# MR-Contrast-Aware Image-to-Image Translations with Generative Adversarial Networks

arXiv: https://arxiv.org/abs/2104.01449 · HTML: https://mlsanity.com/paper/2104.01449/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 29 references that are in the map.
- First posted on arXiv 3 Apr 2021.

## Builds on (most cited first, 12 of 12)

- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [StarGAN v2: Diverse Image Synthesis for Multiple Domains](https://mlsanity.com/paper/1912.01865/) (2019)
- [Conditional Image Synthesis With Auxiliary Classifier GANs](https://mlsanity.com/paper/1610.09585/) (2016)
- [Are GANs Created Equal? A Large-Scale Study](https://mlsanity.com/paper/1711.10337/) (2017)
- [Image Synthesis in Multi-Contrast MRI with Conditional Generative Adversarial Networks](https://mlsanity.com/paper/1802.01221/) (2018)
- [Distribution Matching Losses Can Hallucinate Features in Medical Image Translation](https://mlsanity.com/paper/1805.08841/) (2018)
- [The Unusual Effectiveness of Averaging in GAN Training](https://mlsanity.com/paper/1806.04498/) (2018)
- [GrappaNet: Combining Parallel Imaging with Deep Learning for Multi-Coil MRI Reconstruction](https://mlsanity.com/paper/1910.12325/) (2019)
- [SUSAN: Segment Unannotated image Structure using Adversarial Network](https://mlsanity.com/paper/1812.00555/) (2018)
- [Physics-informed brain MRI segmentation](https://mlsanity.com/paper/2001.10767/) (2020)

## Built on by (most cited first, 10 of 10)

- [One Model to Synthesize Them All: Multi-contrast Multi-scale Transformer for Missing Data Imputation](https://mlsanity.com/paper/2204.13738/) (2022)
- [SMU-Net: Style matching U-Net for brain tumor segmentation with missing modalities](https://mlsanity.com/paper/2204.02961/) (2022)
- [One Model to Unite Them All: Personalized Federated Learning of Multi-Contrast MRI Synthesis](https://mlsanity.com/paper/2207.06509/) (2022)
- [Cascaded Multi-path Shortcut Diffusion Model for Medical Image Translation](https://mlsanity.com/paper/2405.12223/) (2024)
- [Physics-Informed Latent Diffusion for Multimodal Brain MRI Synthesis](https://mlsanity.com/paper/2409.13532/) (2024)
- [Quantitative Metrics for Benchmarking Medical Image Harmonization](https://mlsanity.com/paper/2402.04426/) (2024)
- [Generalizable synthetic MRI with physics-informed convolutional networks](https://mlsanity.com/paper/2305.12570/) (2023)
- [A Plug-and-Play Method for Guided Multi-contrast MRI Reconstruction based on Content/Style Modeling](https://mlsanity.com/paper/2409.13477/) (2024)
- [Mitigating analytical variability in fMRI results with style transfer](https://mlsanity.com/paper/2404.03703/) (2024)
- [MRecover: A Conditional Generative Model for Recovering Motion-Corrupted MR images Using AI Generated Contrast](https://mlsanity.com/paper/2605.21669/) (2026)

## Abstract (arXiv)

Purpose A Magnetic Resonance Imaging (MRI) exam typically consists of several sequences that yield different image contrasts. Each sequence is parameterized through multiple acquisition parameters that influence image contrast, signal-to-noise ratio, acquisition time, and/or resolution. Depending on the clinical indication, different contrasts are required by the radiologist to make a diagnosis. As MR sequence acquisition is time consuming and acquired images may be corrupted due to motion, a method to synthesize MR images with adjustable contrast properties is required. Methods Therefore, we trained an image-to-image generative adversarial network conditioned on the MR acquisition parameters repetition time and echo time. Our approach is motivated by style transfer networks, whereas the "style" for an image is explicitly given in our case, as it is determined by the MR acquisition parameters our network is conditioned on. Results This enables us to synthesize MR images with adjustable image contrast. We evaluated our approach on the fastMRI dataset, a large set of publicly available MR knee images, and show that our method outperforms a benchmark pix2pix approach in the translation of non-fat-saturated MR images to fat-saturated images. Our approach yields a peak signal-to-noise ratio and structural similarity of 24.48 and 0.66, surpassing the pix2pix benchmark model significantly. Conclusion Our model is the first that enables fine-tuned contrast synthesis, which can be used to synthesize missing MR contrasts or as a data augmentation technique for AI training in MRI.