A robust approach to 3D neuron shape representation for quantification and classification

BMC Bioinformatics

Research

B. S. Manjunath¹  Jiaxiang Jiang¹  Michael Goebel¹  William Smith²  Cezar Borba³ 

[1] Department of Electrical and Computer Engineering, University of California, Santa Barbara, USA;Department of Molecular, Cell and Developmental Biology, University of California, Santa Barbara, USA;The Whitney Laboratory for Marine Bioscience, University of Florida, St. Augustine, USA;

关键词: 3D neuron morphology;    Skeleton mesh;    Graph;    Sub-cellular features;    Embedding;    Classification;   

DOI  :  10.1186/s12859-023-05482-y

 received in 2023-03-16, accepted in 2023-09-13,  发布年份 2023

来源: Springer

【 摘 要 】

We consider the problem of finding an accurate representation of neuron shapes, extracting sub-cellular features, and classifying neurons based on neuron shapes. In neuroscience research, the skeleton representation is often used as a compact and abstract representation of neuron shapes. However, existing methods are limited to getting and analyzing “curve” skeletons which can only be applied for tubular shapes. This paper presents a 3D neuron morphology analysis method for more general and complex neuron shapes. First, we introduce the concept of skeleton mesh to represent general neuron shapes and propose a novel method for computing mesh representations from 3D surface point clouds. A skeleton graph is then obtained from skeleton mesh and is used to extract sub-cellular features. Finally, an unsupervised learning method is used to embed the skeleton graph for neuron classification. Extensive experiment results are provided and demonstrate the robustness of our method to analyze neuron morphology.

【 授权许可】

CC BY   
© BioMed Central Ltd., part of Springer Nature 2023

【 图 表 】

42004_2023_990_Article_IEq59.gif

Fig. 4

Fig. 1

Fig. 4

13690_2023_1170_Article_IEq56.gif

Fig. 2

Fig. 1

13690_2023_1170_Article_IEq162.gif

Fig. 10

13690_2023_1170_Article_IEq160.gif

Fig. 1

13690_2023_1170_Article_IEq159.gif

Fig. 1

13395_2023_325_Article_IEq1.gif

13690_2023_1170_Article_IEq157.gif

Fig.7

Fig. 1

40708_2023_202_Article_IEq25.gif

40708_2023_202_Article_IEq10.gif

42004_2023_990_Article_IEq37.gif

Fig. 1

Fig. 7

40249_2023_1134_Article_IEq1.gif

Fig. 5

13690_2023_1170_Article_IEq29.gif

Fig. 2

13690_2023_1170_Article_IEq28.gif

13690_2023_1170_Article_IEq27.gif

13690_2023_1170_Article_IEq26.gif

13690_2023_1170_Article_IEq25.gif

13690_2023_1170_Article_IEq24.gif

13690_2023_1170_Article_IEq139.gif

Fig. 9

13690_2023_1170_Article_IEq137.gif

12888_2023_5172_Article_IEq46.gif

12888_2023_5172_Article_IEq44.gif

Fig. 1

13690_2023_1177_Fige_HTML.png

13690_2023_1170_Article_IEq18.gif

Fig. 2

13690_2023_1170_Article_IEq17.gif

13690_2023_1170_Article_IEq10.gif

13690_2023_1170_Article_IEq124.gif

Fig. 9

Fig. 1

Fig. 5

Fig. 1

Fig. 11

13063_2023_7595_Article_IEq4.gif

Fig. 1

Fig. 4

Fig. 1

13690_2023_1170_Article_IEq14.gif

Fig. 3

Fig. 4

Scheme 1

42004_2023_995_Article_IEq11.gif

Fig. 3

Fig. 4

Fig. 2

12888_2023_5172_Article_IEq13.gif

12888_2023_5172_Article_IEq11.gif

12888_2023_5172_Article_IEq10.gif

Fig. 2

Fig. 1

13690_2023_1170_Article_IEq207.gif

12888_2023_5142_Article_IEq14.gif

13690_2023_1170_Article_IEq188.gif

Fig. 1