MedMNIST Classification Decathlon: A Lightweight AutoML Benchmark for Medical Image Analysis

Abstract

We present MedMNIST, a collection of 10 pre-processed medical open datasets. MedMNIST is standardized to perform classification tasks on lightweight 28x28 images, which requires no background knowledge. Covering the primary data modalities in medical image analysis, it is diverse on data scale (from 100 to 100,000) and tasks (binary/multi-class, ordinal regression and multi-label). MedMNIST could be used for educational purpose, rapid prototyping, multi-modal machine learning or AutoML in medical image analysis. Moreover, MedMNIST Classification Decathlon is designed to benchmark AutoML algorithms on all 10 datasets; We have compared several baseline methods, including open-source or commercial AutoML tools. The datasets, evaluation code and baseline methods for MedMNIST are publicly available at https://medmnist.github.io/.

ISBI 2021. Code and dataset are available at https://medmnist.github.io/

References in corpus (2)

• 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

Cited by in corpus (28)

• MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classification
• Blockchain-based Federated Learning with SMPC Model Verification Against Poisoning Attack for Healthcare Systems
• Quantum Methods for Neural Networks and Application to Medical Image Classification
• Quantum Vision Transformers
• Trustworthy Privacy-preserving Hierarchical Ensemble and Federated Learning in Healthcare 4.0 with Blockchain
• ROCOv2: Radiology Objects in COntext Version 2, an Updated Multimodal Image Dataset
• Image quality assessment for machine learning tasks using meta-reinforcement learning
• Federated Learning Survey: A Multi-Level Taxonomy of Aggregation Techniques, Experimental Insights, and Future Frontiers
• Medical image classification via quantum neural networks
• Collaborative Training of Medical Artificial Intelligence Models with non-uniform Labels
• RibSeg Dataset and Strong Point Cloud Baselines for Rib Segmentation from CT Scans
• Asymmetric 3D Context Fusion for Universal Lesion Detection
• Uncertainty Minimization for Personalized Federated Semi-Supervised Learning
• Investigating the Quality of DermaMNIST and Fitzpatrick17k Dermatological Image Datasets
• FQPDR: Federated Quantum Neural Network for Privacy-preserving Early Detection of Diabetic Retinopathy
• 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
• Universal adversarial perturbations for multiple classification tasks with quantum classifiers
• Topological Information Retrieval with Dilation-Invariant Bottleneck Comparative Measures
• Evolution-aware VAriance (EVA) Coreset Selection for Medical Image Classification
• A Reconfigurable Stream-Based FPGA Accelerator for Bayesian Confidence Propagation Neural Networks
• TraceFL: Interpretability-Driven Debugging in Federated Learning via Neuron Provenance
• A Principled Approach to Failure Analysis and Model Repairment: Demonstration in Medical Imaging
• Distribution-Free Federated Learning with Conformal Predictions
• Navigating Explanatory Multiverse Through Counterfactual Path Geometry
• Insights into Data through Model Behaviour: An Explainability-driven Strategy for Data Auditing for Responsible Computer Vision Applications
• Deep Active Re-Labeling: Toward Noise-Resilient Annotation Efficiency
• Cascade Decoders-Based Autoencoders for Image Reconstruction