Rui Wang1, Huan Liu2, Pan Liang1, Huiping Zhao1, Liming Li1, Jianbo Gao3. 1. Department of Radiology, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, 450052, Henan, China. 2. Advanced Application Team, GE Healthcare, Shanghai, 201203, China. 3. Department of Radiology, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, 450052, Henan, China. Electronic address: jianbogao5678@163.com.
Abstract
PURPOSE: To develop and evaluate a CT-based radiomics nomogram for differentiating gastric neuroendocrine carcinomas (NECs) from gastric adenocarcinomas (ADCs). METHODS: CT images of 63 patients with gastric NECs were collected retrospectively, and 63 patients with gastric ADCs were selected as the control group. Univariate analysis was used to identify the significant factors of clinical characteristics and CT findings for differentiating gastric NECs from ADCs. Radiomics analysis was applied to CT images of unenhanced, arterial phase and venous phase, respectively. A radiomics nomogram incorporating the radiomics signature and the subjective CT findings was developed and its diagnostic ability was evaluated. The diagnostic performances of CT findings model, radiomics signature and radiomics nomogram were compared using DeLong test. RESULTS: The tumor margin and lymph node (LN) metastasis were independent predictors for differentiating gastric NECs from ADCs. The radiomics signature based on venous phase presented superior AUC of 0.798 [95 % confidence interval (CI), 0.657-0.938] in validation cohort. The nomogram incorporated the radiomics signature, tumor margin and LN metastasis showed AUCs of 0.821 (95 %CI: 0.725-0.895) in the primary cohort and 0.809 (95 %CI: 0.649-0.918) in the validation cohort. Moreover, the radiomics nomogram showed good discrimination and calibration. The diagnostic performance of CT findings model was significantly lower than that of radiomics nomogram (p = 0.001) and radiomics signature (p = 0.025). CONCLUSIONS: Radiomics analysis exhibited good performance in differentiating gastric NECs from ADCs, and the radiomics nomogram may have significant clinical implications on preoperative detection of gastric malignant tumors.
PURPOSE: To develop and evaluate a CT-based radiomics nomogram for differentiating gastric neuroendocrine carcinomas (NECs) from gastric adenocarcinomas (ADCs). METHODS: CT images of 63 patients with gastric NECs were collected retrospectively, and 63 patients with gastric ADCs were selected as the control group. Univariate analysis was used to identify the significant factors of clinical characteristics and CT findings for differentiating gastric NECs from ADCs. Radiomics analysis was applied to CT images of unenhanced, arterial phase and venous phase, respectively. A radiomics nomogram incorporating the radiomics signature and the subjective CT findings was developed and its diagnostic ability was evaluated. The diagnostic performances of CT findings model, radiomics signature and radiomics nomogram were compared using DeLong test. RESULTS: The tumor margin and lymph node (LN) metastasis were independent predictors for differentiating gastric NECs from ADCs. The radiomics signature based on venous phase presented superior AUC of 0.798 [95 % confidence interval (CI), 0.657-0.938] in validation cohort. The nomogram incorporated the radiomics signature, tumor margin and LN metastasis showed AUCs of 0.821 (95 %CI: 0.725-0.895) in the primary cohort and 0.809 (95 %CI: 0.649-0.918) in the validation cohort. Moreover, the radiomics nomogram showed good discrimination and calibration. The diagnostic performance of CT findings model was significantly lower than that of radiomics nomogram (p = 0.001) and radiomics signature (p = 0.025). CONCLUSIONS: Radiomics analysis exhibited good performance in differentiating gastric NECs from ADCs, and the radiomics nomogram may have significant clinical implications on preoperative detection of gastric malignant tumors.
Authors: Femke C R Staal; Else A Aalbersberg; Daphne van der Velden; Erica A Wilthagen; Margot E T Tesselaar; Regina G H Beets-Tan; Monique Maas Journal: Eur Radiol Date: 2022-07-26 Impact factor: 7.034