Towards computational analytics of 3D neuron images using deep adversarial learning
Towards computational analytics of 3D neuron images using deep adversarial learning
复制标题
使用深度对抗学习对 3D 神经元图像进行计算分析
DOI：
10.1016/j.neucom.2020.03.129
复制
发表时间：
2021-02-13
期刊：
影响因子：
6
通讯作者：
Fang, Chaowei
中科院分区：
文献类型：
--
作者：
Li, Zhongyu;Fan, Xiayue;Fang, Chaowei
得益于神经元追踪技术的进步，数字重建的三维神经元图像数量不断增加，极大地促进了神经形态学的研究。然而，这些3D神经元数据的庞大数量和复杂性给计算分析带来了重大挑战，例如，有效地发现具有相似形态的神经元，识别神经元类型，将神经元形态与属性关联起来，所有这些都需要精确的测量和快速索引方法，特别是为大量3D神经元图像设计的方法。在本文中，我们基于深度学习和数据挖掘技术的进步，提出了一个准确有效的3D神经元结构计算分析框架。特别是，与以前的方法不同，通过根据树拓扑结构测量预定义的度量来定量描述神经元，我们首先通过提出的3D神经元映射和改进的生成对抗网络（GANs）开发了一种新的形态学特征表示方法。随后，考虑到大规模神经元数据集检索的计算复杂度，我们将神经元特征与基于图的索引相结合，在不损失准确性的前提下显著提高了检索效率。实验结果表明，我们的框架可以有效地测量大量神经元（例如，100,000个神经元）之间的相似性，准确度优于目前的水平，提高了10%以上，效率提高了数百倍。(C) 2021 Elsevier B.V.版权所有
Benefited from advances of neuron tracing techniques, the ever-increasing number of digitally reconstructed 3D neuron images have greatly facilitated the research in neuromorphology. However, the sheer volume and the complexity of these 3D neuron data pose significant challenges for computational analytics, e.g., effectively finding neurons sharing similar morphologies, identifying neuron types, correlating neuron morphologies with properties, all of which require accurate measuring and fast indexing methods especially designed for the massive 3D neuronal images. In this paper, we present an accurate and efficient framework for the computational analytics of 3D neuronal structures based on advances of deep learning and data mining techniques. Particularly, unlike previous methods quantitatively describe neurons by measuring pre-defined metrics according to the tree-topological structures, we first develop a new method for the morphological feature representation by a proposed 3D neuron mapping and a modified generative adversarial networks (GANs). Subsequently, considering the computational complexity when retrieving large-scale neuron datasets, we integrate the neuron features with graph-based indexing, which can significantly improve the retrieval efficiency without losing accuracy. Experimental results show that our framework can effectively measure the similarity among massive neurons (e.g., 100; 000 neurons), outperforming state-of-the-arts with more than 10% in accuracy and hundreds of times in efficiency improvements. (C) 2021 Elsevier B.V. All rights reserved.