mlsanityData to 14 Oct 2026

MedSAM2: Segment Anything in 3D Medical Images and Videos

arXiv 2504.03600 ↗First posted 4 Apr 2025eess.IV cs.AI cs.CVcited by 96

Not on the map. Why?

Abstract (arXiv)

Medical image and video segmentation is a critical task for precision medicine, which has witnessed considerable progress in developing task or modality-specific and generalist models for 2D images. However, there have been limited studies on building general-purpose models for 3D images and videos with comprehensive user studies. Here, we present MedSAM2, a promptable segmentation foundation model for 3D image and video segmentation. The model is developed by fine-tuning the Segment Anything Model 2 on a large medical dataset with over 455,000 3D image-mask pairs and 76,000 frames, outperforming previous models across a wide range of organs, lesions, and imaging modalities. Furthermore, we implement a human-in-the-loop pipeline to facilitate the creation of large-scale datasets resulting in, to the best of our knowledge, the most extensive user study to date, involving the annotation of 5,000 CT lesions, 3,984 liver MRI lesions, and 251,550 echocardiogram video frames, demonstrating that MedSAM2 can reduce manual costs by more than 85%. MedSAM2 is also integrated into widely used platforms with user-friendly interfaces for local and cloud deployment, making it a practical tool for supporting efficient, scalable, and high-quality segmentation in both research and healthcare environments.

Key facts. Cited by 96 papers in the map (data through 14 Oct 2026). Builds on 29 of its 53 references that are in the map. First posted on arXiv 4 Apr 2025.

Builds on

29 of 53 references.

References · 29

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  3. 2023Segment Anythingcited by 8,234
  4. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  5. 2021RoFormer: Enhanced Transformer with Rotary Position Embeddingcited by 4,703
  6. 2016DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFscited by 3,241
  7. 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,223
  8. 2024SAM 2: Segment Anything in Images and Videoscited by 2,863
  9. 2023Medical SAM Adapter: Adapting Segment Anything Model for Medical Image Segmentationcited by 490
  10. 2023Segment Anything in High Qualitycited by 376
  11. 2023Segment Anything Model for Medical Image Analysis: an Experimental Studycited by 291
  12. 2023Hiera: A Hierarchical Vision Transformer without the Bells-and-Whistlescited by 290
17 more
  1. 2019Deep Learning for Segmentation using an Open Large-Scale Dataset in 2D Echocardiographycited by 244
  2. 2022Metrics reloaded: Recommendations for image analysis validationcited by 195
  3. 2019Gradio: Hassle-Free Sharing and Testing of ML Models in the Wildcited by 178
  4. 2024BiomedParse: a biomedical foundation model for image parsing of everything everywhere all at oncecited by 111
  5. 2023SAM-Med3D: Towards General-purpose Segmentation Models for Volumetric Medical Imagescited by 107
  6. 2023SegVol: Universal and Interactive Volumetric Medical Image Segmentationcited by 87
  7. 2022Video Polyp Segmentation: A Deep Learning Perspectivecited by 82
  8. 2023MA-SAM: Modality-agnostic SAM Adaptation for 3D Medical Image Segmentationcited by 82
  9. 2024Foundation Model for Advancing Healthcare: Challenges, Opportunities, and Future Directionscited by 77
  10. 20233DSAM-adapter: Holistic adaptation of SAM from 2D to 3D for promptable tumor segmentationcited by 70
  11. 2024VISTA3D: A Unified Segmentation Foundation Model For 3D Medical Imagingcited by 64
  12. 2023Large-Vocabulary Segmentation for Medical Images with Text Promptscited by 62
  13. 2024A Comprehensive Survey of Foundation Models in Medicinecited by 56
  14. 2024Segment Anything in Medical Images and Videos: Benchmark and Deploymentcited by 42
  15. 2025nnInteractive: Redefining 3D Promptable Segmentationcited by 41
  16. 2024SDR-Former: A Siamese Dual-Resolution Transformer for Liver Lesion Classification Using 3D Multi-Phase Imagingcited by 17
  17. 2024Unleashing the Potential of SAM2 for Biomedical Images and Videos: A Surveycited by 14

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 25; 2026: 71.

96 papers.

Sort:

By area:

