improving diagnosis, monitoring and treatment response in pediatric neuro-oncology.
At the Becker's 11th Annual IT + Revenue Cycle Conference: The Future of AI & Digital Health, taking place September 14–17 in Chicago, healthcare executives and digital leaders from across the country will come together to explore how AI, interoperability, cybersecurity, and revenue cycle innovation are transforming care delivery, strengthening financial performance, and driving the next era of digital health. Apply for complimentary registration now.
