Axon Tracing and Centerline Detection using Topologically-Aware 3D U-Nets.
Axon Tracing and Centerline Detection using Topologically-Aware 3D U-Nets.
复制标题
使用拓扑感知 3D U-Net 进行轴突追踪和中心线检测。
DOI：
10.1109/embc48229.2022.9870879
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Brattain,LauraJ
中科院分区：
文献类型：
--
作者：
Pollack,Dylan;Gjesteby,LarsA;Snyder,Michael;Chavez,David;Kamentsky,Lee;Chung,Kwanghun;Brattain,LauraJ
随着显微成像技术的进步为人类大脑提供了一个更清晰的窗口，神经连接的准确重建可以对大脑结构和功能之间的关系产生有价值的见解。然而，人工跟踪是一项缓慢而费力的任务，并且需要领域专业知识。因此，需要自动化方法来实现快速准确的大规模分析。在本文中，我们探索了用于密集轴突跟踪的深度神经网络，并将轴突拓扑信息纳入损失函数，旨在提高基于体素的分割和轴突中心线检测的性能。我们使用修改后的3D U-Net架构对用光片显微镜成像的小鼠大脑数据集进行了训练，并评估了三种方法，与以前的方法相比，轴突追踪准确性提高了10%。此外，在损失函数中增加中心线意识在所有指标上都优于基线方法，包括将兰德指数提高8%。
As advances in microscopy imaging provide an ever clearer window into the human brain, accurate reconstruction of neural connectivity can yield valuable insight into the relationship between brain structure and function. However, human manual tracing is a slow and laborious task, and requires domain expertise. Automated methods are thus needed to enable rapid and accurate analysis at scale. In this paper, we explored deep neural networks for dense axon tracing and incorporated axon topological information into the loss function with a goal to improve the performance on both voxel-based segmentation and axon centerline detection. We evaluated three approaches using a modified 3D U-Net architecture trained on a mouse brain dataset imaged with light sheet microscopy and achieved a 10% increase in axon tracing accuracy over previous methods. Furthermore, the addition of centerline awareness in the loss function outperformed the baseline approach across all metrics, including a boost in Rand Index by 8%.