  1. 2025MedSAM3: Delving into Segment Anything with Medical Conceptscited by 26
  2. 2025DrVD-Bench: Do Vision-Language Models Reason Like Human Doctors in Medical Image Diagnosis?cited by 10
  3. 2025MedReasoner: Reinforcement Learning Drives Reasoning Grounding from Clinical Thought to Pixel-Level Precisioncited by 10
  4. 2025Ophiuchus: Incentivizing Tool-augmented "Think with Images" for Joint Medical Segmentation, Understanding and Reasoningcited by 10
  5. 2026IBISAgent: Reinforcing Pixel-Level Visual Reasoning in MLLMs for Universal Biomedical Object Referring and Segmentationcited by 10
  6. 2025Citrus-V: Advancing Medical Foundation Models with Unified Medical Image Grounding for Clinical Reasoningcited by 8
  7. 2026MedSAM-Agent: Empowering Interactive Medical Image Segmentation with Multi-turn Agentic Reinforcement Learningcited by 8
  8. 2026MIS-HCC: Hierarchical Channel Clustering for Efficient Medical Image Segmentationcited by 4
  9. 2025RAU: Reference-based Anatomical Understanding with Vision Language Modelscited by 3
  10. 2025Adaptation of Foundation Models for Medical Image Analysis: Strategies, Challenges, and Future Directionscited by 3
  11. 2025Atlas is Your Perfect Context: One-Shot Customization for Generalizable Foundational Medical Image Segmentationcited by 3
  12. 2025ENSAM: an efficient foundation model for interactive segmentation of 3D medical imagescited by 2
38 more
  1. 2025Dynamic Prompt Generation for Interactive 3D Medical Image Segmentation Trainingcited by 2
  2. 2025Comparing SAM 2 and SAM 3 for Zero-Shot Segmentation of 3D Medical Datacited by 2
  3. 2026BAAI Cardiac Agent: An intelligent multimodal agent for automated reasoning and diagnosis of cardiovascular diseases from cardiac magnetic resonance imagingcited by 2
  4. 2026Beyond a Single Frame: Multi-Frame Spatially Grounded Reasoning Across Volumetric MRIcited by 2
  5. 2026Towards Autonomous and Auditable Medical Imaging Model Developmentcited by 2
  6. 2025Live(r) Die: Predicting Survival in Colorectal Liver Metastasiscited by 1
  7. 2025Lite ENSAM: a lightweight cancer segmentation model for 3D Computed Tomographycited by 1
  8. 2025Medal S: Spatio-Textual Prompt Model for Medical Segmentationcited by 1
  9. 2025See in Depth: Training-Free Surgical Scene Segmentation with Monocular Depth Priorscited by 1
  10. 2026Opportunistic Promptable Segmentation: Leveraging Routine Radiological Annotations to Guide 3D CT Lesion Segmentationcited by 1
  11. 20263DLAND: 3D Lesion Abdominal Anomaly Localization Datasetcited by 1
  12. 2026CORE-Seg: Reasoning-Driven Segmentation for Complex Lesions via Reinforcement Learningcited by 1
  13. 2026Delving Aleatoric Uncertainty in Medical Image Segmentation via Vision Foundation Modelscited by 1
  14. 2026VoxCor: Training-Free Volumetric Features for Multimodal Voxel Correspondencecited by 1
  15. 2026MRI2Rep: Autoregressive Structured Report Generation for 3D Liver MRIcited by 1
  16. 2026Parameter-Efficient Adaptation of SAM3 for Prompt-Driven Surgical Concept Segmentationcited by 1
  17. 2026Do Medical Foundation Models Generalize on the African Brain?cited by 1
  18. 2026UltraSAM3: A Concept-Driven Foundation Model for Universal Ultrasound Image Segmentationcited by 1
  19. 2026When Adaptation Hurts: Connecting Representational Drift to OOD Failures in MedSAM Fine-Tuningcited by 1
  20. 2026Hierarchical Prototype-Memory Adaptation of SAM for Surgical Instrument Segmentationcited by 1
  21. 2025Geological Everything Model 3D: A Promptable Foundation Model for Unified and Zero-Shot Subsurface Understandingcited by 0
  22. 2025Towards Affordable Tumor Segmentation and Visualization for 3D Breast MRI Using SAM2cited by 0
  23. 2025MAE-SAM2: Mask Autoencoder-Enhanced SAM2 for Clinical Retinal Vascular Leakage Segmentationcited by 0
  24. 2025Domain-Specialized Interactive Segmentation Framework for Meningioma Radiotherapy Planningcited by 0
  25. 2025When Tracking Fails: Analyzing Failure Modes of SAM2 for Point-Based Tracking in Surgical Videoscited by 0
  26. 2025nnSAM2: nnUNet-Enhanced One-Prompt SAM2 for Few-shot Multi-Modality Segmentation and Composition Analysis of Lumbar Paraspinal Musclescited by 0
  27. 2025TFM Dataset: A Novel Multi-task Dataset and Integrated Pipeline for Automated Tear Film Break-Up Segmentationcited by 0
  28. 2025Scale-Aware Curriculum Learning for Ddata-Efficient Lung Nodule Detection with YOLOv11cited by 0
  29. 2025Echo-CoPilot: A Multiple-Perspective Agentic Framework for Reliable Echocardiography Interpretationcited by 0
  30. 2025SSL-MedSAM2: A Semi-supervised Medical Image Segmentation Framework Powered by Few-shot Learning of SAM2cited by 0
  31. 2026Point Tracking as a Temporal Cue for Robust Myocardial Segmentation in Echocardiography Videoscited by 0
  32. 2026Promptable segmentation with region exploration enables minimal-effort expert-level prostate cancer delineationcited by 0
  33. 2026GLIDE-Reg: Global-to-Local Deformable Registration Using Co-Optimized Foundation and Handcrafted Featurescited by 0
  34. 2026Uncertainty-Aware Concept and Motion Segmentation for Semi-Supervised Angiography Videoscited by 0
  35. 2026LeafInst - Unified Instance Segmentation Network for Fine-Grained Forestry Leaf Phenotype Analysis: A New UAV based Benchmarkcited by 0
  36. 2026Shifting Adaptation from Weight Space to Memory Space: A Memory-Augmented Agent for Medical Image Segmentationcited by 0
  37. 2026TubeMLLM: A Foundation Model for Topology Knowledge Exploration in Vessel-like Anatomycited by 0
  38. 2026Toward Clinically Ready Foundation Models in Medical Image Analysis: Adaptation Mechanisms and Deployment Trade-offscited by 0

50 most cited of 96 All 96 (JSON)