Learning Hierarchical and Shared Features for Improving 3D Neuron Reconstruction
Learning Hierarchical and Shared Features for Improving 3D Neuron Reconstruction
复制标题
DOI：
10.1109/icdm.2019.00091
复制
发表时间：
2019-11
期刊：
影响因子：
--
通讯作者：
Hao Yuan;Na Zou;Shaoting Zhang;Hanchuan Peng;Shuiwang Ji
中科院分区：
文献类型：
--
作者：
Hao Yuan;Na Zou;Shaoting Zhang;Hanchuan Peng;Shuiwang Ji
神经元跟踪，也称为神经元重建，基于成像数据研究神经元的3D形态。神经元重建在计算神经科学中至关重要，因为这是朝着大脑接线和功能进行反向工程的关键步骤。另一方面，由于该任务的复杂性和成本，无法手动追踪所有神经元。因此，它提出了建立计算管道以执行自动神经元重建的需要。在这项工作中，我们提出了一种深入学习方法，以提高3D神经元重建的准确性。首先，我们建议在整个数据集中学习不同图像之间的共享功能。我们的模型以不同的尺度自动学习了这种共享特征。其次，我们建议合并此类功能，以指导网络中的信息流。具体而言，我们建议通过合并层次结构和共享功能来建立编码器和网络解码器之间的跳过连接。我们提出的跳过连接是基于注意机制构建的，在该机制中，层次共享的特征是查询矩阵，局部输入功能充当键和值矩阵。由于自动学习这些参数，因此我们希望仅将有用的空间信息传输到解码器。我们进行定性和定量实验，以证明我们提出的方法的有效性。实验结果表明，我们提出的模型具有捕获神经元的详细结构信息的能力。我们的结果还表明，所提出的模型对噪声是可靠的。此外，定量评估表明，我们的方法比其他方法更好。
Neuron tracing, also known as neuron reconstruction, studies 3D morphologies of neurons based on imaging data. Neuron reconstruction is of fundamental importance in computational neuroscience since it is a crucial step towards reverse engineering of the wiring and functions of a brain. On the other hand, it is not possible to manually trace all neurons due to the complexity and cost of this task. Hence, it raises the need of building a computational pipeline to perform automatic neuron reconstruction. In this work, we propose a deep learning approach for improving the accuracy of 3D neuron reconstruction. First, we propose to learn shared features among different images in the whole dataset. Such shared features are learned automatically by our model at different scales. Second, we propose to incorporate such features to guide the information flow in the network. Specifically, we propose to build skip connections between the encoder and the decoder of our networks by incorporating the hierarchical and shared features. Our proposed skip connections are built based on the attention mechanism, where the hierarchical shared features serve as the query matrix and the local input features serve as the key and value matrices. Since the parameters are learned automatically, we expect that only useful spatial information is transmitted to the decoder. We conduct both qualitative and quantitative experiments to demonstrate the effectiveness of our proposed method. Experimental results show that our proposed model has the ability to capture detailed structural information for neurons. Our results also demonstrate that the proposed model is robust to noise. In addition, quantitative evaluations show that our method achieves better performance than other approaches.