Medical SAM3: A Foundation Model for Universal Prompt-Driven Medical Image Segmentation
tom_doerr · x · 2026-08-15
AIM-Research-Lab has released Medical SAM3, a foundation model designed for universal prompt-driven medical image segmentation across diverse visual modalities.
Key Features:
- Supports segmentation across various medical imaging modalities.
- Provides a toolkit for inference and evaluation on 2D medical benchmarks (e.g., CHASEDB1, STARE, CVC-ClinicDB), supporting box and text prompts.
- Includes code for fine-tuning on 3D annotations and running held-out 3D evaluations.
- Pretrained weights are available on Hugging Face, and the paper is published on arXiv.
More from Research
- Maglev: Sliding Recurrent Memory improves long-context efficiency — UTEXAS · 2026-08-15
- AI-assisted research trends spark a surge in NeurIPS submissions and quality advances — PTenigma · 2026-08-15
- Malliavin Calculus Aids AI Privacy and Biomedical Discovery Prediction — PTenigma · 2026-08-15
- Qwen 3.8-27B demoed to surpass previous SOTA in cybersecurity malware analysis — Potential_Block4598 · 2026-08-15
- INSIDE Framework Accepted to COLM 2026: Modeling Student Reasoning — alexisjross · 2026-08-15
- dots3 preview: Long-horizon agency in real life — otarU · 2026-08-15