文献速递神经外周血管US

基于颈动脉横切面B型超声视频的深度学习模型诊断颈动脉斑块:一项前瞻性多中心研究

Deep learning based on carotid transverse B-mode scan videos for the diagnosis of carotid plaque: a prospective multicenter study.
PubMed 文献 · Eur Radiol · 2022-12-13

这项前瞻性多中心研究在五家医院开发了CaroNet-Dynamic深度学习模型,基于颈动脉横切面超声视频自动检测斑块,以专家标注为参考标准。模型在内部和外部测试集上敏感度分别为87.03%和94.17%,特异度分别为82.07%和74.04%,AUC分别为0.845和0.841,且能显著提升低年资放射科医生的诊断敏感度(最大从46.3%提升至94.44%)。

要点

  • 深度学习模型基于颈动脉横切面超声视频可自动检测斑块,外部测试集敏感度94.17%、特异度74.04%。
  • 模型性能在不同斑块特征和超声扫描系统间无显著差异,提示稳健性较好。
  • 低年资医生借助模型辅助后敏感度最大从46.3%提升至94.44%,可改善临床检出。

核心结论

  • 基于真实检查颈动脉横切面超声视频的深度学习模型对斑块检测具有稳健性能,并显著提升低年资放射科医生的诊断表现。

研究设计与样本

  • 前瞻性多中心研究,在五家医院纳入825例患者的1647段颈动脉横切面超声视频,以具有10年以上颈动脉超声评估经验的专家标注为参考标准。
  • 模型在内部测试集和多中心外部测试集上评估性能,并分析不同斑块特征和超声扫描系统下的稳健性。
  • 通过比较低年资放射科医生(约1年颈动脉超声评估经验)在有和无深度学习模型辅助下的诊断,评估临床适用性。

诊断标准与关键数值

  • 内部测试集:敏感度87.03%,特异度82.07%,AUC 0.845。
  • 多中心外部测试集:敏感度94.17%,特异度74.04%,AUC 0.841。
  • 低年资放射科医生使用深度学习模型后敏感度显著提升,最大从46.3%提升至94.44%。

临床应用与阅片要点

  • 阅片时可借助深度学习模型对颈动脉横切面超声视频进行斑块自动检测,尤其有助于低年资医生提高敏感度、减少漏诊。
  • 模型在不同斑块特征和扫描系统下性能无显著差异,但外部测试集特异度74.04%提示仍需结合医生判断以控制假阳性。

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

OBJECTIVES: Accurate detection of carotid plaque using ultrasound (US) is essential for preventing stroke. However, the diagnostic performance of junior radiologists (with approximately 1 year of experience in carotid US evaluation) is relatively poor. We thus aim to develop a deep learning (DL) model based on US videos to improve junior radiologists' performance in plaque detection.

METHODS: This multicenter prospective study was conducted at five hospitals. CaroNet-Dynamic automatically detected carotid plaque from carotid transverse US videos allowing clinical detection. Model performance was evaluated using expert annotations (with more than 10 years of experience in carotid US evaluation) as the ground truth. Model robustness was investigated on different plaque characteristics and US scanning systems. Furthermore, its clinical applicability was evaluated by comparing the junior radiologists' diagnoses with and without DL-model assistance.

RESULTS: A total of 1647 videos from 825 patients were evaluated. The DL model yielded high performance with sensitivities of 87.03% and 94.17%, specificities of 82.07% and 74.04%, and areas under the receiver operating characteristic curve of 0.845 and 0.841 on the internal and multicenter external test sets, respectively. Moreover, no significant difference in performance was noted among different plaque characteristics and scanning systems. Using the DL model, the performance of the junior radiologists improved significantly, especially in terms of sensitivity (largest increase from 46.3 to 94.44%).

CONCLUSIONS: The DL model based on US videos corresponding to real examinations showed robust performance for plaque detection and significantly improved the diagnostic performance of junior radiologists.

KEY POINTS: • The deep learning model based on US videos conforming to real examinations showed robust performance for plaque detection. • Computer-aided diagnosis can significantly improve the diagnostic performance of junior radiologists in clinical practice.

来源:Eur Radiol,查看原文。版权归原作者所有。

引用

  1. Liu, Zhou, Lin, et al. Deep learning based on carotid transverse B-mode scan videos for the diagnosis of carotid plaque: a prospective multicenter study. Eur Radiol. 2022. PMID: 36512047. doi:10.1007/s00330-022-09324-y

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。