arXiv 2501.091382025-01-15cs.CV

面向3D医学图像分割的免训练基础模型少样本适配

Few-Shot Adaptation of Training-Free Foundation Model for 3D Medical Image Segmentation

Athinoula A. Martinos Center for Biomedical Imaging（阿西诺拉·A.马蒂诺斯生物医学成像中心）；Massachusetts General Hospital（麻省总医院）；Harvard Medical School（哈佛医学院）

Xingxin He, Yifan Hu, Zhaoye Zhou, Mohamed Jarraya, Fang Liu

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

针对SAM等视觉基础模型适配3D医学图像分割需大量微调与人工提示的问题，提出FATE-SAM方法，通过重组SAM2预训练模块、引入体一致性机制，实现免微调、无提示的少样本精准分割，更适配临床应用。

摘要：

视觉基础模型已在各类图像分析任务中取得显著进展。在图像分割任务中，Segment Anything Model（SAM，分割一切模型）等基础模型可通过用户提供的提示实现具备泛化性的零样本分割。然而，SAM主要在自然图像上训练，缺乏医学成像领域的专业知识。这一局限性给SAM应用于医学图像分割带来了挑战，包括需要在专用医学数据集上进行大量微调，且依赖手动提示，这两项工作都耗费人力，还需要医学专家介入。\n本研究提出了Few-shot Adaptation of Training-frEe SAM（FATE-SAM，免训练SAM少样本适配），这是一种专为将先进的Segment Anything Model 2（SAM2）适配到3D医学图像分割任务而设计的新方法。FATE-SAM重组SAM2的预训练模块以实现少样本适配，利用少量支持示例捕捉解剖学知识并执行无提示分割，无需进行模型微调。为处理医学图像的体数据特性，我们引入了体一致性机制，以增强3D切片间的空间连贯性。我们在多个医学成像数据集上评估了FATE-SAM，并将其与监督学习方法、零样本SAM方法以及经过微调的医学SAM方法进行了对比。结果表明，FATE-SAM在无需大型标注数据集和专家介入的前提下，实现了鲁棒且准确的分割。FATE-SAM为医学图像分割提供了一种实用高效的解决方案，使其更易于应用于临床场景。

英文摘要：

Vision foundation models have achieved remarkable progress across various image analysis tasks. In the image segmentation task, foundation models like the Segment Anything Model (SAM) enable generalizable zero-shot segmentation through user-provided prompts. However, SAM primarily trained on natural images, lacks the domain-specific expertise of medical imaging. This limitation poses challenges when applying SAM to medical image segmentation, including the need for extensive fine-tuning on specialized medical datasets and a dependency on manual prompts, which are both labor-intensive and require intervention from medical experts. This work introduces the Few-shot Adaptation of Training-frEe SAM (FATE-SAM), a novel method designed to adapt the advanced Segment Anything Model 2 (SAM2) for 3D medical image segmentation. FATE-SAM reassembles pre-trained modules of SAM2 to enable few-shot adaptation, leveraging a small number of support examples to capture anatomical knowledge and perform prompt-free segmentation, without requiring model fine-tuning. To handle the volumetric nature of medical images, we incorporate a Volumetric Consistency mechanism that enhances spatial coherence across 3D slices. We evaluate FATE-SAM on multiple medical imaging datasets and compare it with supervised learning methods, zero-shot SAM approaches, and fine-tuned medical SAM methods. Results show that FATE-SAM delivers robust and accurate segmentation while eliminating the need for large annotated datasets and expert intervention. FATE-SAM provides a practical, efficient solution for medical image segmentation, making it more accessible for clinical applications.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。