cleanX
CleanX is an open source python library for exploring, cleaning and augmenting large datasets of X-rays, or certain other types of radiological images. JPEG files can be extracted from DICOM files or used directly.
The latest official release:
primary author: Candace Makeda H. Moore
other authors + contributors: Oleg Sivokon, Andrew Murphy
Continous Integration (CI) status
Requirements
- a python installation (3.7, 3.8 or 3.9)
- ability to create virtual environments (recommended, not absolutely necessary)
tesserocr,matplotlib,pandas,pillowandopencv- optional recommendation of
SimpleITKorpydicomfor DICOM/dcm to JPG conversion - Anaconda is now supported, but not technically necessary
Developer's Guide
Please refer to Developer's Giude for more detailed explanation.
Developing Using Anaconda's Python
Use Git to check out the project's source, then, in the source directory run:
conda create -n cleanx
conda activate -n cleanx
python ./setup.py install_dev
You may have to do this for Python 3.7, Python 3.8 and Python 3.9 if you need to check that your changes will work in all supported versions.
Developing Using python.org's Python
Use Git to check out the project's source, then in the source directory run:
python -m venv .venv
. ./.venv/bin/activate
python ./setup.py install_dev
Similar to conda based setup, you may have to use Python versions 3.7, 3.8 and 3.9 to create three different environments to recreate our CI process.
Supported Platforms
cleanX package is a pure Python package, but it has many dependencies on native libraries. We try to test it on as many platforms as we can to see if dependencies can be installed there. Below is the list of platforms that will potentially work.
Whether python.org Python or Anaconda Python are supported, it means that version 3.7, 3.8 and 3.9 are supported. We know for certain that 3.6 is not supported, and there will be no support in the future.
32-bit Intell and ARM
We don't know if either one of these is supported. There's a good chance that 32-bit Intell will work. There's a good chance that ARM won't.
It's unlikely that the support will be added in the future.
AMD64 (x86)
| Linux | Win | OSX | |
|---|---|---|---|
 |
Supported | Unknown | Unknown |
 |
Supported | Supported | Supported |
ARM64
Seems to be unsupported at the moment on both Linux and OSX, but it's likely that support will be added in the future.
Documentation
Online documentation at https://drcandacemakedamoore.github.io/cleanX/
You can also build up-to-date documentation by command.
Documentation can be generated by command:
python setup.py apidoc
python setup.py build_sphinx
The documentation will be generated in ./build/sphinx/html directory. Documentation is generated automatically as new functions are added.
Special additional documentation for medical professionals with limited programming ability is available on the wiki (https://github.com/drcandacemakedamoore/cleanX/wiki/Medical-professional-documentation).
To get a high level overview of some of the functionality of the program you can look at the Jupyter notebooks inside workflow_demo.
Installation
-
setting up a virtual environment is desirable, but not absolutely necessary
-
activate the environment
Anaconda Installation
- use command for conda as below
conda install -c doctormakeda -c conda-forge cleanx
You need to specify both channels because there are some cleanX dependencies that exist in both Anaconda main channel and in conda-forge
pip installation
- use pip as below
pip install cleanX
Getting Started
We will imagine a very simple scenario, where we need to automate normalization of the images we have. We stored the images in directory /images/to/clean/ and they all have jpg extension. We want the cleaned images to be saved in the cleaned directory.
Normalization here means ensuring that the lowest pixel value (the darkest part of the image) is as dark as possible and that the lightest part of the image is as light as possible.
CLI Example
The problem above doesn't require writing any new Python code. We can accomplish our task by calling the cleanX command like this:
mkdir cleaned
python -m cleanX images run-pipeline \
-s Acqure \
-s Normalize \
-s "Save(target='cleaned')" \
-j \
-r "/images/to/clean/*.jpg"
Let's look at the command's options and arguments:
python -m cleanXis the Python's command-line option for loading thecleanXpackage. All command-line arguments that follow this part are interpreted bycleanX.imagessub-command is used for processing of images.run-pipelinesub-command is used to start aPipelineto process the images.-s(repeatable) option specifiesPipelineStep. Steps map to their class names as found in thecleanX.image_work.stepsmodule. If the__init__function of a step doesn't take any arguments, only the class name is necessary. If, however, it takes arguments, they must be given using Python's literals, using Python's named arguments syntax.-joption instructs to create journaling pipeline. Journaling pipelines can be restarted from the point where they failed, or had been interrupted.-rallows to specify source for the pipeline. While, normally, we will want to start withAcquirestep, if the pipeline was interrupted, we need to tell it where to look for the initial sources.
