文献速递甲状腺与浅表头颈US

基于深度学习分割模型的甲状腺高回声灶辅助诊断:一项双中心研究

The auxiliary diagnosis of thyroid echogenic foci based on a deep learning segmentation model: A two-center study.
PubMed 文献 · Eur J Radiol · 2023-08-11

该双中心回顾性研究收集2724例超声扫查(含1038个经病理确诊的高回声灶结节),开发三种深度学习分割模型并选出最优者构建AI辅助诊断软件,比较不同年资放射科医生使用与不使用辅助策略时的诊断效能。结果显示辅助策略可提高初学者、初级和高级医生的AUROC,其中初学者提升最明显。

要点

  • DeepLabV3+(骨干MobileNetV2)分割表现最优,MIoU=0.891、MPA=0.945、Dice=0.919。
  • 放射科初学者使用AI辅助策略的合并AUROC从0.551升至0.693。
  • 初级医生合并AUROC从0.674升至0.757,高级医生从0.745升至0.813。

核心结论

  • 基于超声静态图像的深度学习辅助诊断模型可提高放射科医生和放射科学生对甲状腺高回声灶的识别效能。

研究设计与样本

  • 回顾性研究,从两个独立机构共收集2724例超声扫查,包含1038个经病理确诊的高回声灶结节。

关键影像表现/征象

  • 结节区域含高回声灶,模型对结节区域进行分割并提取特征。
  • 评估指标为MIoU、MPA和Dice系数。
  • 机构2分析中DeepLabV3+(骨干MobileNetV2)分割表现最优,MIoU=0.891、MPA=0.945、Dice=0.919。

诊断标准与关键数值

  • 分割模型性能指标:DeepLabV3+(骨干MobileNetV2)MIoU=0.891、MPA=0.945、Dice=0.919。
  • 放射科初学者合并AUROC:使用AI辅助策略0.693(95%CI 0.595-0.791)vs 不使用0.551(95%CI 0.445-0.657)。
  • 初级医生合并AUROC:使用辅助策略0.757(95%CI 0.666-0.848)vs 不使用0.674(95%CI 0.574-0.774)。
  • 高级医生合并AUROC:使用辅助策略0.813(95%CI 0.730-0.896)vs 不使用0.745(95%CI 0.652-0.838)。

临床应用与阅片要点

  • 作者认为AI辅助策略可提高放射科医生和放射科学生识别甲状腺高回声灶的效能。
  • 使用AI辅助策略后,高级医生和初学者的准确率、敏感度、特异度、阳性预测值和阴性预测值均有不同程度提高。

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

OBJECTIVE: The aim of this study is to develop AI-assisted software incorporating a deep learning (DL) model based on static ultrasound images. The software aims to aid physicians in distinguishing between malignant and benign thyroid nodules with echogenic foci and to investigate how the AI-assisted DL model can enhance radiologists' diagnostic performance.

METHODS: For this retrospective study, a total of 2724 ultrasound (US) scans were collected from two independent institutions, encompassing 1038 echogenic foci nodules. All echogenic foci were confirmed by pathology. Three DL segmentation models (DeepLabV3+, U-Net, and PSPNet) were developed, with each model using two different backbones to extract features from the nodular regions with echogenic foci. Evaluation indexes such as Mean Intersection over Union (MIoU), Mean Pixel Accuracy (MPA), and Dice coefficients were employed to assess the performance of the segmentation model. The model demonstrating the best performance was selected to develop the AI-assisted diagnostic software, enabling radiologists to benefit from AI-assisted diagnosis. The diagnostic performance of radiologists with varying levels of seniority and beginner radiologists in assessing high-echo nodules was then compared, both with and without the use of auxiliary strategies. The area under the receiver operating characteristic curve (AUROC) was used as the primary evaluation index, both with and without the use of auxiliary strategies.

RESULTS: In the analysis of Institution 2, the DeepLabV3+ (backbone is MobileNetV2 exhibited optimal segmentation performance, with MIoU = 0.891, MPA = 0.945, and Dice = 0.919. The combined AUROC (0.693 [95% CI 0.595-0.791]) of radiology beginners using AI-assisted strategies was significantly higher than those without such strategies (0.551 [0.445-0.657]). Additionally, the combined AUROC of junior physicians employing adjuvant strategies improved from 0.674 [0.574-0.774] to 0.757 [0.666-0.848]. Similarly, the combined AUROC of senior physicians increased slightly, rising from 0.745 [0.652-0.838] to 0.813 [0.730-0.896]. With the implementation of AI-assisted strategies, the accuracy, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of both senior physicians and beginners in the radiology department underwent varying degrees of improvement.

CONCLUSIONS: This study demonstrates that the DL-based auxiliary diagnosis model using US static images can improve the performance of radiologists and radiology students in identifying thyroid echogenic foci.

来源:Eur J Radiol,查看原文。版权归原作者所有。

引用

  1. Liu Y, Chen C, Wang K, et al. The auxiliary diagnosis of thyroid echogenic foci based on a deep learning segmentation model: A two-center study. Eur J Radiol. 2023. PMID: 37595399. doi:10.1016/j.ejrad.2023.111033

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。