# Xiaoqi-Zhao-DLUT/MSNet-M2SNet

(MIR 2026 [M2SNet] & MICCAI 2022 GOALS Challenge & MICCAI 2021 [MSNet]) Multi-scale in Multi-scale Subtraction Network for Medical Image Segmentation

Repository: https://github.com/Xiaoqi-Zhao-DLUT/MSNet-M2SNet
Canonical: https://ross.abutalabs.com/products/msnet-m2snet
Language: Python
License Family: other
Last push: 2026-07-20T08:26:43+00:00

## Health v2 (maintenance only)
Score: 74/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 93, release rhythm 35, longevity 100
- inputs: {"age_days": 1904, "days_push": 44, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1042, forks 89 (observed 2026-08-28T04:03:20.795283+00:00)

## What it is
Official PyTorch implementations of MSNet and M2SNet, multi-scale subtraction networks for medical image segmentation such as polyp, lung infection, and breast ultrasound segmentation. Includes pretrained models and links to training/testing datasets.

## Use cases
- segment polyps in endoscopy images
- segment medical images with a multi-scale network
- reproduce MICCAI polyp segmentation results
- segment COVID-19 lung infection CT images
- segment breast ultrasound images
- apply pretrained medical segmentation models

## When to choose
- you need proven medical image segmentation models with pretrained weights
- you work on polyp or ultrasound segmentation research
- you want a strong baseline for multi-scale segmentation

## When to avoid
- you need a production-ready clinical application
- you need a license permitting commercial use (none is provided)
- you need segmentation outside medical imaging domains

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, image-processing, computer-vision
- domain: healthcare, deep-learning, computer-vision, image-processing
- platform: python
- tags: medical-image-segmentation, polyp-segmentation, pytorch, research-code, miccai, gpu

## Member repositories
- Xiaoqi-Zhao-DLUT/MSNet-M2SNet (main) score 74

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:20.795283+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 2026-08-30T07:02:34.271600+00:00, confidence not recorded.
  - readme: https://github.com/Xiaoqi-Zhao-DLUT/MSNet-M2SNet (fetched 2026-08-28T04:03:20.795283+00:00, sha 52d6b30b519c)
- Data as of 2026-08-30T08:39:29.467469+00:00.