Abstract:Traditional morphology-based neuronal classification approaches largely rely on the feature extraction and selection techniques of neuronal spatial structures,a lot of useful information for neuronal classification may be lost.Using the adaptive projection algorithm to convert the three-dimensional neuron data without feature extraction,this paper proposes a neuronal morphology classification approach based on deep learning networks.The three-dimensional voxel reconstruction is used for the original neuron data,and the two-dimensional neuron data is generated through adaptive projection process.Then,the deep learning model of double convolutional gated recurrent neural networks is established to classify neurons.The proposed approach is successfully applied to three neuronal classification datasets,the experiment results show that the proposed method has higher classification accuracy and flexibility than the neuronal classification methods based on feature extraction.
蔺想红, 郑鉴洋, 王向文, 马慧芳. 基于深度学习网络的神经元自适应投影分类方法[J]. 电子学报, 2020, 48(7): 1321-1329.
LIN Xiang-hong, ZHENG Jian-yang, WANG Xiang-wen, MA Hui-fang. A Neuronal Classification Approach with Adaptive Projection Using Deep Learning Networks. Acta Electronica Sinica, 2020, 48(7): 1321-1329.
[1] Wang Y,Li Y,Huang W,et al.Research progression on human brain project[J].Chinese Journal of Medical Physics,2016,33(2):109-112.
[2] 彭丝雨,周到,张家琦,等.基于互信息的脑网络及测谎研究[J].电子学报,2019,47(7):1551-1556. PENG Si-yu,ZHOU Dao,ZHANG Jia-qi,et al.Research on mutual information-based brain network and lie detection[J].Acta Electronica Sinica,2019,47(7):1551-1556.(in Chinese)
[3] Oshio K I,Yamada S,Nakashima M.Neuron classification based on temporal firing patterns by the dynamical analysis with changing time resolution (DCT) method[J].Biological Cybernetics,2003,88(6):438-449.
[4] Lin X,Li Z,Ma H,et al.An evolutionary developmental approach for generation of 3D neuronal morphologies using gene regulatory networks[J].Neurocomputing,2018,273:346-356.
[5] Zeng H,Sanes J R.Neuronal cell-type classification:Challenges,opportunities and the path forward[J].Nature Reviews Neuroscience,2017,18(9):530-546.
[6] Alavi A,Cavanagh B,Tuxworth G,et al.Automated classification of dopaminergic neurons in the rodent brain[A].Proceedings of the International Joint Conference on Neural Networks[C].Atlanta,Ga,USA:IEEE,2009.81-88.
[7] Han F,Zeng J.Research for neuron classification based on support vector machine[A].Proceedings of the 3d International Conference on Digital Manufacturing and Automation[C].Guilin,China:IEEE,2012.646-649.
[8] Mihaljevié B,Benavides-Piccione R,Bielza C,et al.Bayesian network classifiers for categorizing cortical GABAergic interneurons[J].Neuroinformatics,2015,13(2):193-208.
[9] 李佳.基于集成极限学习机的神经元分类算法研究[D].上海:东华大学,2017. Li Jia.Research on Neuron Classification Based on Ensemble of Extreme Learning Machine[D].Shanghai:Donghua University,2017.(in Chinese)
[10] Lin X,Zheng J,Wang X,et al.A neuronal morphology classification approach based on deep residual neural networks[A].Proceedings of the 25th International Conference on Neural Information Processing[C].Siem Reap,Cambodia:Springer,2018.336-348.
[11] Hernández-Pérez L A,Delgado-Castillo D,Martín-Pérez R,et al.New features for neuron classification[J].Neuroinformatics,2019,17(1):5-25.
[12] 张静,邓仕槐,郭航,等.聚类分析在神经元形态特征分类中的应用[J].浙江大学学报(农业与生命科学版),2011,37(5):493-500. Zhang Jing,Deng Shi-Huai,Guo Hang,et al.Application of cluster analysis in morphological characteristics of neurons[J].Journal of Zhejiang University (Agriculture & Life Sciences),2011,37(5):493-500.(in Chinese)
[13] Yu C,Han Z,Zeng W,et al.Morphology cluster and prediction of growth of human brain pyramidal neurons[J].Neural Regeneration Research,2012,7(1):36-40.
[14] López-Cabrera J D,Lorenzo-Ginori J V.Feature selection for the classification of traced neurons[J].Journal of Neuroscience Methods,2018,303:41-54.
[15] Ascoli G A,Donohue D E,Halavi M.NeuroMorpho.Org:A central resource for neuronal morphologies[J].Journal of Neuroscience,2007,27(35):9247-9251.
[16] Salomon D.Transformations and Projections in Computer Graphics[M].Springer London,2006.
[17] 杨勃,邵泉铭,李文彬,等.深度卷积神经网络鉴别正交特征生成及其应用[J].电子学报,2018,46(10):2376-2383. YANG Bo,SHAO Quan-ming,LI Wen-bin,et al.Deepconvolutional neural networks controlled by discriminatively orthogonal feature generation and its application[J].Acta Electronica Sinica,2018,46(10):2376-2383.(in Chinese)
[18] Chung J,Gulcehre C,Cho K H,et al.Empirical evaluation of gated recurrent neural networks on sequence modeling[J].arXiv,2014,1412.3555.
[19] François Chollet et al.Keras[DB/OL].https://github.com/keras-team/keras,2015.
[20] Wu X,Liu J.A new early stopping algorithm for improving neural network generalization[A].Proceedings of the Second International Conference on Intelligent Computation Technology and Automation[C].Changsha,China:IEEE,2009.15-18.
[21] Scorcioni R,Polavaram S,Ascoli G A.L-Measure:A web-accessible tool for the analysis,comparison and search of digital reconstructions of neuronal morphologies[J].International Journal of Cancer,2008,73(4):492-496.
[22] Landgrebe D.A survey of decision tree classifier methodology[J].IEEE Transactions on Systems Man and Cybernetics,2002,21(3):660-674.
[23] Fukunaga K,Hostetler L.Optimization of K-nearest neighbor density estimates[J].IEEE Transactions on Information Theory,1973,19(3):320-326.
[24] 吕品,李全刚,柳厅文,等.基于双向LSTM的误植域名滥用检测方法[J].电子学报,2018,46(9):2081-2086. LÜ Pin,LI Quan-gang,LIU Ting-wen,et al.Towards typosquatting abuse detection using bi-directional LSTM[J].Acta Electronica Sinica,2018,46(9):2081-2086.(in Chinese)
[25] Pedregosa F,Varoquaux G,Gramfort A,et al.Scikit-learn:Machine learning in Python[J].Journal of Machine Learning Research,2011,12:2825-2830.