Skeleton optimization of neuronal morphology based on three-dimensional shape restrictions

A hierarchically annotated dataset drives tangled filament recognition in digital neuron reconstruction

Reconstructing neuronal morphology is vital for classifying neurons and mapping brain connectivity. However, it remains a significant challenge due to its complex structure, dense distribution, and low image contrast. In particular, AI-assisted methods often yield numerous errors that require extensive manual intervention. Therefore, reconstructing hundreds of neurons is already a daunting task for general research projects. A key issue is the lack of specialized training for challenging regions due to inadequate data and training methods. This study extracted 2,800 challenging neuronal blocks and categorized them into multiple density levels. Furthermore, we enhanced images using an axial continuity-based network that improved three-dimensional voxel resolution while reducing the difficulty of neuron recognition. Comparing the pre- and post-enhancement results in automatic algorithms using fluorescence micro-optical sectioning tomography (fMOST) data, we observed a significant increase in the recall rate. Our study not only enhances the throughput of reconstruction but also provides a fundamental dataset for tangled neuron reconstruction.

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

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.

SNAP: a structure-based neuron morphology reconstruction automatic pruning pipeline

Background

Neuron morphology analysis is an essential component of neuron cell-type definition. Morphology reconstruction represents a bottleneck in high-throughput morphology analysis workflow, and erroneous extra reconstruction owing to noise and entanglements in dense neuron regions restricts the usability of automated reconstruction results. We propose SNAP, a structure-based neuron morphology reconstruction pruning pipeline, to improve the usability of results by reducing erroneous extra reconstruction and splitting entangled neurons.

Methods

For the four different types of erroneous extra segments in reconstruction (caused by noise in the background, entanglement with dendrites of close-by neurons, entanglement with axons of other neurons, and entanglement within the same neuron), SNAP incorporates specific statistical structure information into rules for erroneous extra segment detection and achieves pruning and multiple dendrite splitting.

Results

Experimental results show that this pipeline accomplishes pruning with satisfactory precision and recall. It also demonstrates good multiple neuron-splitting performance. As an effective tool for post-processing reconstruction, SNAP can facilitate neuron morphology analysis.

3D Neuron Morphology Analysis

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.

NRRS: a re-tracing strategy to refine neuron reconstruction

It is crucial to develop accurate and reliable algorithms for fine reconstruction of neural morphology from whole-brain image datasets. Even though the involvement of human experts in the reconstruction process can help to ensure the quality and accuracy of the reconstructions, automated refinement algorithms are necessary to handle substantial deviations problems of reconstructed branches and bifurcation points from the large-scale and high-dimensional nature of the image data. Our proposed Neuron Reconstruction Refinement Strategy (NRRS) is a novel approach to address the problem of deviation errors in neuron morphology reconstruction. Our method partitions the reconstruction into fixed-size segments and resolves the deviation problems by re-tracing in two steps. We also validate the performance of our method using a synthetic dataset. Our results show that NRRS outperforms existing solutions and can handle most deviation errors. We apply our method to SEU-ALLEN/BICCN dataset containing 1741 complete neuron reconstructions and achieve remarkable improvements in the accuracy of the neuron skeleton representation, the task of radius estimation and axonal bouton detection. Our findings demonstrate the critical role of NRRS in refining neuron morphology reconstruction.

Availability and implementation

The proposed refinement method is implemented as a Vaa3D plugin and the source code are available under the repository of vaa3d_tools/hackathon/Levy/refinement. The original fMOST images of mouse brains can be found at the BICCN's Brain Image Library (BIL) (https://www.brainimagelibrary.org). The synthetic dataset is hosted on GitHub (https://github.com/Vaa3D/vaa3d_tools/tree/master/hackathon/Levy/refinement).

Supplementary information

Supplementary data are available at Bioinformatics Advances online.