3D whole brain segmentation using spatially localized atlas network tiles
3D whole brain segmentation using spatially localized atlas network tiles
复制标题
DOI：
10.1016/j.neuroimage.2019.03.041
复制
发表时间：
2019-07-01
期刊：
影响因子：
5.7
通讯作者：
Landman, Bennett A.
中科院分区：
文献类型：
--
作者：
Huo, Yuankai;Xu, Zhoubing;Landman, Bennett A.
详细的全脑分割是医学图像分析中必不可少的定量技术，其提供了从临床获得的结构磁共振成像（MRI）测量脑区域的非侵入性方式。最近，深度卷积神经网络（CNN）已被应用于全脑分割。然而，受当前GPU内存的限制，基于2D的方法、基于下采样的3D CNN方法和基于块的高分辨率3D CNN方法已经成为事实上的标准解决方案。基于3D块的高分辨率方法通常在详细的全脑分割的CNN方法中产生上级性能（>100个标签），然而，由于以下挑战，其性能与最先进的多图谱分割方法（MAS）相比通常仍然较差：（1）单个网络通常用于学习块的空间和上下文信息，（2）有限的手动追踪的全脑体积（通常小于50）可用于训练网络。在这项工作中，我们提出了空间局部化图谱网络瓦片（SLANT）方法来分布多个独立的3D全卷积网络（FCN），以实现高分辨率的全脑分割。为了解决第一个挑战，在SLANT方法中使用了多个空间分布式网络，其中每个网络都学习了固定空间位置的上下文信息。为了解决第二个挑战，通过多图谱分割创建了5111个最初未标记的扫描上的辅助标记用于训练。由于该方法将多种传统的医学图像处理方法与深度学习相结合，因此我们开发了一个容器化的管道来部署端到端解决方案。从结果来看，与多图谱分割方法相比，所提出的方法实现了上级性能，同时将计算时间从>30 h减少到15 min。该方法已在开源中提供（https：//github.com/MASILab/SLANTbrainSeg）。
Detailed whole brain segmentation is an essential quantitative technique in medical image analysis, which provides a non-invasive way of measuring brain regions from a clinical acquired structural magnetic resonance imaging (MRI). Recently, deep convolution neural network (CNN) has been applied to whole brain segmentation. However, restricted by current GPU memory, 2D based methods, downsampling based 3D CNN methods, and patch-based high-resolution 3D CNN methods have been the de facto standard solutions. 3D patch-based high resolution methods typically yield superior performance among CNN approaches on detailed whole brain segmentation (>100 labels), however, whose performance are still commonly inferior compared with state-of-the-art multi-atlas segmentation methods (MAS) due to the following challenges: (1) a single network is typically used to learn both spatial and contextual information for the patches, (2) limited manually traced whole brain volumes are available (typically less than 50) for training a network. In this work, we propose the spatially localized atlas network tiles (SLANT) method to distribute multiple independent 3D fully convolutional networks (FCN) for high-resolution whole brain segmentation. To address the first challenge, multiple spatially distributed networks were used in the SLANT method, in which each network learned contextual information for a fixed spatial location. To address the second challenge, auxiliary labels on 5111 initially unlabeled scans were created by multi-atlas segmentation for training. Since the method integrated multiple traditional medical image processing methods with deep learning, we developed a containerized pipeline to deploy the end-to-end solution. From the results, the proposed method achieved superior performance compared with multi-atlas segmentation methods, while reducing the computational time from >30 h to 15 min. The method has been made available in open source (https://github.com/MASILab/SLANTbrainSeg).