Deep learning based on ultrasound images predicting cervical lymph node metastasis in postoperative patients with differentiated thyroid carcinoma.

IF 1.8 4区 医学 Q3 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING
Fengjing Fan, Fei Li, Yixuan Wang, Tong Liu, Kesong Wang, Xiaoming Xi, Bei Wang
{"title":"Deep learning based on ultrasound images predicting cervical lymph node metastasis in postoperative patients with differentiated thyroid carcinoma.","authors":"Fengjing Fan, Fei Li, Yixuan Wang, Tong Liu, Kesong Wang, Xiaoming Xi, Bei Wang","doi":"10.1093/bjr/tqaf047","DOIUrl":null,"url":null,"abstract":"<p><strong>Objectives: </strong>To develop a deep learning (DL) model based on ultrasound (US) images of lymph nodes for predicting cervical lymph node metastasis (CLNM) in postoperative patients with differentiated thyroid carcinoma (DTC).</p><p><strong>Methods: </strong>Retrospective collection of 352 lymph nodes from 330 patients with cytopathology findings between June 2021 and December 2023 at our institution. The database was randomly divided into the training and test cohort at an 8:2 ratio. The DL basic model of longitudinal and cross-sectional of lymph nodes was constructed based on ResNet50 respectively, and the results of the two basic models were fused (1:1) to construct a longitudinal + cross-sectional DL model. Univariate and multivariate analysis were used to assess US features and construct a conventional US model. Subsequently, a combined model was constructed by integrating DL and US.</p><p><strong>Results: </strong>The diagnostic accuracy of the longitudinal + cross-sectional DL model was higher than that of longitudinal or cross-sectional alone. The AUC of the combined model (US+DL) was 0.855 (95%CI: 0.767-0.942), and the accuracy, sensitivity and specificity were 0.786 (95%CI: 0.671-0.875), 0.972 (95%CI: 0.855-0.999) and 0.588 (95%CI: 0.407-0.754), respectively. Compared with US and DL models, the IDI and NRI of the combined model are both positive.</p><p><strong>Conclusions: </strong>This study preliminary shows that the DL model based on US images of lymph nodes has a high diagnostic efficacy for predicting CLNM in postoperative patients with DTC, and the combined model of US+DL is superior to single conventional US and DL for predicting CLNM in this population.</p><p><strong>Advances in knowledge: </strong>We innovatively used DL of lymph node US images to predict the status of cervical lymph nodes in postoperative patients with DTC.</p>","PeriodicalId":9306,"journal":{"name":"British Journal of Radiology","volume":" ","pages":""},"PeriodicalIF":1.8000,"publicationDate":"2025-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"British Journal of Radiology","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1093/bjr/tqaf047","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING","Score":null,"Total":0}
引用次数: 0

Abstract

Objectives: To develop a deep learning (DL) model based on ultrasound (US) images of lymph nodes for predicting cervical lymph node metastasis (CLNM) in postoperative patients with differentiated thyroid carcinoma (DTC).

Methods: Retrospective collection of 352 lymph nodes from 330 patients with cytopathology findings between June 2021 and December 2023 at our institution. The database was randomly divided into the training and test cohort at an 8:2 ratio. The DL basic model of longitudinal and cross-sectional of lymph nodes was constructed based on ResNet50 respectively, and the results of the two basic models were fused (1:1) to construct a longitudinal + cross-sectional DL model. Univariate and multivariate analysis were used to assess US features and construct a conventional US model. Subsequently, a combined model was constructed by integrating DL and US.

Results: The diagnostic accuracy of the longitudinal + cross-sectional DL model was higher than that of longitudinal or cross-sectional alone. The AUC of the combined model (US+DL) was 0.855 (95%CI: 0.767-0.942), and the accuracy, sensitivity and specificity were 0.786 (95%CI: 0.671-0.875), 0.972 (95%CI: 0.855-0.999) and 0.588 (95%CI: 0.407-0.754), respectively. Compared with US and DL models, the IDI and NRI of the combined model are both positive.

Conclusions: This study preliminary shows that the DL model based on US images of lymph nodes has a high diagnostic efficacy for predicting CLNM in postoperative patients with DTC, and the combined model of US+DL is superior to single conventional US and DL for predicting CLNM in this population.

Advances in knowledge: We innovatively used DL of lymph node US images to predict the status of cervical lymph nodes in postoperative patients with DTC.

求助全文
约1分钟内获得全文 求助全文
来源期刊
British Journal of Radiology
British Journal of Radiology 医学-核医学
CiteScore
5.30
自引率
3.80%
发文量
330
审稿时长
2-4 weeks
期刊介绍: BJR is the international research journal of the British Institute of Radiology and is the oldest scientific journal in the field of radiology and related sciences. Dating back to 1896, BJR’s history is radiology’s history, and the journal has featured some landmark papers such as the first description of Computed Tomography "Computerized transverse axial tomography" by Godfrey Hounsfield in 1973. A valuable historical resource, the complete BJR archive has been digitized from 1896. Quick Facts: - 2015 Impact Factor – 1.840 - Receipt to first decision – average of 6 weeks - Acceptance to online publication – average of 3 weeks - ISSN: 0007-1285 - eISSN: 1748-880X Open Access option
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信