Back to all news
Rad Partners Wins $1.29M FDA Grant for AI Radiology Report Evaluation Study
Tags:Research
Cognita Imaging, part of Rad Partners, has received a $1.29M FDA grant to develop a new framework using large language models (LLMs) to evaluate AI-generated radiology reports.
Key Details
- 1Cognita Imaging has been awarded a $1.29 million grant from the FDA.
- 2The 18-month project will create and validate a framework that uses multiple LLMs to assess radiology reports, both human- and AI-generated.
- 3The method is described as "LLMs as a jury," leveraging consensus from several AI models.
- 4This approach addresses scalability limitations of traditional expert reader studies in evaluating AI-generated clinical content.
- 5Radiologists will still review especially challenging cases to ensure quality.
- 6Project aims to improve reliability and generalizability of AI report evaluation in real-world radiology practice.
Why It Matters
Rigorous and scalable evaluation methods for AI-generated radiology reports are essential as automated reporting becomes more prevalent. The project could accelerate safe clinical adoption by increasing the efficiency and consistency of model validation.
Source
Radiology Business
Related News
•Radiology Business
Real-World Study: Radiology AI Best in Emergency and Inpatient Settings
A commercial AI tool for intracranial aneurysm detection outperformed in inpatient and emergency settings but yielded limited benefits for outpatients in a major health system study.
•Radiology Business
New Rubric Enhances Safety of AI-Generated Radiology Summaries
Researchers developed a five-factor rubric to assess the safety and quality of AI-generated, patient-friendly radiology report summaries.
•Radiology Business
AI Model Surpasses Radiologists in Detecting Subtle Hip Fractures
A new AI model outperformed radiologists in identifying difficult-to-detect femoral neck fractures on radiographs.