Metadata-Version: 2.3
Name: pyfroc
Version: 0.1.0
Summary: python toolkit for FROC analysis
Project-URL: Homepage, https://github.com/akchan/pyfroc
Project-URL: Issues, https://github.com/akchan/pyfroc/issues
Author-email: Satoshi Funayama <akchan.acts@gmail.com>
License-File: LICENSE
Classifier: License :: OSI Approved :: GNU General Public License v3 (GPLv3)
Classifier: Operating System :: OS Independent
Classifier: Programming Language :: Python :: 3
Requires-Python: >=3.9
Requires-Dist: bidict>=0.23.1
Requires-Dist: matching>=1.4.3
Requires-Dist: miniballcpp>=0.2.3
Requires-Dist: numpy<2.0.0,>=1.2.0
Requires-Dist: openpyxl>=3.1.4
Requires-Dist: pandas>=2.2.2
Requires-Dist: pydicom>=2.4.4
Requires-Dist: pynrrd>=1.0.0
Requires-Dist: pytypedstream>=0.1.0
Requires-Dist: requests
Requires-Dist: scikit-image>=0.23.2
Requires-Dist: tcia-utils
Requires-Dist: tqdm>=4.66.4
Description-Content-Type: text/markdown

# pyfroc

Python framework for FROC analysis

## About

### What pyfroc does

- Improve FROC analysis procedure.
- Manage responses of raters.
- The responses can be made using segmentation function of [3D Slicer](https://www.slicer.org/).
- Evaluate responses and devide them into true positive or false positive automatically.
- Build a xlsx file for the [RJafroc](https://github.com/dpc10ster/RJafroc), a R library which runs statistical tests of AFROC (alternative Free-response receiver operating characteristic) analysis.
- Write images of responses with paired lesions (if exists).

### What pyfroc doesn't

- Statistical analysis of JAFROC. This is out of scope of pyfroc. Use [RJafroc](https://github.com/dpc10ster/RJafroc) for statistical analysis.
- FROC analysis including multi-modality references because pyfroc doesn't implement an algorithm to match intermodality lesions.

## Table of contents

## Use case

pyfroc is designed for specific scenarios of FROC analysis. pyfroc supports only one modality for reference lesions.

### Example scenario #1

- Compare diagnostic performance between radiologists and AI.
- Using a specific series to record responses.

### Example scenario #2

- Compare a standard MRI protocol with an abbreviated protocol.
- Using same series to record responses.

### Example scenario #3

- Compare images reconstructed using an advanced method with images reconstructed using conventional method.
- Using either series to record responses.

## Instalation

```bash
pip install pyfroc
```

## Tutorial

Use pyfroc with 3D Slicer


## License

GPLv3







