Neuro-VL: A Vision-Language Model Trained on Nearly One Million Neuroimaging Studies
arXiv — cs.AI · Chenhui Zhao, Akshay Rao, Akhil Kondepudi, Yiwei Lyu, Xinhai Hou, Rikhil Seshadri, Cheng Jiang, Soumyanil Banerjee, Rushikesh Joshi, Samir Harake, Ashok Srinivasan, Shruti Mishra, Francisco Rivas-Rodriguez, Seunghong Rhee, Nathaniel Roddenberry, Neeraj Chaudhary, Zach Wilseck, Paul Park, Honglak Lee, Vikas Gulani, Aditya Pandey, Todd Hollon · Published on Readzer
Summary
Researchers introduced Neuro-VL, a vision-language model trained on nearly one million neuroimaging studies from routine clinical care, which can interpret complete imaging examinations and engage in natural language conversations about findings. Across internal and international datasets, Neuro-VL outperformed frontier general-purpose and specialized medical models in diagnosing, localizing, and describing abnormalities, as well as generating comprehensive radiology reports. The model also compared serial examinations to assess disease progression and more reliably resisted misleading clinical assumptions than leading frontier models from OpenAI and Google.
This is a reviewed summary. Read the complete article at the original source.
Why it matters by industry
- Artificial intelligence
This research demonstrates a significant advancement in medical AI, showing how large-scale clinical imaging data can be used to develop specialized vision-language models with broad diagnostic capabilities, relevant to AI model development and multimodal reasoning in healthcare.