Computational Core
Team approach to data science and AI-based research and development to improve health care.
Computational Core Services
- Computational Hardware and Software Development and Management
- CPU and GPU Computing Architecture
- Data Storage and Interoperability Tools and Software
- Advanced Quantitative Imaging Research Resources
- Applications Development for integration into clinical radiology workflow
Who can use this resource
Researchers across UCSF are encouraged to request the services of the Computational Core for projects that would benefit from a collaborative approach to AI and machine learning-based research.
Computational Core Infrastructure
Computational Core Team
Meet the Computational Core Team
Director Jason Crane, PhD leads computational data scientists Bruno Astuto-Arouche Nunes, PhD, Pablo Damasceno, PhD, James Hawkins, Madeline Hess, Beck Olson, and Rutwik Shah, MD
Core’s Infrastructure Team
Meet the Core’s Infrastructure Team
John Mongan MD,PhD, Jeff Block, Emma Bahroos, Peter Storey, Wyatt Tellis, PhD
Software
- Combines in-house algorithms and software provided by external collaborators in both the academic and commercial sectors
- Clinical validation platforms for prospective evaluation of new quantitative software Image
- Annotation: MD.ai, NVIDIA AIAA
Scientific Computing Services
SCS supports the computational core via recharge subscription to Radiology and Biomedical Imaging research groups.
High Performance Computing
- Sun’s Grid Engine (SGE) Scheduler
- NVIDIA’s DGX-2, the world’s first petaFLOPS system combining 16 interconnected GPUs to accelerate machine learning
- Wynton, shared high-performance computing cluster, comprised of approximately 400 CPU cores and 116 GPU
Data and Data Science Platform
- Information Commons
- Clinical Radiological Imaging Data AIR