hustyichi / medical-labelme

Image Polygonal Annotation with Python (polygon, rectangle, circle, line, point and image-level flag annotation).

medical-labelme

Medical image Polygonal Annotation with Python

Description

medical-labelme is a graphical image annotation tool inspired by http://labelme.csail.mit.edu.

It is written in Python and uses Qt for its graphical interface.

Features

• DICOM image annotation, includes single-frame and multi-frame images
• Image annotation for polygon, rectangle, circle, line and point. (tutorial)
• Image flag annotation for classification and cleaning.
• Video annotation. (video annotation)
• GUI customization (predefined labels / flags, auto-saving, label validation, etc).
• Exporting VOC-format dataset for semantic/instance segmentation. (semantic segmentation, instance segmentation)
• Exporting COCO-format dataset for instance segmentation. (instance segmentation)

Installation

Install standalone executable/app from: https://github.com/hustyichi/medical-labelme/releases

How to build standalone executable

Below shows how to build the standalone executable on macOS, Linux and Windows.

# Setup conda
conda create --name medical-labelme python=3.9
conda activate medical-labelme

# Build the standalone executable
pip install .
pip install 'matplotlib<3.3'
pip install pyinstaller
pyinstaller labelme.spec
dist/labelme --version

How to contribute

Make sure below test passes on your environment. See .github/workflows/ci.yml for more detail.

pip install -r requirements-dev.txt

flake8 .
black --line-length 79 --check labelme/
MPLBACKEND='agg' pytest -vsx tests/

Acknowledgement

This repo is the fork of wkentaro/labelme.