MedMNIST

Visit Tool

MedMNIST offers 18 standardized datasets for 2D and 3D biomedical image classification, available in multiple sizes. It supports the development and evaluation of AI models for medical imaging research and education.

Claim this tool

1View

At a glance

Pricing

Open Source

Free tier

Yes

API

Yes

Skill level

Technical

About

What is MedMNIST?

MedMNIST is a comprehensive collection of 18 standardized biomedical image datasets, designed for 2D and 3D classification tasks. It includes 12 datasets for 2D images and 6 for 3D images, with various size options such as MNIST-like 28x28, and larger 64x64, 128x128, and 224x224 for 2D, plus 64x64x64 for 3D. These datasets cover diverse data modalities, scales (from 100 to 100,000 samples), and tasks (binary/multi-class, ordinal regression, multi-label). MedMNIST aims to simplify biomedical image analysis for researchers by providing pre-processed data and standardized train-validation-test splits, making it user-friendly for machine learning algorithm development and comparison. It is particularly useful for educational purposes due to its accessibility and lack of prerequisite background knowledge.

Best used for

Ideal for professors and researchers who need to benchmark and develop AI models for 2D and 3D biomedical image classification, and for educational purposes in biomedical image analysis. Especially valuable for standardizing research and facilitating comparisons of machine learning algorithms across diverse medical imaging tasks.

Common actions

classify biomedical images

benchmark AI models

develop machine learning algorithms

standardize medical datasets

"AI Agents"face swappingautomated workflowgithub copilotworkflowslow-code/no-codedeepfakeopen-sourcecollaboration

Capabilities

Key features

18 standardized biomedical datasets
2D and 3D image classification
Multiple image size options
Diverse data modalities
PyTorch integration
Command-line tools

Target Audience

professor

Integrations

Not yet documented

Pricing & Plans

Open Source

Free

FAQs

What types of biomedical images are included in MedMNIST?

MedMNIST includes a diverse collection of 2D and 3D biomedical images covering various data modalities. These datasets are designed for classification tasks and range in scale from hundreds to hundreds of thousands of samples, supporting binary, multi-class, ordinal regression, and multi-label classifications.

Can MedMNIST datasets be used without PyTorch?

Yes, while MedMNIST is designed to work seamlessly with PyTorch, the underlying data files are standard NumPy serialization files (.npz). This means they can be parsed and used with other programming languages or frameworks, even without PyTorch or Python, by accessing the raw data.

What are the different image size options available in MedMNIST?

MedMNIST offers multiple image size options to cater to various research needs. These include MNIST-like 28x28 for 2D images, and larger sizes such as 64x64, 128x128, and 224x224 for 2D, as well as 64x64x64 for 3D images. These options support both lightweight and foundation model development.

Trending

Subcategories trending in Wellness & Lifestyle

Health & Fitness Gaming & Entertainment Mental Wellness Self-Improvement Medical & Symptom Checking Home & Real Estate

Trending

Also listed in

This tool also appears in

Research & Education › Academic Research Data & Analytics › Data Cleaning & Prep

Explore

Browse AI tools by category

Content & Design Productivity & Business Coding & Development AI Agents & Automation Research & Education Wellness & Lifestyle Career Development Marketing & Growth Data & Analytics Customer Support & CX Finance E-commerce