# Exploring contrast generalisation in deep learning-based brain MRI-to-CT synthesis

arXiv: https://arxiv.org/abs/2303.10202 · HTML: https://mlsanity.com/paper/2303.10202/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 89 references that are in the map.
- First posted on arXiv 17 Mar 2023.

## Builds on (most cited first, 15 of 15)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Do ImageNet Classifiers Generalize to ImageNet?](https://mlsanity.com/paper/1902.10811/) (2019)
- [Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World](https://mlsanity.com/paper/1703.06907/) (2017)
- [A Survey on Deep Learning in Medical Image Analysis](https://mlsanity.com/paper/1702.05747/) (2017)
- [Training Deep Networks with Synthetic Data: Bridging the Reality Gap by Domain Randomization](https://mlsanity.com/paper/1804.06516/) (2018)
- [Efficient Multi-Scale 3D CNN with Fully Connected CRF for Accurate Brain Lesion Segmentation](https://mlsanity.com/paper/1603.05959/) (2016)
- [TorchIO: A Python library for efficient loading, preprocessing, augmentation and patch-based sampling of medical images in deep learning](https://mlsanity.com/paper/2003.04696/) (2020)
- [FastSurfer -- A fast and accurate deep learning based neuroimaging pipeline](https://mlsanity.com/paper/1910.03866/) (2019)
- [Deep MR to CT Synthesis using Unpaired Data](https://mlsanity.com/paper/1708.01155/) (2017)
- [A Learning Strategy for Contrast-agnostic MRI Segmentation](https://mlsanity.com/paper/2003.01995/) (2020)
- [Deep learning-based synthetic-CT generation in radiotherapy and PET: a review](https://mlsanity.com/paper/2102.02734/) (2021)
- [Deep Embedding Convolutional Neural Network for Synthesizing CT Image from T1-Weighted MR Image](https://mlsanity.com/paper/1709.02073/) (2017)
- [Object Detection using Domain Randomization and Generative Adversarial Refinement of Synthetic Images](https://mlsanity.com/paper/1805.11778/) (2018)
- [Deep learning-based synthetic CT generation from MR images: comparison of generative adversarial and residual neural networks](https://mlsanity.com/paper/2103.01609/) (2021)

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

- [Local Gamma Augmentation for Ischemic Stroke Lesion Segmentation on MRI](https://mlsanity.com/paper/2401.06893/) (2024)
- [A Proof-of-Concept Study of Multitask Learning for Cranial Synthetic CT Generation Across Heterogeneous MRI Field Strengths](https://mlsanity.com/paper/2605.00923/) (2026)

## Abstract (arXiv)

Background: Synthetic computed tomography (sCT) has been proposed and increasingly clinically adopted to enable magnetic resonance imaging (MRI)-based radiotherapy. Deep learning (DL) has recently demonstrated the ability to generate accurate sCT from fixed MRI acquisitions. However, MRI protocols may change over time or differ between centres resulting in low-quality sCT due to poor model generalisation. Purpose: investigating domain randomisation (DR) to increase the generalisation of a DL model for brain sCT generation. Methods: CT and corresponding T1-weighted MRI with/without contrast, T2-weighted, and FLAIR MRI from 95 patients undergoing RT were collected, considering FLAIR the unseen sequence where to investigate generalisation. A ``Baseline'' generative adversarial network was trained with/without the FLAIR sequence to test how a model performs without DR. Image similarity and accuracy of sCT-based dose plans were assessed against CT to select the best-performing DR approach against the Baseline. Results: The Baseline model had the poorest performance on FLAIR, with mean absolute error (MAE)=106±20.7 HU (mean±σ). Performance on FLAIR significantly improved for the DR model with MAE=99.0±14.9 HU, but still inferior to the performance of the Baseline+FLAIR model (MAE=72.6±10.1 HU). Similarly, an improvement in γ-pass rate was obtained for DR vs Baseline. Conclusions: DR improved image similarity and dose accuracy on the unseen sequence compared to training only on acquired MRI. DR makes the model more robust, reducing the need for re-training when applying a model on sequences unseen and unavailable for retraining.