(RP22) Supercomputer-Scale Training of Large AI Radiology Models
Event Type
Research Poster
AI/Machine Learning/Deep Learning
HPC workflows
Parallel Algorithms
TimeTuesday, June 18th8:30am - 10am CEST
LocationSubstanz 1, 2
DescriptionThe health care industry is expected to be an early adopter of AI and deep learning to improve patient outcomes, reduce costs, and speed up diagnosis. We have developed models for using AI to diagnose pneumonia, emphysema, and other thoracic pathologies from chest x-rays. Using the Stanford University CheXNet model as inspiration, we explore ways of developing highly-accurate models for this problem with fast parallel training on Zenith, the Intel Xeon-based supercomputer at Dell EMC's HPC and AI Innovation Lab. We explore various network topologies to gain insight into what types of neural networks scale well and improve training time from days to hours, while at the same time giving significantly better predictions . We then explore transferring this learned knowledge to other radiology subdomains, such as mammography, and whether this leads to better models than developing subdomain models independently.
Poster PDF
Poster Authors
Artificial Intelligence Research
AI Software Principal Engineer
Principal Engineer