Department of Biomedical Engineering, Tsinghua University, Beijing, China; Wellcome Centre for Integrative Neuroimaging, FMRIB, Nuffield Department of Clinical Neurosciences, University of Oxford, Oxford, United Kingdom.
Athinoula A. Martinos Center for Biomedical Imaging, Department of Radiology, Massachusetts General Hospital, Charlestown, MA, United States; Harvard Medical School, Boston, MA, United States.
Med Image Anal. 2023 May;86:102744. doi: 10.1016/j.media.2023.102744. Epub 2023 Jan 19.
Diffusion MRI is a useful neuroimaging tool for non-invasive mapping of human brain microstructure and structural connections. The analysis of diffusion MRI data often requires brain segmentation, including volumetric segmentation and cerebral cortical surfaces, from additional high-resolution T-weighted (T1w) anatomical MRI data, which may be unacquired, corrupted by subject motion or hardware failure, or cannot be accurately co-registered to the diffusion data that are not corrected for susceptibility-induced geometric distortion. To address these challenges, this study proposes to synthesize high-quality T1w anatomical images directly from diffusion data using convolutional neural networks (CNNs) (entitled "DeepAnat"), including a U-Net and a hybrid generative adversarial network (GAN), and perform brain segmentation on synthesized T1w images or assist the co-registration using synthesized T1w images. The quantitative and systematic evaluations using data of 60 young subjects provided by the Human Connectome Project (HCP) show that the synthesized T1w images and results for brain segmentation and comprehensive diffusion analysis tasks are highly similar to those from native T1w data. The brain segmentation accuracy is slightly higher for the U-Net than the GAN. The efficacy of DeepAnat is further validated on a larger dataset of 300 more elderly subjects provided by the UK Biobank. Moreover, the U-Nets trained and validated on the HCP and UK Biobank data are shown to be highly generalizable to the diffusion data from Massachusetts General Hospital Connectome Diffusion Microstructure Dataset (MGH CDMD) acquired with different hardware systems and imaging protocols and therefore can be used directly without retraining or with fine-tuning for further improved performance. Finally, it is quantitatively demonstrated that the alignment between native T1w images and diffusion images uncorrected for geometric distortion assisted by synthesized T1w images substantially improves upon that by directly co-registering the diffusion and T1w images using the data of 20 subjects from MGH CDMD. In summary, our study demonstrates the benefits and practical feasibility of DeepAnat for assisting various diffusion MRI data analyses and supports its use in neuroscientific applications.
弥散磁共振成像是一种有用的神经影像学工具，可用于无创性绘制人类大脑微观结构和结构连接图。弥散磁共振成像数据的分析通常需要从额外的高分辨率 T 加权（T1w）解剖磁共振成像数据中对大脑进行分割，包括容积分割和大脑皮质表面分割，但这些额外的 T1w 数据可能无法获取，或者受到受试者运动或硬件故障的影响而损坏，或者无法准确地与未校正磁化率引起的几何变形的弥散数据配准。为了解决这些挑战，本研究提出了使用卷积神经网络（CNN）（名为“DeepAnat”）直接从弥散数据中合成高质量的 T1w 解剖图像，包括 U-Net 和混合生成对抗网络（GAN），并在合成的 T1w 图像上进行大脑分割，或使用合成的 T1w 图像协助配准。使用人类连接组计划（HCP）提供的 60 名年轻受试者的数据进行的定量和系统评估表明，合成的 T1w 图像以及大脑分割和全面弥散分析任务的结果与原始 T1w 数据高度相似。U-Net 比 GAN 具有更高的大脑分割精度。DeepAnat 在 UK Biobank 提供的 300 多名年龄较大的受试者的更大数据集上的有效性也得到了进一步验证。此外，在 HCP 和 UK Biobank 数据上训练和验证的 U-Nets 被证明可以高度推广到使用不同硬件系统和成像协议采集的马萨诸塞州总医院连接体弥散微观结构数据集（MGH CDMD）的弥散数据，因此无需重新训练或微调即可直接使用，以进一步提高性能。最后，定量证明了在未校正几何变形的情况下，使用合成的 T1w 图像辅助进行原始 T1w 图像与弥散图像的配准，可以显著提高使用 MGH CDMD 的 20 名受试者的数据直接对弥散和 T1w 图像进行配准的效果。总之，本研究证明了 DeepAnat 辅助各种弥散磁共振成像数据分析的益处和实际可行性，并支持其在神经科学应用中的使用。
