{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T12:55:50Z","timestamp":1787921750073,"version":"build-2784847793"},"reference-count":31,"publisher":"Public Library of Science (PLoS)","issue":"1","license":[{"start":{"date-parts":[[2025,1,6]],"date-time":"2025-01-06T00:00:00Z","timestamp":1736121600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["91230027"],"award-info":[{"award-number":["91230027"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:sec id=\"sec001\">\n<jats:title>Objective<\/jats:title>\n<jats:p>This study aimed to assess the feasibility of the deep learning in generating T2 weighted (T2W) images from diffusion-weighted imaging b0 images.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec002\">\n<jats:title>Materials and methods<\/jats:title>\n<jats:p>This retrospective study included 53 patients who underwent head magnetic resonance imaging between September 1 and September 4, 2023. Each b0 image was matched with a corresponding T2-weighted image. A total of 954 pairs of images were divided into a training set with 763 pairs and a test set with 191 pairs. The Hybrid-Fusion Network (Hi-Net) and pix2pix algorithms were employed to synthesize T2W (sT2W) images from b0 images. The quality of the sT2W images was evaluated using three quantitative indicators: Peak Signal-to-Noise Ratio (PSNR), Structural Similarity (SSIM), and Normalized Mean Squared Error (NMSE). Subsequently, two radiologists were required to determine the authenticity of (s)T2W images and further scored the visual quality of sT2W images in the test set using a five-point Likert scale. The overall quality score, anatomical sharpness, tissue contrast and homogeneity were used to reflect the quality of the images at the level of overall and focal parts.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec003\">\n<jats:title>Results<\/jats:title>\n<jats:p>The indicators of pix2pix algorithm in test set were as follows: PSNR, 20.549\u00b11.916; SSIM, 0.702\u00b10.0864; NMSE, 0.239\u00b10.150. The indicators of Hi-Net algorithm were as follows: PSNR, 20.646 \u00b1 2.194; SSIM, 0.722 \u00b1 0.0955; NMSE, 0.469 \u00b1 0.124. Hi-Net performs better than pix2pix, so the sT2W images obtained by Hi-Net were used for radiologist assessment. The two readers accurately identified the nature of the images at rates of 69.90% and 71.20%, respectively. The synthetic images were falsely identified as real at rates of 57.6% and 57.1%, respectively. The overall quality score, sharpness, tissue contrast, and image homogeneity of the sT2Ws images ranged between 1.63 \u00b1 0.79 and 4.45 \u00b1 0.88. Specifically, the quality of the brain parenchyma, skull and scalp, and middle ear region was superior, while the quality of the orbit and paranasal sinus region was not good enough.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec004\">\n<jats:title>Conclusion<\/jats:title>\n<jats:p>The Hi-Net is able to generate sT2WIs from low-resolution b0 images, with a better performance than pix2pix. It can therefore help identify incidental lesion through providing additional information, and demonstrates the potential to shorten the acquisition time of brain MRI during acute ischemic stroke imaging.<\/jats:p>\n<\/jats:sec>","DOI":"10.1371\/journal.pone.0316642","type":"journal-article","created":{"date-parts":[[2025,1,6]],"date-time":"2025-01-06T18:31:42Z","timestamp":1736188302000},"page":"e0316642","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":1,"title":["Using deep learning to shorten the acquisition time of brain MRI in acute ischemic stroke: Synthetic T2W images generated from b0 images"],"prefix":"10.1371","volume":"20","author":[{"given":"Yun","family":"Peng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunmiao","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ke","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zihao","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liangxia","family":"Xiong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyu","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Min","family":"Wan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lianggeng","family":"Gong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2025,1,6]]},"reference":[{"key":"pone.0316642.ref001","article-title":"Efficacy of Monitoring Platelet Function by an Automated PL-12 Analyzer During the Treatment of Acute Cerebral Infarction With Antiplatelet Medicine","volume":"27","author":"C Yue","year":"2021","journal-title":"Clin Appl Thromb Hemost"},{"issue":"10","key":"pone.0316642.ref002","doi-asserted-by":"crossref","first-page":"e146","DOI":"10.1161\/CIR.0000000000000485","article-title":"Heart Disease and Stroke Statistics-2017 Update: