SAMRI-3D: Adapting SAM2 for 3D MRI Segmentation with Global Volume Tokens

• URL: http://arxiv.org/abs/2607.18014v1
• Date: Mon, 20 Jul 2026 14:48:11 GMT
• Title: SAMRI-3D: Adapting SAM2 for 3D MRI Segmentation with Global Volume Tokens
• Abstract summary: We present SAMRI-3D, a benchmark and method for 3D MRI segmentation with SAM2.<n>The SAMRI-3D benchmark is the largest MRI-only evaluation to date.<n>This full model, SAMRI-3D, attains the best accuracy (0.78) and lowest variance across all 34 datasets.
• Score: 7.014494732923701
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Foundation models such as Segment Anything Model 2 (SAM2) have transformed natural-image and video segmentation, and recent work has begun adapting them to medical imaging. These adaptations, however, are largely general-purpose models that treat MRI as one modality among many; large-scale, MRI-specific modelling and benchmarking remain limited, even though MRI's low soft-tissue contrast leaves many boundaries effectively invisible on individual slices. We present SAMRI-3D, a benchmark and method for 3D MRI segmentation with SAM2. The SAMRI-3D benchmark is the largest MRI-only evaluation to date - 10,392 volumes from 34 datasets (27 public, 7 in-house) spanning 12 anatomical domains and 10+ sequences, with explicit seen/unseen splits. Freezing the image encoder and fine-tuning only the lightweight decoder and memory modules raises mean Dice from 0.58 (zero-shot SAM2) to 0.76, surpassing recent SAM-based medical models (SAMed-2 0.69, Medical-SAM2 0.49, SAM-Med3D 0.37) with strong statistical significance. To target invisible boundaries, we introduce Global Volume Tokens (GVT): persistent memory tokens trained with a Truncated Signed Distance Field (TSDF) reconstruction objective that is discarded at inference (zero added cost). This full model, SAMRI-3D, attains the best accuracy (0.78) and lowest variance across all 34 datasets and, uniquely, shows no drop on 8 held-out datasets (0.79 unseen vs. 0.78 seen); per-sequence analysis confirms the TSDF objective helps most where per-slice contrast is weakest. We will release the benchmark, code, and models in this paper.

