ScholarMate
English简体中文繁體中文
客服热线:400-1616-289
登录注册
期刊论文

Deep learning for the diagnosis of suspicious thyroid nodules based on multimodal ultrasound images

Tao, Yi; Yu, Yanyan*; Wu, Tong; Xu, Xiangli; Dai, Quan; Kong, Hanqing; Zhang, Lei; Yu, Weidong; Leng, Xiaoping; Qiu, Weibao; Tian, Jiawei*哈尔滨医科大学; 中国科学院
Frontiers in Oncology2022-11-8DOI: 10.3389/fonc.2022.1012724
4被引7阅读
引用收藏
分享

摘要

ObjectivesThis study aimed to differentially diagnose thyroid nodules (TNs) of Thyroid Imaging Reporting and Data System (TI-RADS) 3-5 categories using a deep learning (DL) model based on multimodal ultrasound (US) images and explore its auxiliary role for radiologists with varying degrees of experience. MethodsPreoperative multimodal US images of 1,138 TNs of TI-RADS 3-5 categories were randomly divided into a training set (n = 728), a validation set (n = 182), and a test set (n = 228) in a 4:1:1.25 ratio. Grayscale US (GSU), color Doppler flow imaging (CDFI), strain elastography (SE), and region of interest mask (Mask) images were acquired in both transverse and longitudinal sections, all of which were confirmed by pathology. In this study, fivefold cross-validation was used to evaluate the performance of the proposed DL model. The diagnostic performance of the mature DL model and radiologists in the test set was compared, and whether DL could assist radiologists in improving diagnostic performance was verified. Specificity, sensitivity, accuracy, positive predictive value, negative predictive value, and area under the receiver operating characteristics curves (AUC) were obtained. ResultsThe AUCs of DL in the differentiation of TNs were 0.858 based on (GSU + SE), 0.909 based on (GSU + CDFI), 0.906 based on (GSU + CDFI + SE), and 0.881 based (GSU + Mask), which were superior to that of 0.825-based single GSU (p = 0.014, p< 0.001, p< 0.001, and p = 0.002, respectively). The highest AUC of 0.928 was achieved by DL based on (G + C + E + M)US, the highest specificity of 89.5% was achieved by (G + C + E)US, and the highest accuracy of 86.2% and sensitivity of 86.9% were achieved by DL based on (G + C + M)US. With DL assistance, the AUC of junior radiologists increased from 0.720 to 0.796 (p< 0.001), which was slightly higher than that of senior radiologists without DL assistance (0.796 vs. 0.794, p > 0.05). Senior radiologists with DL assistance exhibited higher accuracy and comparable AUC than that of DL based on GSU (83.4% vs. 78.9%, p = 0.041; 0.822 vs. 0.825, p = 0.512). However, the AUC of DL based on multimodal US images was significantly higher than that based on visual diagnosis by radiologists (p< 0.05). ConclusionThe DL models based on multimodal US images showed exceptional performance in the differential diagnosis of suspicious TNs, effectively increased the diagnostic efficacy of TN evaluations by junior radiologists, and provided an objective assessment for the clinical and surgical management phases that follow.

学科与关键词

关键词
thyroid noduledeep learningmultimodalultrasounddiagnosis
相关
加载中…
  • The value of S-Detect in improving the diagnostic performance of radiologists for the differential diagnosis of thyroid nodules
    Wei, Qi; Zeng, Shu-E; Wang, Li-Ping; Yan, Yu-Jing; Wang, Ting; Xu, Jian-Wei; Zhang, Meng-Yi; Lv, Wen-Zhi; Cui, Xin-Wu*; Dietrich, Christoph F.Medical Ultrasonography, 2020, 22(4): 415-423.被引 22
  • The auxiliary diagnosis of thyroid echogenic foci based on a deep learning segmentation model: A two-center study
    Liu, Yuanzhen; Chen, Chen; Wang, Kai; Zhang, Maoliang; Yan, Yuqi; Sui, Lin; Yao, Jincao; Zhu, Xi; Wang, Hui; Pan, Qianmeng; Wang, Yifan*; Liang, Ping*; Xu, Dong*EUROPEAN JOURNAL OF RADIOLOGY, 2023, 167: 111033.被引 4
  • An Artificial Intelligence Model Based on ACR TI-RADS Characteristics for US Diagnosis of Thyroid Nodules
    Chen, Yufan; Gao, Zixiong; He, Yanni; Mai, Wuping; Li, Jinhua; Zhou, Meijun; Li, Sushu; Yi, Wenhong; Wu, Shuyu; Bai, Tong; Zhang, Ning; Zeng, Weibo; Lu, Yao; Liu, Hongmei*RADIOLOGY, 2022, 303(3): 613-619.被引 15
查看全部 →

发表信息

论文状态
公开发表
期刊
Frontiers in Oncology
发表日期
2022-11-08
卷期
第 12 卷
页码
1012724
DOI
10.3389/fonc.2022.1012724
期刊等级
3区
成果收录
SCIE
资助标注
National Key R&D Program of China [2018YFA0701400]; Shenzhen Universities Stabilization Support Program [20200812144239001]; National Nature Science Foundation Grants of China [12174267, 62022086, 11874382, 81827802]; Shenzhen Foundation [JCYJ20200109114237902, SGDX2020110309400200, ZDSYS201802061806314]; CAS research projects [KFJ-PTXM-012, 2011DP173015]; Natural Science Foundation of Guangdong Province [2022A1515011343, 2020B1111130002, 2020B1212060051]; Youth Innovation Promotion Association [CAS 2018391]

作者

  • T

    Tao, Yi (第一作者)

    2 · harbin med univ

  • Y

    Yu, Yanyan (通讯)

    shenzhen univ

查看全部 11 位作者收起作者
  • W

    Wu, Tong

    2 · harbin med univ

  • X

    Xu, Xiangli

  • D

    Dai, Quan

    2 · harbin med univ

  • K

    Kong, Hanqing

    2 · harbin med univ

  • Z

    Zhang, Lei

    2 · harbin med univ

  • Y

    Yu, Weidong

    2 · harbin med univ

  • L

    Leng, Xiaoping

    2 · harbin med univ

  • Q

    Qiu, Weibao

    chinese acad sci

  • T

    Tian, Jiawei (通讯)

    2 · harbin med univ

登录解锁更多功能

  • 收藏这篇,随时在“我的 · 收藏”找回
  • 认领你的成果,生成推广素材
  • 关注作者获取最新成果
  • 加入项目组、协同写作
注册 / 登录

产品服务

  • 科研之友
  • 创新城
  • 科创云

服务支持

  • 帮助中心
  • 隐私政策
  • 服务条款

联系方式

在线客服:【】
客服热线:400-1616-289
电子邮箱:support@scholarmate.com

关注或下载科研之友

微信二维码
微信公众号
客户端下载二维码
下载客户端
科研成果科研人员科研机构科研动态爱瑞思软件

©2026 深圳市科研之友网络服务有限公司

公安备案图标粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417