Segment Anything Model (SAM) 因其能够根据提示分割图像中的各种物体而受到了广泛关注。最近开发的 SAM 2 将这种能力扩展到了视频输入。这为将 SAM 应用于3D图像提供了机会，而这是医学成像领域的基本任务之一。在本文中，我们广泛评估了 SAM 2 分割2D和3D医学图像的能力，首先收集了21个医学成像数据集，包括手术视频，常见的3D模态如计算机断层扫描 (CT)、磁共振成像 (MRI) 和正电子发射断层扫描 (PET)，以及2D模态如X射线和超声。我们考虑了 SAM 2 的两种评估设置：(1) 多帧3D分割，其中提示被提供给从体积中选取的一个或多个切片；(2) 单帧2D分割，其中提示被提供给每个切片。前者仅适用于视频和3D模态，而后者适用于所有数据集。我们的结果表明，在单帧2D分割下，SAM 2 表现出与 SAM 相似的性能；而在多帧3D分割下，其性能则根据所选注释切片、传播方向、传播期间使用的预测等而有所变化。我们相信我们的工作增强了对 SAM 2 在医学领域行为的理解，并为未来将 SAM 2 适应于该领域的工作提供了方向。我们的代码可在以下网址获取：https://github.com/mazurowski-lab/segment-anything2-medical-evaluation。
英文摘要：
Segment Anything Model (SAM) has gained significant attention because of its ability to segment various objects in images given a prompt. The recently developed SAM 2 has extended this ability to video inputs. This opens an opportunity to apply SAM to 3D images, one of the fundamental tasks in the medical imaging field. In this paper, we extensively evaluate SAM 2's ability to segment both 2D and 3D medical images by first collecting 21 medical imaging datasets, including surgical videos, common 3D modalities such as computed tomography (CT), magnetic resonance imaging (MRI), and positron emission tomography (PET) as well as 2D modalities such as X-ray and ultrasound. Two evaluation settings of SAM 2 are considered: (1) multi-frame 3D segmentation, where prompts are provided to one or multiple slice(s) selected from the volume, and (2) single-frame 2D segmentation, where prompts are provided to each slice. The former only applies to videos and 3D modalities, while the latter applies to all datasets. Our results show that SAM 2 exhibits similar performance as SAM under single-frame 2D segmentation, and has variable performance under multi-frame 3D segmentation depending on the choices of slices to annotate, the direction of the propagation, the predictions utilized during the propagation, etc. We believe our work enhances the understanding of SAM 2's behavior in the medical field and provides directions for future work in adapting SAM 2 to this domain. Our code is available at: https://github.com/mazurowski-lab/segment-anything2-medical-evaluation.
MedSAM3: Delving into Segment Anything with Medical Concepts
The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Southeast University（东南大学）；The Hong Kong University of Science and Technology（香港科技大学）
EviPrompt: A Training-Free Evidential Prompt Generation Method for Segment Anything Model in Medical Images
Beijing University of Posts and Telecommunications（北京邮电大学）；National Institute of Health Data Science, Peking University（北京大学健康数据科学研究所）；The Chinese University of Hong Kong（香港中文大学）
SAM3D: Segment Anything Model in Volumetric Medical Images
University of Arkansas（阿肯色大学）；University of Science, Vietnam National University（越南国家大学科学大学）；John von Neumann Institute, Vietnam National University（越南国家大学约翰·冯·诺依曼研究所）；West Virginia University（西弗吉尼亚大学）；University of Arkansas for Medical Sciences（阿肯色医科大学）
Segment Anything in Medical Images and Videos: Benchmark and Deployment
Peter Munk Cardiac Centre, University Health Network（彼得·芒克心脏中心，大学健康网络）；Vector Institute for Artificial Intelligence（向量人工智能研究所）；AI Hub, University Health Network（人工智能中心，大学健康网络）；University of Toronto（多伦多大学）
本文对 SAM2 在 11 种医学图像模态和视频上进行了全面基准测试，并通过微调迁移学习及 3D Slicer 插件和 Gradio API 部署，验证了其快速适应医学领域并实现高效 3D 分割的能力。
MedSAM2: Segment Anything in 3D Medical Images and Videos
University Health Network（多伦多大学健康网络）；Vector Institute（向量研究院）；Harvard Medical School（哈佛医学院）；Harvard University（哈佛大学）；University of Toronto（多伦多大学）；Peter Munk Cardiac Centre（彼得·芒克心脏中心）；AI Hub（人工智能中心）
提出MedSAM2，通过微调Segment Anything Model 2构建3D医学图像和视频分割基础模型，结合人在回路流程显著降低标注成本并提升分割性能。
ViPSAM: Visual Prompting Medical Image Segmentation Using Segment Anything Model
