The Segment Anything Model (SAM) has recently emerged as a groundbreaking model in the field of image segmentation. Nevertheless, both the original SAM and its medical adaptations necessitate slice-by-slice annotations, which directly increase the annotation workload with the size of the dataset. We propose MedLSAM to address this issue, ensuring a constant annotation workload irrespective of dataset size and thereby simplifying the annotation process. Our model introduces a 3D localization foundation model capable of localizing any target anatomical part within the body. To achieve this, we develop a Localize Anything Model for 3D Medical Images (MedLAM), utilizing two self-supervision tasks: unified anatomical mapping (UAM) and multi-scale similarity (MSS) across a comprehensive dataset of 14,012 CT scans. We then establish a methodology for accurate segmentation by integrating MedLAM with SAM. By annotating several extreme points across three directions on a few templates, our model can autonomously identify the target anatomical region on all data scheduled for annotation. This allows our framework to generate a 2D bbox for every slice of the image, which is then leveraged by SAM to carry out segmentation. We carried out comprehensive experiments on two 3D datasets encompassing 38 distinct organs. Our findings are twofold: 1) MedLAM is capable of directly localizing any anatomical structure using just a few template scans, yet its performance surpasses that of fully supervised models; 2) MedLSAM not only aligns closely with the performance of SAM and its specialized medical adaptations with manual prompts but achieves this with minimal reliance on extreme point annotations across the entire dataset. Furthermore, MedLAM has the potential to be seamlessly integrated with future 3D SAM models, paving the way for enhanced performance.

翻译：分割一切模型（Segment Anything Model, SAM）近期已成为图像分割领域的开创性模型。然而，原始SAM及其医学改编版本均需逐切片标注，导致标注工作量随数据集规模直接增加。为解决此问题，我们提出MedLSAM，确保标注工作量恒定、不受数据集规模影响，从而简化标注流程。该模型引入一种3D定位基础模型，能定位体内任意目标解剖部位。为此，我们开发了3D医学图像任意目标定位模型（MedLAM），利用两种自监督任务——统一解剖映射（UAM）与多尺度相似性（MSS）——在包含14,012例CT扫描的综合数据集上进行训练。随后，我们通过将MedLAM与SAM集成，建立了一种精准分割方法。通过在少数模板上沿三个方向标注若干极值点，模型可自主识别待标注全部数据上的目标解剖区域，从而为图像每个切片生成2D边界框，供SAM执行分割。我们在涵盖38个不同器官的两个3D数据集上进行了全面实验，结果双方面：1）MedLAM仅需少量模板扫描即可直接定位任意解剖结构，且性能超越全监督模型；2）MedLSAM不仅与采用人工提示的SAM及其专用医学改编版本性能高度一致，且在整个数据集上极值点标注的依赖性极低。此外，MedLAM具备与未来3D SAM模型无缝集成的潜力，为性能提升铺平道路。