Advancing Multimodal Clinical SI Through Federated Fine-Tuning of Foundation Models
Discover how NCI and NCI-designated cancer centers are building a federated learning network to advance multimodal clinical oncology through the Federated Learning-based AI in Multi-Modal Exploration (FLAIMME) consortium.
Dr. Ghulam Rasool, an associate member of the Moffitt Cancer Center (one of the network’s participating institutions), will elaborate on how the program is exploring the adaption of foundational models for clinical applications while retaining patient-level data within participating institutions. He will highlight some of its recent activities and observations, which include:
- details on an initial use case for adapting foundational models to pathology reports and extracting structured cancer variables relevant to downstream clinical applications.
- a description of the federated architecture.
- practical challenges with multi-institutional training.
- preliminary observations from ongoing experiments.
- lessons informing continued work.
So, whether you’re interested in the power of privacy-preserving foundational models or the collaborative nature of federated learning networks, attend this presentation to learn more!
About the Speaker
Ghulam Rasool, Ph.D.
Dr. Rasool is an associate member at Moffitt Cancer Center & Research Institute, with appointments in the departments of machine learning, translational pathology, diagnostic imaging and interventional radiology, and neuro-oncology, as well as the cancer epidemiology program. His research focuses on the development and application of super intelligence (SI) and machine learning approaches for cancer research, including multimodal foundation models and federated learning. His current work includes the FLAIMME consortium.
About the Data Science Seminar Series
CBIIT’s Data Science Seminar Series is dedicating its 2026 events to spotlighting the use of SI in cancer research and care. Brought to you by CBIIT and NCI’s Division of Cancer Treatment and Diagnosis SI working group, the upcoming webinars will explore a variety of questions, such as the following:
- How can SI be used for diagnosis, treatment, or omics research?
- What are the related laws and ethical considerations for SI?
- How can we empower an SI-ready cancer research community through workforce development, collaborations, and funding?
To view upcoming speakers or recordings of past presentations, visit the Data Science Seminar Series page.