# Synthetic CT Generation from MRI Using Improved DualGAN

arXiv: https://arxiv.org/abs/1909.08942 · HTML: https://mlsanity.com/paper/1909.08942/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Sep 2019.

## Built on by (most cited first, 2 of 2)

- [A survey on GANs for computer vision: Recent research, analysis and taxonomy](https://mlsanity.com/paper/2203.11242/) (2022)
- [Towards Ultrafast MRI via Extreme k-Space Undersampling and Superresolution](https://mlsanity.com/paper/2103.02940/) (2021)

## Abstract (arXiv)

Synthetic CT image generation from MRI scan is necessary to create radiotherapy plans without the need of co-registered MRI and CT scans. The chosen baseline adversarial model with cycle consistency permits unpaired image-to-image translation. Perceptual loss function term and coordinate convolutional layer were added to improve the quality of translated images. The proposed architecture was tested on paired MRI-CT dataset, where the synthetic CTs were compared to corresponding original CT images. The MAE between the synthetic CT images and the real CT scans is 61 HU computed inside of the true CTs body shape.