Pith. sign in

REVIEW 10 cited by

SAM-Med3D: Towards General-purpose Segmentation Models for Volumetric Medical Images

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2310.15161 v3 pith:D4N4NXF4 submitted 2023-10-23 cs.CV

Haoyu Wang , Sizheng Guo , Jin Ye , Zhongying Deng , Junlong Cheng , Tianbin Li , Jianpin Chen , Yanzhou Su
show 6 more authors
Ziyan Huang Yiqing Shen Bin Fu Shaoting Zhang Junjun He Yu Qiao
This is my paper · ORCID
classification cs.CV
keywords medicalsam-med3dsegmentationdatasetanatomicaldiversegeneral-purposeimages
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Existing volumetric medical image segmentation models are typically task-specific, excelling at specific target but struggling to generalize across anatomical structures or modalities. This limitation restricts their broader clinical use. In this paper, we introduce SAM-Med3D for general-purpose segmentation on volumetric medical images. Given only a few 3D prompt points, SAM-Med3D can accurately segment diverse anatomical structures and lesions across various modalities. To achieve this, we gather and process a large-scale 3D medical image dataset, SA-Med3D-140K, from a blend of public sources and licensed private datasets. This dataset includes 22K 3D images and 143K corresponding 3D masks. Then SAM-Med3D, a promptable segmentation model characterized by the fully learnable 3D structure, is trained on this dataset using a two-stage procedure and exhibits impressive performance on both seen and unseen segmentation targets. We comprehensively evaluate SAM-Med3D on 16 datasets covering diverse medical scenarios, including different anatomical structures, modalities, targets, and zero-shot transferability to new/unseen tasks. The evaluation shows the efficiency and efficacy of SAM-Med3D, as well as its promising application to diverse downstream tasks as a pre-trained model. Our approach demonstrates that substantial medical resources can be utilized to develop a general-purpose medical AI for various potential applications. Our dataset, code, and models are available at https://github.com/uni-medical/SAM-Med3D.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 10 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. SLIP: Segmentation with Low-latency Interactive Prompting for 3D Medical Images

    cs.CV 2026-07 conditional novelty 6.0 of 10

    SLIP decouples image encoding from prompt refinement via a patch memory bank, achieving 0.06s latency and reversible prompting for interactive 3D medical segmentation.

  2. Rethink Domain Generalization in Heterogeneous Sequence MRI Segmentation

    eess.IV 2025-07 conditional novelty 6.0 of 10

    A semi-supervised pretraining method improves cross-sequence pancreas segmentation Dice from 43.55% to 70.39% (NU) and from 35.62% to 66.61% (IH) on the new PancreasDG benchmark.

  3. Semantic-guided Masked Mutual Learning for Multi-modal Brain Tumor Segmentation with Arbitrary Missing Modalities

    stat.ME 2025-07 conditional novelty 6.0 of 10

    A dual-branch mutual-learning framework with SAM-based semantic refinement improves brain tumor segmentation accuracy under all missing-modality combinations on three BraTS datasets.

  4. MedSeg-R: Medical Image Segmentation with Clinical Reasoning

    cs.CV 2025-06 conditional novelty 6.0 of 10

    MedSeg-R injects structured location, texture, and shape priors into a frozen SAM backbone, improving Dice scores on small and overlapping medical structures across multiple modalities.

  5. Background Matters: A Cross-view Bidirectional Modeling Framework for Semi-supervised Medical Image Segmentation

    cs.CV 2025-05 conditional novelty 6.0 of 10

    CVBM adds a background segmentation branch and a bidirectional consistency loss to a mean-teacher framework, improving semi-supervised medical image segmentation accuracy.

  6. Segment Anything for Cell Tracking

    cs.CV 2025-09 conditional novelty 5.0 of 10

    SAM2-based, annotation-free cell tracking links cells and detects divisions in 2D and 3D time-lapse videos, achieving top-3 linking accuracy on Cell Tracking Challenge benchmarks.

  7. Register Anything: Estimating "Corresponding Prompts" for Segment Anything Model

    cs.CV 2025-08 reject novelty 5.0 of 10

    PromptReg registers two images by estimating point prompts that make SAM segment the same anatomical regions in both, without any training.

  8. AI-Driven MRI-based Brain Tumour Segmentation Benchmarking

    cs.CV 2025-06 conditional novelty 5.0 of 10

    Fine-tuned SAM and SAM 2 with high-quality bounding-box prompts achieve higher Dice scores than zero-shot nnU-Net on pediatric brain tumor segmentation, but nnU-Net remains more practical.

  9. RAPS-3D: Efficient interactive segmentation for 3D radiological imaging

    cs.CV 2025-07 conditional novelty 4.0 of 10

    RAPS-3D is a 3D promptable CT segmentation model that reports 86.8 Dice on AMOS-CT with a single 2D bounding-box prompt, using zoom-out/zoom-in inference with no sliding window.

  10. Prompt Mechanisms in Medical Imaging: A Comprehensive Survey

    eess.IV 2025-06 conditional novelty 4.0 of 10

    A broad survey that organizes prompt mechanisms for medical image generation, segmentation, and classification into a two-dimensional taxonomy of core technologies and clinical applications.

Pith tools