MedMNIST
Project (Website) | Dataset (Zenodo) | Paper (arXiv) | MedMNIST v1 (ISBI'21)
Jiancheng Yang, Rui Shi, Donglai Wei, Zequan Liu, Lin Zhao, Bilian Ke, Hanspeter Pfister, Bingbing Ni
We introduce MedMNIST v2, a large-scale MNIST-like collection of standardized biomedical images, including 12 datasets for 2D and 6 datasets for 3D. All images are pre-processed into 28x28 (2D) or 28x28x28 (3D) with the corresponding classification labels, so that no background knowledge is required for users. Covering primary data modalities in biomedical images, MedMNIST v2 is designed to perform classification on lightweight 2D and 3D images with various data scales (from 100 to 100,000) and diverse tasks (binary/multi-class, ordinal regression and multi-label). The resulting dataset, consisting of 708,069 2D images and 10,214 3D images in total, could support numerous research / educational purposes in biomedical image analysis, computer vision and machine learning. We benchmark several baseline methods on MedMNIST v2, including 2D / 3D neural networks and open-source / commercial AutoML tools.
For more details, please refer to our paper:
MedMNIST v2: A Large-Scale Lightweight Benchmark for 2D and 3D Biomedical Image Classification (arXiv)
Key Features
- Diverse: It covers diverse data modalities, dataset scales (from 100 to 100,000), and tasks (binary/multi-class, multi-label, and ordinal regression). It is as diverse as the VDD and MSD to fairly evaluate the generalizable performance of machine learning algorithms in different settings, but both 2D and 3D biomedical images are provided.
- Standardized: Each sub-dataset is pre-processed into the same format, which requires no background knowledge for users. As an MNIST-like dataset collection to perform classification tasks on small images, it primarily focuses on the machine learning part rather than the end-to-end system. Furthermore, we provide standard train-validation-test splits for all datasets in MedMNIST v2, therefore algorithms could be easily compared.
- Lightweight: The small size of 28×28 (2D) or 28×28×28 (3D) is friendly to evaluate machine learning algorithms.
- Educational: As an interdisciplinary research area, biomedical image analysis is difficult to hand on for researchers from other communities, as it requires background knowledge from computer vision, machine learning, biomedical imaging, and clinical science. Our data with Creative Commons (CC) Licenses is easy to use for educational purposes.
Please note that this dataset is NOT intended for clinical use.
Code Structure
medmnist/:dataset.py: PyTorch datasets and dataloaders of MedMNIST.evaluator.py: Standardized evaluation functions.info.py: Dataset informationdictfor each subset of MedMNIST.
examples/:getting_started.ipynb: To explore the MedMNIST dataset with jupyter notebook. It is ONLY intended for a quick exploration, i.e., it does not provide full training and evaluation functionalities.getting_started_without_PyTorch.ipynb: This notebook provides snippets about how to use MedMNIST data (the.npzfiles) without PyTorch.
setup.py: To installmedmnistas a module.- [EXTERNAL]
MedMNIST/experiments: training and evaluation scripts to reproduce both 2D and 3D experiments in our paper, including PyTorch, auto-sklearn, AutoKeras and Google AutoML Vision together with their weights ;)
Installation and Requirements
Setup the required environments and install medmnist as a standard Python package:
pip install --upgrade git+https://github.com/MedMNIST/MedMNIST.git
Check whether you have installed the latest version:
>>> import medmnist
>>> print(medmnist.__version__)
The code requires only common Python environments for machine learning. Basically, it was tested with
- Python 3 (Anaconda 3.6.3 specifically)
- PyTorch==1.3.1
- numpy==1.18.5, pandas==0.25.3, scikit-learn==0.22.2, Pillow==8.0.1, fire
Higher (or lower) versions should also work (perhaps with minor modifications).
If you use PyTorch
-
Great! Our code is designed to work with PyTorch.
-
Explore the MedMNIST dataset with jupyter notebook (
getting_started.ipynb), and train basic neural networks in PyTorch.
If you do not use PyTorch
- Although our code is tested with PyTorch, you are free to parse them with your own code (without PyTorch or even without Python!), as they are only standard NumPy serialization files. It is simple to create a dataset without PyTorch.
