Classifying the tracing difficulty of 3D neuron image blocks based on deep learning

doi:10.1186/s40708-021-00146-0

CORC > 自动化研究所 > 中国科学院自动化研究所 > 精密感知与控制研究中心 > 人工智能与机器学习

	Classifying the tracing difficulty of 3D neuron image blocks based on deep learning
	Yang,Bin 1,4; Huang,Jiajin 1,4; Wu,Gaowei 2,3; Yang,Jian 1,2,4
刊名	Brain Informatics
	2021-11-05
卷号	8 期号:1
关键词	Deep learning Tracing difficulty classification Residual neural network Fully connected neural network Long short-term memory network
ISSN号	2198-4018
DOI	10.1186/s40708-021-00146-0
通讯作者	Yang,Jian(jianyang@bjut.edu.cn)
英文摘要	AbstractQuickly and accurately tracing neuronal morphologies in large-scale volumetric microscopy data is a very challenging task. Most automatic algorithms for tracing multi-neuron in a whole brain are designed under the Ultra-Tracer framework, which begins the tracing of a neuron from its soma and traces all signals via a block-by-block strategy. Some neuron image blocks are easy for tracing and their automatic reconstructions are very accurate, and some others are difficult and their automatic reconstructions are inaccurate or incomplete. The former are called low Tracing Difficulty Blocks (low-TDBs), while the latter are called high Tracing Difficulty Blocks (high-TDBs). We design a model named 3D-SSM to classify the tracing difficulty of 3D neuron image blocks, which is based on 3D Residual neural Network (3D-ResNet), Fully Connected Neural Network (FCNN) and Long Short-Term Memory network (LSTM). 3D-SSM contains three modules: Structure Feature Extraction (SFE), Sequence Information Extraction (SIE) and Model Fusion (MF). SFE utilizes a 3D-ResNet and a FCNN to extract two kinds of features in 3D image blocks and their corresponding automatic reconstruction blocks. SIE uses two LSTMs to learn sequence information hidden in 3D image blocks. MF adopts a concatenation operation and a FCNN to combine outputs from SIE. 3D-SSM can be used as a stop condition of an automatic tracing algorithm in the Ultra-Tracer framework. With its help, neuronal signals in low-TDBs can be traced by the automatic algorithm and in high-TDBs may be reconstructed by annotators. 12732 training samples and 5342 test samples are constructed on neuron images of a whole mouse brain. The 3D-SSM achieves classification accuracy rates 87.04% on the training set and 84.07% on the test set. Furthermore, the trained 3D-SSM is tested on samples from another whole mouse brain and its accuracy rate is 83.21%.
语种	英语
出版者	Springer Berlin Heidelberg
WOS记录号	BMC:10.1186/S40708-021-00146-0
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/46120]
专题	精密感知与控制研究中心_人工智能与机器学习
通讯作者	Yang,Jian
作者单位	1.Beijing University of Technology; Faculty of Information Technology 2.University of Chinese Academy of Sciences; School of Artificial Intelligence 3.Chinese Academy of Sciences; Institute of Automation 4.Beijing International Collaboration Base on Brain Informatics and Wisdom Services
推荐引用方式 GB/T 7714	Yang,Bin,Huang,Jiajin,Wu,Gaowei,et al. Classifying the tracing difficulty of 3D neuron image blocks based on deep learning[J]. Brain Informatics,2021,8(1).
APA	Yang,Bin,Huang,Jiajin,Wu,Gaowei,&Yang,Jian.(2021).Classifying the tracing difficulty of 3D neuron image blocks based on deep learning.Brain Informatics,8(1).
MLA	Yang,Bin,et al."Classifying the tracing difficulty of 3D neuron image blocks based on deep learning".Brain Informatics 8.1(2021).