Deep whole brain segmentation of 7T structural MRI
Deep whole brain segmentation of 7T structural MRI
复制标题
DOI：
10.1117/12.2654108
复制
发表时间：
2023-02
影响因子：
3.8
通讯作者：
Karthik Ramadass;Xin Yu;L. Cai;Yucheng Tang;Shunxing Bao;Cailey I. Kerley;Micah D’Archangel;Laura A. Barquero;A. Newton;I. Gauthier;Rankin W. McGugin;B. Dawant;L. Cutting;Yuankai Huo;Bennett A. Landman
中科院分区：
文献类型：
--
作者：
Karthik Ramadass;Xin Yu;L. Cai;Yucheng Tang;Shunxing Bao;Cailey I. Kerley;Micah D’Archangel;Laura A. Barquero;A. Newton;I. Gauthier;Rankin W. McGugin;B. Dawant;L. Cutting;Yuankai Huo;Bennett A. Landman
7 T磁共振成像（MRI）有可能通过新的对比度和增强的分辨率来推动我们对人类大脑功能的理解。全脑分割是一种关键的神经成像技术，可以对大脑进行逐区域分析。分割也是一个重要的预备步骤，为运行其他神经成像管道提供空间和体积信息。空间局部化图谱网络瓦片（SLANT）是一种流行的3D卷积神经网络（CNN）工具，它将整个大脑分割任务分解为局部化的子任务。每个子任务涉及由独立的3D卷积网络处理的特定空间位置，以提供高分辨率的全脑分割结果。SLANT已被广泛用于从3 T MRI上采集的结构扫描生成全脑分割。然而，由于在7 T MRI中通常在整个大脑中看到的不均匀的图像对比度，使用SLANT从结构性7 T MRI扫描进行全脑分割尚未成功。例如，我们证明了3 T扫描-再扫描之间SLANT标记体积的平均百分比差异约为1.73%，而其3 T-7 T扫描-再扫描对应物的差异更高，约为15.13%。我们解决这个问题的方法是将在3 T MRI到7 T MRI上执行的全脑分割配准，并使用此信息微调SLANT以用于结构7 T MRI。使用微调的SLANT管道，我们观察到从结构性7 T MRI数据采集的标记体积的平均相对差异较低，约为8.43%。3 T MRI扫描上的SLANT分割与7 T MRI上微调后的SLANT分割之间的Dice相似系数从0.79增加到0.83，p<0.01。这些结果表明，SLANT的微调是一种可行的解决方案，用于改善高分辨率7 T结构成像上的全脑分割。
7T magnetic resonance imaging (MRI) has the potential to drive our understanding of human brain function through new contrast and enhanced resolution. Whole brain segmentation is a key neuroimaging technique that allows for region-by-region analysis of the brain. Segmentation is also an important preliminary step that provides spatial and volumetric information for running other neuroimaging pipelines. Spatially localized atlas network tiles (SLANT) is a popular 3D convolutional neural network (CNN) tool that breaks the whole brain segmentation task into localized sub-tasks. Each subtask involves a specific spatial location handled by an independent 3D convolutional network to provide high resolution whole brain segmentation results. SLANT has been widely used to generate whole brain segmentations from structural scans acquired on 3T MRI. However, the use of SLANT for whole brain segmentation from structural 7T MRI scans has not been successful due to the inhomogeneous image contrast usually seen across the brain in 7T MRI. For instance, we demonstrate the mean percent difference of SLANT label volumes between a 3T scan-rescan is approximately 1.73%, whereas its 3T-7T scan-rescan counterpart has higher differences around 15.13%. Our approach to address this problem is to register the whole brain segmentation performed on 3T MRI to 7T MRI and use this information to finetune SLANT for structural 7T MRI. With the finetuned SLANT pipeline, we observe a lower mean relative difference in the label volumes of ~8.43% acquired from structural 7T MRI data. Dice similarity coefficient between SLANT segmentation on the 3T MRI scan and the after finetuning SLANT segmentation on the 7T MRI increased from 0.79 to 0.83 with p<0.01. These results suggest finetuning of SLANT is a viable solution for improving whole brain segmentation on high resolution 7T structural imaging.