- Go to
getting_started_without_PyTorch.ipynb, which provides snippets about how to use MedMNIST data (the.npzfiles) without PyTorch. - Simply change the super class of
MedMNISTfromtorch.utils.data.Datasettocollections.Sequence, you will get a standard dataset without PyTorch. Checkdataset_without_pytorch.pyfor more details. - You still have most functionality of our MedMNIST code ;)
Dataset
Please download the dataset(s) via Zenodo. You could also use our code to download automatically by setting download=True in dataset.py.
The MedMNIST dataset contains several subsets. Each subset (e.g., pathmnist.npz) is comprised of 6 keys: train_images, train_labels, val_images, val_labels, test_images and test_labels.
train_images/val_images/test_images:N× 28 × 28 for 2D gray-scale datasets,N× 28 × 28 × 3 for 2D RGB datasets,N× 28 × 28 × 28 for 3D datasets.Ndenotes the number of samples.train_labels/val_labels/test_labels:NxL.Ndenotes the number of samples.Ldenotes the number of task labels; for single-label (binary/multi-class) classification,L=1, and{0,1,2,3,..,C}denotes the category labels (C=1for binary); for multi-label classificationL!=1, e.g.,L=14forchestmnist.npz.
Command Line Tools
-
List all available datasets:
python -m medmnist available -
Download all available datasets:
python -m medmnist download -
Delete all downloaded npz from root:
python -m medmnist clean -
Print the dataset details given a subset flag:
python -m medmnist info --flag=xxxmnist -
Save the dataset as standard figure and csv files, which could be used for AutoML tools, e.g., Google AutoML Vision:
python -m medmnist save --flag=xxxmnist --folder=tmp/ -
Parse and evaluate a standard result file, refer to
Evaluator.parse_and_evaluatefor details.python -m medmnist evaluate --path=folder/{flag}_{split}@{run}.csv
Citation
If you find this project useful, please cite both v1 and v2 paper as:
Jiancheng Yang, Rui Shi, Donglai Wei, Zequan Liu, Lin Zhao, Bilian Ke, Hanspeter Pfister, Bingbing Ni. "MedMNIST v2: A Large-Scale Lightweight Benchmark for 2D and 3D Biomedical Image Classification". arXiv preprint arXiv:2110.14795, 2021.
Jiancheng Yang, Rui Shi, Bingbing Ni. "MedMNIST Classification Decathlon: A Lightweight AutoML Benchmark for Medical Image Analysis". IEEE 18th International Symposium on Biomedical Imaging (ISBI), 2021.
or using the bibtex:
@article{medmnistv2,
title={MedMNIST v2: A Large-Scale Lightweight Benchmark for 2D and 3D Biomedical Image Classification},
author={Yang, Jiancheng and Shi, Rui and Wei, Donglai and Liu, Zequan and Zhao, Lin and Ke, Bilian and Pfister, Hanspeter and Ni, Bingbing},
journal={arXiv preprint arXiv:2110.14795},
year={2021}
}
@inproceedings{medmnistv1,
title={MedMNIST Classification Decathlon: A Lightweight AutoML Benchmark for Medical Image Analysis},
author={Yang, Jiancheng and Shi, Rui and Ni, Bingbing},
booktitle={IEEE 18th International Symposium on Biomedical Imaging (ISBI)},
pages={191--195},
year={2021}
}
Please also cite the corresponding paper of source data if you use any subset of MedMNIST as per the project page.
LICENSE
The code is under Apache-2.0 License.
The datasets are under Creative Commons (CC) Licenses in general. Each subset keeps the same license as that of the source dataset.
126 Dec 3, 2022
209 Dec 29, 2022
48 Dec 30, 2022
290 Dec 29, 2022
1 Jan 6, 2022
71 Dec 30, 2022
53 Jul 4, 2022
0 Jan 23, 2022
308 Jan 5, 2023
97 Jan 5, 2023
1 Dec 29, 2021
188 Dec 17, 2022
8 Oct 29, 2022
373 Jan 2, 2023
54 Nov 25, 2022
223 Dec 27, 2022
103 Nov 25, 2022
168 Dec 29, 2022
129 Jan 4, 2023