Skip to main content

๐Ÿง  SAM-Med3D

A 3D promptable segmentation model adapted from SAM for volumetric medical images. Its original workflow uses iterative foreground/background point prompts and returns a volumetric mask.

Official codePaperWeights

โ† Model atlas

At a glanceโ€‹

FieldDetails
Model type3D point-prompt segmentation model
Research team / organizationShanghai Jiao Tong University; Shanghai Artificial Intelligence Laboratory; Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences.
Input / modality3D medical volumes; the project benchmarks CT, MRI and other volumetric modalities.
Prompt / interactionInteractive 3D point prompts; iterative corrections.
Code licenseCode: Apache-2.0. Check the checkpoint page for the weight-specific terms.

๐Ÿ“š Paper and publicationโ€‹

SAM-Med3D: Towards General-purpose Segmentation Models for Volumetric Medical Images โ€” arXiv:2310.15161 (2023); the project README reports acceptance as an ECCV BIC 2024 Oral.

๐Ÿ“ฆ Checkpoints and accessโ€‹

The upstream project currently highlights the newer SAM-Med3D-turbo checkpoint. Its README links Hugging Face, Google Drive and HF-Mirror. The Hugging Face model blueyo0/SAM-Med3D exposes sam_med3d_turbo.pth and is referenced by the upstream MedIM example.

The code, model checkpoint and any required foundation-model checkpoint can have different terms. Review each linked source before use or redistribution.

โš™๏ธ Official setup and inferenceโ€‹

git clone https://github.com/uni-medical/SAM-Med3D.git
cd SAM-Med3D
pip install medim
# Configure the image, ground-truth and output paths in the upstream demo
python medim_val_single.py

The demo is an evaluation example and expects a paired ground-truth mask. For model construction and checkpoint selection, see the official MedIM example.

โš ๏ธ Version and practical notesโ€‹

The project currently highlights the newer SAM-Med3D-turbo checkpoint. Keep it distinct from the original paper checkpoint, and record the exact weight and prompt protocol when reproducing published results.

๐Ÿ“œ Licenseโ€‹

Code: Apache-2.0. Check the checkpoint page for the weight-specific terms.

Citation: Cite the paper above and the upstream project as directed by its authors. This repository links to the original paper; it does not redistribute the code or weights.

Source pages checked: 27 October 2026. Upstream environments, weights and access policies may change; use the linked project as the source of truth.