3D Neuron Morphology Analysis
This addresses a limitation in neuroscience for analyzing non-tubular neuron shapes, though it appears incremental by extending skeleton-based methods.
The paper tackles the problem of representing and analyzing complex 3D neuron shapes by introducing a skeleton mesh representation and a method to compute it from surface point clouds, then using it for feature extraction and classification, with experiments demonstrating robustness.
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.