MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classification

Abstract

We introduce MedMNIST v2, a large-scale MNIST-like dataset collection of standardized biomedical images, including 12 datasets for 2D and 6 datasets for 3D. All images are pre-processed into a small size of 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 dataset 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/.

The data and code are publicly available at https://medmnist.com/. arXiv admin note: text overlap with arXiv:2010.14925

References in corpus (5)

• Array Programming with NumPy
• MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classification
• Skin Lesion Analysis Toward Melanoma Detection 2018: A Challenge Hosted by the International Skin Imaging Collaboration (ISIC)
• A large annotated medical image dataset for the development and evaluation of segmentation algorithms
• A Principled Approach to Failure Analysis and Model Repairment: Demonstration in Medical Imaging

Cited by in corpus (56)

• MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classification
• BiomedGPT: A Generalist Vision-Language Foundation Model for Diverse Biomedical Tasks
• Recent Progress in Transformer-based Medical Image Analysis
• Quantum Vision Transformers
• Trustworthy Privacy-preserving Hierarchical Ensemble and Federated Learning in Healthcare 4.0 with Blockchain
• Enhancing Skin Disease Classification Leveraging Transformer-based Deep Learning Architectures and Explainable AI
• Self-Supervised Pre-Training with Contrastive and Masked Autoencoder Methods for Dealing with Small Datasets in Deep Learning for Medical Imaging
• Federated Learning Survey: A Multi-Level Taxonomy of Aggregation Techniques, Experimental Insights, and Future Frontiers
• The Impact of ChatGPT and LLMs on Medical Imaging Stakeholders: Perspectives and Use Cases
• MedShapeNet -- A Large-Scale Dataset of 3D Medical Shapes for Computer Vision
• Medical Image Classification with KAN-Integrated Transformers and Dilated Neighborhood Attention
• Privacy-preserving machine learning for healthcare: open challenges and future perspectives
• Evaluating Pre-trained Convolutional Neural Networks and Foundation Models as Feature Extractors for Content-based Medical Image Retrieval
• Improving Representation of High-frequency Components for Medical Visual Foundation Models
• Investigating the Quality of DermaMNIST and Fitzpatrick17k Dermatological Image Datasets
• Audit to Forget: A Unified Method to Revoke Patients' Private Data in Intelligent Healthcare
• Fusion: Efficient and Secure Inference Resilient to Malicious Servers
• Personalized Graph Federated Learning with Differential Privacy
• Counterfactual Explanations for Medical Image Classification and Regression using Diffusion Autoencoder
• Towards Trustworthy Dataset Distillation
• When Federated Learning Meets Quantum Computing: Survey and Research Opportunities
• Rethinking model prototyping through the MedMNIST+ dataset collection
• Digital-analog quantum convolutional neural networks for image classification
• Hybrid Quantum Machine Learning Assisted Classification of COVID-19 from Computed Tomography Scans
• mAIstro: an open-source multi-agentic system for automated end-to-end development of radiomics and deep learning models for medical imaging
• EvalAttAI: A Holistic Approach to Evaluating Attribution Maps in Robust and Non-Robust Models
• A comprehensive and easy-to-use multi-domain multi-task medical imaging meta-dataset
• Split Learning for Distributed Collaborative Training of Deep Learning Models in Health Informatics
• RadCLIP: Enhancing Radiologic Image Analysis through Contrastive Language-Image Pre-training
• Sparse Bayesian Networks: Efficient Uncertainty Quantification in Medical Image Analysis
• Less is More: Selective Reduction of CT Data for Self-Supervised Pre-Training of Deep Learning Models with Contrastive Learning Improves Downstream Classification Performance
• Universal adversarial perturbations for multiple classification tasks with quantum classifiers
• Quantum Adjoint Convolutional Layers for Effective Data Representation
• Coherence Awareness in Diffractive Neural Networks
• Do Sharpness-based Optimizers Improve Generalization in Medical Image Analysis?
• Evolution-aware VAriance (EVA) Coreset Selection for Medical Image Classification
• Passive All-Optical Nonlinear Neuron Activation via PPLN Nanophotonic Waveguides
• A Reconfigurable Stream-Based FPGA Accelerator for Bayesian Confidence Propagation Neural Networks
• Distance Matters For Improving Performance Estimation Under Covariate Shift
• Stochastic Entanglement Configuration for Constructive Entanglement Topologies in Quantum Machine Learning with Application to Cardiac MRI
• TraceFL: Interpretability-Driven Debugging in Federated Learning via Neuron Provenance
• Beyond a Single Mode: GAN Ensembles for Diverse Medical Data Generation
• MedLeak: Multimodal Medical Data Leakage in Secure Federated Learning with Crafted Models
• $\text{sentropy}$: A Python Package for Revealing Hidden Differences in Complex Datasets
• PET-TURTLE: Deep Unsupervised Support Vector Machines for Imbalanced Data Clusters
• Building Continuous Quantum-Classical Bayesian Neural Networks for a Classical Clinical Dataset
• ILPO-NET: Network for the invariant recognition of arbitrary volumetric patterns in 3D
• The Need for Benchmarks to Advance AI-Enabled Player Risk Detection in Gambling
• Towards Continuous-variable Quantum Neural Networks for Biomedical Imaging
• MedSymmFlow: Bridging Generative Modeling and Classification in Medical Imaging through Symmetrical Flow Matching
• Quantum Encoding of Structured Data with Matrix Product States
• Uncertainty-driven training for three-dimensional calibrated lung nodule classification
• DuoGNN: Topology-aware Graph Neural Network with Homophily and Heterophily Interaction-Decoupling
• DAWN-FM: Data-Aware and Noise-Informed Flow Matching for Solving Inverse Problems
• Unmasking Biases and Reliability Concerns in Convolutional Neural Networks Analysis of Cancer Pathology Images
• Explanatory Model Monitoring to Understand the Effects of Feature Shifts on Performance