醫學 SAM 2：通過 Segment Anything 模型將醫學影像分割為視頻。

Medical SAM 2: Segment medical images as video via Segment Anything Model 2

August 1, 2024

作者: Jiayuan Zhu, Yunli Qi, Junde Wu

cs.AI

摘要

本文介紹了醫學SAM 2（MedSAM-2），這是一個先進的分割模型，利用SAM 2框架處理2D和3D醫學影像分割任務。通過將醫學影像視為視頻的理念，MedSAM-2不僅適用於3D醫學影像，還開啟了新的單提示分割功能。這使用戶只需針對一個特定影像對象提供提示，之後模型就可以自主地在所有後續影像中分割相同類型的對象，而不受影像之間時間關係的影響。我們在各種醫學影像模態下評估了MedSAM-2，包括腹部器官、視神經盤、腦腫瘤、甲狀腺結節和皮膚病變，並將其與傳統和交互式分割設置中的最先進模型進行了比較。我們的研究結果表明，MedSAM-2不僅在性能上超越了現有模型，而且在各種醫學影像分割任務中表現出更優越的泛化能力。我們的代碼將在以下鏈接發布：https://github.com/MedicineToken/Medical-SAM2

English

In this paper, we introduce Medical SAM 2 (MedSAM-2), an advanced segmentation model that utilizes the SAM 2 framework to address both 2D and 3D medical image segmentation tasks. By adopting the philosophy of taking medical images as videos, MedSAM-2 not only applies to 3D medical images but also unlocks new One-prompt Segmentation capability. That allows users to provide a prompt for just one or a specific image targeting an object, after which the model can autonomously segment the same type of object in all subsequent images, regardless of temporal relationships between the images. We evaluated MedSAM-2 across a variety of medical imaging modalities, including abdominal organs, optic discs, brain tumors, thyroid nodules, and skin lesions, comparing it against state-of-the-art models in both traditional and interactive segmentation settings. Our findings show that MedSAM-2 not only surpasses existing models in performance but also exhibits superior generalization across a range of medical image segmentation tasks. Our code will be released at: https://github.com/MedicineToken/Medical-SAM2