本文探讨了使用Segment Anything Model (SAM) 进行膝关节半月板分割的可行性。半月板损伤是导致膝关节骨关节炎 (OA) 的主要原因，而 OA 是一种导致残疾的常见疾病。研究将SAM应用于3D膝关节磁共振图像，并与3D U-Net模型进行比较。结果表明，虽然SAM在通用性方面表现出色，但在半月板分割任务中，其性能并未超越基础的3D U-Net模型。该研究突出了SAM在处理低对比度和边界不清晰的精细解剖结构时，可能存在局限性。

🦵 研究背景：半月板是膝关节内的软骨组织，对关节润滑和体重分散至关重要。半月板损伤可能导致骨关节炎（OA），而OA是导致残疾的主要原因。准确的半月板自动分割有助于早期发现和治疗半月板异常，并深入了解半月板在OA发病机制中的作用。

💡 研究方法：研究采用了Segment Anything Model (SAM) 和3D U-Net模型，用于从3D膝关节磁共振图像中进行半月板的自动分割。SAM是一个基础分割模型，因其在训练中使用的大量数据而在各种任务中表现出色。

📊 研究结果：当仅微调SAM的解码器时，其Dice评分为0.81±0.03，低于3D U-Net的0.87±0.03。然而，当端到端微调SAM时，Dice评分为0.87±0.03，与3D U-Net的性能相当。在豪斯多夫距离方面，两种SAM配置均不如3D U-Net，表明SAM在匹配半月板形态方面表现较差。

🔍 研究结论：尽管SAM具有通用性，但在半月板分割任务中，其性能并未超越基础的3D U-Net。SAM可能不适用于类似的3D医学图像分割任务，特别是涉及低对比度和边界不清晰的精细解剖结构的任务。

arXiv:2504.13340v1 Announce Type: cross Abstract: Menisci are cartilaginous tissue found within the knee that contribute to joint lubrication and weight dispersal. Damage to menisci can lead to onset and progression of knee osteoarthritis (OA), a condition that is a leading cause of disability, and for which there are few effective therapies. Accurate automated segmentation of menisci would allow for earlier detection and treatment of meniscal abnormalities, as well as shedding more light on the role the menisci play in OA pathogenesis. Focus in this area has mainly used variants of convolutional networks, but there has been no attempt to utilise recent large vision transformer segmentation models. The Segment Anything Model (SAM) is a so-called foundation segmentation model, which has been found useful across a range of different tasks due to the large volume of data used for training the model. In this study, SAM was adapted to perform fully-automated segmentation of menisci from 3D knee magnetic resonance images. A 3D U-Net was also trained as a baseline. It was found that, when fine-tuning only the decoder, SAM was unable to compete with 3D U-Net, achieving a Dice score of $0.81\pm0.03$, compared to $0.87\pm0.03$, on a held-out test set. When fine-tuning SAM end-to-end, a Dice score of $0.87\pm0.03$ was achieved. The performance of both the end-to-end trained SAM configuration and the 3D U-Net were comparable to the winning Dice score ($0.88\pm0.03$) in the IWOAI Knee MRI Segmentation Challenge 2019. Performance in terms of the Hausdorff Distance showed that both configurations of SAM were inferior to 3D U-Net in matching the meniscus morphology. Results demonstrated that, despite its generalisability, SAM was unable to outperform a basic 3D U-Net in meniscus segmentation, and may not be suitable for similar 3D medical image segmentation tasks also involving fine anatomical structures with low contrast and poorly-defined boundaries.