MedShapeNetCore: [Show case, Release page, Zenodo, Publication]

MedShapeNetCore is a subset of MedShapeNet, containing more lightweight 3D anatomical shapes in the format of mask, point cloud and mesh. The shape data are stored as numpy arrays in nested dictonaries in npz format (Zenodo). This API provides means to downloading, accessing and processing the shape data via Python, which integrates MedShapeNetCore seamless into Python-based machine learning workflows.

Check out Show case for the latest update.

Installation (Python >=3.8, Release page)

pip install MedShapeNetCore

or install from source:

python setup.py install

Getting started ()

basic commands:

 python -m MedShapeNetCore info  # check the general information of the dataset 
 python -m MedShapeNetCore download DATASET # download a dataset (replace DATASETA with the one you want to download e.g.,  ASOCA)
 python -m MedShapeNetCore download all # download all datasets at once
 python -m MedShapeNetCore check_available_keys DATASET # check the available keys of the DATASET

python -m MedShapeNetCore download all

how to import module functions in python:

 from MedShapeNetCore.MedShapeNetCore import MyDict,MSNLoader,MSNVisualizer,MSNSaver,MSNTransformer,__version__

For more commands and detailed usage, please refer to the colab notebook.

Use MedShapeNetCore in Machine Learning Workflows (Minimal Reproducible Example)

• 3D Shape Classification with MONAI
• 3D Shape Classification with Tensorflow

Reference

    @article{li2023medshapenet,
         title={MedShapeNet--A Large-Scale Dataset of 3D Medical Shapes for Computer Vision},
         author={Li, Jianning and Pepe, Antonio and Gsaxner, Christina and Luijten, Gijs and Jin, Yuan and Ambigapathy, Narmada and Nasca, Enrico and Solak, Naida and Melito, Gian Marco and Memon, Afaque R and others},
         journal={arXiv preprint arXiv:2308.16139},
         year={2023}}