A Report From the American Heart Association","volume":"135","author":"EJ Benjamin","year":"2017","journal-title":"Circulation"},{"issue":"1","key":"pone.0316642.ref003","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1177\/17474930211065917","article-title":"World Stroke Organization (WSO): Global Stroke Fact Sheet 2022","volume":"17","author":"VL Feigin","year":"2022","journal-title":"Int J Stroke"},{"issue":"8","key":"pone.0316642.ref004","first-page":"e44492","article-title":"Volumetric-Modulated Arc-Based Re-radiosurgery With Simultaneous Reduced-Dose Whole-Brain Irradiation for Local Failures Following Prior Radiosurgery of Brain Oligometastases From Small Cell Lung Cancer","volume":"15","author":"K Ohtakara","year":"2023","journal-title":"Cureus"},{"key":"pone.0316642.ref005","doi-asserted-by":"crossref","first-page":"103117","DOI":"10.1016\/j.nicl.2022.103117","article-title":"The value of diffusion weighted imaging in predicting the clinical progression of perforator artery cerebral infarction","volume":"35","author":"W Yu","year":"2022","journal-title":"Neuroimage Clin"},{"key":"pone.0316642.ref006","first-page":"8255018","article-title":"Infarction Patterns and Recurrent Adverse Cerebrovascular Events in Moyamoya Disease","volume":"2022","author":"SC Yu","year":"2022","journal-title":"Dis Markers"},{"issue":"14","key":"pone.0316642.ref007","doi-asserted-by":"crossref","first-page":"1451","DOI":"10.1001\/jama.2015.3058","article-title":"Acute stroke intervention: a systematic review","volume":"313","author":"S Prabhakaran","year":"2015","journal-title":"JAMA"},{"issue":"5","key":"pone.0316642.ref008","doi-asserted-by":"crossref","first-page":"497","DOI":"10.1038\/nm1735","article-title":"A new penumbra: transitioning from injury into repair after stroke","volume":"14","author":"EH Lo","year":"2008","journal-title":"Nat Med"},{"issue":"5","key":"pone.0316642.ref009","doi-asserted-by":"crossref","first-page":"643","DOI":"10.1001\/jamaneurol.2019.5106","article-title":"Temporal Dynamics of Cortical Microinfarcts in Cerebral Small Vessel Disease","volume":"77","author":"A Ter Telgte","year":"2020","journal-title":"JAMA Neurol"},{"issue":"6","key":"pone.0316642.ref010","doi-asserted-by":"crossref","first-page":"651","DOI":"10.3348\/kjr.2011.12.6.651","article-title":"Diffusion tensor imaging: exploring the motor networks and clinical applications","volume":"12","author":"S Ahn","year":"2011","journal-title":"Korean J Radiol"},{"key":"pone.0316642.ref011","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1016\/j.radonc.2022.08.028","article-title":"A deep learning approach to generate synthetic CT in low field MR-guided radiotherapy for lung cases","volume":"176","author":"J Lenkowicz","year":"2022","journal-title":"Radiother Oncol"},{"key":"pone.0316642.ref012","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1016\/j.ejmp.2021.09.006","article-title":"Comparison of different deep learning architectures for synthetic CT generation from MR images","volume":"90","author":"A Bahrami","year":"2021","journal-title":"Phys Med"},{"issue":"4","key":"pone.0316642.ref013","doi-asserted-by":"crossref","first-page":"1408","DOI":"10.1002\/mp.12155","article-title":"MR-based synthetic CT generation using a deep convolutional neural network method","volume":"44","author":"X. Han","year":"2017","journal-title":"Med Phys"},{"issue":"9","key":"pone.0316642.ref014","doi-asserted-by":"crossref","first-page":"2772","DOI":"10.1109\/TMI.2020.2975344","article-title":"Hi-Net: Hybrid-Fusion Network for Multi-Modal MR Image Synthesis","volume":"39","author":"T Zhou","year":"2020","journal-title":"IEEE Trans Med Imaging"},{"issue":"4","key":"pone.0316642.ref015","doi-asserted-by":"crossref","first-page":"431","DOI":"10.2463\/mrms.mp.2020-0132","article-title":"Investigating the Image Quality and Utility of Synthetic MRI in the Breast","volume":"20","author":"T Fujioka","year":"2021","journal-title":"Magn Reson Med Sci"},{"issue":"4","key":"pone.0316642.ref016","article-title":"Multi-Contrast MRI Image Synthesis Using Switchable Cycle-Consistent Generative Adversarial Networks","volume":"12","author":"H Zhang","year":"2022","journal-title":"Diagnostics (Basel)"},{"issue":"3","key":"pone.0316642.ref017","doi-asserted-by":"crossref","first-page":"e222211","DOI":"10.1148\/radiol.222211","article-title":"Using Machine Learning to Reduce the Need for Contrast Agents in Breast MRI through Synthetic Images","volume":"307","author":"G Muller-Franzes","year":"2023","journal-title":"Radiology"},{"issue":"4","key":"pone.0316642.ref018","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1097\/RLI.0000000000000628","article-title":"Deep Learning Approach for