Laboratory of Biomedical Imaging and Signal Processing, The University of Hong Kong, SAR, Hong Kong, China.
Department of Electrical and Electronic Engineering, The University of Hong Kong, SAR, Hong Kong, China.
Magn Reson Med. 2023 Aug;90(2):400-416. doi: 10.1002/mrm.29642. Epub 2023 Apr 3.
Recent development of ultra-low-field (ULF) MRI presents opportunities for low-power, shielding-free, and portable clinical applications at a fraction of the cost. However, its performance remains limited by poor image quality. Here, a computational approach is formulated to advance ULF MR brain imaging through deep learning of large-scale publicly available 3T brain data.
A dual-acquisition 3D superresolution model is developed for ULF brain MRI at 0.055 T. It consists of deep cross-scale feature extraction, attentional fusion of two acquisitions, and reconstruction. Models for T -weighted and T -weighted imaging were trained with 3D ULF image data sets synthesized from the high-resolution 3T brain data from the Human Connectome Project. They were applied to 0.055T brain MRI with two repetitions and isotropic 3-mm acquisition resolution in healthy volunteers, young and old, as well as patients.
The proposed approach significantly enhanced image spatial resolution and suppressed noise/artifacts. It yielded high 3D image quality at 0.055 T for the two most common neuroimaging protocols with isotropic 1.5-mm synthetic resolution and total scan time under 20 min. Fine anatomical details were restored with intrasubject reproducibility, intercontrast consistency, and confirmed by 3T MRI.
The proposed dual-acquisition 3D superresolution approach advances ULF MRI for quality brain imaging through deep learning of high-field brain data. Such strategy can empower ULF MRI for low-cost brain imaging, especially in point-of-care scenarios or/and in low-income and mid-income countries.
超低频（ULF）MRI 的最新发展为低成本、无屏蔽、便携式临床应用提供了机会，其功率仅为传统 MRI 的一小部分。然而，其性能仍然受到图像质量差的限制。在这里，我们提出了一种计算方法，通过对大规模公开的 3T 脑数据进行深度学习来提高 ULF MR 脑成像的性能。
我们开发了一种用于 0.055 T ULF 脑 MRI 的双采集 3D 超分辨率模型。它由深度跨尺度特征提取、两个采集的注意力融合以及重建组成。T加权和 T加权成像模型是用从人类连接组计划的高分辨率 3T 脑数据合成的 3D ULF 图像数据集进行训练的。我们将其应用于健康志愿者、年轻人和老年人以及患者的 0.055T 脑 MRI，采集重复两次，采集分辨率为各向同性 3mm。
该方法显著提高了图像的空间分辨率并抑制了噪声/伪影。它在 0.055 T 下实现了两种最常见的神经影像学协议的高 3D 图像质量，各向同性合成分辨率为 1.5mm，总扫描时间不到 20 分钟。通过与 3T MRI 的对比，该方法可以恢复精细的解剖细节，具有很好的可重复性和一致性。
该双采集 3D 超分辨率方法通过对高场脑数据进行深度学习，提高了 ULF MRI 的图像质量。这种策略可以为低成本脑成像赋能，特别是在即时医疗场景或低收入和中等收入国家。
