FastSurfer - A fast and accurate deep learning based neuroimaging pipeline.
FastSurfer - A fast and accurate deep learning based neuroimaging pipeline.
复制标题
DOI：
10.1016/j.neuroimage.2020.117012
复制
发表时间：
2020-10-01
期刊：
影响因子：
5.7
通讯作者：
Reuter M
中科院分区：
文献类型：
--
作者：
Henschel L;Conjeti S;Estrada S;Diers K;Fischl B;Reuter M
传统的神经图像分析流程涉及计算密集、耗时的优化步骤，因此不能很好地扩展到具有数千或数万个体的大型队列研究。在这项工作中，我们提出了一种快速准确的基于深度学习的神经成像管道，用于自动处理结构性人脑MRI扫描，复制FreeSurfer的解剖分割，包括表面重建和皮质分割。为此，我们引入了一种先进的深度学习架构，能够将全脑分割成95个类。该网络架构通过竞争性密集块和竞争性跳过路径，以及多切片信息聚合，结合了局部和全局竞争，这些信息聚合专门针对皮质和皮质下结构的准确分割来定制网络性能。此外，我们进行快速皮质表面重建和厚度分析，通过引入光谱球面嵌入和直接映射的皮质标签从图像的表面。这种方法为体积分析（在1分钟内）和基于表面的厚度分析（仅在大约1小时的运行时间内）提供了完整的FreeSurfer替代方案。对于这种方法的可持续性，我们进行了广泛的验证：我们断言几个看不见的数据集的分割精度高，测量的概括性，并表现出增加的重测可靠性，以及对痴呆症的群体差异的高敏感性。
Traditional neuroimage analysis pipelines involve computationally intensive, time-consuming optimization steps, and thus, do not scale well to large cohort studies with thousands or tens of thousands of individuals. In this work we propose a fast and accurate deep learning based neuroimaging pipeline for the automated processing of structural human brain MRI scans, replicating FreeSurfer’s anatomical segmentation including surface reconstruction and cortical parcellation. To this end, we introduce an advanced deep learning architecture capable of whole-brain segmentation into 95 classes. The network architecture incorporates local and global competition via competitive dense blocks and competitive skip pathways, as well as multi-slice information aggregation that specifically tailor network performance towards accurate segmentation of both cortical and subcortical structures. Further, we perform fast cortical surface reconstruction and thickness analysis by introducing a spectral spherical embedding and by directly mapping the cortical labels from the image to the surface. This approach provides a full FreeSurfer alternative for volumetric analysis (in under 1 min) and surface-based thickness analysis (within only around 1 h runtime). For sustainability of this approach we perform extensive validation: we assert high segmentation accuracy on several unseen datasets, measure generalizability and demonstrate increased test-retest reliability, and high sensitivity to group differences in dementia.
登录
查看更多内容
影响因子：
3.3
作者：
Estrada, Santiago;Lu, Ran;Reuter, Martin
通讯作者：
Reuter, Martin
DOI：
10.1093/brain/aww083
发表时间：
2016-07
期刊：
Brain : a journal of neurology
影响因子：
--
作者：
Aggleton JP;Pralus A;Nelson AJ;Hornberger M
通讯作者：
Hornberger M
影响因子：
2.4
作者：
Alex, Varghese;Vaidhya, Kiran;Krishnamurthi, Ganapathy
通讯作者：
Krishnamurthi, Ganapathy
影响因子：
5.7
作者：
Dale, AM;Fischl, B;Sereno, MI
通讯作者：
Sereno, MI
影响因子：
5.7
作者：
Chen, Hao;Dou, Qi;Heng, Pheng-Ann
通讯作者：
Heng, Pheng-Ann