基于深度学习的二维超声心动图区域图像质量评分
研究开发并比较三种自动估计超声心动图区域图像质量的方法:基于像素的gCNR度量、基于U-Net的局部图像相干性预测和端到端深度卷积网络,以三位有经验心脏病学家的手动区域质量标注为参考。结果显示端到端学习模型与标注的Spearman相关性ρ=0.69,最佳,与观察者间相关性ρ=0.63相当;相干性方法ρ=0.58,优于经典度量且更通用;gCNR性能较差,ρ=0.24。
要点
- 端到端深度卷积网络对区域图像质量的预测最准确,与手动标注的Spearman相关性ρ=0.69,与观察者间相关性ρ=0.63相当。
- 基于局部图像相干性的方法ρ=0.58,优于经典gCNR度量,且比端到端方法更具通用性。
- 经典像素级gCNR度量在本研究中性能较差,与标注的Spearman相关性仅为ρ=0.24。
核心结论
- 深度卷积网络提供了最准确的区域质量预测,而基于相干性的方法提供了更通用的解决方案;gCNR在本研究中效果有限。
研究设计与样本
- 开发并比较三种自动估计超声心动图区域图像质量的方法,以三位有经验心脏病学家提供的区域质量手动标注为参考标准进行评估。
诊断标准与关键数值
- gCNR度量与手动标注的Spearman相关性ρ=0.24。
- 端到端学习模型与手动标注的Spearman相关性ρ=0.69,与观察者间相关性ρ=0.63相当。
- 基于相干性的方法与手动标注的Spearman相关性ρ=0.58。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
英文原文(摘要)· 点击展开
OBJECTIVE: To develop and compare methods to automatically estimate regional ultrasound image quality for echocardiography separate from view correctness.
METHODS: Three methods for estimating image quality were developed: (i) classic pixel-based metric: the generalized contrast-to-noise ratio (gCNR), computed on myocardial segments (region of interest) and left ventricle lumen (background), extracted by a U-Net segmentation model; (ii) local image coherence: the average local coherence as predicted by a U-Net model that predicts image coherence from B-mode ultrasound images at the pixel level; (iii) deep convolutional network: an end-to-end deep-learning model that predicts the quality of each region in the image directly. These methods were evaluated against manual regional quality annotations provided by three experienced cardiologists.
RESULTS: The results indicated poor performance of the gCNR metric, with Spearman correlation to annotations of ρ = 0.24. The end-to-end learning model obtained the best result, ρ = 0.69, comparable to the inter-observer correlation, ρ = 0.63. Finally, the coherence-based method, with ρ = 0.58, out-performed the classical metrics and was more generic than the end-to-end approach.
CONCLUSION: The deep convolutional network provided the most accurate regional quality prediction, while the coherence-based method offered a more generalizable solution. gCNR showed limited effectiveness in this study. The image quality prediction tool is available as an open-source Python library at https://github.com/GillesVanDeVyver/arqee.
引用
- Vyver GV, Måsøy SE, Dalen H, et al. Regional Image Quality Scoring for 2-D Echocardiography Using Deep Learning. Ultrasound Med Biol. 2025. PMID: 39864961. doi:10.1016/j.ultrasmedbio.2024.12.008
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。