融合多种超声图像表示，提升肝病分类准确率
Learning from Complementary Ultrasound Representations for Liver Disease Classification
- 用物理引导与相位特征补充传统超声图像
- 准确率最高提升32.4%，F1-score提高91.2%
- 在不同人群和设备下均表现稳定，适合临床应用
使用超声检查区分非酒精性脂肪性肝炎（NASH）与非酒精性脂肪肝（NAFLD）仍具挑战，因组织变化细微且常规B模式成像信息有限。本文研究同一采集数据中互补的超声表示是否能提升分类效果。具体地，将传统B模式与物理引导、局部相位图像表示相结合，采用自监督掩码自编码器（MAEs）与图卷积网络（GCNs）进行评估。实验基于多中心梅奥诊所队列，包含125名患者共2,547例肝脏超声扫描。相比仅使用传统B模式，引入互补表示后分类性能持续提升，准确率最高提升32.4%，F1-score提升91.2%。性能增益在不同年龄、性别、种族、民族及采集站点间均一致可见。
原文摘要 · Abstract (English)
Differentiating non-alcoholic steatohepatitis (NASH) from non-alcoholic fatty liver disease (NAFLD) using ultrasound remains challenging due to subtle tissue alterations and the limited information available in conventional B-mode imaging. In this work, we investigate whether complementary ultrasound representations derived from the same acquisition can improve NASH versus NAFLD classification. Specifically, we combine conventional B-mode ultrasound with physics-guided and local phase-based image representations and evaluate their effectiveness using self-supervised masked autoencoders (MAEs) and graph convolutional networks (GCNs). Experiments were conducted on a multi-site Mayo Clinic cohort consisting of 2,547 liver ultrasound scans from 125 patients. Compared with conventional B-mode ultrasound alone, complementary ultrasound representations consistently improved classification performance, yielding gains of up to 32.4% in accuracy and 91.2% in F1-score. Furthermore, performance improvements were consistently observed across age groups, sex, race, ethnicity,and acquisition sites.
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。