Skip to content

A Python package that utilizes machine learning to correct split mistakes in a fragmented neuron segmentation.

License

Notifications You must be signed in to change notification settings

AllenInstitute/deep-neurographs

Repository files navigation

GraphTrace

License Code Style semantic-release: angular Interrogate Coverage Python

Overview

GraphTrace is a Python library that automatically correct splits in fragmented neuron segmentations from whole-brain images by.


Figure: Neuron fragments corrected by using GraphTrace.

Briefly describe inference pipeline, to do...

  • Graph Construction: Reads neuron fragments stored as swc files and loads them into a Networkx graph.
  • Proposals: Generates potential connections between nearby fragments to correct false splits in the segmentation
  • Feature Generation: Extracts geometric and image-based features from the graph to be utilized by a machine learning model that classifies the proposals.
  • Graph Neural Network (GNN) Inference: Predicts whether to accept or reject proposals based on the generated features and graphical structure.
  • Graph Update: Integrates inference results by merging fragments corresponding to an accepted proposal.

pipeline
Figure: Visualization of split correction pipeline, see Inference section for description of each step.

Usage

To do...

Inference

Step 1: Graph Construction

To do...

Step 2: Proposal Generation

To do...

Step 3: Proposal Classification

To do...

Installation

To use the software, in the root directory, run

pip install -e .

License

GraphTrace is licensed under the MIT License.

About

A Python package that utilizes machine learning to correct split mistakes in a fragmented neuron segmentation.

Resources

License

Stars

Watchers

Forks

Packages

No packages published