[Aida-compute-users] AIDA input to Nvidia DGX for Medical Imaging?

[Joel Hedlund]

Hi AIDA DGX-2 users!

Do you have opinions on what Nvidia should be doing to better support medical imaging workflows?

Nvidia is reaching out to AIDA for feedback, so let me know if you want to get involved, and we will see how to best take this forward. Feel free to reply by email, or post in #aida-dgx2 <https://nbisweden.slack.com/archives/C01S39EQ9S9/p1632841938053200> chat, or contact Leif directly if you want (cf below)!

As a conversation starter, Leif lets us know that they have recently integrated a few things as OpenSource/MONAI (cf below).

Cheers!
/Joel Hedlund
AIDA DGX-2 Service owner
Data director AIDA

-------- Forwarded Message --------
Subject: 	Input till Nvidia DGX för Medical Imaging
Date: 	Tue, 28 Sep 2021 11:39:22 +0000
From: 	Leif Nordlund <lnordlund at nvidia.com>
To: 	Joel Hedlund <joel.hedlund at liu.se>



Hej Joel

Vi utvecklar nu vår plattform vidare och önskar feedback på verktyg och annat som kan förbättra för användare av Medical Imaging workflows. Hur skulle vi kunna få feedback av era användare , kan du facilitetera eller skall vi kontakta några användare från Nvidia ?

Saker vi integrerat nyligen efter input som Open Source / MONAI är

  *


    UNETR: Transformers for Medical Image Segmentation

  *

    Enhancements of the base metric interfaces

  *

    C++/CUDA extension modules via PyTorch JIT compilation

  *

    Backward compatibility and enhanced continuous integration/continuous delivery

  *

    Collaboration with Project-MONAI/MONAILabel for smooth integration


    MONAI Label 0.1 första release:


    MONAI Label is an intelligent open source image labeling and learning tool that enables users to create annotated datasets and build AI annotation models for clinical evaluation. MONAI Label enables application developers to build labeling apps in a /serverless/ way, where custom labeling apps are exposed as a service through the MONAI Label Server.


// Leif
-------------- next part --------------
En HTML-bilaga skiljdes ut...
URL: <http://lists.liu.se/pipermail/aida-compute-users/attachments/20210928/9f8efb62/attachment.html>