GraphTrace is a Python library that automatically corrects split errors in fragmented neuron segmentations from whole-brain images. It takes SWC files as input and uses a graph-based neural network pipeline to propose, score, and merge candidate connections between neuron fragments. GraphTrace efficiently handles datasets with millions of fragments across whole-brain volumes, enabling high-throughput proofreading and reconstruction at scale.
Figure: GraphTrace reconnects fragmented neuron segments into coherent traces.
The neuron fragment split correction pipeline consists of three main steps:
a. Graph Construction: Reads neuron fragments stored as SWC files and loads them into a Networkx graph.
b. Proposal Generation: Generates potential connections between nearby fragments.
c. GNN-Based Inference: Predicts whether to accept or reject proposals based on the geometric and image-based features.
Figure: Visualization of split correction pipeline, see Inference section for description of each step.
To do...
To do...
To do...
To use the software, in the root directory, run
pip install -e .To do...
For any inquiries, feedback, or contributions, please do not hesitate to contact us. You can reach us via email at [email protected] or connect on LinkedIn.
GraphTrace is licensed under the MIT License.