用于胸部X射线图像中泛化疾病诊断的基础模型
A foundation model for generalizable disease diagnosis in chest X-ray images
- Centre for Perceptual and Interactive Intelligence, the Chinese University of Hong Kong（香港中文大学感知与交互智能中心）
- Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）
- SenseTime Research（商汤科技研究院）
- Department of Electronic Engineering, the Chinese University of Hong Kong（香港中文大学电子工程系）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对胸部X射线AI模型依赖标注数据且泛化能力弱的问题，提出基础模型CXRBase，通过自监督学习104万张无标签图像并微调，实现疾病准确分类，提升泛化性并减轻专家标注负担。
AI中文摘要：
医疗人工智能（AI）正通过提供用于疾病诊断的稳健工具，彻底改变胸部X射线（CXR）图像的解读方式。然而，这些AI模型的有效性通常受限于其对大量特定任务标注数据的依赖，以及在不同临床环境间缺乏泛化能力。为了应对这些挑战，我们引入了CXRBase，这是一个旨在从无标签CXR图像中学习通用表示的基础模型，以促进对各种临床任务的高效适应。CXRBase最初使用自监督学习方法在104万张无标签CXR图像的大量数据集上进行训练。这种方法使模型能够在无需显式标签的情况下识别有意义的模式。在此初始阶段之后，CXRBase使用标注数据进行微调，以增强其在疾病检测中的性能，从而实现对胸部疾病的准确分类。CXRBase提供了一个泛化解决方案，以提高模型性能并减轻专家的标注工作量，从而实现基于胸部影像的广泛临床AI应用。
英文摘要：
Medical artificial intelligence (AI) is revolutionizing the interpretation of chest X-ray (CXR) images by providing robust tools for disease diagnosis. However, the effectiveness of these AI models is often limited by their reliance on large amounts of task-specific labeled data and their inability to generalize across diverse clinical settings. To address these challenges, we introduce CXRBase, a foundational model designed to learn versatile representations from unlabelled CXR images, facilitating efficient adaptation to various clinical tasks. CXRBase is initially trained on a substantial dataset of 1.04 million unlabelled CXR images using self-supervised learning methods. This approach allows the model to discern meaningful patterns without the need for explicit labels. After this initial phase, CXRBase is fine-tuned with labeled data to enhance its performance in disease detection, enabling accurate classification of chest diseases. CXRBase provides a generalizable solution to improve model performance and alleviate the annotation workload of experts to enable broad clinical AI applications from chest imaging.
