Currently, there are shortcomings in diagnosing gastric cancer with or without serous invasion, making it difficult for patients to receive appropriate treatment. Therefore, we aimed to develop a radiomic nomogram for preoperative identification of serosal invasion.
We selected 315 patients with gastric cancer, confirmed by pathology, and randomly divided them into two groups: the training group (189 patients) and the verification group (126 patients). We obtained patient splenic imaging data for the training group. A p-value of <0.05 was considered significant for features that were selected for lasso regression. Eight features were chosen to construct a serous invasion prediction model. Patients were divided into high- and low-risk groups according to the radiologic tumor invasion risk score. Subsequently, univariate and multivariate regression analyses were performed with other invasion-related factors to establish a visual combined prediction model.
The diagnostic accuracy of the radiologic tumor invasion score was consistent in the training and verification groups (p<0.001 and p=0.009, respectively). Univariate and multivariate analyses of invasion risk factors revealed that the radiologic tumor invasion index (p=0.002), preoperative hemoglobin <100 (p=0.042), and the platelet and lymphocyte ratio <92.8 (p=0.031) were independent risk factors for serosal invasion in the training cohort. The prediction model based on the three indexes accurately predicted the serosal invasion risk with an area under the curve of 0.884 in the training cohort and 0.837 in the testing cohort.
Radiological tumor invasion index based on splenic imaging combined with other factors accurately predicts serosal invasion of gastric cancer, increases diagnostic precision for the most effective treatment, and is time-efficient.