文献速递泌尿生殖腹部MR

深度学习分析MRI预测膀胱癌肌层浸润:与VI-RADS对比

Predicting muscle invasion in bladder cancer by deep learning analysis of MRI: comparison with vesical imaging-reporting and data system.
PubMed 文献 · Eur Radiol · 2022-11-25

本研究纳入215个膀胱癌肿瘤,比较基于T2加权成像的深度学习模型与VI-RADS在预测肌层浸润中的诊断性能。结果显示DL模型在内外部验证集中AUC分别为0.963和0.861,对VI-RADS 2或3分肿瘤的诊断准确率高于放射科医生,且处理时间更短。

要点

  • DL模型在VI-RADS 2或3分肿瘤中诊断准确率显著高于放射科医生
  • DL模型内外部验证AUC分别为0.963和0.861,泛化性良好
  • DL方法处理时间约38-43秒,比医生阅片缩短超过100秒

核心结论

  • 基于T2加权成像的深度学习模型在预测膀胱癌肌层浸润方面优于使用VI-RADS的放射科医生,且处理时间更短、泛化性稳健。

研究设计与样本

  • 回顾性研究,共纳入215个肿瘤(中心1:129个训练、31个内部验证;中心2:55个外部验证),以病理检查为参考标准,构建深度卷积神经网络并与两组放射科医生的VI-RADS评分独立比较。

诊断标准与关键数值

  • DL模型、读者1和读者2在内外部验证集中的AUC分别为:内部验证集0.963、0.843、0.852;外部验证集0.861、0.808、0.876。
  • 在VI-RADS 2或3分的肿瘤中,外部验证集DL模型准确率高于读者1(0.886 vs. 0.600,p=0.006)和读者2(0.879 vs. 0.636,p=0.021)。

临床应用与阅片要点

  • DL模型有望辅助术前评估膀胱癌肌层浸润,尤其在VI-RADS 2或3分等诊断不确定的肿瘤中可提高准确率并缩短阅片时间。

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: To compare the diagnostic performance of a novel deep learning (DL) method based on T2-weighted imaging with the vesical imaging-reporting and data system (VI-RADS) in predicting muscle invasion in bladder cancer (MIBC).

METHODS: A total of 215 tumours (129 for training and 31 for internal validation, centre 1; 55 for external validation, centre 2) were included. MIBC was confirmed by pathological examination. VI-RADS scores were provided by two groups of radiologists (readers 1 and readers 2) independently. A deep convolutional neural network was constructed in the training set, and validation was conducted on the internal and external validation sets. ROC analysis was performed to evaluate the performance for MIBC diagnosis.

RESULTS: The AUCs of the DL model, readers 1, and readers 2 were as follows: in the internal validation set, 0.963, 0.843, and 0.852, respectively; in the external validation set, 0.861, 0.808, and 0.876, respectively. The accuracy of the DL model in the tumours scored VI-RADS 2 or 3 was higher than that of radiologists in the external validation set: for readers 1, 0.886 vs. 0.600, p = 0.006; for readers 2, 0.879 vs. 0.636, p = 0.021. The average processing time (38 s and 43 s in two validation sets) of the DL method was much shorter than the readers, with a reduction of over 100 s in both validation sets.

CONCLUSIONS: Compared to radiologists using VI-RADS, the DL method had a better diagnostic performance, shorter processing time, and robust generalisability, indicating good potential for diagnosing MIBC.

KEY POINTS: • The DL model shows robust performance for MIBC diagnosis in both internal and external validation. • The diagnostic performance of the DL model in the tumours scored VI-RADS 2 or 3 is better than that obtained by radiologists using VI-RADS. • The DL method shows potential in the preoperative assessment of MIBC.

来源:Eur Radiol,查看原文。版权归原作者所有。

引用

  1. Li, Cao, Lin, et al. Predicting muscle invasion in bladder cancer by deep learning analysis of MRI: comparison with vesical imaging-reporting and data system. Eur Radiol. 2022. PMID: 36434397. doi:10.1007/s00330-022-09272-7

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。