文献速递甲状腺与浅表头颈US

基于甲状腺超声图像的深度学习影像组学鉴别良恶性甲状腺结节

Differential Diagnosis of Benign and Malignant Thyroid Nodules Using Deep Learning Radiomics of Thyroid Ultrasound Images.
PubMed 文献 · Eur J Radiol · 2020-04-12

该回顾性研究纳入1734例患者共1750个甲状腺结节的超声图像和细针穿刺活检结果,构建深度学习影像组学甲状腺(DLRT)模型,并与基础卷积神经网络、迁移学习模型及人类观察者比较。DLRT在训练集、内部验证集和外部验证集的AUC分别为0.96、0.95和0.97,显著优于其他深度学习模型(P<0.01)和人类观察者(P<0.001),且在不同超声仪器上应用时无显著差异。

要点

  • DLRT在训练集AUC 0.96(95%CI 0.94-0.98)、内部验证集0.95(0.93-0.97)、外部验证集0.97(0.95-0.99)。
  • DLRT诊断效能显著优于其他深度学习模型(P<0.01)和人类观察者(P<0.001)。
  • 不同超声仪器采集的图像应用DLRT无显著差异,提示模型稳健性。

诊断标准与关键数值

  • DLRT在训练集AUC为0.96(95%CI 0.94-0.98)。
  • DLRT在内部验证集AUC为0.95(95%CI 0.93-0.97)。
  • DLRT在外部验证集AUC为0.97(95%CI 0.95-0.99)。
  • DLRT的AUC显著优于其他深度学习模型(P<0.01)。
  • DLRT的AUC显著优于人类观察者(P<0.001)。

临床应用与阅片要点

  • DLRT在不同超声仪器采集的甲状腺超声图像上应用时无显著差异,原文未据此给出具体阅片建议。

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: We aimed to propose a highly automatic and objective model named deep learning Radiomics of thyroid (DLRT) for the differential diagnosis of benign and malignant thyroid nodules from ultrasound (US) images.

METHODS: We retrospectively enrolled and finally include US images and fine-needle aspiration biopsies from 1734 patients with 1750 thyroid nodules. A basic convolutional neural network (CNN) model, a transfer learning (TL) model, and a newly designed model named deep learning Radiomics of thyroid (DLRT) were used for the investigation. Their diagnostic accuracy was further compared with human observers (one senior and one junior US radiologist). Moreover, the robustness of DLRT over different US instruments was also validated. Analysis of receiver operating characteristic (ROC) curves were performed to calculate optimal area under it (AUC) for benign and malignant nodules. One observer helped to delineate the nodules.

RESULTS: AUCs of DLRT were 0.96 (95% confidence interval [CI]: 0.94-0.98), 0.95 (95% confidence interval [CI]: 0.93-0.97) and 0.97 (95% confidence interval [CI]: 0.95-0.99) in the training, internal and external validation cohort, respectively, which were significantly better than other deep learning models (P < 0.01) and human observers (P < 0.001). No significant difference was found when applying DLRT on thyroid US images acquired from different US instruments.

CONCLUSIONS: DLRT shows the best overall performance comparing with other deep learning models and human observers. It holds great promise for improving the differential diagnosis of benign and malignant thyroid nodules.

来源:Eur J Radiol,查看原文。版权归原作者所有。

引用

  1. Zhou H, Jin Y, Dai L, et al. Differential Diagnosis of Benign and Malignant Thyroid Nodules Using Deep Learning Radiomics of Thyroid Ultrasound Images. Eur J Radiol. 2020. PMID: 32339983. doi:10.1016/j.ejrad.2020.108992

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。