Deep learning based on ultrasound images assists breast lesion diagnosis in China: a multicenter diagnostic study

作者全名："Gu, Yang; Xu, Wen; Lin, Bin; An, Xing; Tian, Jiawei; Ran, Haitao; Ren, Weidong; Chang, Cai; Yuan, Jianjun; Kang, Chunsong; Deng, Youbin; Wang, Hui; Luo, Baoming; Guo, Shenglan; Zhou, Qi; Xue, Ensheng; Zhan, Weiwei; Zhou, Qing; Li, Jie; Zhou, Ping; Chen, Man; Gu, Ying; Chen, Wu; Zhang, Yuhong; Li, Jianchu; Cong, Longfei; Zhu, Lei; Wang, Hongyan; Jiang, Yuxin"

作者地址："[Gu, Yang; Xu, Wen; Li, Jianchu; Wang, Hongyan; Jiang, Yuxin] Chinese Acad Med Sci & Peking Union Med Coll, Peking Union Med Coll Hosp, Dept Ultrasound, 1 Shuai Fu Yuan, Beijing 100730, Peoples R China; [Lin, Bin; An, Xing; Cong, Longfei] Shenzhen Mindray Biomed Elect Co Ltd, Beijing Res Inst, Dept Med Imaging Adv Res, Beijing, Peoples R China; [Tian, Jiawei] Harbin Med Univ, Affiliated Hosp 2, Dept Ultrasound, Harbin, Peoples R China; [Ran, Haitao] Chongqing Med Univ, Affiliated Hosp 2, Dept Ultrasound, Chongqing, Peoples R China; [Ran, Haitao] Chongqing Key Lab Ultrasound Mol Imaging, Chongqing, Peoples R China; [Ren, Weidong] China Med Univ, Shengjing Hosp, Dept Ultrasound, Shenyang, Peoples R China; [Chang, Cai] Fudan Univ, Shanghai Canc Ctr, Dept Med Ultrasound, Shanghai, Peoples R China; [Yuan, Jianjun] Henan Prov Peoples Hosp, Dept Ultrasonog, Zhengzhou, Peoples R China; [Kang, Chunsong] Shanxi Acad Med Sci, Shanxi Bethune Hosp, Dept Ultrasound, Taiyuan, Peoples R China; [Deng, Youbin] Huazhong Univ Sci & Technol, Tongji Med Coll, Tongji Hosp, Dept Med Ultrasound, Wuhan, Peoples R China; [Wang, Hui] Jilin Univ, China Japan Union Hosp, Dept Ultrasound, Changchun, Peoples R China; [Luo, Baoming] Sun Yat Sen Univ, Sun Yat Sen Mem Hosp, Dept Ultrasound, Guangzhou, Peoples R China; [Guo, Shenglan] Guangxi Med Univ, Affiliated Hosp 1, Dept Ultrasonog, Nanning, Peoples R China; [Zhou, Qi] Xi An Jiao Tong Univ, Sch Med, Affiliated Hosp 2, Dept Med Ultrasound, Xian, Peoples R China; [Xue, Ensheng] Fujian Med Univ, Fujian Inst Ultrasound Med, Union Hosp, Dept Ultrasound, Fuzhou, Peoples R China; [Zhan, Weiwei] Shanghai Jiao Tong Univ, Sch Med, Ruijin Hosp, Dept Ultrasound, Shanghai, Peoples R China; [Zhou, Qing] Wuhan Univ, Renmin Hosp, Dept Ultrasonog, Wuhan, Peoples R China; [Li, Jie] Shandong Univ, Qilu Hosp, Dept Ultrasound, Jinan 250012, Peoples R China; [Zhou, Ping] Cent South Univ, Xiangya Hosp 3, Dept Ultrasound, Changsha, Peoples R China; [Chen, Man] Shanghai Jiao Tong Univ, Sch Med, Tongren Hosp, Dept Ultrasound Med, Shanghai, Peoples R China; [Gu, Ying] Guizhou Med Univ, Affiliated Hosp, Dept Ultrasonog, Guiyang, Peoples R China; [Chen, Wu] Shanxi Med Univ, Hosp 1, Dept Ultrasound, Taiyuan, Peoples R China; [Zhang, Yuhong] Dalian Med Univ, Hosp 2, Dept Ultrasound, Dalian, Peoples R China; [Zhu, Lei] Shenzhen Mindray Biomed Elect Co Ltd, Dept Med Imaging Adv Res, Shenzhen, Peoples R China"

通信作者："Wang, HY; Jiang, YX (通讯作者)，Chinese Acad Med Sci & Peking Union Med Coll, Peking Union Med Coll Hosp, Dept Ultrasound, 1 Shuai Fu Yuan, Beijing 100730, Peoples R China."

来源：INSIGHTS INTO IMAGING

ESI学科分类：CLINICAL MEDICINE

WOS号：WOS:000832727200001

JCR分区：Q1

影响因子：4.7

年份：2022

卷号：13

期号：1

开始页：　

结束页：　

文献类型：Article

关键词：Deep learning; Ultrasonography; Breast neoplasms; Diagnosis; Artificial intelligence

摘要："Background Studies on deep learning (DL)-based models in breast ultrasound (US) remain at the early stage due to a lack of large datasets for training and independent test sets for verification. We aimed to develop a DL model for differentiating benign from malignant breast lesions on US using a large multicenter dataset and explore the model's ability to assist the radiologists. Methods A total of 14,043 US images from 5012 women were prospectively collected from 32 hospitals. To develop the DL model, the patients from 30 hospitals were randomly divided into a training cohort (n = 4149) and an internal test cohort (n = 466). The remaining 2 hospitals (n = 397) were used as the external test cohorts (ETC). We compared the model with the prospective Breast Imaging Reporting and Data System assessment and five radiologists. We also explored the model's ability to assist the radiologists using two different methods. Results The model demonstrated excellent diagnostic performance with the ETC, with a high area under the receiver operating characteristic curve (AUC, 0.913), sensitivity (88.84%), specificity (83.77%), and accuracy (86.40%). In the comparison set, the AUC was similar to that of the expert (p = 0.5629) and one experienced radiologist (p = 0.2112) and significantly higher than that of three inexperienced radiologists (p < 0.01). After model assistance, the accuracies and specificities of the radiologists were substantially improved without loss in sensitivities. Conclusions The DL model yielded satisfactory predictions in distinguishing benign from malignant breast lesions. The model showed the potential value in improving the diagnosis of breast lesions by radiologists."

基金机构：Beijing Natural Science Foundation [7202156]; International Health Exchange and Cooperation Center; Peking Union Medical College Hospital [10023201900113]

基金资助正文："This work was supported by the Beijing Natural Science Foundation (Grant No. 7202156), the International Health Exchange and Cooperation Center (Grant No. ihecc2018C0032-2), and the Peking Union Medical College Hospital (Grant No. 10023201900113)."