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

Journal Article · 28 September 2023 · BMC Bioinformatics

DOI: https://doi.org/10.1186/s12859-023-05482-y · OSTI ID:2338178

Jiang, Jiaxiang ^[1]; Goebel, Michael ^[2]; Borba, Cezar ^[3]; Smith, William ^[2]; Manjunath, B. S. ^[2]

---

1. University of California, Santa Barbara, CA (United States); Univeristy of California Santa Barbara
2. University of California, Santa Barbara, CA (United States)
3. University of Florida, St. Augustine, FL (United States)

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.

• Research Organization: University of California, Santa Barbara, CA (United States)
• Sponsoring Organization: USDOE Office of Science (SC), Advanced Scientific Computing Research (ASCR)
• Grant/Contract Number: SC0021978
• OSTI ID: 2338178
• Journal Information: BMC Bioinformatics, Journal Name: BMC Bioinformatics Journal Issue: 1 Vol. 24; ISSN 1471-2105
• Publisher: BioMed CentralCopyright Statement
• Country of Publication: United States
• Language: English