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

• Published in: European journal of radiology 2024-01, Vol.170, p.111197-111197, Article 111197
• Main Authors: Wu, Yu-ping, Wu, Lan, Ou, Jing, Cao, Jin-ming, Fu, Mao-yong, Chen, Tian-wu, Ouchi, Erika, Hu, Jiani
• Format: Article
• Language: English
• Subjects: Computed Tomography; Esophageal squamous cell carcinoma; Lymph node metastasis; Radiomics
• ISSN: 0720-048X; 1872-7727
• DOI: 10.1016/j.ejrad.2023.111197

•For the first time, LN CT radiomics model is developed to preoperatively detect LN+.•A combined radiomics model integrates features of ESCC and LN to detect LN+.•CT radiomics model of LN demonstrates good performance compared to the model of ESCC.•The combined model shows an excellent ability compared to models of LN and ESCC. To develop CT radiomics models of resectable esophageal squamous cell carcinoma (ESCC) and lymph node (LN) to preoperatively identify LN+. 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. 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). To preoperatively determine LN+, the combined model is superior to models of ESCC and LN alone.