medigan : a Python library of pretrained generative models for medical image synthesis.

Richard Osuala Grzegorz Skorupko Noussair Lazrak Lidia Garrucho Eloy García Smriti Joshi Socayna Jouide Michael W Rutherford Fred W Prior Kaisar Kushibar Oliver Díaz Karim Lekadir

Published in: Journal of medical imaging (Bellingham, Wash.) (2023)

's viability as platform for generative model sharing. Our multimodel synthetic data experiments uncover standards for assessing and reporting metrics, such as FID, in image synthesis studies.

Keyphrases

deep learning
healthcare
electronic health record
social media
high throughput
big data
adverse drug
emergency department
machine learning
single cell
data analysis