MedMNIST v2: A Large-Scale Lightweight Benchmark for 2D and 3D Biomedical Image Classification
Open accessAbstract
Note: We recommend to download from Zenodo official link, which is integrated with our code. However, if you find download problem, you can also use this mirror link from Google Drive. Abstract 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. The data and code are publicly available at https://medmnist.com/. Note: This dataset is NOT intended for clinical use. We recommend our official code to download, parse and use the MedMNIST dataset: pip install medmnist 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 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(s) of source data if you use any subset of MedMNIST as per the description on the project website. License The dataset is licensed under Creative Commons Attribution 4.0 International (CC BY 4.0). The code is under Apache-2.0 License.
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The data files of MedMNIST v2 can be accessed at Zenodo, containing 12 pre-processed 2D datasets and 6 pre-processed 3D datasets.
“The data files of MedMNIST v2 dataset can be accessed at Zenodo38. It contains 12 pre-processed 2D datasets (MedMNIST2D) and 6 pre-processed 3D datasets (MedMNIST3D).”
From MedMNIST v2 - A large-scale lightweight benchmark for 2D and 3D biomedical image classification (2023) · cites this paper as [38]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Cites
Still being checked.
Cited by
Sorted by citations
MedMNIST v2 - A large-scale lightweight benchmark for 2D and 3D biomedical image classification
Yang, J., Shi, R., Wei, D., Liu, Z., Zhao, L., Ke, B., Pfister, H., & Ni, B. (2023) · Scientific Data · doi:10.1038/s41597-022-01721-8 · Cited by 1,043 · see citing works
Self-citationTariq, A., Serhani, M. A., Sallabi, F., Barka, E. S., Qayyum, T., Khater, H. M., & Shuaib, K. (2024) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2024.3438264 · Cited by 110 · see citing works
Abdar, M., Fahami, M. A., Rundo, L., Radeva, P. I., Frangi, A. F., Acharya, U. R., Khosravi, A., Lam, H., Jung, A., & Nahavandi, S. (2022) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2022.3168887 · Cited by 69 · see citing works
Quantum-classical convolutional neural networks in radiological image classification
Matic, A., Monnet, M., Lorenz, J. M., Schachtner, B. M., & Messerer, T. (2022) · IEEE International Conference on Quantum Computing and Engineering (QCE) · doi:10.1109/qce53715.2022.00024 · Cited by 70 · see citing works
Zhang, X., Xiao, Z., Wu, X., Chen, Y., Zhao, J., Hu, Y., & Liu, J. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2024.3399164 · Cited by 43 · see citing works
Auditable and Verifiable Federated Learning Based on Blockchain-Enabled Decentralization
Kalapaaking, A. P., Khalil, I., Yi, X., Lam, K., Huang, G.-B., & Wang, N. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2024.3407670 · Cited by 41 · see citing works
DSFL: A Decentralized SplitFed Learning Approach for Healthcare Consumers in the Metaverse
Stephanie, V., Khalil, I., & Atiquzzaman, M. (2024) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2024.3360994 · Cited by 25 · see citing works
Re-Thinking Federated Active Learning Based on Inter-Class Diversity
Kim, S., Bae, S., Song, H., & Yun, S.-Y. (2023) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52729.2023.00384 · Cited by 25 · see citing works
FedOSS: Federated Open Set Recognition via Inter-Client Discrepancy and Collaboration
Zhu, M., Liao, J., Liu, J., & Yuan, Y. (2023) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2023.3294014 · Cited by 23 · see citing works
Experimenting With Normalization Layers in Federated Learning on Non-IID Scenarios
Casella, B., Esposito, R., Sciarappa, A., Cavazzoni, C., & Aldinucci, M. (2024) · IEEE Access · doi:10.1109/access.2024.3383783 · Cited by 22 · see citing works
Continual learning in medical image analysis: A survey
Wu, X., Xu, Z., & Tong, R. K. (2024) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2024.109206 · Cited by 22 · see citing works
CareFL: C ontribution Guided Byz a ntine- R obust F e derated Learning
Dong, Q., Yang, S., Dai, Z., Gao, Y., Wang, S., Cao, Y., Fu, A., & Susilo, W. (2024) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2024.3477912 · Cited by 19 · see citing works
A Self-Adaptive Discriminative Autoencoder for Medical Applications
Ge, X., Qu, Y., Shang, C., Yang, L., & Shen, Q. (2022) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2022.3195727 · Cited by 17 · see citing works
Yu, C., Shen, S., Wang, S., Zhang, K., & Hai, Z. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2024.3383748 · Cited by 17 · see citing works
