CT Radiomics for Distinction of Human Epidermal Growth Factor Receptor 2 Negative Gastric Cancer

• Published in: Academic radiology Vol. 28; no. 3; p. e86
• Main Authors: Wang, Yue, Yu, Yang, Han, Wei, Zhang, Ying-Jing, Jiang, Lin, Xue, Hua-Dan, Lei, Jing, Jin, Zheng-Yu, Yu, Jian-Chun
• Format: Journal Article
• Language: English
• Published: United States 01.03.2021
• Subjects: Humans; Random Allocation; Receptor, ErbB-2; Retrospective Studies; ROC Curve; Stomach Neoplasms - diagnostic imaging; Stomach Neoplasms - genetics; Tomography, X-Ray Computed; HER2; Molecular targeted therapy; Gastric cancer
• ISSN: 1878-4046
• DOI: 10.1016/j.acra.2020.02.018

The purpose of this study was to investigate the role of computed tomography (CT) radiomics for the prediction of the human epidermal growth factor 2 (HER2) status in patients with gastric cancer. One hundred and thirty two consecutive patients with advanced gastric cancer undergoing radical gastrectomy were retrospectively reviewed. All patients received preoperative contrast CT examination, and immunohistochemistry results of their HER2 status were available. All the subjects were randomly divided into a training cohort (n = 90) and a test cohort (n = 42). Arterial phase (AP) and portal phase (PP) contrast CT images were retrieved for tumor segmentation and feature extraction. Receiver operating characteristics (ROC) curves and area under the curve (AUC) were used to evaluate the performance of the radiomics classifiers. Among the 132 patients, a total of 99 patients were HER2 negative, and the remaining 33 patients were border line or positive. The AP radiomics model could distinguish HER2-negative cases with an AUC of 0.756 (95% confidence interval [CI]: 0.656-0.840) in the training cohort, which was confirmed in the test cohort with AUC of 0.830 (95% CI: 0.678-0.930). The PP radiomics model showed AUCs of 0.715 (95% CI: 0.612-0.804) and 0.718 (95% CI: 0.554-0.849) in the training and test cohort for distinction of negative HER2 cases, respectively. Radiomics models based on standard-of-care CT images hold promise for distinguishing HER2-negative gastric cancer.