Harvard researchers presented an AI system that generates video radiology reports rated highly by radiologists for patient communication.
Key Details
- 1The ReXplain AI system creates patient-friendly video radiology reports using a large-language model, image segmentation, and conversational avatars.
- 2Tested with five radiologists and 10 CT video reports, the tool received 98-100% positive agreement on understandability and accuracy.
- 3Radiologists strongly agreed that image explanations and normal comparisons improved comprehension.
- 480% were comfortable providing videos to patients, with some hesitance for pre-visit distribution (60%).
- 5Feedback on 3D image rendering was mixed (50%).
- 6Further patient-centered studies are planned.
Why It Matters
Improving patient understanding of radiology results is a key unmet need; AI-generated multimedia reports could bridge the gap between medical reports and patient comprehension, helping radiology demonstrate direct value to patients.
Source
AuntMinnie
Related News
•AuntMinnie
Paul Chang Discusses Foundation Models and Agentic AI at RSNA 2025
Dr. Paul Chang shares his insights on the role of foundation models and agentic AI in radiology at RSNA 2025.
•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.