# Synthesizing brain tumor images and annotations by combining progressive growing GAN and SPADE

arXiv: https://arxiv.org/abs/2009.05946 · HTML: https://mlsanity.com/paper/2009.05946/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Sep 2020.

## Built on by (most cited first, 9 of 9)

- [Brain tumor segmentation using synthetic MR images -- A comparison of GANs and diffusion models](https://mlsanity.com/paper/2306.02986/) (2023)
- [Data synthesis and adversarial networks: A review and meta-analysis in cancer imaging](https://mlsanity.com/paper/2107.09543/) (2021)
- [A 3D generative model of pathological multi-modal MR images and segmentations](https://mlsanity.com/paper/2311.04552/) (2023)
- [Soft-CP: A Credible and Effective Data Augmentation for Semantic Segmentation of Medical Lesions](https://mlsanity.com/paper/2203.10507/) (2022)
- [Does an ensemble of GANs lead to better performance when training segmentation networks with synthetic images?](https://mlsanity.com/paper/2211.04086/) (2022)
- [Generation of Synthetic Rat Brain MRI scans with a 3D Enhanced Alpha-GAN](https://mlsanity.com/paper/2112.13626/) (2021)
- [MIPR:Automatic Annotation of Medical Images with Pixel Rearrangement](https://mlsanity.com/paper/2204.10513/) (2022)
- [Impact of Synthetic Lesional MR Images in Automated Focal Cortical Dysplasia Detection in Low-Data Scenarios](https://mlsanity.com/paper/2606.07381/) (2026)
- [Diffusion-Based Tumor Inpainting for Renal Segmentation under Clinical Data Scarcity](https://mlsanity.com/paper/2609.21698/) (2026)

## Abstract (arXiv)

Training segmentation networks requires large annotated datasets, but manual annotation is time consuming and costly. We here investigate if the combination of a noise-to-image GAN and an image-to-image GAN can be used to synthesize realistic brain tumor images as well as the corresponding tumor annotations (labels), to substantially increase the number of training images. The noise-to-image GAN is used to synthesize new label images, while the image-to-image GAN generates the corresponding MR image from the label image. Our results indicate that the two GANs can synthesize label images and MR images that look realistic, and that adding synthetic images improves the segmentation performance, although the effect is small.