AUTHOR=Pan Bujian , Zhang Weiteng , Chen Wenjing , Zheng Jingwei , Yang Xinxin , Sun Jing , Sun Xiangwei , Chen Xiaodong , Shen Xian 

TITLE=Establishment of the Radiologic Tumor Invasion Index Based on Radiomics Splenic Features and Clinical Factors to Predict Serous Invasion of Gastric Cancer

JOURNAL=Frontiers in Oncology

VOLUME=Volume 11 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2021.682456

DOI=10.3389/fonc.2021.682456

ISSN=2234-943X

ABSTRACT=Background: Currently, there are shortcomings in the diagnosis of gastric cancer (GC) with or without serous invasion, making it difficult for patients to get appropriate treatment. Therefore, we aimed to develop a radiomic nomogram for preoperative identification of serosal invasion.
Methods: We selected 315 patients with GC confirmed by pathology and randomly divided them into two groups, the modeling group (189 patients) and the validation group (126 patients). We obtained patient splenic imaging data in the training group. A P-value of <0.05 was considered statistically significant for features that were selected for lasso regression, and eight features were chosen to construct a serous invasion prediction model. Patients were divided into the high- and low-risk groups according to the radiologic tumor invasion risk score. Then, univariate and multivariate regression analyses were done with other invasion-related factors to establish a visual combined prediction model. 
Results: The diagnostic accuracy of radiologic tumor invasion score was consistent in the training and verification groups (p<0.001and p=0.009, respectively). Univariate and multivariate analyses of invasion risk factors showed that the radiologic tumor invasion index (p=0.001), preoperative hemoglobin(g) <100 (p=0.040), and ratio between platelet and lymphocyte (PLR) <92.8（p=0.033) were independent risk factors for serosal invasion. The prediction model based on the three indexes could accurately predict the serosal invasion risk. 
Conclusions: The radiological tumor invasion index based on splenic imaging combined with other factors can accurately predict serosal invasion of gastric cancer, increase diagnostic precision for the best treatment, and save time.