{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T06:51:26Z","timestamp":1780987886996,"version":"3.54.1"},"reference-count":53,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T00:00:00Z","timestamp":1750204800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>Recent advances in MRI reconstruction have demonstrated remarkable success through deep learning-based models. However, most existing methods rely heavily on large-scale, task-specific datasets, making reconstruction in data-limited settings a critical yet underexplored challenge. While regularization by denoising (RED) leverages denoisers as priors for reconstruction, we propose Regularization by Neural Style Transfer (RNST), a novel framework that integrates a neural style transfer (NST) engine with a denoiser to enable magnetic field-transfer reconstruction. RNST generates high-field-quality images from low-field inputs without requiring paired training data, leveraging style priors to address limited-data settings. Our experiment results demonstrate RNST\u2019s ability to reconstruct high-quality images across diverse anatomical planes (axial, coronal, sagittal) and noise levels, achieving superior clarity, contrast, and structural fidelity compared to lower-field references. Crucially, RNST maintains robustness even when style and content images lack exact alignment, broadening its applicability in clinical environments where precise reference matches are unavailable. By combining the strengths of NST and denoising, RNST offers a scalable, data-efficient solution for MRI field-transfer reconstruction, demonstrating significant potential for resource-limited settings.<\/jats:p>","DOI":"10.3389\/frai.2025.1579251","type":"journal-article","created":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T05:40:50Z","timestamp":1750225250000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Regularization by neural style transfer for MRI field-transfer reconstruction with limited data"],"prefix":"10.3389","volume":"8","author":[{"given":"Guoyao","family":"Shen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yancheng","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mengyu","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ryan","family":"McNaughton","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hernan","family":"Jara","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sean B.","family":"Andersson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chad W.","family":"Farris","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stephan","family":"Anderson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,6,18]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.2140\/pjm.1966.16.1","article-title":"Minimization of functions having Lipschitz continuous first partial derivatives","volume":"16","author":"Armijo","year":"1966","journal-title":"Pac. J. Math."},{"key":"ref2","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2018.00789","article-title":"Multi-content GAN for few-shot font style transfer","author":"Azadi","year":"2018"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1109\/MSP.2007.914731","article-title":"An introduction to compressive sampling","volume":"25","author":"Candes","year":"2008","journal-title":"IEEE Signal Process. Mag."},{"key":"ref4","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2018.00696","article-title":"Stereoscopic Neural Style Transfer","author":"Chen","year":"2018"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"2080","DOI":"10.1109\/TIP.2007.901238","article-title":"Image Denoising by sparse 3-D transform-domain collaborative filtering","volume":"16","author":"Dabov","year":"2007","journal-title":"IEEE Trans. Image Process."},{"key":"ref6","volume-title":"Newton methods for nonlinear problems: Affine invariance and adaptive algorithms","author":"Deuflhard","year":"2005"},{"key":"ref7","first-page":"720","article-title":"A disentangled latent space for cross-site MRI harmonization","volume-title":"Medical Image Computing and Computer Assisted Intervention","author":"Dewey","year":"2020"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"1289","DOI":"10.1109\/TIT.2006.871582","article-title":"Compressed sensing","volume":"52","author":"Donoho","year":"2006","journal-title":"IEEE Trans. Inf. Theory"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"1323","DOI":"10.1016\/j.mri.2012.05.001","article-title":"3D slicer as an image computing platform for the quantitative imaging network","volume":"30","author":"Fedorov","year":"2012","journal-title":"Magn. Reson. Imaging"},{"key":"ref10","first-page":"475","article-title":"Image reconstruction for MRI using deep CNN priors trained without Groundtruth","author":"Gan","year":"2020"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"2371","DOI":"10.1109\/TMI.2022.3163018","article-title":"Deformation-compensated