Medical SAM3: A Foundation Model for Universal Prompt-Driven Medical Image Segmentation

TL;DR

Medical SAM3 is a fine-tuned foundation model that significantly improves prompt-driven medical image segmentation across diverse datasets and modalities, addressing domain shifts and complex anatomical structures.

Contribution

We fully fine-tuned SAM3 on large-scale medical datasets, enabling robust, universal, prompt-driven segmentation for medical images across multiple modalities and structures.

Findings

Significant performance improvements across 33 datasets and 10 modalities.

Enhanced segmentation accuracy in complex and ambiguous cases.

Preserved prompt flexibility after full model adaptation.

Abstract

Promptable segmentation foundation models such as SAM3 have demonstrated strong generalization capabilities through interactive and concept-based prompting. However, their direct applicability to medical image segmentation remains limited by severe domain shifts, the absence of privileged spatial prompts, and the need to reason over complex anatomical and volumetric structures. Here we present Medical SAM3, a foundation model for universal prompt-driven medical image segmentation, obtained by fully fine-tuning SAM3 on large-scale, heterogeneous 2D and 3D medical imaging datasets with paired segmentation masks and text prompts. Through a systematic analysis of vanilla SAM3, we observe that its performance degrades substantially on medical data, with its apparent competitiveness largely relying on strong geometric priors such as ground-truth-derived bounding boxes. These findings motivate full model adaptation beyond prompt engineering alone. By fine-tuning SAM3's model parameters on 33 datasets spanning 10 medical imaging modalities, Medical SAM3 acquires robust domain-specific representations while preserving prompt-driven flexibility. Extensive experiments across organs, imaging modalities, and dimensionalities demonstrate consistent and significant performance gains, particularly in challenging scenarios characterized by semantic ambiguity, complex morphology, and long-range 3D context. Our results establish Medical SAM3 as a universal, text-guided segmentation foundation model for medical imaging and highlight the importance of holistic model adaptation for achieving robust prompt-driven segmentation under severe domain shift. Code and model will be made available at https://github.com/AIM-Research-Lab/Medical-SAM3.