December 03, 2025
1 min read
Key takeaways:
- Innovations like medical image analysis models may improve diagnosis accuracy and consistency across institutions.
- Federated learning approaches may preserve patient privacy and reduce data-transfer risks.
SAN DIEGO — Visual intelligence and collaborative AI approaches may advance health care, according to a keynote speaker at AIMed25.
“Our recent work focuses on making AI for health care more accurate, efficient and deployable in real clinical settings,” Chen Chen, PhD, associate professor at the Center for Research in Computer Vision, the department of computer science and the Institute of Artificial Intelligence at the University of Central Florida, told Healio.
Data were derived from Chen C, et al. Advancing health care through visual intelligence and collaborative AI. Presented at: AIMed25; Nov. 9-12, 2025; San Diego.
Chen and colleagues have developed advanced medical image analysis models for tasks like tumor segmentation, pathology slide interpretation and MRI analysis that require far fewer labels and run much faster than traditional models. In addition, they have developed multimodal foundation models that can understand both medical images and clinical text together, as well as video and motion-based AI tools, including surgical scene understanding and privacy-preserving patient monitoring using sensors like radar.
Chen Chen
“Overall, we are building AI systems that are both powerful and practical for everyday clinical use,” Chen said. “These innovations aim to bring expert-level AI support closer to the point of care. In the long term, this means more timely, personalized and equitable care for patients.”
Chen also said federated learning approaches are imperative to allow hospitals to collaborate on AI development without sharing raw patient data, which preserves patient privacy and reduces data-transfer risks. In addition, he said the collaboration between institutions allows for larger, more diverse datasets, which improves model fairness and generalizability.
“It’s a practical path to building strong, trustworthy medical AI across health care systems,” Chen said.
For more information:
Chen Chen, PhD, can be contacted at chen.chen@ucf.edu.
Sources/Disclosures
Source:
Chen C, et al. Advancing health care through visual intelligence and collaborative AI. Presented at: AIMed25; Nov. 9-12, 2025; San Diego.
Disclosures:
Chen reports receiving research support from the National Science Foundation Directorate for Computer and Information Science and Engineering Core program and the National Science Foundation–Intel Partnership on Machine Learning and Wireless Networks.
Ask a clinical question and tap into Healio AI’s knowledge base.
- PubMed, enrolling/recruiting trials, guidelines
- Clinical Guidance, Healio CME, FDA news
- Healio’s exclusive daily news coverage of clinical data
