基于卷积自编码器与点云配准的神经元形态相似性度量方法

doi:10.3969/j.issn.0258-8021.2023.01.007

Abstract
Figure/Table
References
Related Citation (15)

Download: PDF (7551 KB) HTML (1 KB)
Export: BibTeX | EndNote (RIS)

Abstract Morphology of neurons is closely related to their function. With the advancement of neuron tracing technology, more and more high-quality digitally reconstructed 3D neuron morphology data are emerging. A two-step neuron morphology measurement framework, based on deep learning and 3D spatial data registration technology, was proposed for the computational analysis of 3D neuronal structures. Through fast comparison and fine comparison, the framework could be used for the growing volume of neuron morphological data from the whole neuron to the branch. 99 453 neurons from the NeuroMorpho dataset were selected for the experiment. Compared with the existing fine comparison algorithms, this framework was more than 20 times faster with good universality, which could be applied to any neuron morphological data without other prior conditions. For the neurons registered in the brain atlas template, 233 uPNs were selected as the validation data, and 97.39% retrieval accuracy was achieved. For unregistered neurons, three types of neuron data were selected for verification, including 495 glutamatergic neurons, 389 multi-dendritic-dendritic arborization neurons, and 249 pyramidal neurons. The retrieval accuracy reached 91.7%, 93.79% and 83.1% respectively. Our proposed method is expected to be used for neuron type identification and correlation analysis of neuron morphology and characteristics.

Key words： neuron morphology unsupervised learning point cloud registration computational neuroscience

Received: 20 July 2021

PACS:

R318

Corresponding Authors: ^* E-mail:zhongyuli@xjtu.edu.cn

About author:: ^&Co-first outhor

	Service

	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	Fan Xiayue
	Zhen Haotian
	Shang Zengyi
	Xu Wenfei
	Li Zhongyu

Cite this article:

Fan Xiayue,Zhen Haotian,Shang Zengyi, et al. Similarity Measurement of Neuronal Morphology Based on Convolutional Auto-Encoder and Spatial Registration[J]. Chinese Journal of Biomedical Engineering, 2023, 42(1): 62-73.

URL:

http://cjbme.csbme.org/EN/10.3969/j.issn.0258-8021.2023.01.007 OR http://cjbme.csbme.org/EN/Y2023/V42/I1/62

