arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.11446cs.CVcs.AI
收藏

增强型便携式超低场扩散张量成像与贝叶斯伪影校正及基于深度学习的超分辨率

Enhanced Portable Ultra Low-Field Diffusion Tensor Imaging with Bayesian Artifact Correction and Deep Learning-Based Super-Resolution

Picower Institute, Massachusetts Institute of Technology(麻省理工学院皮考尔研究所);Institute for Medical Engineering and Science, Massachusetts Institute of Technology(麻省理工学院医学工程与科学研究所);Massachusetts General Hospital(麻省总医院);Harvard Medical School(哈佛医学院);MIT/MGH Brain Arousal State Control Innovation Center, Massachusetts Institute of Technology(麻省理工学院MIT/MGH脑觉醒状态控制创新中心);Athinoula A. Martinos Center for Biomedical Imaging, Massachusetts General Hospital and Harvard Medical School(麻省总医院与哈佛医学院阿西诺拉·A·马蒂诺斯生物医学成像中心);Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology(麻省理工学院计算机科学与人工智能实验室);Hawkes Institute, University College London(伦敦大学学院霍克斯研究所)

Mark D. Olchanyi, Annabel Sorby-Adams, John Kirsch, Brian L. Edlow, Ava Farnan, Renfei Liu, Matthew S. Rosen, Emery N. Brown, W. Taylor Kimberly, Juan Eugenio Iglesias

AI总结:

本文提出了一种便携式超低场扩散张量成像序列及贝叶斯伪影校正算法,结合深度学习超分辨率技术,提升白质成像质量并应用于阿尔茨海默病分类。

摘要:

便携式、超低场(ULF)磁共振成像有潜力扩大神经成像的可及性,但目前存在空间和角度分辨率低以及信噪比低的问题。扩散张量成像(DTI)是一种专门用于检测和重建大脑白质纤维的序列,由于固有序列设计和长时间扫描时间的影响,特别容易受到这种成像退化的影响。此外,ULF DTI扫描在空间和角度域中均会出现伪影,需要定制建模算法进行后续校正。我们介绍了一种九方向、单壳ULF DTI序列,以及一个具有角度依赖性的贝叶斯偏场校正算法和基于卷积神经网络的超分辨率算法(称为“DiffSR”),该算法可以跨DTI数据集通用,且无需重新训练。我们通过合成降采样实验和真实匹配的ULF与高场DTI扫描中的白质评估,证明这些算法可以在ULF下恢复微结构和体积白质信息。我们还证明DiffSR可以直接应用于基于白质的阿尔茨海默病分类,在合成退化扫描中显示出DTI指标之间的一致性显著提高。我们免费分发贝叶斯偏场校正算法和DiffSR,旨在进一步推动ULF重建方法和通用DTI序列协调的进步。我们发布所有与DiffSR相关的代码供公众使用(https://github.com/markolchanyi/DiffSR)。

英文摘要:

Portable, ultra-low-field (ULF) magnetic resonance imaging has the potential to expand access to neuroimaging but currently suffers from coarse spatial and angular resolutions and low signal-to-noise ratios. Diffusion tensor imaging (DTI), a sequence tailored to detect and reconstruct white matter tracts within the brain, is particularly prone to such imaging degradation due to inherent sequence design coupled with prolonged scan times. In addition, ULF DTI scans exhibit artifacting that spans both the space and angular domains, requiring a custom modelling algorithm for subsequent correction. We introduce a nine-direction, single-shell ULF DTI sequence, as well as a companion Bayesian bias field correction algorithm that possesses angular dependence and convolutional neural network-based superresolution algorithm that is generalizable across DTI datasets and does not require re-training (''DiffSR''). We show through a synthetic downsampling experiment and white matter assessment in real, matched ULF and high-field DTI scans that these algorithms can recover microstructural and volumetric white matter information at ULF. We also show that DiffSR can be directly applied to white matter-based Alzheimers disease classification in synthetically degraded scans, with notable improvements in agreement between DTI metrics, as compared to un-degraded scans. We freely disseminate the Bayesian bias correction algorithm and DiffSR with the goal of furthering progress on both ULF reconstruction methods and general DTI sequence harmonization. We release all code related to DiffSR for $\href{https://github.com/markolchanyi/DiffSR}{public \space use}$.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