Related papers

• A Hybrid Mamba-SAM Architecture for Efficient 3D Medical Image Segmentation [0.4358626952482685]
  Mamba-SAM is a novel and efficient hybrid architecture that combines a frozen SAM encoder with the linear-time efficiency and long-range modeling capabilities of Mamba-based State Space Models (SSMs)<n>We introduce Multi-Frequency Gated Convolution (MFGC), which enhances feature representation by jointly analyzing spatial and frequency-domain information via 3D discrete cosine transforms and adaptive gating.<n>The dual-branch Mamba-SAM-Base model achieves a mean Dice score of 0.906, comparable to UNet++ (0.907), while outperforming all baselines on Myocardium (0.910) and Left Ventric
  arXiv  Detail & Related papers  (2026-01-31T10:51:17Z)
• VesSAM: Efficient Multi-Prompting for Segmenting Complex Vessel [68.24765319399286]
  We present VesSAM, a powerful and efficient framework tailored for 2D vessel segmentation.<n>VesSAM integrates (1) a convolutional adapter to enhance local texture features, (2) a multi-prompt encoder that fuses anatomical prompts, and (3) a lightweight mask decoder to reduce jagged artifacts.<n>VesSAM consistently outperforms state-of-the-art PEFT-based SAM variants by over 10% Dice and 13% IoU.
  arXiv  Detail & Related papers  (2025-11-02T15:47:05Z)
• AI-Driven MRI-based Brain Tumour Segmentation Benchmarking [0.0]
  This research uses pediatrics Segment Anything Model (SAM), Segment Anything Model 2 (SAM 2), MedSAM, SAM-Med-3D, and nnU-Net to obtain zero-shot inference on the BraTS 2023 adult glioma and pediatrics dataset.<n>Several models exhibit promising Dice scores, particularly SAM and SAM 2 achieving scores of up to 0.894 and 0.893, respectively when given extremely accurate bounding box prompts.<n>However, nnU-Net remains the dominant medical image segmentation network due to the impracticality of providing highly accurate prompts to the models.
  arXiv  Detail & Related papers  (2025-06-25T19:18:26Z)
• Putting the Segment Anything Model to the Test with 3D Knee MRI - A Comparison with State-of-the-Art Performance [2.167419736510938]
  Menisci are cartilaginous tissue found within the knee that contribute to joint lubrication and weight dispersal.<n> Accurate automated segmentation of menisci would allow for earlier detection and treatment of meniscal abnormalities.
  arXiv  Detail & Related papers  (2025-04-17T21:18:58Z)
• SMILE-UHURA Challenge -- Small Vessel Segmentation at Mesoscopic Scale from Ultra-High Resolution 7T Magnetic Resonance Angiograms [60.35639972035727]
  The lack of publicly available annotated datasets has impeded the development of robust, machine learning-driven segmentation algorithms. The SMILE-UHURA challenge addresses the gap in publicly available annotated datasets by providing an annotated dataset of Time-of-Flight angiography acquired with 7T MRI. Dice scores reached up to 0.838 $pm$ 0.066 and 0.716 $pm$ 0.125 on the respective datasets, with an average performance of up to 0.804 $pm$ 0.15.
  arXiv  Detail & Related papers  (2024-11-14T17:06:00Z)
• Improved Baselines with Synchronized Encoding for Universal Medical Image Segmentation [34.08601740109437]
  We introduce SyncSAM, which employs a synchronized dual-branch encoder that integrates convolution and Transformer features in a synchronized manner to enhance medical image encoding.<n>SyncSAM achieves state-of-the-art performance on test sets and also exhibits strong zero-shot capabilities on unseen datasets.
  arXiv  Detail & Related papers  (2024-08-19T11:01:00Z)
• Novel adaptation of video segmentation to 3D MRI: efficient zero-shot knee segmentation with SAM2 [1.6237741047782823]
  We introduce a method for zero-shot, single-prompt segmentation of 3D knee MRI by adapting Segment Anything Model 2. By treating slices from 3D medical volumes as individual video frames, we leverage SAM2's advanced capabilities to generate motion- and spatially-aware predictions. We demonstrate that SAM2 can efficiently perform segmentation tasks in a zero-shot manner with no additional training or fine-tuning.
  arXiv  Detail & Related papers  (2024-08-08T21:39:15Z)
• TotalSegmentator MRI: Robust Sequence-independent Segmentation of Multiple Anatomic Structures in MRI [59.86827659781022]
  A nnU-Net model (TotalSegmentator) was trained on MRI and segment 80atomic structures.<n>Dice scores were calculated between the predicted segmentations and expert reference standard segmentations to evaluate model performance.<n>Open-source, easy-to-use model allows for automatic, robust segmentation of 80 structures.
  arXiv  Detail & Related papers  (2024-05-29T20:15:54Z)
• Stitching, Fine-tuning, Re-training: A SAM-enabled Framework for Semi-supervised 3D Medical Image Segmentation [40.79197318484472]
  Segment Anything Model (SAM) fine-tuning has shown remarkable performance in medical image segmentation in a fully supervised manner.<n>We propose a three-stage framework, i.e., Stitching, Fine-tuning, and Re-training (SFR)<n>Our SFR framework is plug-and-play, and easily compatible with various popular semi-supervised methods.
  arXiv  Detail & Related papers  (2024-03-17T14:30:56Z)
• Comprehensive Multimodal Segmentation in Medical Imaging: Combining YOLOv8 with SAM and HQ-SAM Models [0.24578723416255752]
  The proposed method harnesses the capabilities of the YOLOv8 model for approximate boundary box detection across modalities. To generate boundary boxes, the YOLOv8 model was trained using a limited set of 100 images and masks from each modality. A comparative analysis was conducted to assess the individual and combined performance of the YOLOv8, YOLOv8+SAM, and YOLOv8+HQ-SAM models.
  arXiv  Detail & Related papers  (2023-10-04T20:30:49Z)
• MA-SAM: Modality-agnostic SAM Adaptation for 3D Medical Image Segmentation [58.53672866662472]
  We introduce a modality-agnostic SAM adaptation framework, named as MA-SAM. Our method roots in the parameter-efficient fine-tuning strategy to update only a small portion of weight increments. By injecting a series of 3D adapters into the transformer blocks of the image encoder, our method enables the pre-trained 2D backbone to extract third-dimensional information from input data.
  arXiv  Detail & Related papers  (2023-09-16T02:41:53Z)
• 3DSAM-adapter: Holistic adaptation of SAM from 2D to 3D for promptable tumor segmentation [52.699139151447945]
  We propose a novel adaptation method for transferring the segment anything model (SAM) from 2D to 3D for promptable medical image segmentation. Our model can outperform domain state-of-the-art medical image segmentation models on 3 out of 4 tasks, specifically by 8.25%, 29.87%, and 10.11% for kidney tumor, pancreas tumor, colon cancer segmentation, and achieve similar performance for liver tumor segmentation.
  arXiv  Detail & Related papers  (2023-06-23T12:09:52Z)
• Segment Anything Model for Medical Images? [38.44750512574108]
  The Segment Anything Model (SAM) is the first foundation model for general image segmentation. We built a large medical segmentation dataset with 18 modalities, 84 objects, 125 object-modality paired targets, 1050K 2D images, and 6033K masks. SAM showed remarkable performance in some specific objects but was unstable, imperfect, or even totally failed in other situations.
  arXiv  Detail & Related papers  (2023-04-28T07:23:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.