[1] Peng Hanchuan, Zhou Zhi, Meijering E, et al. Automatic tracing of ultra-volumes of neuronal images[J]. Nature Methods, 2017, 14(4): 332-333.
[2] Li Rongjian, Zeng Tao, Peng Hanchuan et al. Deep learning segmentation of optical microscopy images improves 3-D neuron reconstruction[J]. IEEE Transactions on Medical Imaging, 2017,36(7): 1533-1541.
[3] Peng Hanchuan, Hawrylycz M, Roskams J, et al. BiNeuron: large-scale 3D neuron reconstruction from optical microscopy images[J]. Neuron, 2015, 87(2): 252-256.
[4] Ascoli GA, Donohue DE, Halavi M. NeuroMorpho. Org: a central resource for neuronal morphologies[J]. Journal of Neuroscience, 2007, 27(35): 9247-9251.
[5] Ascoli GA. NeuroMorpho.Org[OL]. http://neuromorpho.org/, 2022-12-06/2021-07-25.
[6] Chklovskii DB. Synaptic connectivity and neuronal morphology: two sides of the same coin[J]. Neuron, 2004, 43(5): 609-617.
[7] Peng Hanchuan, Ruan Zongcai, Long Fuhui, et al. V3D enables real-time 3D visualization and quantitative analysis of large-scale biological image data sets[J]. Nature biotechnology, 2010, 28(4): 348-353.
[8] Gao Ruixuan, Asano SM, Upadhyayula S, et al. Cortical column and whole-brain imaging with molecular contrast and nanoscale resolution[J]. Science, 2019, 363(6424): eaau8302.
[9] Nanda S, Allaham MM, Bergamino M, et al. Doubling up on the fly: neuromorpho. org meets big data[J]. Neuroinformatics, 2015, 13(1): 127-129.
[10] DeFelipe J, López-Cruz PL, Benavides-Piccione R, et al. New insights into the classification and nomenclature of cortical GABAergic interneurons[J]. Nature Reviews Neuroscience, 2013, 14(3): 202-216.
[11] Armananzas R, Ascoli GA. Towards the automatic classification of neurons[J]. Trends in Neurosciences, 2015, 38(5): 307-318.
[12] Scorcioni R, Polavaram S, Ascoli GA. L-Measure: a web-accessible tool for the analysis, comparison and search of digital reconstructions of neuronal morphologies[J]. Nature Protocols, 2008, 3(5): 866-876.
[13] Costa LDF, Zawadzki K, Miazaki M, et al. Unveiling the neuromorphological space[J]. Frontiers in Computational Neuroscience, 2010, 4: 150.
[14] Snider J, Pillai A, Stevens CF. A universal property of axonal and dendritic arbors[J]. Neuron, 2010, 66(1): 45-56.
[15] Kanari L, Dłotko P, Scolamiero M, et al. A topological representation of branching neuronal morphologies[J]. Neuroinformatics, 2018, 16(1): 3-13.
[16] Li Zhongyu, Butler E, Li Kang, et al. Large-scale exploration of neuronal morphologies using deep learning and augmented reality[J]. Neuroinformatics, 2018, 16(3): 339-349.
[17] Li Zhongyu, Fan Xiaye, Shang Zengyi, et al. Towards computational analytics of 3D neuron images using deep adversarial learning[J]. Neurocomputing, 2021, 438: 323-333.
[18] 常令琛, 李钟毓, 樊夏玥, 等. 基于三维深度神经网络的大规模神经元形态表征与检索方法[J]. 中国科学: 信息科学, 2021, 51(12): 2089-2101.
[19] Wan Yinan, Long Fuhui, Qu Lei, et al. BlastNeuron for automated comparison, retrieval and clustering of 3D neuron morphologies[J]. Neuroinformatics, 2015, 13(4): 487-499.
[20] Hu MK. Visual pattern recognition by moment invariants[J]. IRE Transactions on Information Theory, 1962, 8(2): 179-187.
[21] Costa M, Manton JD, Ostrovsky AD, et al. NBLAST: rapid, sensitive comparison of neuronal structure and construction of neuron family databases[J]. Neuron, 2016, 91(2): 293-311.
[22] Masci J, Meier U, Cire塂an D, et al. Stacked convolutional auto-encoders for hierarchical feature extraction[C] //International conference on artificial neural networks. Berlin: Springer-Verlag, 2011: 52-59.
[23] Belongie S, Mori G, Malik J. Matching with shape contexts[M]//Statistics and Analysis of Shapes. Boston: Birkhäuser, 2006: 81-105.
[24] Cannon RC, Turner DA, Pyapali GK, et al. An on-line archive of reconstructed hippocampal neurons[J]. Journal of Neuroscience Methods, 1998, 84(1-2): 49-54.
[25] Cachero S, Ostrovsky AD, Jai YY, et al. Sexual dimorphism in the fly brain[J]. Current Biology, 2010, 20(18): 1589-1601.
[26] Fischler MA, Bolles RC. Random sample consensus: a paradigm for model fitting with applications to image analysis and automated cartography[J]. Communications of the ACM, 1981, 24(6): 381-395.
[27] Jefferis GSXE, Potter CJ, Chan A M, et al. Comprehensive maps of Drosophila higher olfactory centers: spatially segregated fruit and pheromone representation[J]. Cell, 2007, 128(6): 1187-1203.
[28] Conjeti S, Katouzian A, Kazi A, et al. Metric hashing forests[J]. Medical Image Analysis, 2016, 34: 13-29.
[29] Radford A. Unsupervised representation learning with deep convolutional generative adversarial networks [OL]. https://doi.org/10.48550/arXiv.1511.06434, 2016-01-07/2021-07-25.
[30] Huo Yuda, Lu Wen, Tian Yuan, et al. Prkn knockout mice show autistic-like behaviors and aberrant synapse formation[J]. Iscience, 2022, 25(7): 104573.
[31] 李娇娇,孙红岩,董雨,等. 基于深度学习的3维点云处理综述[J].计算机研究与发展,2022,59(5):1160-1179.