Confidence Calibration of a Medical Imaging Classification System That is Robust to Label Noise
Penso, C., Frenkel, L., & Goldberger, J. (2024) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2024.3353762 · Cited by 23 · see citing works
Personalized Graph Federated Learning With Differential Privacy
Gauthier, F., Gogineni, V. C., Werner, S., Huang, Y.-F., & Kuh, A. (2023) · IEEE Transactions on Signal and Information Processing over Networks · doi:10.1109/tsipn.2023.3325963 · Cited by 15 · see citing works
A Hybrid of Generative and Discriminative Models Based on the Gaussian-Coupled Softmax Layer
Hayashi, H. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2024.3358113 · Cited by 14 · see citing works
Quantum Fourier networks for solving parametric PDEs
Jain, N., Landman, J., Mathur, N., & Kerenidis, I. (2024) · Quantum Science and Technology · doi:10.1088/2058-9565/ad42ce · Cited by 14 · see citing works
Rethinking model prototyping through the MedMNIST+ dataset collection
Doerrich, S., Salvo, F. D., Brockmann, J., & Ledig, C. (2025) · Scientific Reports · doi:10.1038/s41598-025-92156-9 · Cited by 19 · see citing works
Reprogrammable-FL: Improving Utility-Privacy Tradeoff in Federated Learning via Model Reprogramming
Arif, H., Gittens, A., & Chen, P. (2023) · IEEE Conference on Secure and Trustworthy Machine Learning (SaTML) · doi:10.1109/satml54575.2023.00022 · Cited by 8 · see citing works
FLAN: feature-wise latent additive neural models for biological applications
Nguyen, A.-P., Vasilaki, S., & Martínez, M. R. (2023) · Briefings in Bioinformatics · doi:10.1093/bib/bbad056 · Cited by 6 · see citing works
Expert with Outlier Exposure for Continual Learning of New Diseases
Xu, Z., Chen, K., Zheng, W., Tan, Z., Yang, X., & Wang, R. (2022) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm55620.2022.9995352 · Cited by 5 · see citing works
Hierarchical Federated Learning for Edge Intelligence through Average Consensus
Menegatti, D., Manfredi, S., Pietrabissa, A., Poli, C., & Giuseppi, A. (2023) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2023.10.1673 · Cited by 4 · see citing works
Continual Learning of Medical Image Classification Based on Feature Replay
Li, X., Li, H., & Ma, L. (2022) · International Conference on Signal Processing · doi:10.1109/icsp56322.2022.9965230 · Cited by 4 · see citing works
Classification of rotation-invariant biomedical images using equivariant neural networks
Bernander, K. B., Sintorn, I., Strand, R., & Nyström, I. (2024) · Scientific Reports · doi:10.1038/s41598-024-65597-x · Cited by 2 · see citing works
Sorgente, V., Biagiucci, D., Cesarelli, M., Brunese, L., Santone, A., Martinelli, F., & Mercaldo, F. (2025) · Journal of Imaging · doi:10.3390/jimaging11070214 · Cited by 1 · see citing works
Proposal Medical Image Protection System Based on Hybrid CNN-Transformer Model and Chaotic Maps
Ali, R. S., Hasoun, R. K., Al-Adhami, A. H., Jabber, S. A., & Hashem, S. H. (2025) · IEEE Access · doi:10.1109/access.2025.3586562 · Cited by 1 · see citing works
Liu, L., Su, X., Wang, X., & Gao, G. (2025) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2025.108308 · Cited by 1 · see citing works
Jabeur, N. H., & Abdelli, A. (2023) · International Conference on Electrical, Computer, Communications and Mechatronics Engineering (ICECCME) · doi:10.1109/iceccme57830.2023.10253217
Ugwumba, N. K. (2025) · Research Square · doi:10.21203/rs.3.rs-8182728/v1
- Authors
- Yang, J., Shi, R., Wei, D., Liu, Z., Zhao, L., Ke, B., Pfister, H., & Ni, B.
- Affiliations
- Shanghai Jiao Tong University (CN)
- Boston College (US)
- RWTH Aachen University (DE)
- Fudan University (CN)
- Harvard University (US)
- Venue
- Zenodo
- Publisher
- Zenodo
- Published
- 2021-08-16
- OpenAlex
- W4393559311
- Cited by
- 30
- References
- 0
- Citations by year
- 2025: 5 · 2024: 12 · 2023: 8 · 2022: 5
- Type
- dataset
- Language
- en
- Open access
- green
- zenodo.org
- Licence
- Locations
- Zenodo (CERN European Organization for Nuclear Research) (submittedVersion, cc-by)
- Zenodo (CERN European Organization for Nuclear Research) (cc-by)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Medical Image Segmentation Techniques
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Artificial Intelligence › AI in cancer detection
- Keywords
- MedMNIST, medical image classification, 3D medical images, medical foundation models, ordinal regression, multi-label classification, PathMNIST, medical image registration, medical image synthesis, medical image denoising, medical image enhancement
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