Generating MRA Images From 3D Quantitative Synthetic MRI Without Additional Scans","volume":"55","author":"S Fujita","year":"2020","journal-title":"Invest Radiol"},{"issue":"4","key":"pone.0316642.ref019","doi-asserted-by":"crossref","first-page":"2538","DOI":"10.1002\/mp.16847","article-title":"Synthetic CT generation from MRI using 3D transformer-based denoising diffusion model","volume":"51","author":"S Pan","year":"2024","journal-title":"Med Phys"},{"issue":"24","key":"pone.0316642.ref020","doi-asserted-by":"crossref","DOI":"10.1088\/1361-6560\/ad0ddc","article-title":"Mitigating misalignment in MRI-to-CT synthesis for improved synthetic CT generation: an iterative refinement and knowledge distillation approach","volume":"68","author":"L Zhou","year":"2023","journal-title":"Phys Med Biol"},{"issue":"5","key":"pone.0316642.ref021","doi-asserted-by":"crossref","DOI":"10.3390\/jimaging7050083","article-title":"Variational Autoencoder for Image-Based Augmentation of Eye-Tracking Data","volume":"7","author":"M Elbattah","year":"2021","journal-title":"J Imaging"},{"key":"pone.0316642.ref022","doi-asserted-by":"crossref","first-page":"102799","DOI":"10.1016\/j.media.2023.102799","article-title":"ImUnity: A generalizable VAE-GAN solution for multicenter MR image harmonization","volume":"88","author":"S Cackowski","year":"2023","journal-title":"Med Image Anal"},{"key":"pone.0316642.ref023","doi-asserted-by":"crossref","first-page":"5629","DOI":"10.1109\/TIP.2022.3197976","article-title":"Inference-Reconstruction Variational Autoencoder for Light Field Image Reconstruction","volume":"31","author":"K Han","year":"2022","journal-title":"IEEE Trans Image Process"},{"key":"pone.0316642.ref024","doi-asserted-by":"crossref","first-page":"374","DOI":"10.1016\/j.neunet.2019.11.003","article-title":"Generative adversarial networks with mixture of t-distributions noise for diverse image generation","volume":"122","author":"J Sun","year":"2020","journal-title":"Neural Netw"},{"key":"pone.0316642.ref025","doi-asserted-by":"crossref","first-page":"102965","DOI":"10.1016\/j.media.2023.102965","article-title":"Backdoor attack and defense in federated generative adversarial network-based medical image synthesis","volume":"90","author":"R Jin","year":"2023","journal-title":"Med Image Anal"},{"key":"pone.0316642.ref026","doi-asserted-by":"crossref","first-page":"101938","DOI":"10.1016\/j.artmed.2020.101938","article-title":"GANs for medical image analysis","volume":"109","author":"S Kazeminia","year":"2020","journal-title":"Artif Intell Med"},{"issue":"3","key":"pone.0316642.ref027","doi-asserted-by":"crossref","first-page":"1180","DOI":"10.1109\/TPAMI.2020.3022406","article-title":"DE-GAN: A Conditional Generative Adversarial Network for Document Enhancement","volume":"44","author":"MA Souibgui","year":"2022","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"3","key":"pone.0316642.ref028","doi-asserted-by":"crossref","first-page":"840","DOI":"10.1148\/rg.2021200151","article-title":"Generative Adversarial Networks: A Primer for Radiologists","volume":"41","author":"JM Wolterink","year":"2021","journal-title":"Radiographics"},{"issue":"7","key":"pone.0316642.ref029","doi-asserted-by":"crossref","first-page":"3539","DOI":"10.21037\/qims-21-1042","article-title":"Pix2Pix generative adversarial network for low dose myocardial perfusion SPECT denoising","volume":"12","author":"J Sun","year":"2022","journal-title":"Quant Imaging Med Surg"},{"issue":"23","key":"pone.0316642.ref030","doi-asserted-by":"crossref","first-page":"5299","DOI":"10.1093\/bioinformatics\/btac688","article-title":"Improving and evaluating deep learning models of cellular organization","volume":"38","author":"H Sun","year":"2022","journal-title":"Bioinformatics"},{"issue":"2","key":"pone.0316642.ref031","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1007\/s13139-022-00786-y","article-title":"Applying Pix2pix to Translate Hyperemia in Blood Pool Image into Corresponding Increased Bone Uptake in Delayed Image in Three-Phase Bone Scintigraphy","volume":"57","author":"KS Park","year":"2023","journal-title":"Nucl Med Mol Imaging"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0316642","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,6]],"date-time":"2025-01-06T18:31:51Z","timestamp":1736188311000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0316642"}},"subtitle":[],"editor":[{"given":"Hadeel K.","family":"Aljobouri","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2025,1,6]]},"references-count":31,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,1,6]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0316642","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,6]]}}}