From the The Department of Radiology, Affiliated Jiangmen Hospital of Sun Yat-Sen University, Jiangmen City, Guangdong Province.
School of Electronic Information and Automation, Guilin University of Aerospace Technology, Guilin City, Guangxi Province.
J Comput Assist Tomogr. 2021;45(2):191-202. doi: 10.1097/RCT.0000000000001117.
This study aimed to preoperatively differentiate primary gastric lymphoma from Borrmann type IV gastric cancer by heterogeneity nomogram based on routine contrast-enhanced computed tomographic images.
We enrolled 189 patients from 2 hospitals (90 in the training cohort and 99 in the validation cohort). Subjective findings, including high-enhanced mucosal sign, high-enhanced serosa sign, nodular or an irregular outer layer of the gastric wall, and perigastric fat infiltration, were assessed to construct a subjective finding model. A deep learning model was developed to segment tumor areas, from which 1680 three-dimensional heterogeneity radiomic parameters, including first-order entropy, second-order entropy, and texture complexity, were extracted to build a heterogeneity signature by least absolute shrinkage and selection operator logistic regression. A nomogram that integrates heterogeneity signature and subjective findings was developed by multivariate logistic regression. The diagnostic performance of the nomogram was assessed by discrimination and clinical usefulness.
High-enhanced serosa sign and nodular or an irregular outer layer of the gastric wall were identified as independent predictors for building the subjective finding model. High-enhanced serosa sign and heterogeneity signature were significant predictors for differentiating the 2 groups (all, P < 0.05). The area under the curve with heterogeneity nomogram was 0.932 (95% confidence interval, 0.863-0.973) in the validation cohort. Decision curve analysis and stratified analysis confirmed the clinical utility of the heterogeneity nomogram.
The proposed heterogeneity radiomic nomogram on contrast-enhanced computed tomographic images may help differentiate primary gastric lymphoma from Borrmann type IV gastric cancer preoperatively.
本研究旨在通过基于常规增强 CT 图像的异质性列线图，术前鉴别原发性胃淋巴瘤与 Borrmann Ⅳ型胃癌。
我们从 2 家医院招募了 189 名患者（训练队列 90 例，验证队列 99 例）。评估了主观发现，包括高增强黏膜征、高增强浆膜征、结节或胃壁不规则外层和胃周脂肪浸润，以构建主观发现模型。开发了一个深度学习模型来分割肿瘤区域，从该区域提取了 1680 个三维异质性放射组学参数，包括一阶熵、二阶熵和纹理复杂度，通过最小绝对收缩和选择算子逻辑回归构建异质性特征。通过多变量逻辑回归建立了一个集成异质性特征和主观发现的列线图。通过判别和临床实用性评估了列线图的诊断性能。
高增强浆膜征和结节或胃壁不规则外层被确定为构建主观发现模型的独立预测因子。高增强浆膜征和异质性特征是区分两组的显著预测因子（均 P<0.05）。验证队列中，异质性列线图的曲线下面积为 0.932（95%置信区间，0.863-0.973）。决策曲线分析和分层分析证实了异质性列线图的临床实用性。
基于增强 CT 图像的提出的异质性放射组学列线图可能有助于术前鉴别原发性胃淋巴瘤与 Borrmann Ⅳ型胃癌。
