HiLab-git/SSL4MIS

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

2676 stars · 424 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

A benchmark and code collection of semi-supervised learning methods for medical image segmentation, re-implementing approaches like Mean Teacher, Cross Pseudo Supervision, and FixMatch. It includes literature reviews and supports multiple 2D/3D backbone networks such as UNet, nnUNet, and Swin-UNet.

Use cases

• train semi-supervised segmentation models on medical images
• benchmark SSL methods for medical image segmentation
• compare semi-supervised learning algorithms fairly
• segment CT or MRI scans with limited labeled data
• reproduce research papers on semi-supervised segmentation
• find a starting codebase for medical image segmentation research

When to choose

• you need a fair benchmark of many SSL segmentation methods in one codebase
• you have limited labeled medical images and want to leverage unlabeled data
• you want reference implementations of papers like Mean Teacher or Cross Pseudo Supervision

When to avoid

• you need a production-ready clinical segmentation tool rather than research code
• your task is not image segmentation
• you need a polished GUI or turnkey pipeline with minimal configuration

Facets

library · maturity active

machine-learning deep-learning image-processing benchmarking deep-learning computer-vision healthcare machine-learning python semi-supervised-learning medical-imaging image-segmentation research-code pytorch linux gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="HiLab-git/SSL4MIS")