基于深度学习的心肌超声造影图像质量自动评估:对心肌灌注评价的影响
本研究采用Resnet-18深度神经网络在内部和外部数据集上训练与测试,实现心肌超声造影图像质量的自动评估,评估涵盖左心室显影、声影和闪烁 adequacy 三方面。结果显示该网络预测耗时0.045秒/帧,内部验证和外部测试的F1与宏F1均大于90%,序列质量评分的组内相关系数分别为0.954和0.892;随着基于DNN的质量评分降低,被判定为不可解读的节段比例增加,不同超声医师间灌注评估的一致性下降,且同一医师两次扫描间评分差异越大,灌注评估一致性越低。结论认为该DNN可实时自动评估MCE质量,并可能减少超声医师间灌注评估的变异性。
要点
- DNN预测耗时0.045秒/帧,内部验证和外部测试质量评估F1及宏F1均大于90%。
- 序列质量评分的组内相关系数内部验证为0.954、外部测试为0.892。
- 基于DNN的质量评分越低,被判为不可解读的节段比例越高,不同医师间灌注评估一致性越差。
核心结论
- 基于Resnet-18的DNN可实时自动评估心肌超声造影图像质量,并可能减少超声医师间灌注评估的变异性。
研究设计与样本
- 采用Resnet-18模型在内部和外部数据集上训练与测试,质量评估涵盖左心室显影、声影和闪烁 adequacy 三方面,并分析DNN质量评分对两名高级、一名初级和一名新手超声医师灌注评估(正常、延迟或阻塞)的影响。
诊断标准与关键数值
- DNN在内部验证和外部测试中质量评估的F1与宏F1均大于90%。
- 序列质量评分的组内相关系数内部验证为0.954、外部测试为0.892。
- DNN预测时间成本为0.045秒/帧。
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: The image quality of myocardial contrast echocardiography (MCE) is critical for precise myocardial perfusion evaluation but challenging for echocardiographers. Differences in quality may lead to diagnostic heterogeneity. This study was aimed at achieving automatic MCE image quality assessment using a deep neural network (DNN) and investigating its impact on myocardial perfusion evaluation.
METHODS: The Resnet-18 model was used for training and testing on internal and external data sets. Quality assessment involved three aspects: left ventricular opacification (LVO), shadowing, and flash adequacy; the quality score was calculated based on image quality. This study explored the impact of the DNN-based quality score on perfusion evaluation (normal, delay or obstruction) by echocardiographers (two seniors, one junior and one novice). Additionally, the effect of the score difference between re-scans on perfusion evaluation was investigated.
RESULTS: The time cost for DNN prediction was 0.045 s/frame. In internal validation and external testing, the DNN achieved F1 and macro F1 scores >90% for quality assessment and had high intraclass correlation coefficients (0.954 and 0.892, respectively) in sequence quality scores. The proportion of segments deemed uninterpretable increased as the DNN-based quality score decreased. The agreement of perfusion assessment between one senior and others decreased as the quality score decreased. And the greater the score difference between the re-scans, the lower was the agreement on perfusion assessment by the same echocardiographer.
CONCLUSION: This study determined the effectiveness of DNN for real-time automatic MCE quality assessment. It has the potential to reduce the variability in perfusion evaluation among echocardiographers.
引用
- Li M, Zeng D, Fei H, et al. Automatic Myocardial Contrast Echocardiography Image Quality Assessment Using Deep Learning: Impact on Myocardial Perfusion Evaluation. Ultrasound Med Biol. 2023. PMID: 37495498. doi:10.1016/j.ultrasmedbio.2023.07.002
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。