让心脏超声模型自动生成解释性文字，提升医生信任度
EchoNarrator: Generating natural text explanations for ejection fraction predictions
- 单次推理同时完成心室轮廓估计与运动特征计算
- 生成的自然语言解释准确率高，预测性能媲美顶尖模型
- 适合临床辅助诊断场景，帮助医生理解AI决策逻辑
左心室射血分数（EF）是急性心力衰竭诊断的关键指标，可在心脏超声检查中估算。尽管深度学习模型已能有效预测EF，但缺乏对预测结果的可解释性。为提升心脏病学家对模型的信任，本文提出一种生成自然语言解释（NLE）的框架。该模型在一次前向传播中，联合估计多帧图像中的左心室轮廓，并通过一系列模块计算与EF相关的运动与形状特征。这些特征随后输入大语言模型，生成类人表达的解释文本。实验表明，该模型在预测性能上达到当前最优水平的同时，能够生成准确且有意义的自然语言解释。项目主页见：https://github.com/guybenyosef/EchoNarrator。
原文摘要 · Abstract (English)
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 .
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。