Skip to content

Deploy Working Group

Jump to bottom Edit New page
David Bericat edited this page Feb 23, 2021 · 21 revisions

Expanding MONAI to cover the "end-to-end AI lifecycle"

Project MONAI was created with the goal of “accelerating the pace of research and development by providing a common software foundation and a vibrant community for medical imaging deep learning”.

There is a lot of research in the development and training of AI models by data science teams across the world, and the discipline is becoming mature thanks to initiatives like MONAI.

But in order to realize the value of all that effort and investments, the medical community has to naturally evolve to put all that new innovation seamlessly integrated within the different clinical workflows and systems, supporting and augmenting physicians, and freeing up their time to spend more time providing care to patients. That jump today is simply too high, almost a leap of blind faith. When we are talking about people’s lives, disease detection, diagnosis and treatment, not knowing how the results will affect care is simply unacceptable.

Therefore, we see an opportunity to create a set of intermediate steps, where researchers and physicians can build confidence in the techniques and approaches used with AI, deploy and connect with their research medical devices and systems in a controlled environment (i.e. Research PACS), and consume the results they need at the speed they are ready to, iterating over time until the overall AI inference infrastructure is ready to move to clinical environments, with a high certainty the transition will go smoothly.

We would love project MONAI to be the community where this idea develops, expanding its scope from AI from model training to QA evaluation first, and then to clinical deployments.

MONAI Deploy WG - scope diagram

Focus

The focus areas defined by the Deploy Strategy and Governance working group for 2021 are:

  1. Define the journey from development and research to clinical environments in hospitals.
  2. Implementation mindset. Create tangible assets: code and demos/prototypes. Start by defining an open AI deployment API.
  3. Imaging first, then other modalities.
  4. Interoperability with clinical systems. Starting with DICOM, then EHR.
  5. Central repository to facilitate collaboration among institutions.

Deliverables

  1. By April 1st, use cases reviewed and high level systems architecture.
  2. By May 1st, pick a use case to map out end-to-end and draft 2021 deployment roadmap.
  3. By June 1st, open AI deployment API definition
  4. By Sept 1st, first demo/prototype.

Members

Group Lead

  1. David Bericat (NVIDIA) - dbericat@nvidia.com

Strategy and Governance Group members (~monthly 60 mins)

  1. Ralf Floca (DKFZ) - r.floca@Dkfz-Heidelberg.de
  2. Klaus Maier-Hein (DKFZ) - K.Maier-Hein@Dkfz-Heidelberg.de
  3. Klaus Kades (DKFZ) - k.kades@dkfz-heidelberg.de
  4. Jonas Scherer (DKFZ) - jonas.scherer@dkfz-heidelberg.de
  5. Marco Nolden (DKFZ) - m.nolden@dkfz-heidelberg.de
  6. Daniel Rubin (Stanford) - dlrubin@stanford.edu
  7. Bennett Landman (Vanderbilt University/NSF) - bennett.landman@vanderbilt.edu
  8. Steve Langer (FlowSigma/NSF) - steve.langer@flowsigma.com
  9. Brad Ericksonn (Mayo/FlowSigma) - bje@mayo.edu
  10. Jayashree Kalpathy-Cramer (MGH) - JKALPATHY-CRAMER@mgh.harvard.edu
  11. Sharmila Majumdar (UCSF) - Sharmila.Majumdar@ucsf.edu
  12. Anthony Costa (Mt. Sinai) - anthony.costa@mssm.edu
  13. Haris Shuaib (Guy’s & St Thomas NHS Foundation Trust) - haris.shuaib@kcl.ac.uk
  14. Krishna Juluru (NIH/MSKCC) - kjulurumd@gmail.com
  15. Jorge Cardoso (KCL) - m.jorge.cardoso@kcl.ac.uk
  16. Selnur Erdal (Mayo Jacksonville) erdal.barbaros@mayo.edu
  17. Stephen Aylward (Kitware) stephen.aylward@kitware.com
  18. Mona Flores (NVIDIA) - mflores@nvidia.com
  19. Risto Haukioja (NVIDIA) rhaukioja@nvidia.com
  20. Rahul Choudhury (NVIDIA) rahulc@nvidia.com
  21. Dana Groff (NVIDIA) dgroff@nvidia.com
  22. Michael Zephyr (NVIDIA) mzephyr@nvidia.com
  23. Brad Genereaux (NVIDIA) bgenereaux@nvidia.com

Core WG members (~bi-weekly 90 mins)

  1. Laurence Jackson (Guy’s & St Thomas NHS Foundation Trust) -laurence.jackson@kcl.ac.uk

  2. Pouria Rouzrokh (Mayo) rouzrokh.pouria@mayo.edu

  3. Karthik Ramadass (Vanderbilt) karthik.ramadass@vanderbilt.edu

  4. Yankai Huo (Vanderbilt) yuankai.huo@vanderbilt.edu

  5. Kilian Hett (Vanderbilt) kilian.hett@vanderbilt.edu

    +Ralf Floca (DKFZ), Haris Shuaib (GSTT), Steve Langer (FlowSigma/NSF), Bennett Landman (Vanderbilt University/NSF), David Bericat (NVIDIA)

Meeting Notes

Kick-off

Strategy and Governance - 4th Thursday of each month - 8am PST, 11am PST, 5pm EU - 60 mins.

Core - Weekly - 8am PST, 11am PST, 5pm EU - 90 mins (when not conflicting with Strategy and Governance - bi-weekly in the future)

Master document

MONAI Deploy WG - master doc

Copyright (c) MONAI Consortium

Working Groups

Clone this wiki locally