# Adversarial and Perceptual Refinement for Compressed Sensing MRI Reconstruction

arXiv: https://arxiv.org/abs/1806.11216 · HTML: https://mlsanity.com/paper/1806.11216/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Jun 2018.

## Built on by (most cited first, 13 of 13)

- [Generative Adversarial Registration for Improved Conditional Deformable Templates](https://mlsanity.com/paper/2105.04349/) (2021)
- [FakeNews: GAN-based generation of realistic 3D volumetric data -- A systematic review and taxonomy](https://mlsanity.com/paper/2207.01390/) (2022)
- [Invertible Sharpening Network for MRI Reconstruction Enhancement](https://mlsanity.com/paper/2206.02838/) (2022)
- [Generative Adversarial Networks (GAN) Powered Fast Magnetic Resonance Imaging -- Mini Review, Comparison and Perspectives](https://mlsanity.com/paper/2105.01800/) (2021)
- [JoJoNet: Joint-contrast and Joint-sampling-and-reconstruction Network for Multi-contrast MRI](https://mlsanity.com/paper/2210.12548/) (2022)
- [Fast T2w/FLAIR MRI Acquisition by Optimal Sampling of Information Complementary to Pre-acquired T1w MRI](https://mlsanity.com/paper/2111.06400/) (2021)
- [Swap-Free Fat-Water Separation in Dixon MRI using Conditional Generative Adversarial Networks](https://mlsanity.com/paper/2107.14175/) (2021)
- [Adaptive Gradient Balancing for Undersampled MRI Reconstruction and Image-to-Image Translation](https://mlsanity.com/paper/2104.01889/) (2021)
- [Accelerated MRI With Deep Linear Convolutional Transform Learning](https://mlsanity.com/paper/2204.07923/) (2022)
- [Artificial Intelligence-Based Image Reconstruction in Cardiac Magnetic Resonance](https://mlsanity.com/paper/2209.10298/) (2022)
- [Dual-Domain Multi-Contrast MRI Reconstruction with Synthesis-based Fusion Network](https://mlsanity.com/paper/2312.00661/) (2023)
- [Unsupervised Adaptive Implicit Neural Representation Learning for Scan-Specific MRI Reconstruction](https://mlsanity.com/paper/2312.00677/) (2023)
- [No Image, No Problem: End-to-End Multi-Task Cardiac Analysis from Undersampled k-Space](https://mlsanity.com/paper/2603.09945/) (2026)

## Abstract (arXiv)

Deep learning approaches have shown promising performance for compressed sensing-based Magnetic Resonance Imaging. While deep neural networks trained with mean squared error (MSE) loss functions can achieve high peak signal to noise ratio, the reconstructed images are often blurry and lack sharp details, especially for higher undersampling rates. Recently, adversarial and perceptual loss functions have been shown to achieve more visually appealing results. However, it remains an open question how to (1) optimally combine these loss functions with the MSE loss function and (2) evaluate such a perceptual enhancement. In this work, we propose a hybrid method, in which a visual refinement component is learnt on top of an MSE loss-based reconstruction network. In addition, we introduce a semantic interpretability score, measuring the visibility of the region of interest in both ground truth and reconstructed images, which allows us to objectively quantify the usefulness of the image quality for image post-processing and analysis. Applied on a large cardiac MRI dataset simulated with 8-fold undersampling, we demonstrate significant improvements (p<0.01) over the state-of-the-art in both a human observer study and the semantic interpretability score.