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

Bin Yang; Jiajin Huang; Gaowei Wu; Jian Yang

doi:10.1186/s40708-021-00146-0

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

Brain Inform. 2021 Nov 5;8(1):25. doi: 10.1186/s40708-021-00146-0.

Authors

Bin Yang^{1

2}, Jiajin Huang^{1

2}, Gaowei Wu^{3

4}, Jian Yang^{5

6

7}

Affiliations

¹ Faculty of Information Technology, Beijing University of Technology, Beijing, China.
² Beijing International Collaboration Base on Brain Informatics and Wisdom Services, Beijing, China.
³ School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China.
⁴ Institute of Automation, Chinese Academy of Sciences, Beijing, China.
⁵ Faculty of Information Technology, Beijing University of Technology, Beijing, China. jianyang@bjut.edu.cn.
⁶ Beijing International Collaboration Base on Brain Informatics and Wisdom Services, Beijing, China. jianyang@bjut.edu.cn.
⁷ School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China. jianyang@bjut.edu.cn.

Abstract

Quickly 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%.

Keywords: Deep learning; Fully connected neural network; Long short-term memory network; Residual neural network; Tracing difficulty classification.