Explicit Abnormality Extraction for Unsupervised Motion Artifact Reduction in Magnetic Resonance Imaging
Not on the map. Why?
Abstract (arXiv)
Motion artifacts compromise the quality of magnetic resonance imaging (MRI) and pose challenges to achieving diagnostic outcomes and image-guided therapies. In recent years, supervised deep learning approaches have emerged as successful solutions for motion artifact reduction (MAR). One disadvantage of these methods is their dependency on acquiring paired sets of motion artifact-corrupted (MA-corrupted) and motion artifact-free (MA-free) MR images for training purposes. Obtaining such image pairs is difficult and therefore limits the application of supervised training. In this paper, we propose a novel UNsupervised Abnormality Extraction Network (UNAEN) to alleviate this problem. Our network is capable of working with unpaired MA-corrupted and MA-free images. It converts the MA-corrupted images to MA-reduced images by extracting abnormalities from the MA-corrupted images using a proposed artifact extractor, which intercepts the residual artifact maps from the MA-corrupted MR images explicitly, and a reconstructor to restore the original input from the MA-reduced images. The performance of UNAEN was assessed by experimenting with various publicly available MRI datasets and comparing them with state-of-the-art methods. The quantitative evaluation demonstrates the superiority of UNAEN over alternative MAR methods and visually exhibits fewer residual artifacts. Our results substantiate the potential of UNAEN as a promising solution applicable in real-world clinical environments, with the capability to enhance diagnostic accuracy and facilitate image-guided therapies. Our codes are publicly available at https://github.com/YuSheng-Zhou/UNAEN.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 21 of its 56 references that are in the map. First posted on arXiv 4 Jan 2023.
Builds on
21 of 56 references.
References · 21
- 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
- 2022Generative Adversarial Networkscited by 5,603
- 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
- 2014Conditional Generative Adversarial Netscited by 2,152
- 2018Image Super-Resolution Using Very Deep Residual Channel Attention Networkscited by 1,256
- 2017Deep Image Priorcited by 1,097
- 2014NICE: Non-linear Independent Components Estimationcited by 1,052
- 2016Least Squares Generative Adversarial Networkscited by 1,000
- 2016Conditional Image Generation with PixelCNN Decoderscited by 859
- 2018Noise2Noise: Learning Image Restoration without Clean Datacited by 526
- 2018Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challengecited by 508
- 2018fastMRI: An Open Dataset and Benchmarks for Accelerated MRIcited by 464
9 more
- 2018Noise2Void - Learning Denoising from Single Noisy Imagescited by 359
- 2022Revisiting RCAN: Improved Training for Image Super-Resolutioncited by 32
- 2017Deep Learning with Domain Adaptation for Accelerated Projection-Reconstruction MRcited by 31
- 2019Unsupervised Adversarial Correction of Rigid MR Motion Artifactscited by 11
- 2018Method for motion artifact reduction using a convolutional neural network for dynamic contrast enhanced MRI of the livercited by 7
- 2021ISCL: Interdependent Self-Cooperative Learning for Unpaired Image Denoisingcited by 6
- 2013Sparse MRI for motion correctioncited by 5
- 2021An unsupervised deep learning framework for medical image denoisingcited by 4
- 2022SRNR: Training neural networks for Super-Resolution MRI using Noisy high-resolution Reference datacited by 1
Built on by
Citing papers per year: 2023: 1.
1 paper.