Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{206759,
        author = {Ms.Sukshma R.D and Dr.Thimmaraju S.N},
        title = {Deep Learning for Artifacts Reduction: Motion Correction in Medical Imaging: A Comprehensive Literature Review},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {2},
        pages = {2610-2620},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=206759},
        abstract = {Magnetic Resonance Imaging (MRI) provides unmatched soft-tissue contrast for the diagnosis of neurological, musculoskeletal, cardiovascular, and oncological conditions, but its comparatively long acquisition time makes it highly sensitive to voluntary and involuntary patient motion. Motion-induced artifacts blurring, ghosting, ringing, and geometric distortion degrade diagnostic confidence and frequently necessitate costly re-scans. Over the past decade, artificial intelligence (AI) and deep learning (DL) have transformed retrospective MRI motion correction and image reconstruction, giving rise to convolutional, adversarial, transformer-based, diffusion-based, and physics-guided k-space learning paradigms. This paper presents a structured, thematically organized review of 40 recent IEEE-indexed studies on AI-driven MRI motion correction and reconstruction. A comparative analysis contrasts representative architectures across datasets, reported quantitative performance, advantages, and limitations. Persistent challenges concerning cross-scanner generalization, hallucinated anatomy, computational cost, and the scarcity of paired real-motion clinical data are identified, and future directions combining physics-informed constraints with generative priors are proposed to guide the development of clinically trustworthy, artifact-robust MRI reconstruction systems.},
        keywords = {Magnetic Resonance Imaging; Motion Artifact Correction; Deep Learning; Generative Adversarial Networks; Vision Transformers; Diffusion Models; Image Reconstruction; k-Space Learning; Compressed Sensing.},
        month = {July},
        }