School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China; Shanghai AI Lab, Shanghai, China.
School of Biomedical Engineering, Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, China; West China Biomedical Big Data Center, West China Hospital, Sichuan University, Chengdu, China.
Med Image Anal. 2025 Jan;99:103370. doi: 10.1016/j.media.2024.103370. Epub 2024 Oct 15.
Recent advancements in foundation models have shown significant potential in medical image analysis. However, there is still a gap in models specifically designed for medical image localization. To address this, we introduce MedLAM, a 3D medical foundation localization model that accurately identifies any anatomical part within the body using only a few template scans. MedLAM employs two self-supervision tasks: unified anatomical mapping (UAM) and multi-scale similarity (MSS) across a comprehensive dataset of 14,012 CT scans. Furthermore, we developed MedLSAM by integrating MedLAM with the Segment Anything Model (SAM). This innovative framework requires extreme point annotations across three directions on several templates to enable MedLAM to locate the target anatomical structure in the image, with SAM performing the segmentation. It significantly reduces the amount of manual annotation required by SAM in 3D medical imaging scenarios. We conducted extensive experiments on two 3D datasets covering 38 distinct organs. Our findings are twofold: (1) MedLAM can directly localize anatomical structures using just a few template scans, achieving performance comparable to fully supervised models; (2) MedLSAM closely matches the performance of SAM and its specialized medical adaptations with manual prompts, while minimizing the need for extensive point annotations across the entire dataset. Moreover, MedLAM has the potential to be seamlessly integrated with future 3D SAM models, paving the way for enhanced segmentation performance. Our code is public at https://github.com/openmedlab/MedLSAM.
最近，基础模型在医学图像分析方面取得了重大进展。然而，专门为医学图像定位设计的模型仍然存在差距。为了解决这个问题，我们引入了 MedLAM，这是一种 3D 医学基础定位模型，仅使用少数模板扫描即可准确识别体内的任何解剖部位。MedLAM 采用了两种自监督任务：统一解剖映射（UAM）和多尺度相似性（MSS），涵盖了 14012 个 CT 扫描的综合数据集。此外，我们通过将 MedLAM 与 Segment Anything Model（SAM）集成，开发了 MedLSAM。这个创新的框架需要在几个模板上的三个方向上进行极端点注释，以使 MedLAM 能够在图像中定位目标解剖结构，而 SAM 则执行分割。它大大减少了 3D 医学成像场景中 SAM 所需的手动注释量。我们在两个涵盖 38 个不同器官的 3D 数据集上进行了广泛的实验。我们的发现有两个方面：（1）MedLAM 仅使用少数模板扫描即可直接定位解剖结构，其性能可与完全监督的模型相媲美；（2）MedLSAM 与 SAM 及其带有手动提示的专门医学适应模型的性能非常匹配，同时最大限度地减少了在整个数据集上进行广泛点注释的需求。此外，MedLAM 有可能与未来的 3D SAM 模型无缝集成，为增强分割性能铺平道路。我们的代码可在 https://github.com/openmedlab/MedLSAM 上获得。
