arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2410.23744cs.CV
收藏

EchoNarrator:为射血分数预测生成自然文本解释

EchoNarrator: Generating natural text explanations for ejection fraction predictions

University of Oslo(奥斯陆大学);GE Healthcare(GE医疗);GE HealthCare Technology & Innovation Center(GE医疗技术与创新中心)

Sarina Thomas, Qing Cao, Anna Novikova, Daria Kulikova, Guy Ben-Yosef

AI总结:

针对现有深度学习EF预测模型缺乏可解释性的问题,提出EchoNarrator模型,结合多帧左心室轮廓估计与属性计算,通过大语言模型生成自然语言解释,实现了媲美SOTA的EF预测性能与准确合理的解释输出。

摘要:

左心室(LV)射血分数(EF)被认为是诊断急性心力衰竭的最重要指标之一,可在心脏超声采集过程中进行估算。尽管近期深度学习研究已成功实现EF值的估算,但现有模型通常缺乏对预测结果的解释。然而,为临床测量预测提供清晰直观的解释,将提升心脏科医生对这些模型的信任度。本文中,我们探索了带有自然语言解释(NLE)的EF测量预测方法。我们提出的模型通过单次前向传播,结合多帧左心室轮廓估计,以及一组用于计算与射血分数相关的各类运动和形状属性的模块与流程,随后将这些属性输入大语言模型,生成类人风格的文本,帮助解释网络的输出结果。我们对模型的解释输出以及EF预测进行了实验评估,结果表明,该模型的EF预测性能可与当前最优水平相媲美,同时能为预测提供有意义且准确的自然语言解释。项目页面可访问https://github.com/guybenyosef/EchoNarrator 。

英文摘要:

Ejection fraction (EF) of the left ventricle (LV) is considered as one of the most important measurements for diagnosing acute heart failure and can be estimated during cardiac ultrasound acquisition. While recent successes in deep learning research successfully estimate EF values, the proposed models often lack an explanation for the prediction. However, providing clear and intuitive explanations for clinical measurement predictions would increase the trust of cardiologists in these models. In this paper, we explore predicting EF measurements with Natural Language Explanation (NLE). We propose a model that in a single forward pass combines estimation of the LV contour over multiple frames, together with a set of modules and routines for computing various motion and shape attributes that are associated with ejection fraction. It then feeds the attributes into a large language model to generate text that helps to explain the network's outcome in a human-like manner. We provide experimental evaluation of our explanatory output, as well as EF prediction, and show that our model can provide EF comparable to state-of-the-art together with meaningful and accurate natural language explanation to the prediction. The project page can be found at https://github.com/guybenyosef/EchoNarrator .

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。

↑