Enhanced CT-based radiomics predicts pathological complete response after neoadjuvant chemotherapy for advanced adenocarcinoma of the esophagogastric junction: a two-center study

作者：Wenpeng Huang, Liming Li, Siyun Liu, Yunjin Chen, Chenchen Liu, Yijing Han, Fang Wang, Pengchao Zhan, Huiping Zhao, Jing Li, Jianbo Gao · 发表于：Insights into Imaging · 年份：2022 · DOI：10.1186/s13244-022-01273-w · 被引用次数：18 · 研究领域：Radiomics and Machine Learning in Medical Imaging、Esophageal Cancer Research and Treatment、Gastric Cancer Management and Outcomes

PURPOSE: This study aimed to develop and validate CT-based models to predict pathological complete response (pCR) after neoadjuvant chemotherapy (NAC) for advanced adenocarcinoma of the esophagogastric junction (AEG). METHODS: Pre-NAC clinical and imaging data of AEG patients who underwent surgical resection after preoperative-NAC at two centers were retrospectively collected from November 2014 to September 2020. The dataset included training (n = 60) and external validation groups (n = 32). Three models, including CT-based radiomics, clinical and radiomics-clinical combined models, were established to differentiate pCR (tumor regression grade (TRG) = grade 0) and nonpCR (TRG = grade 1-3) patients. For the radiomics model, tumor-region-based radiomics features in the arterial and venous phases were extracted and selected. The naïve Bayes classifier was used to establish arterial- and venous-phase radiomics models. The selected candidate clinical factors were used to establish a clinical model, which was further incorporated into the radiomics-clinical combined model. ROC analysis, calibration and decision curves were used to assess the model performance. RESULTS: For the radiomics model, the AUC values obtained using the venous data were higher than those obtained using the arterial data (training: 0.751 vs. 0.736; validation: 0.768 vs. 0.750). Borrmann typing, tumor thickness and degree of differentiation were utilized to establish the clinical model (AUC-training: 0.753; AU...