Metadata-Version: 2.4
Name: grand-challenge-metrics
Version: 0.6.0
Summary: useful functions for evaluating machine learning models in the context of medical imaging
Author: James Meakin
License: MIT
Project-URL: repository, https://github.com/DIAGNijmegen/rse-grand-challenge-metrics
Classifier: Development Status :: 3 - Alpha
Classifier: Intended Audience :: Developers
Classifier: Intended Audience :: Healthcare Industry
Classifier: Natural Language :: English
Requires-Python: <4.0,>=3.10
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: scipy
Requires-Dist: numpy
Requires-Dist: scikit-learn
Dynamic: license-file

# Grand Challenge Metrics

[![Build Status](https://github.com/DIAGNijmegen/rse-grand-challenge-metrics/workflows/CI/badge.svg?branch=main)](https://github.com/DIAGNijmegen/rse-grand-challenge-metrics/actions?query=workflow%3ACI+branch%3Amain)
[![PyPI version](https://badge.fury.io/py/grand-challenge-metrics.svg)](https://badge.fury.io/py/grand-challenge-metrics)
[![PyPI - Python Version](https://img.shields.io/pypi/pyversions/grand-challenge-metrics)](https://pypi.org/project/grand-challenge-metrics/)
[![Documentation Status](https://img.shields.io/badge/docs-passing-4a4c4c1.svg)](https://comic.github.io/grand-challenge-metrics/)
[![Code style](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/ambv/black)

Grand Challenge Metrics contains useful functions for evaluating machine learning models in the context of medical imaging.

  - Free software: MIT license
  - Documentation: <https://diagnijmegen.github.io/rse-grand-challenge-metrics/>.

## Features

  - Bounding box annotations with Jaccard Index calculations
  - Calculations of bootstrapped ROC curves
  - Scoring for detection tasks
  - Efficient calculation of confusion matrices, jaccard scores, dice scores, hausdorff distances,
    absolute volume differences, and relative volume differences

## Getting Started

[Grand Challenge Metrics](https://github.com/DIAGNijmegen/rse-grand-challenge-metrics) requires Python 3.10 or above, and can be installed from `pip`.
Please see the [Getting Started](https://diagnijmegen.github.io/rse-grand-challenge-metricsusage.html) documentation for more details.
