# Motion Artifact-Aware Self-Supervised Representation Learning for 3D Brain MRI Motion Artifact Reduction

arXiv: https://arxiv.org/abs/2608.10170 · HTML: https://mlsanity.com/paper/2608.10170/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 48 references that are in the map.
- First posted on arXiv 10 Aug 2026.

## Builds on (most cited first, 22 of 22)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [Spectral Normalization for Generative Adversarial Networks](https://mlsanity.com/paper/1802.05957/) (2018)
- [Medical Image Segmentation Review: The success of U-Net](https://mlsanity.com/paper/2211.14830/) (2022)
- [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)
- [Automated brain extraction of multi-sequence MRI using artificial neural networks](https://mlsanity.com/paper/1901.11341/) (2019)
- [Deep Learning in Medical Image Registration: A Review](https://mlsanity.com/paper/1912.12318/) (2019)
- [Modulating Image Restoration with Continual Levels via Adaptive Feature Modification Layers](https://mlsanity.com/paper/1904.08118/) (2019)
- [Deep Learning for Retrospective Motion Correction in MRI: A Comprehensive Review](https://mlsanity.com/paper/2305.06739/) (2023)
- [Stacked U-Nets with Self-Assisted Priors Towards Robust Correction of Rigid Motion Artifact in Brain MRI](https://mlsanity.com/paper/2111.06401/) (2021)
- [Learning MRI Artifact Removal With Unpaired Data](https://mlsanity.com/paper/2110.04604/) (2021)
- [Annealed Score-Based Diffusion Model for MR Motion Artifact Reduction](https://mlsanity.com/paper/2301.03027/) (2023)
- [SISMIK for brain MRI: Deep-learning-based motion estimation and model-based motion correction in k-space](https://mlsanity.com/paper/2312.13220/) (2023)
- [Physics-Informed Deep Learning for Motion-Corrected Reconstruction of Quantitative Brain MRI](https://mlsanity.com/paper/2403.08298/) (2024)
- [IM-MoCo: Self-supervised MRI Motion Correction using Motion-Guided Implicit Neural Representations](https://mlsanity.com/paper/2407.02974/) (2024)
- [Moner: Motion Correction in Undersampled Radial MRI with Unsupervised Neural Representation](https://mlsanity.com/paper/2409.16921/) (2024)
- [A Physics-Informed Deep Learning Model for MRI Brain Motion Correction](https://mlsanity.com/paper/2502.09296/) (2025)
- [DIMA: DIffusing Motion Artifacts for unsupervised correction in brain MRI images](https://mlsanity.com/paper/2504.06767/) (2025)
- [Systematic Review and Meta-analysis of AI-driven MRI Motion Artifact Detection and Correction](https://mlsanity.com/paper/2509.05071/) (2025)
- [Self-Supervised k-Space Regularization for Motion-Resolved Abdominal MRI Using Neural Implicit k-Space Representation](https://mlsanity.com/paper/2404.08350/) (2024)

## Abstract (arXiv)

Patient motion remains a source of image degradation in brain MRI, leading to signal loss, blurring, and geometric distortion that compromise quantitative analysis. Existing deep learning methods for motion correction typically rely on paired clean-corrupted data or k-space acquisitions, which are rarely available in clinical settings. We propose SSRL-MAR, a motion artifact-aware unpaired representation learning framework for motion artifact reduction that requires neither paired training data nor explicit motion labels. SSRL-MAR employed a three-stage training strategy: (1) contrastive learning on 3D patches to extract motion representations by contrasting clean and synthetically corrupted images, (2) a motion artifact-aware synthesis network to generate motion artifacts from clean scans, and (3) a motion artifact-aware generator to restore clean volumes using the learned degrader for self-supervised supervision. On in-silico dataset, SSRL-MAR achieved PSNR 23.81dB, SSIM 91.55%, and NMSE 0.79%. On in-vivo MR-ART dataset, the pretrained model reduced motion distortion, and unsupervised domain adaptation further improved anatomical fidelity. Against a source-only supervised model trained on the same simulated pairs, SSRL-MAR improved PSNR by up to 2.0 dB on MR-ART after unsupervised domain adaptation, and remained within 0.25-0.47 dB of an oracle supervised model that requires real paired data unavailable in practice. At the milder motion level, volumetric error in structures such as the corpus callosum and ventricular system decreased by more than 50%, confirming improved neuroanatomical consistency. These results indicate that SSRL-MAR provides a robust and scalable image-domain solution for 3D brain MRI motion correction, enabling reliable structural quantification in large-scale neuroimaging studies without requiring prospectively acquired pairs or acquisition-specific calibration.