Department of Artificial Intelligence, Sungkyunkwan University, Republic of Korea（人工智能系，成均馆大学，大韩民国）；Department of Radiation Oncology, Samsung Medical Center, Sungkyunkwan University School of Medicine, Republic of Korea（放射肿瘤科，三星医疗中心，成均馆大学医学院，大韩民国）；Department of MetaBioHealth, Sungkyunkwan University, Republic of Korea（元生物健康系，成均馆大学，大韩民国）
Peter Munk Cardiac Centre, University Health Network（彼得·芒克心脏中心，大学健康网络）；University of Toronto（多伦多大学）；Vector Institute（矢量研究所）；Western University（西安大略大学）；Tandon School of Engineering, New York University（纽约大学坦登工程学院）；Yale University（耶鲁大学）；UHN AI Hub（大学健康网络人工智能中心）
Encoding Structural Constraints into Segment Anything Models via Probabilistic Graphical Models
The George Washington University（乔治·华盛顿大学）；Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences（深圳先进技术研究所，中国科学院）；University of Alabama at Birmingham（阿拉巴马大学伯明翰分校）
SQA-SAM: Segmentation Quality Assessment for Medical Images Utilizing the Segment Anything Model
Nanjing University of Science and Technology（南京理工大学）；Digital Medical Research Center, School of Basic Medical Sciences, Fudan University（复旦大学基础医学院数字医学研究中心）；The Chinese University of Hong Kong（香港中文大学）；University of Notre Dame（圣母大学）
Part-aware Prompted Segment Anything Model for Adaptive Segmentation
Department of Computer Science and Engineering, University of Michigan（计算机科学与工程系，密歇根大学）；Department of Electrical and Computer Engineering, University of Michigan（电气与计算机工程系，密歇根大学）
Segment Anything Model (SAM) for Radiation Oncology
Mayo Clinic（梅奥诊所）；University of Georgia（佐治亚大学）；The University of Texas at Arlington（德克萨斯大学阿灵顿分校）；Massachusetts General Hospital（麻省总医院）；Harvard Medical School（哈佛医学院）
Adapting Segment Anything Model 3 for Concept-Driven Lesion Segmentation in Medical Images: An Experimental Study
The Medical Artificial Intelligence and Automation (MAIA) Laboratory, Department of Radiation Oncology, University of Texas Southwestern Medical Center（德克萨斯大学西南医学中心放射肿瘤学系医学人工智能与自动化（MAIA）实验室）；Medical Image Processing Group, Department of Radiology, University of Pennsylvania（宾夕法尼亚大学放射学系医学图像处理组）；Division of Digestive and Liver Diseases, Department of Internal Medicine, University of Texas Southwestern Medical Center（德克萨斯大学西南医学中心内科学系消化与肝脏疾病科）
Eye image segmentation using visual and concept prompts with Segment Anything Model 3 (SAM3)
Lund University Humanities Lab \& Dept. of Psychology, Lund University Lund Sweden；Lund University Humanities Lab Lund Sweden；Lund University Humanities Lab \& Dept. of Psychology, Lund University；Lund University Humanities Lab
We introduce the Segment Anything (SA) project: a new task, model, and dataset for image segmentation. Using our efficient model in a data collection loop, we built the largest segmentation dataset to date (by far), with over 1 billion masks on 11M licensed and privacy respecting images. The model is designed and trained to be promptable, so it can transfer zero-shot to new image distributions and tasks. We evaluate its capabilities on numerous tasks and find that its zero-shot performance is impressive -- often competitive with or even superior to prior fully supervised results. We are releas…
Segment Anything for Satellite Imagery: A Strong Baseline and a Regional Dataset for Automatic Field Delineation
University of Modena and Reggio Emilia（摩德纳和雷吉奥艾米利亚大学）；ABACO Group SpA（ABACO集团）；Institute of Informatics and Telematics, National Research Council（信息与电信研究所，国家研究 council）
Medical SAM Adapter: Adapting Segment Anything Model for Medical Image Segmentation
University of Oxford（牛津大学）；National University of Singapore（新加坡国立大学）；University of Alberta（阿尔伯塔大学）；A*STAR（新加坡科技研究局）；Carnegie Mellon University（卡内基梅隆大学）；Singapore Eye Research Institute（新加坡眼科研究所）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；University of Hongkong（香港大学）
本文提出Medical SAM Adapter（Med-SA），通过轻量适配技术将医学知识融入SAM，利用SD-Trans和HyP-Adpt适配2D模型至3D医学图像，在17个任务上以仅2%参数更新超越SOTA方法。
