利用弱监督加速多线圈磁共振图像重建

IF 2 4区 医学 Q3 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING
Arda Atalık, Sumit Chopra, Daniel K Sodickson
{"title":"利用弱监督加速多线圈磁共振图像重建","authors":"Arda Atalık, Sumit Chopra, Daniel K Sodickson","doi":"10.1007/s10334-024-01206-2","DOIUrl":null,"url":null,"abstract":"<p><p>Deep-learning-based MR image reconstruction in settings where large fully sampled dataset collection is infeasible requires methods that effectively use both under-sampled and fully sampled datasets. This paper evaluates a weakly supervised, multi-coil, physics-guided approach to MR image reconstruction, leveraging both dataset types, to improve both the quality and robustness of reconstruction. A physics-guided end-to-end variational network (VarNet) is pretrained in a self-supervised manner using a 4 <math><mo>×</mo></math> under-sampled dataset following the self-supervised learning via data undersampling (SSDU) methodology. The pre-trained weights are transferred to another VarNet, which is fine-tuned using a smaller, fully sampled dataset by optimizing multi-scale structural similarity (MS-SSIM) loss in image space. The proposed methodology is compared with fully self-supervised and fully supervised training. Reconstruction quality improvements in SSIM, PSNR, and NRMSE when abundant training data is available (the high-data regime), and enhanced robustness when training data is scarce (the low-data regime) are demonstrated using weak supervision for knee and brain MR image reconstructions at 8 <math><mo>×</mo></math> and 10 <math><mo>×</mo></math> acceleration, respectively. Multi-coil physics-guided MR image reconstruction using both under-sampled and fully sampled datasets is achievable with transfer learning and fine-tuning. This methodology can provide improved reconstruction quality in the high-data regime and improved robustness in the low-data regime at high acceleration rates.</p>","PeriodicalId":18067,"journal":{"name":"Magnetic Resonance Materials in Physics, Biology and Medicine","volume":" ","pages":""},"PeriodicalIF":2.0000,"publicationDate":"2024-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Accelerating multi-coil MR image reconstruction using weak supervision.\",\"authors\":\"Arda Atalık, Sumit Chopra, Daniel K Sodickson\",\"doi\":\"10.1007/s10334-024-01206-2\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>Deep-learning-based MR image reconstruction in settings where large fully sampled dataset collection is infeasible requires methods that effectively use both under-sampled and fully sampled datasets. This paper evaluates a weakly supervised, multi-coil, physics-guided approach to MR image reconstruction, leveraging both dataset types, to improve both the quality and robustness of reconstruction. A physics-guided end-to-end variational network (VarNet) is pretrained in a self-supervised manner using a 4 <math><mo>×</mo></math> under-sampled dataset following the self-supervised learning via data undersampling (SSDU) methodology. The pre-trained weights are transferred to another VarNet, which is fine-tuned using a smaller, fully sampled dataset by optimizing multi-scale structural similarity (MS-SSIM) loss in image space. The proposed methodology is compared with fully self-supervised and fully supervised training. Reconstruction quality improvements in SSIM, PSNR, and NRMSE when abundant training data is available (the high-data regime), and enhanced robustness when training data is scarce (the low-data regime) are demonstrated using weak supervision for knee and brain MR image reconstructions at 8 <math><mo>×</mo></math> and 10 <math><mo>×</mo></math> acceleration, respectively. Multi-coil physics-guided MR image reconstruction using both under-sampled and fully sampled datasets is achievable with transfer learning and fine-tuning. This methodology can provide improved reconstruction quality in the high-data regime and improved robustness in the low-data regime at high acceleration rates.</p>\",\"PeriodicalId\":18067,\"journal\":{\"name\":\"Magnetic Resonance Materials in Physics, Biology and Medicine\",\"volume\":\" \",\"pages\":\"\"},\"PeriodicalIF\":2.0000,\"publicationDate\":\"2024-10-09\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Magnetic Resonance Materials in Physics, Biology and Medicine\",\"FirstCategoryId\":\"3\",\"ListUrlMain\":\"https://doi.org/10.1007/s10334-024-01206-2\",\"RegionNum\":4,\"RegionCategory\":\"医学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Magnetic Resonance Materials in Physics, Biology and Medicine","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1007/s10334-024-01206-2","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING","Score":null,"Total":0}
引用次数: 0

摘要

在无法收集大量全采样数据集的情况下,基于深度学习的磁共振图像重建需要同时有效利用欠采样和全采样数据集的方法。本文评估了一种弱监督、多线圈、物理引导的磁共振图像重建方法,利用这两种数据集来提高重建的质量和鲁棒性。采用数据欠采样自监督学习(SSDU)方法,使用 4 × 欠采样数据集,以自监督方式预训练物理引导的端到端变异网络(VarNet)。通过优化图像空间中的多尺度结构相似性(MS-SSIM)损失,使用较小的完全采样数据集对该数据集进行微调。所提出的方法与完全自我监督和完全监督训练进行了比较。在膝关节和脑部磁共振图像重建中,分别在 8 倍和 10 倍加速度下使用弱监督,证明了在有大量训练数据时(高数据机制),重建质量在 SSIM、PSNR 和 NRMSE 方面的改善,以及在训练数据稀缺时(低数据机制),鲁棒性的增强。通过迁移学习和微调,可以使用欠采样和全采样数据集进行多线圈物理引导磁共振图像重建。在高加速度下,这种方法可以提高高数据机制的重建质量和低数据机制的鲁棒性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Accelerating multi-coil MR image reconstruction using weak supervision.

Deep-learning-based MR image reconstruction in settings where large fully sampled dataset collection is infeasible requires methods that effectively use both under-sampled and fully sampled datasets. This paper evaluates a weakly supervised, multi-coil, physics-guided approach to MR image reconstruction, leveraging both dataset types, to improve both the quality and robustness of reconstruction. A physics-guided end-to-end variational network (VarNet) is pretrained in a self-supervised manner using a 4 × under-sampled dataset following the self-supervised learning via data undersampling (SSDU) methodology. The pre-trained weights are transferred to another VarNet, which is fine-tuned using a smaller, fully sampled dataset by optimizing multi-scale structural similarity (MS-SSIM) loss in image space. The proposed methodology is compared with fully self-supervised and fully supervised training. Reconstruction quality improvements in SSIM, PSNR, and NRMSE when abundant training data is available (the high-data regime), and enhanced robustness when training data is scarce (the low-data regime) are demonstrated using weak supervision for knee and brain MR image reconstructions at 8 × and 10 × acceleration, respectively. Multi-coil physics-guided MR image reconstruction using both under-sampled and fully sampled datasets is achievable with transfer learning and fine-tuning. This methodology can provide improved reconstruction quality in the high-data regime and improved robustness in the low-data regime at high acceleration rates.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
CiteScore
4.60
自引率
0.00%
发文量
58
审稿时长
>12 weeks
期刊介绍: MAGMA is a multidisciplinary international journal devoted to the publication of articles on all aspects of magnetic resonance techniques and their applications in medicine and biology. MAGMA currently publishes research papers, reviews, letters to the editor, and commentaries, six times a year. The subject areas covered by MAGMA include: advances in materials, hardware and software in magnetic resonance technology, new developments and results in research and practical applications of magnetic resonance imaging and spectroscopy related to biology and medicine, study of animal models and intact cells using magnetic resonance, reports of clinical trials on humans and clinical validation of magnetic resonance protocols.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信