文献速递神经外周血管头颈CT

基于深度学习在计算机断层扫描血管造影中全自动筛查颈动脉斑块:一项多中心研究

Deep learning-based fully automatic screening of carotid artery plaques in computed tomography angiography: a multicenter study.
PubMed 文献 · Clin Radiol · 2024-05-06

这项回顾性多中心研究纳入400例患者(中心Ⅰ 300例、中心Ⅱ 100例),由三位放射科医师共同标注颈动脉斑块并以修订后的钙化状态(非钙化、混合、钙化)为参考标准,开发并验证基于3D-UNet和ResUNet的两步深度学习系统用于CTA上颈动脉斑块的自动检测与三分类。内部验证集在3.0个假阳性/CTA扫描时敏感度为83.4%,外部验证集为78.9%;三分类Cohen kappa分别为0.728和0.703,表明该全自动算法用于颈动脉斑块检测和三分类具有可行性,可能有助于减轻放射科医师工作负荷。

要点

  • 内部验证集在3.0个假阳性/CTA扫描时敏感度83.4%,外部验证集78.9%。
  • 斑块检测F1-score内部验证集0.764、外部验证集0.769。
  • 三分类Cohen kappa内部验证集0.728、外部验证集0.703。

核心结论

  • 研究证明基于深度学习的全自动算法用于颈动脉斑块检测和三分类具有可行性,可能有助于减轻放射科医师的工作负荷。

研究设计与样本

  • 回顾性多中心研究,纳入400例患者(中心Ⅰ 300例、中心Ⅱ 100例),三位放射科医师共同标注斑块并以修订后的钙化状态(非钙化、混合、钙化)为参考标准;中心Ⅰ患者随机分为训练集和内部验证集,中心Ⅱ患者作为外部验证集;采用改良3D-UNet分割颈动脉区域,再用基于ResUNet的两步深度学习系统检测和分类斑块。

诊断标准与关键数值

  • 内部验证集在3.0个假阳性/CTA扫描时敏感度83.4%,最优阈值下F1-score 0.764,fROC曲线下面积0.756;外部验证集敏感度78.9%,F1-score 0.769,fROC曲线下面积0.738;三分类Cohen kappa内部验证集0.728、外部验证集0.703。

临床应用与阅片要点

  • 原文未据此给出推荐。

局限性

  • 原文未报告局限性。

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

AIM: To develop and validate a deep learning (DL) algorithm for the automated detection and classification of carotid artery plaques (CAPs) on computed tomography angiography (CTA) images.

MATERIALS AND METHODS: This retrospective study enrolled 400 patients (300 in the Center Ⅰ and 100 in Ⅱ). Three radiologists co-labeled CAPs, and their revised calcification status (noncalcified, mixed, and calcified) was regarded as ground truth. Center Ⅰ patients were randomly divided into training and internal validation datasets, while Center Ⅱ patients served as the external validation dataset. Carotid artery regions were segmented using a modified 3D-UNet network, followed by CAPs detection and classification using a ResUNet-based architecture in a two-step DL system. The DL model's detection and classification performance were evaluated on the validation dataset using precision-recall curve, free-response receiver operating characteristic (fROC) curve, Cohen's kappa, and ROC curve analysis.

RESULTS: The DL model had achieved 83.4% sensitivity at 3.0 false positives (FPs)/CTA scan in internal validation and 78.9% in external validation. F1-scores were 0.764 and 0.769 at the optimal threshold, and area under fROC curves were 0.756 and 0.738, respectively, indicating good overall accuracy for CAP detection. The DL model also showed good performance for the ternary classification of CAPs, with Cohen's kappa achieved 0.728 and 0.703 in both validation datasets.

CONCLUSION: This study demonstrated the feasibility of using a fully automated DL-based algorithm for the detection and ternary classification of CAPs, which could be helpful for the workloads of radiologists.

来源:Clin Radiol,查看原文。版权归原作者所有。

引用

  1. Zhai D, Liu R, Liu Y, et al. Deep learning-based fully automatic screening of carotid artery plaques in computed tomography angiography: a multicenter study. Clin Radiol. 2024. PMID: 38789330. doi:10.1016/j.crad.2024.04.015

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。