learning for image reconstruction without ground truth","volume":"41","author":"Gan","year":"2022","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"326","DOI":"10.1167\/16.12.326","article-title":"A neural algorithm of artistic style","volume":"16","author":"Gatys","year":"","journal-title":"Arxiv"},{"key":"ref13","article-title":"Texture synthesis using convolutional neural networks","volume":"28","author":"Gatys","year":"","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref14","article-title":"Generative Adversarial Nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref15","doi-asserted-by":"publisher","first-page":"582","DOI":"10.1109\/TMI.2023.3314747","article-title":"ReconFormer: accelerated MRI reconstruction using recurrent transformer","volume":"43","author":"Guo","year":"2024","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"3055","DOI":"10.1002\/mrm.26977","article-title":"Learning a variational network for reconstruction of accelerated MRI data","volume":"79","author":"Hammernik","year":"2018","journal-title":"Magn. Reson. Med."},{"key":"ref17","first-page":"768","article-title":"Distributionally robust image classifiers for stroke diagnosis in accelerated MRI","volume-title":"Medical Image Computing and Computer Assisted Intervention (MICCAI)","author":"Hao","year":"2023"},{"key":"ref18","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2016.90","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"ref19","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref20","doi-asserted-by":"publisher","first-page":"3365","DOI":"10.1109\/TVCG.2019.2921336","article-title":"Neural style transfer: a review","volume":"26","author":"Jing","year":"2020","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"key":"ref21","doi-asserted-by":"publisher","first-page":"102846","DOI":"10.1016\/j.media.2023.102846","article-title":"Diffusion models in medical imaging: a comprehensive survey","volume":"88","author":"Kazerouni","year":"2023","journal-title":"Med. Image Anal."},{"key":"ref22","first-page":"12715","article-title":"DCFace: synthetic face generation with dual condition diffusion model","author":"Kim","year":"2023"},{"key":"ref23","first-page":"4015","article-title":"Segment anything","author":"Kirillov","year":"2023"},{"key":"ref24","article-title":"Flow matching for generative modeling","volume-title":"Arxiv","author":"Lipman","year":"2023"},{"key":"ref25","article-title":"Flow matching guide and code","volume-title":"Arxiv","author":"Lipman","year":"2024"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"632","DOI":"10.3390\/app14020632","article-title":"Biomedical image segmentation using Denoising diffusion probabilistic models: a comprehensive review and analysis","volume":"14","author":"Liu","year":"2024","journal-title":"Appl. Sci."},{"key":"ref27","doi-asserted-by":"publisher","first-page":"313","DOI":"10.1007\/978-3-030-87199-4_30","article-title":"Style transfer using generative adversarial networks for multi-site MRI harmonization","volume":"12903","author":"Liu","year":"2021","journal-title":"Med. Image Comput. Comput. Assist. Interv."},{"key":"ref28","doi-asserted-by":"publisher","first-page":"1088","DOI":"10.1109\/JSTSP.2020.2998402","article-title":"RARE: image reconstruction using deep priors learned without Groundtruth","volume":"14","author":"Liu","year":"2020","journal-title":"IEEE J. Sel. Top. Signal Process."},{"key":"ref29","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2017.740","article-title":"Deep photo style transfer","author":"Luan","year":"2017"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"1182","DOI":"10.1002\/mrm.21391","article-title":"Sparse MRI: the application of compressed sensing for rapid MR imaging","volume":"58","author":"Lustig","year":"2007","journal-title":"Magn. Reson. Med."},{"key":"ref31","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2015.7299155","article-title":"Understanding deep image representations by inverting them","author":"Mahendran","year":"2015"},{"key":"ref32","article-title":"DeepRED: deep image prior powered by RED","author":"Mataev","year":"2019"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"419","DOI":"10.1148\/radiol.210385","article-title":"Quantitative MRI characterization of the extremely preterm brain at adolescence: atypical versus Neurotypical developmental pathways","volume":"304","author":"McNaughton","year":"2022","journal-title":"Radiology"},{"key":"ref34","first-page":"3501","article-title":"prDeep: robust phase retrieval with a flexible deep network","author":"Metzler","year":"2018"},{"key":"ref35","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref36","doi-asserted-by":"publisher","first-page":"632","DOI":"10.1109\/ISBI.2004.1398617","article-title":"3D slicer","volume":"1","author":"Pieper","year":"2004","journal-title":"IEEE Int. Symp. Biomed. Imaging"},{"key":"ref37","doi-asserted-by":"publisher","first-page":"1804","DOI":"10.1137\/16M1102884","article-title":"The little engine that could: regularization by Denoising (RED)","volume":"10","author":"Romano","year":"2017","journal-title":"SIAM J. Imaging Sci."