Train the Trainer Workshop (Advanced Track)

For the advanced track, we will leverage our existing partnership with NVIDIA to train instructors. Participants will receive training on deep learning with emphasis on medical AI and use cases based on CHORUS data. The trainees will also receive training on classroom delivery skills as well as on effective use of NVIDIA tools. We will especially encourage applicants from partnering Tribal and HBCU institutions. This session will be open to up to 40 trainees who are CHORUS members.

This training will focus on MONAI (Medical Open Network for Artificial Intelligence). Project MONAI was developed by NVIDIA and King’s College London to establish an inclusive community of AI researchers for the development and exchange of best practices for AI in healthcare imaging across academia and enterprise researchers.

In order to participate in the advanced track, it is recommended that learners have some experience with:

  • Python tools such as NumPy and pandas
  • Pytorch (MONAI is built with Pytorch framework)
  • Some idea of how to use a cluster is needed (can take any online course on Slurm for Beginners)
  • Understanding medical image data types and workflows for AI applications preferred, but not required
  • Knowledge of labelers is not required (will be reviewed in the workshop)


Workshop Sessions will run in two blocks: 8:30 am-11:45 am and 1:30 pm-4:45 pm

The advanced workshop will cover the following topics:

  • Overview of Clara
  • Overview of MONAI
  • MONAI Core (presentation + hands-on)
  • MONAI Label (presentation + hands-on)
  • MONAI Deploy (presentation + hands-on)
  • Introduction of cuPY, RAPIDS, bring end-to-end pipeline on GPU

Participants in this session will be asked to complete the following questions prior to the workshop:

  1. What is your current computer hardware?
    1. Do you use a multi-GPU cluster/workstation?
    2. What are the GPUs in the cluster/workstation?
  2. What is your current AI pipeline for medical images?
  3. Do you feel bottlenecked from compute power?
    1. Would multi-GPU work flow allow you to do bigger/better research in your current research focus?
  4. What DL framework do you use for your research?
  5. What value do you see in having state-of-the-art AI models ready to be used on your data with little to no coding changes?

Participants: The Advanced Track can host 40 total participants:

  • 10 seats will be held for UF engineering students and allocated through a similar process as the seats for residents and fellows in the beginner track. These participants will receive $500 to cover their travel and free registration.
  • 10 additional seats held for CHoRUS members, with free registration
  • 20 open to all with a registration fee of $300