Deep learning-based computer-aided diagnosis system for the automatic detection and classification of lateral cervical lymph nodes on original ultrasound images of papillary thyroid carcinoma: a prospective diagnostic study

作者全名："Yuan, Yuquan; Pan, Bin; Mo, Hongbiao; Wu, Xing; Long, Zhaoxin; Yang, Zeyu; Zhu, Junping; Ming, Jing; Qiu, Lin; Sun, Yiceng; Yin, Supeng; Zhang, Fan"

作者地址："[Yuan, Yuquan; Pan, Bin; Mo, Hongbiao; Yang, Zeyu; Zhu, Junping; Ming, Jing; Qiu, Lin; Sun, Yiceng; Yin, Supeng; Zhang, Fan] Chongqing Gen Hosp, Dept Breast & Thyroid Surg, Chongqing, Peoples R China; [Yuan, Yuquan; Pan, Bin; Yang, Zeyu; Zhang, Fan] Chongqing Med Univ, Grad Sch Med, Chongqing, Peoples R China; [Wu, Xing; Long, Zhaoxin] Chongqing Univ, Coll Comp Sci, Chongqing, Peoples R China; [Yin, Supeng; Zhang, Fan] Chongqing Hosp Tradit Chinese Med, Chongqing, Peoples R China"

通信作者："Yin, SP; Zhang, F (通讯作者)，Chongqing Gen Hosp, Dept Breast & Thyroid Surg, Chongqing, Peoples R China.; Zhang, F (通讯作者)，Chongqing Med Univ, Grad Sch Med, Chongqing, Peoples R China.; Yin, SP; Zhang, F (通讯作者)，Chongqing Hosp Tradit Chinese Med, Chongqing, Peoples R China."

来源：ENDOCRINE

ESI学科分类：BIOLOGY & BIOCHEMISTRY

WOS号：WOS:001196262300004

JCR分区：Q2

影响因子：3.7

年份：2024

卷号：　

期号：　

开始页：　

结束页：　

文献类型：Article; Early Access

关键词：Artificial intelligence; Object detection; Lymphatic metastasis; Thyroid cancer; Neural network

摘要："PurposeThis study aims to develop a deep learning-based computer-aided diagnosis (CAD) system for the automatic detection and classification of lateral cervical lymph nodes (LNs) on original ultrasound images of papillary thyroid carcinoma (PTC) patients.MethodsA retrospective data set of 1801 cervical LN ultrasound images from 1675 patients with PTC and a prospective test set including 185 images from 160 patients were collected. Four different deep leaning models were trained and validated in the retrospective data set. The best model was selected for CAD system development and compared with three sonographers in the retrospective and prospective test sets.ResultsThe Deformable Detection Transformer (DETR) model showed the highest diagnostic efficacy, with a mean average precision score of 86.3% in the retrospective test set, and was therefore used in constructing the CAD system. The detection performance of the CAD system was superior to the junior sonographer and intermediate sonographer with accuracies of 86.3% and 92.4% in the retrospective and prospective test sets, respectively. The classification performance of the CAD system was better than all sonographers with the areas under the curve (AUCs) of 94.4% and 95.2% in the retrospective and prospective test sets, respectively.ConclusionsThis study developed a Deformable DETR model-based CAD system for automatically detecting and classifying lateral cervical LNs on original ultrasound images, which showed excellent diagnostic efficacy and clinical utility. It can be an important tool for assisting sonographers in the diagnosis process."

基金机构：Chongqing Medical Scientific Research Project(Joint Project of Chongqing Health Commission and Science and Technology Bureau)

基金资助正文："The authors thank all the sonographers in the Department of Medical Ultrasound, Chongqing General Hospital, for their help in collecting the imaging data and diagnosing the test data in this study."