# Evaluating the Performance of StyleGAN2-ADA on Medical Images

arXiv: https://arxiv.org/abs/2210.03786 · HTML: https://mlsanity.com/paper/2210.03786/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 29 references that are in the map.
- First posted on arXiv 7 Oct 2022.

## Builds on (most cited first, 14 of 14)

- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Training Generative Adversarial Networks with Limited Data](https://mlsanity.com/paper/2006.06676/) (2020)
- [Alias-Free Generative Adversarial Networks](https://mlsanity.com/paper/2106.12423/) (2021)
- [ChestX-ray8: Hospital-scale Chest X-ray Database and Benchmarks on Weakly-Supervised Classification and Localization of Common Thorax Diseases](https://mlsanity.com/paper/1705.02315/) (2017)
- [Unsupervised Anomaly Detection with Generative Adversarial Networks to Guide Marker Discovery](https://mlsanity.com/paper/1703.05921/) (2017)
- [A large annotated medical image dataset for the development and evaluation of segmentation algorithms](https://mlsanity.com/paper/1902.09063/) (2019)
- [Are GANs Created Equal? A Large-Scale Study](https://mlsanity.com/paper/1711.10337/) (2017)
- [Pros and Cons of GAN Evaluation Measures](https://mlsanity.com/paper/1802.03446/) (2018)
- [GANs for Medical Image Synthesis: An Empirical Study](https://mlsanity.com/paper/2105.05318/) (2021)
- [Evaluating the Clinical Realism of Synthetic Chest X-Rays Generated Using Progressively Growing GANs](https://mlsanity.com/paper/2010.03975/) (2020)
- [TarGAN: Target-Aware Generative Adversarial Networks for Multi-modality Medical Image Translation](https://mlsanity.com/paper/2105.08993/) (2021)
- [Unsupervised anomaly detection in digital pathology using GANs](https://mlsanity.com/paper/2103.08945/) (2021)
- [Rapid treatment planning for low-dose-rate prostate brachytherapy with TP-GAN](https://mlsanity.com/paper/2103.09996/) (2021)

## Built on by (most cited first, 11 of 11)

- [Feature Extraction for Generative Medical Imaging Evaluation: New Evidence Against an Evolving Trend](https://mlsanity.com/paper/2311.13717/) (2023)
- [Self-Guided Generation of Minority Samples Using Diffusion Models](https://mlsanity.com/paper/2407.11555/) (2024)
- [Backdoor Attack and Defense in Federated Generative Adversarial Network-based Medical Image Synthesis](https://mlsanity.com/paper/2210.10886/) (2022)
- [Image Synthesis under Limited Data: A Survey and Taxonomy](https://mlsanity.com/paper/2307.16879/) (2023)
- [Report on the AAPM Grand Challenge on deep generative modeling for learning medical image statistics](https://mlsanity.com/paper/2405.01822/) (2024)
- [Hyperparameter-Free Medical Image Synthesis for Sharing Data and Improving Site-Specific Segmentation](https://mlsanity.com/paper/2404.06240/) (2024)
- [Joint Holistic and Lesion Controllable Mammogram Synthesis via Gated Conditional Diffusion Model](https://mlsanity.com/paper/2507.19201/) (2025)
- [MCR-VQGAN: A Scalable and Cost-Effective Tau PET Synthesis Approach for Alzheimer's Disease Imaging](https://mlsanity.com/paper/2512.15947/) (2025)
- [SRA-Seg: Synthetic to Real Alignment for Semi-Supervised Medical Image Segmentation](https://mlsanity.com/paper/2602.02944/) (2026)
- [Do Synthetic Brain MRIs Reliably Improve Tumour Classification? A StyleGAN2-ADA Class-Plane Augmentation Study on BRISC 2025](https://mlsanity.com/paper/2605.23094/) (2026)
- [StyleGAN2-based Out-of-Distribution Detection for Medical Imaging](https://mlsanity.com/paper/2307.10193/) (2023)

## Abstract (arXiv)

Although generative adversarial networks (GANs) have shown promise in medical imaging, they have four main limitations that impeded their utility: computational cost, data requirements, reliable evaluation measures, and training complexity. Our work investigates each of these obstacles in a novel application of StyleGAN2-ADA to high-resolution medical imaging datasets. Our dataset is comprised of liver-containing axial slices from non-contrast and contrast-enhanced computed tomography (CT) scans. Additionally, we utilized four public datasets composed of various imaging modalities. We trained a StyleGAN2 network with transfer learning (from the Flickr-Faces-HQ dataset) and data augmentation (horizontal flipping and adaptive discriminator augmentation). The network's generative quality was measured quantitatively with the Fr'echet Inception Distance (FID) and qualitatively with a visual Turing test given to seven radiologists and radiation oncologists. The StyleGAN2-ADA network achieved a FID of 5.22 (± 0.17) on our liver CT dataset. It also set new record FIDs of 10.78, 3.52, 21.17, and 5.39 on the publicly available SLIVER07, ChestX-ray14, ACDC, and Medical Segmentation Decathlon (brain tumors) datasets. In the visual Turing test, the clinicians rated generated images as real 42% of the time, approaching random guessing. Our computational ablation study revealed that transfer learning and data augmentation stabilize training and improve the perceptual quality of the generated images. We observed the FID to be consistent with human perceptual evaluation of medical images. Finally, our work found that StyleGAN2-ADA consistently produces high-quality results without hyperparameter searches or retraining.