Mayo Clinic has taken a major step towards integrating AI solutions in healthcare after deploying the NVIDIA DGX SuperPOD supercomputer with NVIDIA DGX B200 systems – an advanced AI infrastructure with state-of-the-art AI compute capabilities.
This move marks Mayo’s Bold. Forward. strategy, helping new generative AI tools and digital pathology innovations.
The advanced Blackwell infrastructure will help in developing the foundational models for pathomics, drug discovery, and precision medicine.
“Our aspiration for AI is to meaningfully improve patient outcomes by detecting disease early enough to intervene. What was once a hypothetical — ‘If only we had the right data’ — is now becoming reality thanks to AI and advanced computing,” said Matthew Callstrom, M.D., Ph.D., medical director of the Department of Strategy and leader of Mayo Clinic’s Generative Artificial Intelligence Program.
Decoding the Blackwell infrastructure
The NVIDIA Blackwell-powered DGX SuperPOD is efficient enough to process large, high-resolution imaging required for training AI models.
The Blackwell infrastructure is designed for speed and scalability, and it will help Mayo Clinic accelerate pathology slide analysis and foundation model development. This advanced computing infrastructure will also advance Mayo Clinic’s generative AI and multimodal digital pathology foundation model development.
The speed of this infrastructure will reduce four weeks’ work to just one, helping improve patient outcomes.
Before Blackwell
Initially, the Mayo Clinic developed a leading pathology foundation model called Atlas in partnership with Aignostics. Atlas is trained on more than 1.2 million histopathology whole-slide images.
With this model, clinicians and researchers can fast-track administrative tasks. The new computing capabilities will accelerate and improve clinical model development.
“This compute power, coupled with Mayo’s unparalleled clinical expertise and platform data of over 20 million digitized pathology slides, will allow Mayo to build on its existing foundation models, said Jim Rogers, CEO of Mayo Clinic Digital Pathology.
“We’re transforming healthcare by quickly and safely developing innovative AI solutions that can improve patient outcomes and enable clinicians to dedicate more time to patient care while also accelerating commercial affiliations with other industry leaders,” he continued.
Rogers believes this supercomputer is a massive step for digital pathology and will help patients get personalized medicines.
“We now can get to a future very quickly where personalized medicine is the norm, where a physician would know to a granular level what’s occurring in you when you come into that individual’s office,” he said.
Leading the future
Mayo Clinic’s partnership with NVIDIA reflects a growing trend in healthcare – traditional medical institutions teaming up with tech leaders to redefine what’s possible in medicine.
With the DGX SuperPOD built for speed and scalability, Mayo can rapidly grow its AI capabilities to meet new challenges and handle ever-expanding datasets. With this collaboration, Mayo Clinic has positioned itself as a leader in the practical infrastructure of artificial intelligence in medicine.
A combination of world-class clinical expertise, massive datasets, and now cutting-edge computational power will create an environment where the future of AI-driven healthcare can be developed, tested, and deployed at scale.