Metadata-Version: 2.4
Name: femura
Version: 0.1.0
Summary: Processing pipeline for femur CT metrics
Author: University of Manchester
License-Expression: Apache-2.0
Requires-Python: >=3.10
Description-Content-Type: text/markdown
License-File: LICENSE
Requires-Dist: numpy
Requires-Dist: nibabel
Requires-Dist: pydicom
Requires-Dist: scikit-image
Requires-Dist: trimesh
Requires-Dist: SimpleITK
Requires-Dist: scikit-learn
Requires-Dist: matplotlib
Requires-Dist: nnunetv2
Requires-Dist: py-cpuinfo
Requires-Dist: requests
Requires-Dist: numpy
Requires-Dist: SimpleITK
Requires-Dist: scikit-image>=0.19.3
Requires-Dist: torch
Requires-Dist: psutil
Requires-Dist: GPUtil
Provides-Extra: dev
Requires-Dist: pytest; extra == "dev"
Requires-Dist: black; extra == "dev"
Requires-Dist: flake8; extra == "dev"
Requires-Dist: pylint; extra == "dev"
Requires-Dist: mypy; extra == "dev"
Dynamic: license-file

<!--
SPDX-FileCopyrightText: 2024 - 2026 University of Manchester

SPDX-License-Identifier: apache-2.0
-->

# FEMURA

## About
This softare is for processing CT scans.

## Installation
`pip install femura`

Alternatively, clone this repository, and `pip install` it as a local package.

## Usage
The software is split into 5 scripts, which are run sequentially.
SLURM jobscripts are given in [jobscripts](jobscripts).

There is a command line tool `femura` which runs all five scripts as a pipeline.
`femura --help` gives an explanation of how to run the software.

## For developers
There is functionality to compare the summary output `final_output.csv` from two analyses,
to guard against regressions when developing the software.
The idea is to compare the output from processing the same DICOM files
using two different versions of the software.
The default relative tolerance in numerical output fields is 0.005 i.e. 0.5%.

```
femura_verify ref_output_file new_output_file [--rel_tol REL_TOL]
```
