# OpenGVLab/SAM-Med2D

Official implementation of SAM-Med2D

Repository: https://github.com/OpenGVLab/SAM-Med2D
Canonical: https://ross.abutalabs.com/products/sam-med2d
Language: Jupyter Notebook
License: Apache-2.0
License Family: permissive
Last push: 2024-06-18T13:23:31+00:00

## Health v2 (maintenance only)
Score: 28/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 78
- inputs: {"age_days": 1103, "days_push": 806, "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 1134, forks 110 (observed 2026-08-28T04:03:43.135501+00:00)

## What it is
Official implementation of SAM-Med2D, a fine-tuned Segment Anything Model (SAM) for 2D medical image segmentation, trained on the SA-Med2D-20M dataset (4.6M images, 19.7M masks). Includes training, testing, and inference code plus pretrained weights.

## Use cases
- segment medical images like CT and MRI scans
- fine-tune SAM on medical imaging data
- run promptable segmentation with point, bbox, or mask prompts on medical images
- evaluate a medical image segmentation model on large-scale datasets
- download a large medical segmentation dataset

## When to choose
- you need promptable segmentation adapted to 2D medical images
- you want the largest curated medical segmentation dataset for training or benchmarking
- you want pretrained weights and train/test code for medical SAM fine-tuning

## When to avoid
- you need 3D medical image segmentation (use SAM-Med3D instead)
- you need general-purpose natural image segmentation (original SAM suffices)
- you need a production-ready clinical application rather than research code

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, image-processing, computer-vision
- domain: healthcare, deep-learning
- platform: python
- tags: segment-anything, medical-imaging, segmentation, fine-tuning, promptable-segmentation, gpu

## Member repositories
- OpenGVLab/SAM-Med2D (main) score 28

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:43.135501+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 2026-08-30T06:36:52.824991+00:00, confidence not recorded.
  - readme: https://github.com/OpenGVLab/SAM-Med2D (fetched 2026-08-28T04:03:43.135501+00:00, sha a9862fa57f8b)
- Data as of 2026-08-30T08:39:29.467469+00:00.