Python package for evaluating neuron segmentations in terms of the number of splits and merges
Project description
SkeletonMetrics
Python package for evaluating the accuracy of a predicted segmentation of neuronal arbors by comparing it to a set of ground truth skeletons. This tool detects topological mistakes such as splits and merges in the predicted segmentation, then computes several skeleton-based metrics that quantify its topological accuracy.
Details
Ground truth skeletons must be stored as SWC files so that each can be represented as a graph with xyz coordinates as a node-level attribute. The evaluation is performed for each by first iterating over the ground truth skeletons (i.e. graphs) and labeling the nodes with the segment ids from the predicted segmentation. Topological mistakes are detected by examining the labels of individual nodes, neighboring nodes, and nodes across different ground truth skeletons.
Metrics computed for each ground truth skeleton:
- Number of Splits: Number of segments that a ground truth skeleton is broken into.
- Number of Merges: Number multiple segments are incorrectly merged into a single segment.
- Percentage of Omit Edges: Proportion of edges in the ground truth that are omitted in the predicted segmentation.
- Percentage of Merged Edges: Proportion of edges that are merged in the predicted segmentation compared to the ground truth.
- Edge Accuracy: Evaluates how accurately the edges of the predicted segmentation match the ground truth.
- Expected Run Length (ERL): Expected length of segments or edges in the predicted segmentation.
Usage
Here is a simple example of evaluating a predicted segmentation. Note that this package supports a number of different input types, see documentation for details.
import os
from aind_segmentation_evaluation.evaluate import run_evaluation
from aind_segmentation_evaluation.conversions import volume_to_graph
from tifffile import imread
if __name__ == "__main__":
# Initializations
data_dir = "./resources"
target_graphs_dir = os.path.join(data_dir, "target_graphs")
path_to_target_labels = os.path.join(data_dir, "target_labels.tif")
pred_labels = imread(os.path.join(data_dir, "pred_labels.tif"))
pred_graphs = volume_to_graph(pred_labels)
# Evaluation
stats = run_evaluation(
target_graphs_dir,
path_to_target_labels,
pred_graphs,
pred_labels,
filetype="tif",
output="tif",
output_dir=data_dir,
permute=[2, 1, 0],
scale=[1.101, 1.101, 1.101],
)
# Write out results
print("Graph-based evaluation...")
for key in stats.keys():
print(" {}: {}".format(key, stats[key])
Installation
To use the software, in the root directory, run
pip install -e .
To develop the code, run
pip install -e .[dev]
To install this package from PyPI, run
pip install aind-segmentation-evaluation
Pull requests
For internal members, please create a branch. For external members, please fork the repository and open a pull request from the fork. We'll primarily use Angular style for commit messages. Roughly, they should follow the pattern:
<type>(<scope>): <short summary>
where scope (optional) describes the packages affected by the code changes and type (mandatory) is one of:
- build: Changes that affect build tools or external dependencies (example scopes: pyproject.toml, setup.py)
- ci: Changes to our CI configuration files and scripts (examples: .github/workflows/ci.yml)
- docs: Documentation only changes
- feat: A new feature
- fix: A bugfix
- perf: A code change that improves performance
- refactor: A code change that neither fixes a bug nor adds a feature
- test: Adding missing tests or correcting existing tests
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for segmentation_skeleton_metrics-4.8.10.tar.gz
Algorithm | Hash digest | |
---|---|---|
SHA256 | 7579814f950f45389cceace94a4923938902d9a4c2baa3904aa70b792e5fcf11 |
|
MD5 | 8970996a822d380a0a32c87920a4516c |
|
BLAKE2b-256 | 055116a08debefba777e9b3d649005e4d54c74196c643ec5d07da4890ea3e07c |
Hashes for segmentation_skeleton_metrics-4.8.10-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 15a512d429404f8779e7d78bd906938baf089fe5e763111c1b31c1ced00e9334 |
|
MD5 | 0fad0be14ba46182ce74f609c346616a |
|
BLAKE2b-256 | 202d5e7084ef37fe81284968524e0231a42e07b369fdf25cea9dd746288bd9f5 |