ImprintLab/Medical-SAM-Adapter

Health v2 · maintenance only

Adoption not part of the score

1322 stars · 127 forks observed · 2026-08-28

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

Medical SAM Adapter (MSA) is a Python framework that fine-tunes Meta's Segment Anything Model for medical image segmentation using lightweight adapter modules. It supports multiple SAM variants (SAM, MobileSAM, EfficientSAM) and LoRA-based adaptation, with pre-trained adapters available in a model zoo.

Use cases

• segment medical images like fundus or CT scans with SAM
• fine-tune Segment Anything Model on medical imaging datasets
• adapt SAM to a new domain without full model retraining
• use pre-trained medical segmentation adapters without training
• compare SAM, MobileSAM, and EfficientSAM for medical segmentation
• train a lightweight LoRA adapter on top of SAM

When to choose

• you need parameter-efficient fine-tuning of SAM for medical images
• you want pre-trained medical segmentation adapters instead of training from scratch
• you need a lightweight alternative to full SAM fine-tuning

When to avoid

• you need general-purpose (non-medical) image segmentation
• you want a production-ready clinical application rather than a research framework
• you need segmentation models unrelated to the SAM architecture

Facets

library · maturity active

machine-learning deep-learning image-processing computer-vision llm-training deep-learning computer-vision healthcare machine-learning python segment-anything adapter-tuning medical-image-segmentation parameter-efficient-fine-tuning lora pytorch research-code medical-imaging gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="ImprintLab/Medical-SAM-Adapter")