# HiLab-git/SSL4MIS

Semi Supervised Learning for Medical Image Segmentation, a collection of literature reviews and code implementations.

Repository: https://github.com/HiLab-git/SSL4MIS
Canonical: https://ross.abutalabs.com/products/ssl4mis
Language: Python
License: MIT
License Family: permissive
Topics: semi-supervised-learning
Last push: 2025-06-07T04:37:09+00:00

## Health v2 (maintenance only)
Score: 44/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 25, release rhythm 35, longevity 100
- inputs: {"age_days": 2168, "days_push": 452, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2676, forks 424 (observed 2026-08-28T04:07:09.758584+00:00)

## What it is
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
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, image-processing, benchmarking
- domain: deep-learning, computer-vision, healthcare, machine-learning
- platform: python
- tags: semi-supervised-learning, medical-imaging, image-segmentation, research-code, pytorch, linux, gpu

## Member repositories
- HiLab-git/SSL4MIS (main) score 44

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:09.758584+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:18:01.468695+00:00, confidence not recorded.
  - readme: https://github.com/HiLab-git/SSL4MIS (fetched 2026-08-28T04:07:09.758584+00:00, sha 7041e4ef09c5)
- Data as of 2026-08-30T08:39:29.467469+00:00.