文献速递腹部MR

卷积神经网络自动评估肝胆期充分性可能优化检查时间

Convolutional neural network-automated hepatobiliary phase adequacy evaluation may optimize examination time.
PubMed 文献 · Eur J Radiol · 2020-01-14

本研究回顾性纳入2011-2018年钆塞酸二钠增强MRI肝胆期序列,开发并评估基于卷积神经网络的自动充分性评估算法,内部数据集AUC为0.97、外部数据集AUC为0.95;应用该算法可使48%(50/105)的检查缩短时间。

要点

  • CNN算法对肝胆期图像充分性分类的内部AUC为0.97、外部AUC为0.95。
  • 应用该算法后48%(50/105)的检查可能缩短检查时间。
  • 算法可辅助识别技术上欠佳的图像,避免诊断陷阱。

核心结论

  • 基于CNN的算法对肝胆期图像充分性分类的AUC高于95%,应用该算法可能缩短检查时间并帮助放射科医生识别技术上欠佳的图像,避免诊断陷阱。

研究设计与样本

  • 回顾性研究,纳入2011-2018年钆塞酸二钠增强MRI肝胆期序列,来自内部和外部数据集,共1408个序列、484例患者。
  • 算法由肝脏分割和分类CNN组成,输出充分性评分;以两名腹部放射科医生共识判定为参考标准进行训练和验证。
  • 采用受试者工作特征(ROC)分析和曲线下面积(AUC)评估算法性能,读者一致性用Cohen kappa评估。

诊断标准与关键数值

  • 读者间kappa一致性内部数据集为0.67,外部数据集为0.80。
  • 算法AUC内部数据集为0.97(0.96-0.99),外部数据集为0.95(0.92-0.96),两者无显著差异(p=0.24)。
  • 应用算法后48%(50/105)的检查可能缩短检查时间。

临床应用与阅片要点

  • 原文结论认为该算法可能缩短检查时间并帮助放射科医生识别技术上欠佳的图像,避免诊断陷阱。

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

PURPOSE: To develop and evaluate the performance of a fully-automated convolutional neural network (CNN)-based algorithm to evaluate hepatobiliary phase (HBP) adequacy of gadoxetate disodium (EOB)-enhanced MRI. Secondarily, we explored the potential of the proposed CNN algorithm to reduce examination length by applying it to EOB-MRI examinations.

METHODS: We retrospectively identified EOB-enhanced MRI-HBP series from examinations performed 2011-2018 (internal and external datasets). Our algorithm, comprising a liver segmentation and classification CNN, produces an adequacy score. Two abdominal radiologists independently classified series as adequate or suboptimal. The consensus determination of HBP adequacy was used as ground truth for CNN model training and validation. Reader agreement was evaluated with Cohen's kappa. Performance of the algorithm was assessed by receiver operating characteristics (ROC) analysis and computation of the area under the ROC curve (AUC). Potential examination duration reduction was evaluated descriptively.

RESULTS: 1408 HBP series from 484 patients were included. Reader kappa agreement was 0.67 (internal dataset) and 0.80 (external dataset). AUCs were 0.97 (0.96-0.99) for internal and 0.95 (0.92-96) for external and were not significantly different from each other (p = 0.24). 48 % (50/105) examinations could have been shorter by applying the algorithm.

CONCLUSION: A proposed CNN-based algorithm achieves higher than 95 % AUC for classifying HBP images as adequate versus suboptimal. The application of this algorithm could potentially shorten examination time and aid radiologists in recognizing technically suboptimal images, avoiding diagnostic pitfalls.

来源:Eur J Radiol,查看原文。版权归原作者所有。

引用

  1. Cunha GM, Hasenstab KA, Higaki A, et al. Convolutional neural network-automated hepatobiliary phase adequacy evaluation may optimize examination time. Eur J Radiol. 2020. PMID: 31958630. doi:10.1016/j.ejrad.2020.108837

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。