Preoperative CT radiomics of esophageal squamous cell carcinoma and lymph node to predict nodal disease with a high diagnostic capability

作者全名："Wu, Yu-ping; Wu, Lan; Ou, Jing; Cao, Jin-ming; Fu, Mao-yong; Chen, Tian-wu; Ouchi, Erika; Hu, Jiani"

作者地址："[Wu, Yu-ping; Wu, Lan; Chen, Tian-wu] Chongqing Med Univ, Affiliated Hosp 2, Dept Radiol, Chongqing 400010, Peoples R China; [Wu, Yu-ping; Ou, Jing; Cao, Jin-ming; Chen, Tian-wu] North Sichuan Med Coll, Affiliated Hosp, Med Imaging Key Lab Sichuan Prov, Nanchong, Sichuan, Peoples R China; [Wu, Yu-ping; Ou, Jing; Cao, Jin-ming; Ouchi, Erika] North Sichuan Med Coll, Affiliated Hosp, Dept Radiol, Nanchong, Sichuan, Peoples R China; [Cao, Jin-ming] Nanchong Cent Hosp, Clin Med Coll 2, North Sichuan Med Coll, Dept Radiol, Nanchong, Peoples R China; [Fu, Mao-yong] North Sichuan Med Coll, Dept Thorac Surg, Affiliated Hosp, Nanchong, Peoples R China; [Ouchi, Erika; Hu, Jiani] Wayne State Univ, Dept Radiol, Detroit, MI USA"

通信作者："Chen, TW (通讯作者)，Chongqing Med Univ, Affiliated Hosp 2, Dept Radiol, Chongqing 400010, Peoples R China."

来源：EUROPEAN JOURNAL OF RADIOLOGY

ESI学科分类：CLINICAL MEDICINE

WOS号：WOS:001125692400001

JCR分区：Q1

影响因子：3.3

年份：2024

卷号：170

期号：　

开始页：　

结束页：　

文献类型：Article

关键词：Radiomics; Esophageal squamous cell carcinoma; Lymph node metastasis; Computed Tomography

摘要："Purpose: To develop CT radiomics models of resectable esophageal squamous cell carcinoma (ESCC) and lymph node (LN) to preoperatively identify LN+. Materials and Methods: 299 consecutive patients with ESCC were enrolled in the study, 140 of whom were LN+ and 159 were LN-. Of the 299 patients, 249 (from the same hospital) were randomly divided into a training cohort (n = 174) and a test cohort (n = 75). The remaining 50 patients, from a second hospital, were assigned to an external validation cohort. In the training cohort, preoperative contrast-enhanced CT radiomics features of ESCC and LN were extracted, then integrated with clinical features to develop three models: ESCC, LN and combined. The performance of these models was assessed using area under receiver operating characteristic curve (AUC), and F-1 score, which were validated in both the test cohort and external validation cohort. Results: An ESCC model was developed for the training cohort utilizing the 8 tumor radiomics features, and an LN model was constructed using 9 nodal radiomics features. A combined model was constructed using both ESCC and LN extracted features, in addition to cT stage and LN+ distribution. This combined model had the highest predictive ability among the three models in the training cohort (AUC = 0.948, F1-score = 0.878). The predictive ability was validated in both the test and external validation cohorts (AUC = 0.885 and 0.867, F1-score = 0.816 and 0.773, respectively). Conclusion: To preoperatively determine LN+, the combined model is superior to models of ESCC and LN alone."

基金机构：National Natural Science Foundation of China [82271959]; Nanchong-University Coopera- tive Research Project [20SXQT0329]

基金资助正文："<BOLD>Funding</BOLD> This work was supported by the National Natural Science Foundation of China (grant no. 82271959) , and the Nanchong-University Coopera- tive Research Project (grant no: 20SXQT0329) ."