Once the command finishes, we should see the cleaned directory filled with images with the same names they had in the source directory.
Let's consider another simple task: batch-extraction of images from DICOM files:
mkdir extracted
python -m cleanX dicom extract \
-i dir /path/to/dicoms/
-o extracted
This calls cleanX CLI in the way similar to the example above, however, it calls the dicom sub-command with extract-images subcommand.
-itellscleanXto look for directory named/path/to/dicoms-otellscleanXto save extracted JPGs inextracteddirectory.
If you have any problems with this check #40 and add issues or discussions.
Coding Example
Below is the equivalent code in Python:
import os
from cleanX.image_work import (
Acquire,
Save,
GlobSource,
Normalize,
create_pipeline,
)
dst = 'cleaned'
os.mkdir(dst)
src = GlobSource('/images/to/clean/*.jpg')
p = create_pipeline(
steps=(
Acquire(),
Normalize(),
Save(dst),
),
journal=True,
)
p.process(src)
Let's look at what's going on here. As before, we've created a pipeline using create_pipeline with three steps: Acquire, Normalize and Save. There are several kinds of sources available for pipelines. We'll use the GlobSource to match our CLI example. We'll specify journal=True to match the -j flag in our CLI example.
And for the DICOM extraction we might use similar code:
imort os
from cleanX.dicom_processing import DicomReader, DirectorySource
dst = 'extracted'
os.mkdir(dst)
reader = DicomReader()
reader.rip_out_jpgs(DirectorySource('/path/to/dicoms/', 'file'), dst)
This will look for the files with dcm extension in /path/to/dicoms/ and try to extract images found in those files, saving them in extracted directory.
About using this library
If you use the library, please credit me and my collaborators. You are only free to use this library according to license. We hope that if you use the library you will open source your entire code base, and send us modifications. You can get in touch with me by starting a discussion (https://github.com/drcandacemakedamoore/cleanX/discussions/37) if you have a legitimate reason to use my library without open-sourcing your code base, or following other conditions, and I can make you specifically a different license.
We are adding new functions and classes all the time. Many unit tests are available in the test folder. Test coverage is currently partial. Some newly added functions allow for rapid automated data augmentation (in ways that are realistic for radiological data). Some other classes and functions are for cleaning datasets including ones that:
- Get image and metadata out of dcm (DICOM) files into jpeg and csv files
- Process datasets from csv or json or other formats to generate reports
- Run on dataframes to make sure there is no image leakage
- Run on a dataframe to look for demographic or other biases in patients
- Crop off excessive black frames (run this on single images) one at a time
- Run on a list to make a prototype tiny Xray others can be compared to
- Run on image files which are inside a folder to check if they are "clean"
- Take a dataframe with image names and return plotted(visualized) images
- Run to make a dataframe of pics in a folder (assuming they all have the same 'label'/diagnosis)
- Normalize images in terms of pixel values (multiple methods)
All important functions are documented in the online documentation for programmers. You can also check out one of our videos by clicking the linked picture below:
![[Security] Workflow on-tag.yml is using vulnerable action s-weigand/setup-conda](https://avatars.githubusercontent.com/u/72508088?v=4)
94 Jan 04, 2023
1 Nov 08, 2021
1 Dec 26, 2021
1 Feb 15, 2022
11 Dec 30, 2022
43 Nov 29, 2022
4 Feb 11, 2022
4.7k Jan 09, 2023
11 Jan 07, 2022
17 Jul 09, 2022
3 Jun 30, 2022
31 Dec 16, 2022
61 Oct 02, 2022
34 Nov 18, 2022
98 Dec 31, 2022
0 Sep 07, 2021
159 Dec 10, 2022
2.8k Dec 31, 2022
27 Dec 28, 2022
2.2k Dec 28, 2022