Learning neuroimaging models from health system-scale data
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912766580752384 |
|---|---|
| author | Lyu, Yiwei Harake, Samir Chowdury, Asadur Banerjee, Soumyanil Gologorsky, Rachel Liu, Shixuan Meissner, Anna-Katharina Rao, Akshay Zhao, Chenhui Kondepudi, Akhil Jiang, Cheng Hou, Xinhai Joshi, Rushikesh S. Neuschmelting, Volker Srinivasan, Ashok Kleindorfer, Dawn Athey, Brian Gulani, Vikas Pandey, Aditya Lee, Honglak Hollon, Todd |
| author_facet | Lyu, Yiwei Harake, Samir Chowdury, Asadur Banerjee, Soumyanil Gologorsky, Rachel Liu, Shixuan Meissner, Anna-Katharina Rao, Akshay Zhao, Chenhui Kondepudi, Akhil Jiang, Cheng Hou, Xinhai Joshi, Rushikesh S. Neuschmelting, Volker Srinivasan, Ashok Kleindorfer, Dawn Athey, Brian Gulani, Vikas Pandey, Aditya Lee, Honglak Hollon, Todd |
| contents | Neuroimaging is a ubiquitous tool for evaluating patients with neurological diseases. The global demand for magnetic resonance imaging (MRI) studies has risen steadily, placing significant strain on health systems, prolonging turnaround times, and intensifying physician burnout. These challenges disproportionately impact patients in low-resource and rural settings. Here, we utilized a large academic health system as a data engine to develop Prima, the first vision language model (VLM) serving as an AI foundation for neuroimaging that supports real-world, clinical MRI studies as input. Trained on over 220,000 MRI studies, Prima uses a hierarchical vision architecture that provides general and transferable MRI features. Prima was tested in a 1-year health system-wide study that included 30K MRI studies. Across 52 radiologic diagnoses from the major neurologic disorders, including neoplastic, inflammatory, infectious, and developmental lesions, Prima achieved a mean diagnostic area under the ROC curve of 92.0, outperforming other state-of-the-art general and medical AI models. Prima offers explainable differential diagnoses, worklist priority for radiologists, and clinical referral recommendations across diverse patient demographics and MRI systems. Prima demonstrates algorithmic fairness across sensitive groups and can help mitigate health system biases, such as prolonged turnaround times for low-resource populations. These findings highlight the transformative potential of health system-scale VLMs and Prima's role in advancing AI-driven healthcare. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_18638 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Learning neuroimaging models from health system-scale data Lyu, Yiwei Harake, Samir Chowdury, Asadur Banerjee, Soumyanil Gologorsky, Rachel Liu, Shixuan Meissner, Anna-Katharina Rao, Akshay Zhao, Chenhui Kondepudi, Akhil Jiang, Cheng Hou, Xinhai Joshi, Rushikesh S. Neuschmelting, Volker Srinivasan, Ashok Kleindorfer, Dawn Athey, Brian Gulani, Vikas Pandey, Aditya Lee, Honglak Hollon, Todd Computer Vision and Pattern Recognition Artificial Intelligence Neuroimaging is a ubiquitous tool for evaluating patients with neurological diseases. The global demand for magnetic resonance imaging (MRI) studies has risen steadily, placing significant strain on health systems, prolonging turnaround times, and intensifying physician burnout. These challenges disproportionately impact patients in low-resource and rural settings. Here, we utilized a large academic health system as a data engine to develop Prima, the first vision language model (VLM) serving as an AI foundation for neuroimaging that supports real-world, clinical MRI studies as input. Trained on over 220,000 MRI studies, Prima uses a hierarchical vision architecture that provides general and transferable MRI features. Prima was tested in a 1-year health system-wide study that included 30K MRI studies. Across 52 radiologic diagnoses from the major neurologic disorders, including neoplastic, inflammatory, infectious, and developmental lesions, Prima achieved a mean diagnostic area under the ROC curve of 92.0, outperforming other state-of-the-art general and medical AI models. Prima offers explainable differential diagnoses, worklist priority for radiologists, and clinical referral recommendations across diverse patient demographics and MRI systems. Prima demonstrates algorithmic fairness across sensitive groups and can help mitigate health system biases, such as prolonged turnaround times for low-resource populations. These findings highlight the transformative potential of health system-scale VLMs and Prima's role in advancing AI-driven healthcare. |
| title | Learning neuroimaging models from health system-scale data |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2509.18638 |