{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,29]],"date-time":"2025-12-29T00:22:49Z","timestamp":1766967769830,"version":"3.48.0"},"reference-count":23,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2025,12,26]],"date-time":"2025-12-26T00:00:00Z","timestamp":1766707200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100002496","name":"Hongik University","doi-asserted-by":"publisher","award":["2025S101801"],"award-info":[{"award-number":["2025S101801"]}],"id":[{"id":"10.13039\/501100002496","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Imaging"],"abstract":"<jats:p>Long scan times remain a fundamental challenge in Magnetic Resonance Imaging (MRI). Accelerated MRI, which undersamples k-space, requires robust reconstruction methods to solve the ill-posed inverse problem. Recent methods have shown promise by processing image-domain features to capture global spatial context. However, these approaches are often limited, as they fail to fully leverage the unique, sequential characteristics of the k-space data themselves, which are critical for disentangling aliasing artifacts. This study introduces a novel, hybrid, dual-domain deep learning architecture that combines a ViT-based autoencoder with Bidirectional Recurrent Neural Networks (BiRNNs). The proposed architecture is designed to synergistically process information from both domains: it uses the ViT to learn features from image patches and the BiRNNs to model sequential dependencies directly from k-space data. We conducted a comprehensive comparative analysis against a standard ViT with only an MLP head (Model 1), a ViT autoencoder operating solely in the image domain (Model 2), and a competitive UNet baseline. Evaluations were performed on retrospectively undersampled neuro-MRI data using R = 4 and R = 8 acceleration factors with both regular and random sampling patterns. The proposed architecture demonstrated superior performance and robustness, significantly outperforming all other models in challenging high-acceleration and random-sampling scenarios. The results confirm that integrating sequential k-space processing via BiRNNs is critical for superior artifact suppression, offering a robust solution for accelerated MRI.<\/jats:p>","DOI":"10.3390\/jimaging12010011","type":"journal-article","created":{"date-parts":[[2025,12,28]],"date-time":"2025-12-28T23:54:36Z","timestamp":1766966076000},"page":"11","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Hybrid Vision Transformer-BiRNN Architecture for Direct k-Space to Image Reconstruction in Accelerated MRI"],"prefix":"10.3390","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7472-7702","authenticated-orcid":false,"given":"Changheun","family":"Oh","sequence":"first","affiliation":[{"name":"Department of Software and Communication Engineering, Hongik University, Sejong 30016, Republic of Korea"}]}],"member":"1968","published-online":{"date-parts":[[2025,12,26]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"573","DOI":"10.1002\/jmri.24687","article-title":"Image reconstruction: An overview for clinicians","volume":"41","author":"Hansen","year":"2015","journal-title":"J. Magn. Reson. Imaging"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"952","DOI":"10.1002\/(SICI)1522-2594(199911)42:5<952::AID-MRM16>3.0.CO;2-S","article-title":"SENSE: Sensitivity encoding for fast MRI","volume":"42","author":"Pruessmann","year":"1999","journal-title":"Magn. Reson. Med."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1202","DOI":"10.1002\/mrm.10171","article-title":"Generalized autocalibrating partially parallel acquisitions (GRAPPA)","volume":"47","author":"Griswold","year":"2002","journal-title":"Magn. Reson. Med. Off. J. Int. Soc. Magn. Reson. Med."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"650","DOI":"10.1002\/mrm.21679","article-title":"Comparison of parallel MRI reconstruction methods for accelerated 3D fast spin-echo imaging","volume":"60","author":"Xiao","year":"2008","journal-title":"Magn. Reson. Med."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"487","DOI":"10.1038\/nature25988","article-title":"Image reconstruction by domain-transform manifold learning","volume":"555","author":"Zhu","year":"2018","journal-title":"Nature"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"116579","DOI":"10.1016\/j.neuroimage.2020.116579","article-title":"Fidelity imposed network edit (FINE) for solving ill-posed image reconstruction","volume":"211","author":"Zhang","year":"2020","journal-title":"Neuroimage"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"108098","DOI":"10.1016\/j.compbiomed.2024.108098","article-title":"Domain transformation learning for MR image reconstruction from dual domain input","volume":"170","author":"Oh","year":"2024","journal-title":"Comput. Biol. Med."