通过图像-图对比预训练学习通用医学图像表示
Learning Generalized Medical Image Representations through Image-Graph Contrastive Pretraining
AI总结：
为减轻医学图像标注负担，研究提出图像-图对比学习框架，结合胸部X光与放射报告提取的知识图谱，经实验验证在少样本等场景下性能优于图像-文本对比方法且接近放射科医生水平。
摘要：
基于深度学习的医学图像解读已展现出应用前景，但通常需要大量专家标注的数据集。为减轻这一标注负担，我们开发了图像-图对比学习（Image-Graph Contrastive Learning）框架，将胸部X光片与从放射科报告中自动提取的结构化报告知识图谱配对。该方法通过关系图卷积网络和Transformer注意力机制，对离散的图组件进行编码，这是其独特之处。在CheXpert数据集上的实验表明，在1%线性评估和少样本设置下，这种新颖的图编码策略使该框架优于现有采用图像-文本对比学习的方法，同时取得了与放射科医生相当的性能。通过利用未标注的配对图像和文本，本框架证明了结构化临床见解可增强医学图像的对比学习。该工作为减少对医学专家的标注需求、提升诊断精度、通过鲁棒的医学图像理解改善患者护理指明了方向。
英文摘要：
Medical image interpretation using deep learning has shown promise but often requires extensive expert-annotated datasets. To reduce this annotation burden, we develop an Image-Graph Contrastive Learning framework that pairs chest X-rays with structured report knowledge graphs automatically extracted from radiology notes. Our approach uniquely encodes the disconnected graph components via a relational graph convolution network and transformer attention. In experiments on the CheXpert dataset, this novel graph encoding strategy enabled the framework to outperform existing methods that use image-text contrastive learning in 1% linear evaluation and few-shot settings, while achieving comparable performance to radiologists. By exploiting unlabeled paired images and text, our framework demonstrates the potential of structured clinical insights to enhance contrastive learning for medical images. This work points toward reducing demands on medical experts for annotations, improving diagnostic precision, and advancing patient care through robust medical image understanding.
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。
