Abdominal MRI Synthesis using StyleGAN2-ADA

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Citation (Scopus)


The lack of labelled medical data still poses as one of the biggest issues when creating Deep Learning models in the medical field. Modern data augmentation techniques like the generation of synthetic images have gained a special interest. In recent years there has been a significant improvement in GANs. StyleGAN2 achieves impressive results in the generation of natural images. StyleGAN2-ADA was created to respond to the lack of training data when training an image synthesis model, which is very frequent in the medical field. Some works used styleGAN to generate melanomas, breast cancer histological images, MR and CT images. In this work we apply, for the first time, a styleGAN2-ADA to a small dataset of abdominal MRI with 1.3k images. From the augmentation pipeline created by the authors of styleGAN2-ADA, we removed all augmentations except the geometric transformations and pixel blitting operations. We trained our network for 70 hours. Our generated dataset has a precision score of 59,33 % and a FID score of 18,14. We conclude that the styleGAN2-ADA is a viable solution to generate MRI using a small dataset.
Original languageEnglish
Title of host publication2023 IST-Africa Conference (IST-Africa)
Place of PublicationMassachusetts
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Number of pages9
ISBN (Electronic)978-1-905824-71-7
ISBN (Print)979-8-3503-0639-2
Publication statusPublished - 2023
Event2023 IST-Africa Conference, IST-Africa 2023 - Tshwane, South Africa
Duration: 31 May 20232 Jun 2023

Publication series

PublisherInstitute of Electrical and Electronics Engineers (IEEE)
ISSN (Print)2576-859X
ISSN (Electronic)2576-8581


Conference2023 IST-Africa Conference, IST-Africa 2023
Country/TerritorySouth Africa


  • Generative Adversarial Networks
  • Image Synthesis
  • Magnetic Resonance Imaging
  • Medical Imaging
  • StyleGAN2


Dive into the research topics of 'Abdominal MRI Synthesis using StyleGAN2-ADA'. Together they form a unique fingerprint.

Cite this