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"128","DOI":"10.1109\/MSP.2019.2950640","article-title":"Deep-learning methods for parallel magnetic resonance imaging reconstruction: A survey of the current approaches, trends, and issues","volume":"37","author":"Knoll","year":"2020","journal-title":"IEEE Signal Process. Mag."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"400","DOI":"10.1016\/S1470-2045(23)00641-1","article-title":"Deep-learning-based reconstruction of undersampled MRI to reduce scan times: A multicentre, retrospective, cohort study","volume":"25","author":"Rastogi","year":"2024","journal-title":"Lancet Oncol."},{"key":"ref_10","unstructured":"Lin, K., and Heckel, R. (2022, January 6\u20138). Vision transformers enable fast and robust accelerated MRI. Proceedings of the International Conference on Medical Imaging with Deep Learning, Zurich, Switzerland."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"6135","DOI":"10.1609\/aaai.v39i6.32656","article-title":"Boosting vit-based mri reconstruction from the perspectives of frequency modulation, spatial purification, and scale diversification","volume":"39","author":"Meng","year":"2025","journal-title":"AAAI"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Chen, H., Wang, Y., Guo, T., Xu, C., Deng, Y., Liu, Z., Ma, S., Xu, C., Xu, C., and Gao, W. (2021, January 20\u201325). Pre-trained image processing transformer. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.01212"},{"key":"ref_13","unstructured":"Dosovitskiy, A. (2020). An image is worth 16x16 words: Transformers for image recognition at scale. arXiv."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Li, W., Lin, Z., Zhou, K., Qi, L., Wang, Y., and Jia, J. (2022, January 18\u201324). Mat: Mask-aware transformer for large hole image inpainting. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, New Orleans, LA, USA.","DOI":"10.1109\/CVPR52688.2022.01049"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Yalcinbas, M.F., Ozturk, C., Ozyurt, O., Emir, U.E., and Bagci, U. (2025). Rosette Trajectory MRI Reconstruction with Vision Transformers. Tomography, 11.","DOI":"10.20944\/preprints202502.0324.v1"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Li, R., Pan, J., Zhu, Y., Ni, J., and Rueckert, D. (2024). Classification, Regression and Segmentation directly from k-Space in Cardiac MRI. International Workshop on Machine Learning in Medical Imaging, Springer.","DOI":"10.1007\/978-3-031-73284-3_4"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"281","DOI":"10.1016\/j.neucom.2022.04.051","article-title":"Swin transformer for fast MRI","volume":"493","author":"Huang","year":"2022","journal-title":"Neurocomputing"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"280","DOI":"10.1109\/TMI.2018.2863670","article-title":"Convolutional recurrent neural networks for dynamic MR image reconstruction","volume":"38","author":"Qin","year":"2018","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"2033","DOI":"10.1109\/TMI.2022.3153849","article-title":"Pyramid convolutional RNN for MRI image reconstruction","volume":"41","author":"Chen","year":"2022","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_20","unstructured":"Zbontar, J., Knoll, F., Sriram, A., Murrell, T., Huang, Z., Muckley, M.J., Defazio, A., Stern, R., Johnson, P., and Bruno, M. (2018). fastMRI: An open dataset and benchmarks for accelerated MRI. arXiv."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1109\/TIP.2003.819861","article-title":"Image quality assessment: From error visibility to structural similarity","volume":"13","author":"Wang","year":"2004","journal-title":"IEEE Trans. Image Process."},{"key":"ref_22","first-page":"2117","article-title":"A visual information fidelity approach to video quality assessment","volume":"Volume 7","author":"Sheikh","year":"2005","journal-title":"The First International Workshop on Video Processing and Quality Metrics for Consumer Electronics"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"10991","DOI":"10.1038\/s41598-024-59705-0","article-title":"Accelerated MRI reconstructions via variational network and feature domain learning","volume":"14","author":"Giannakopoulos","year":"2024","journal-title":"Sci. Rep."}],"container-title":["Journal of Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-433X\/12\/1\/11\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,29]],"date-time":"2025-12-29T00:18:02Z","timestamp":1766967482000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-433X\/12\/1\/11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,26]]},"references-count":23,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1]]}},"alternative-id":["jimaging12010011"],"URL":"https:\/\/doi.org\/10.3390\/jimaging12010011","relation":{},"ISSN":["2313-433X"],"issn-type":[{"value":"2313-433X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,26]]}}}