Create Infinite Medical Imaging Data With Generative AI

RadImageGAN: Multi-Modal Generative AI for Medical Imaging [S51264]

Related links:


Nvidia said:

We introduce RadImageGAN, a new multi-modal (CT/MR/ultrasound) generative AI for radiology capable of generating 165 distinct classes with various pathologies over 14 anatomical regions. This work uses StyleGAN-XL, and was trained on 1.3 million…

GTC session about this:
Thursday, Mar 23, 2:00 PM - 2:25 PM GMT -03

It’s nice that Slicer is used by Nvidia in this video (second 34)

MONAI’s new Generative AI for medical imaging could ease training of segmentation models by creating representative, deidentified, distilled training data

Thanks for posting that @mau_igna_06. I agree there’s lots of potential here.

I attended a workshop on the topic - others might want to watch the video of it which should be posted tomorrow: GTC 2023: #1 AI Conference

2 Likes