# Multi-scale GANs for Memory-efficient Generation of High Resolution Medical Images

arXiv: https://arxiv.org/abs/1907.01376 · HTML: https://mlsanity.com/paper/1907.01376/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Jul 2019.

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

- [Deep Learning for Chest X-ray Analysis: A Survey](https://mlsanity.com/paper/2103.08700/) (2021)
- [A Survey of Multimodal Hallucination Evaluation and Detection](https://mlsanity.com/paper/2507.19024/) (2025)
- [Brain Image Synthesis with Unsupervised Multivariate Canonical CSCℓ4Net](https://mlsanity.com/paper/2103.11587/) (2021)
- [Toward Generating Synthetic CT Volumes using a 3D-Conditional Generative Adversarial Network](https://mlsanity.com/paper/2104.02060/) (2021)
- [Self-supervised learning for analysis of temporal and morphological drug effects in cancer cell imaging data](https://mlsanity.com/paper/2203.04289/) (2022)
- [Leapfrog Latent Consistency Model (LLCM) for Medical Images Generation](https://mlsanity.com/paper/2411.15084/) (2024)
- [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](https://mlsanity.com/paper/2501.15572/) (2025)
- [Memory-Efficient 3D High-Resolution Medical Image Synthesis Using CRF-Guided GANs](https://mlsanity.com/paper/2503.10899/) (2025)
- [Conditional Flow Matching for Generation of 3D Multi-variable Instantaneous Urban Microclimate Fields](https://mlsanity.com/paper/2610.10430/) (2026)

## Abstract (arXiv)

Currently generative adversarial networks (GANs) are rarely applied to medical images of large sizes, especially 3D volumes, due to their large computational demand. We propose a novel multi-scale patch-based GAN approach to generate large high resolution 2D and 3D images. Our key idea is to first learn a low-resolution version of the image and then generate patches of successively growing resolutions conditioned on previous scales. In a domain translation use-case scenario, 3D thorax CTs of size 512x512x512 and thorax X-rays of size 2048x2048 are generated and we show that, due to the constant GPU memory demand of our method, arbitrarily large images of high resolution can be generated. Moreover, compared to common patch-based approaches, our multi-resolution scheme enables better image quality and prevents patch artifacts.