The introduction of the Segment Anything Model (SAM) has marked a significant advancement in prompt-driven image segmentation. However, SAM's application to medical image segmentation requires manual prompting of target structures to obtain acceptable performance, which is still labor-intensive. Despite attempts of auto-prompting to turn SAM into a fully automatic manner, it still exhibits subpar performance and lacks of reliability in the field of medical imaging. In this paper, we propose UR-SAM, an uncertainty rectified SAM framework to enhance the robustness and reliability for auto-prompting medical image segmentation. Our method incorporates a prompt augmentation module to estimate the distribution of predictions and generate uncertainty maps, and an uncertainty-based rectification module to further enhance the performance of SAM. Extensive experiments on two public 3D medical datasets covering the segmentation of 35 organs demonstrate that without supplementary training or fine-tuning, our method further improves the segmentation performance with up to 10.7 % and 13.8 % in dice similarity coefficient, demonstrating efficiency and broad capabilities for medical image segmentation without manual prompting.

翻译：任意分割模型（SAM）的引入标志着提示驱动图像分割领域的重大进展。然而，SAM在医学图像分割中的应用仍需手动提示目标结构以获得可接受的性能，这仍然劳动密集。尽管已有尝试通过自动提示将SAM转变为全自动方式，但在医学成像领域，其表现仍不理想且缺乏可靠性。本文提出UR-SAM，一种基于不确定性校正的SAM框架，旨在增强自动提示医学图像分割的鲁棒性和可靠性。我们的方法包含一个提示增强模块，用于估计预测分布并生成不确定性图，以及一个基于不确定性的校正模块，以进一步提升SAM的性能。在两个覆盖35个器官分割的公开三维医学数据集上的大量实验表明，无需额外训练或微调，我们的方法在Dice相似系数上进一步提升了高达10.7%和13.8%的分割性能，证明了其在无需手动提示的医学图像分割中的高效性和广泛能力。