EchoDino：面向全生命周期可迁移超声心动图分析的儿科基础模型
EchoDino: A pediatric foundation model for transferable echocardiographic analysis across the lifespan
浏览论文内容
中文总结 AI 辅助
EchoDino利用DINOv3框架在170万段无标注儿科超声心动图视频上自监督训练，通过MEMS采样提升视图分类、疾病检测、年龄估计等多项任务性能，并泛化至成人数据，为全生命周期心脏分析提供基础模型。
中文摘要 AI 辅助
超声心动图是最广泛使用的心脏成像方式，然而其解读需要整合来自整体解剖、局部结构和动态心脏运动的视觉证据。机器学习模型已能自动化单项任务，但它们通常为单一目的而构建，并依赖昂贵标注的数据集——这一障碍在儿科护理中尤为突出，因为儿科数据稀缺且解剖结构随年龄变化。在此，我们提出EchoDino，一个自监督的超声心动图基础模型，通过将DINOv3框架适配到来自170万段无标注儿科超声心动图视频的370万帧而创建。在编码器冻结的情况下，EchoDino生成捕捉全局上下文、局部解剖和密集空间细节的表征。我们引入了运动偏置熵最大化采样（MEMS）来选择用于视频级分析的最具信息量的帧。在九个儿科和成人数据集上，EchoDino优于强基线模型，将视图分类准确率从0.609提升至0.889，将结构性心脏病检测的受试者工作特征曲线下面积从0.811提升至0.872，同时将年龄估计误差从3.857年降至1.389年，实现了最佳分割精度并降低了射血分数误差。通过从无标签儿科数据泛化到成人超声心动图，EchoDino为全生命周期的心脏图像分析提供了一个多功能基础模型。
英文摘要
Echocardiography is the most widely used cardiac imaging modality, yet interpretation demands integrating visual evidence across global anatomy, localized structures and dynamic cardiac motion. Machine-learning models have automated individual tasks, but they are typically built for a single purpose and depend on expensively labeled datasets - a barrier particularly acute in pediatric care, where data are scarce and anatomy changes with age. Here we present EchoDino, a self-supervised foundation model for echocardiography, created by adapting the DINOv3 framework to 3.7 million frames from 1.7 million unlabeled pediatric echocardiography videos. With its encoder frozen, EchoDino produces representations that capture global context, local anatomy, and dense spatial detail. We introduce Motion-biased Entropy Maximization Sampling (MEMS) to select the most informative frames for video-level analysis. Across nine pediatric and adult datasets, EchoDino outperformed strong baseline models, raising view-classification accuracy from 0.609 to 0.889 and the area under the receiver operating characteristic curve for structural-heart-disease detection from 0.811 to 0.872, while also cutting age-estimation error from 3.857 to 1.389 years, achieving the best segmentation accuracy and lowering ejection-fraction errors. By generalizing from label-free pediatric data to adult echocardiography, EchoDino offers a versatile foundation for cardiac image analysis across the lifespan.
发表机构
- Rice University（莱斯大学）
- Baylor College of Medicine（贝勒医学院）
机构由 AI 辅助整理，请以论文原文为准。
