# Comparative clinical evaluation of "memory-efficient" synthetic 3d generative adversarial networks (gan) head-to-head to state of art: results on computed tomography of the chest

arXiv: https://arxiv.org/abs/2501.15572 · HTML: https://mlsanity.com/paper/2501.15572/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 42 references that are in the map.
- First posted on arXiv 26 Jan 2025.

## Builds on (most cited first, 20 of 20)

- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Improved Training of Wasserstein GANs](https://mlsanity.com/paper/1704.00028/) (2017)
- [Density estimation using Real NVP](https://mlsanity.com/paper/1605.08803/) (2016)
- [Autoencoding beyond pixels using a learned similarity metric](https://mlsanity.com/paper/1512.09300/) (2015)
- [GAN-based Synthetic Medical Image Augmentation for increased CNN Performance in Liver Lesion Classification](https://mlsanity.com/paper/1803.01229/) (2018)
- [Validation, comparison, and combination of algorithms for automatic detection of pulmonary nodules in computed tomography images: the LUNA16 challenge](https://mlsanity.com/paper/1612.08012/) (2016)
- [An empirical study on evaluation metrics of generative adversarial networks](https://mlsanity.com/paper/1806.07755/) (2018)
- [Generation of 3D Brain MRI Using Auto-Encoding Generative Adversarial Networks](https://mlsanity.com/paper/1908.02498/) (2019)
- [GANs for Medical Image Synthesis: An Empirical Study](https://mlsanity.com/paper/2105.05318/) (2021)
- [Hierarchical Amortized Training for Memory-efficient High Resolution 3D GAN](https://mlsanity.com/paper/2008.01910/) (2020)
- [3D Convolutional Encoder-Decoder Network for Low-Dose CT via Transfer Learning from a 2D Trained Network](https://mlsanity.com/paper/1802.05656/) (2018)
- [3D-StyleGAN: A Style-Based Generative Adversarial Network for Generative Modeling of Three-Dimensional Medical Images](https://mlsanity.com/paper/2107.09700/) (2021)
- [Deep CT to MR Synthesis using Paired and Unpaired Data](https://mlsanity.com/paper/1805.10790/) (2018)
- [Vox2Vox: 3D-GAN for Brain Tumour Segmentation](https://mlsanity.com/paper/2003.13653/) (2020)
- [Synthesizing Diverse Lung Nodules Wherever Massively: 3D Multi-Conditional GAN-based CT Image Augmentation for Object Detection](https://mlsanity.com/paper/1906.04962/) (2019)
- [Cancer Metastasis Detection With Neural Conditional Random Field](https://mlsanity.com/paper/1806.07064/) (2018)
- [Virtual Thin Slice: 3D Conditional GAN-based Super-resolution for CT Slice Interval](https://mlsanity.com/paper/1908.11506/) (2019)
- [Artificial Intelligence in Glioma Imaging: Challenges and Advances](https://mlsanity.com/paper/1911.12886/) (2019)
- [Multi-scale GANs for Memory-efficient Generation of High Resolution Medical Images](https://mlsanity.com/paper/1907.01376/) (2019)
- [CT-SGAN: Computed Tomography Synthesis GAN](https://mlsanity.com/paper/2110.09288/) (2021)

## Abstract (arXiv)

Generative Adversarial Networks (GANs) are increasingly used to generate synthetic medical images, addressing the critical shortage of annotated data for training Artificial Intelligence systems. This study introduces CRF-GAN, a novel memory-efficient GAN architecture that enhances structural consistency in 3D medical image synthesis. Integrating Conditional Random Fields within a two-step generation process allows CRF-GAN improving spatial coherence while maintaining high-resolution image quality. The model's performance is evaluated against the state-of-the-art hierarchical (HA)-GAN model. Materials and Methods: We evaluate the performance of CRF-GAN against the HA-GAN model. The comparison between the two models was made through a quantitative evaluation, using FID and MMD metrics, and a qualitative evaluation, through a two-alternative forced choice (2AFC) test completed by a pool of 12 resident radiologists, to assess the realism of the generated images. Results: CRF-GAN outperformed HA-GAN with lower FID and MMD scores, indicating better image fidelity. The 2AFC test showed a significant preference for images generated by CRF-Gan over those generated by HA-GAN. Additionally, CRF-GAN demonstrated 9.34% lower memory usage and achieved up to 14.6% faster training speeds, offering substantial computational savings. Discussion: CRF-GAN model successfully generates high-resolution 3D medical images with non-inferior quality to conventional models, while being more memory-efficient and faster. The key objective was not only to lower the computational cost but also to reallocate the freed-up resources towards the creation of higher-resolution 3D imaging, which is still a critical factor limiting their direct clinical applicability. Moreover, unlike many previous studies, we combined qualitative and quantitative assessments to obtain a more holistic feedback on the model's performance.