arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2510.00520cs.CV
收藏

CardioBench: 心脏超声基础模型是否能超越实验室?

CardioBench: Do Echocardiography Foundation Models Generalize Beyond the Lab?

Mohamed bin Zayed University of Artificial Intelligence(莫莫德·本·扎耶德人工智能大学)

Darya Taratynova, Ahmed Aly, Numan Saeed, Mohammad Yaqub

AI总结:

本文提出CardioBench,一个用于评估心脏超声基础模型的基准,通过统一多个公开数据集,评估不同模型在零样本、探测和对齐协议下的性能,揭示通用模型在功能任务上表现优异,但细粒度区分任务上存在不足。

摘要:

基础模型正在重塑医学影像,但其在心脏超声中的应用仍然有限,受制于对私有数据集的依赖,限制了可重复的比较。心脏超声具有独特的挑战,包括噪声采集、高帧冗余和有限的多样化公开数据集。为了解决这个问题,我们引入了CardioBench,一个全面的心脏超声基础模型基准。具体而言,CardioBench将八个公开可用的数据集统一为一个标准化的套件,涵盖四个回归和五个分类任务,覆盖功能、结构、诊断和视图识别终点。利用这一框架,我们评估了几种领先的基座模型,包括心脏专用、生物医学和通用编码器,在一致的零样本、探测和对齐协议下。我们的分析显示,尽管通用编码器转移良好,往往接近探测,但在视图分类和细微病理识别等细粒度区分任务上表现不佳。结果表明,能够捕捉心脏时间动态的模型在功能任务上表现最佳,而基于检索的方法在跨数据集的泛化上更加一致。通过发布预处理、分割和公开评估流程,CardioBench建立了可重复的参考点,以指导未来心脏超声和可能其他医学影像基础模型的架构设计。

英文摘要:

Foundation models are reshaping medical imaging, yet their application in echocardiography remains limited, hindered by a heavy reliance on private datasets that prevent reproducible comparison. Echocardiography poses unique challenges, including noisy acquisitions, high frame redundancy, and limited diverse public datasets. To address this, we introduce CardioBench, a comprehensive benchmark for echocardiography foundation models. Specifically, CardioBench unifies eight publicly available datasets into a standardized suite spanning four regression and five classification tasks, covering functional, structural, diagnostic, and view recognition endpoints. Leveraging this framework, we evaluate several leading foundation models, including cardiac-specific, biomedical, and general-purpose encoders, under consistent zero-shot, probing, and alignment protocols. Our analysis reveals that while general-purpose encoders transfer well and often close the gap with probing, they struggle significantly with fine-grained distinctions like view classification and subtle pathology recognition. Results indicate that models capturing temporal cardiac dynamics perform best on functional tasks, while retrieval-based approaches generalize more consistently across datasets. By releasing preprocessing, splits, and public evaluation pipelines, CardioBench establishes a reproducible reference point to guide the architectural design of future echocardiography and possibly other medical imaging foundation models.

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。

↑