},{"key":"ref38","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1097\/RLI.0000000000000824","article-title":"The clinical utility of magnetic resonance imaging according to field strength, specifically addressing the breadth of current state-of-the-art Systems, which include 0.55 T, 1.5 T, 3 T, and 7 T","volume":"57","author":"Runge","year":"2022","journal-title":"Investig. Radiol."},{"key":"ref39","doi-asserted-by":"publisher","first-page":"4713","DOI":"10.1109\/TPAMI.2022.3204461","article-title":"Image super-resolution via iterative refinement","volume":"45","author":"Saharia","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref40","doi-asserted-by":"publisher","first-page":"680","DOI":"10.1097\/RLI.0000000000000812","article-title":"1.5 vs 3 tesla magnetic resonance imaging: a review of favorite clinical applications for both field strengths\u2014part 1","volume":"56","author":"Schick","year":"2021","journal-title":"Investig. Radiol."},{"key":"ref41","doi-asserted-by":"publisher","first-page":"046116","DOI":"10.1063\/5.0165485","article-title":"Attention hybrid variational net for accelerated MRI reconstruction","volume":"1","author":"Shen","year":"2023","journal-title":"APL Mach. Learn."},{"key":"ref42","doi-asserted-by":"publisher","first-page":"21877","DOI":"10.1038\/s41598-024-72820-2","article-title":"Learning to reconstruct accelerated MRI through K-space cold diffusion without noise","volume":"14","author":"Shen","year":"2024","journal-title":"Sci. Rep."},{"key":"ref43","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/978-3-030-00536-8_1","article-title":"Medical image synthesis for data augmentation and anonymization using generative adversarial networks","volume-title":"Simulation and Synthesis in Medical Imaging","author":"Shin","year":"2018"},{"key":"ref44","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Arxiv","author":"Simonyan","year":"2015"},{"key":"ref45","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1007\/978-3-030-59713-9_7","article-title":"End-to-end Variational networks for accelerated MRI reconstruction","volume":"2020","author":"Sriram","year":"2020","journal-title":"MICCAI"},{"key":"ref46","doi-asserted-by":"publisher","first-page":"303","DOI":"10.3390\/jimaging8110303","article-title":"Harmonization strategies in multicenter MRI-based Radiomics","volume":"8","author":"Stamoulou","year":"2022","journal-title":"J. Imaging"},{"key":"ref47","doi-asserted-by":"publisher","first-page":"503","DOI":"10.1007\/s11075-009-9350-8","article-title":"Accelerated gradient descent methods with line search","volume":"54","author":"Stanimirovi\u0107","year":"2010","journal-title":"Numer. Algorit."},{"key":"ref48","first-page":"945","article-title":"Plug-and-play priors for model based reconstruction","author":"Venkatakrishnan","year":"2013"},{"key":"ref49","doi-asserted-by":"publisher","first-page":"510","DOI":"10.1002\/jmri.29088","article-title":"Deep learning-driven transformation: a novel approach for mitigating batch effects in diffusion MRI beyond traditional harmonization","volume":"60","author":"Wada","year":"2024","journal-title":"J. Magn. Reson. Imaging"},{"key":"ref50","doi-asserted-by":"crossref","DOI":"10.1109\/ICCVW.2019.00482","article-title":"Online regularization by Denoising with applications to phase retrieval","author":"Wu","year":"2019"},{"key":"ref51","article-title":"fastMRI: An open dataset and benchmarks for accelerated MRI","volume-title":"Arxiv","author":"Zbontar","year":"2019"},{"key":"ref52","article-title":"Conditional image synthesis with diffusion models: a survey","volume-title":"Arxiv","author":"Zhan","year":"2024"},{"key":"ref53","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1631\/FITEE.1700808","article-title":"Visual interpretability for deep learning: a survey","volume":"19","author":"Zhang","year":"2018","journal-title":"Front. Inf. Technol. Electron. Eng."}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1579251\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T05:40:54Z","timestamp":1750225254000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1579251\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,18]]},"references-count":53,"alternative-id":["10.3389\/frai.2025.1579251"],"URL":"https:\/\/doi.org\/10.3389\/frai.2025.1579251","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,18]]},"article-number":"1579251"}}