Artificial Intelligence (AI) has the potential to revolutionize diagnosis and segmentation in medical imaging. However, development and clinical implementation face multiple challenges including limited data availability, lack of generalizability, and the necessity to incorporate multi-modal data effectively. A foundation model, which is a large-scale pre-trained AI model, offers a versatile base that can be adapted to a variety of specific tasks and contexts. Here, we present a novel foundation model, VISION-MAE, specifically designed for medical imaging. Specifically, VISION-MAE is trained on a dataset of 2.5 million unlabeled images from various modalities (CT, MR, PET, X-rays, and ultrasound), using self-supervised learning techniques. It is then adapted to classification and segmentation tasks using explicit labels. VISION-MAE has high label efficiency, outperforming several benchmark models in both in-domain and out-of-domain applications, and achieves high performance even with reduced availability of labeled data. This model represents a significant advancement in medical imaging AI, offering a generalizable and robust solution for improving segmentation and classification tasks while reducing the data annotation workload.

人工智能（AI）在医学影像诊断和分割方面具有改革潜力，但其发展和临床应用面临多个挑战，包括数据有限性、泛化能力不足以及有效整合多模态数据的必要性。我们提出了一种新的基础模型VISION-MAE，针对医学影像进行专门设计。VISION-MAE是在包含各种模态（CT、MR、PET、X射线和超声）的250万张未标记图像数据集上使用自监督学习技术进行训练的，并使用明确的标签对其进行分类和分割任务的自适应。VISION-MAE具有较高的标签效率，在领域内外应用中表现优于几个基准模型，并且即使数据标注可用性减少，也能实现高性能。该模型代表了医学影像人工智能的重大进展，为改善分割和分类任务提供了具有泛化性和稳健性的解决方案，同时减轻了数据标注工作量。

VISION-MAE: 医学图像分割和分类的基础模型