Background: Peritoneal recurrence (PR) is the predominant pattern of relapse after curative-intent surgery in gastric cancer (GC) and indicates a dismal prognosis. Accurate prediction of PR is crucial for patient management and treatment. We aimed to develop a noninvasive imaging biomarker from computed tomography (CT) for PR evaluation, and investigate its associations with prognosis and chemotherapy benefit. Methods: In this multicenter study including five independent cohorts of 2005 GC patients, we extracted 584 quantitative features from the intratumoral and peritumoral regions on contrast-enhanced CT images. The artificial intelligence algorithms were used to select significant PR-related features, and then integrated into a radiomic imaging signature. And improvements of diagnostic accuracy for PR by clinicians with the signature assistance were quantified. Using Shapley values, we determined the most relevant features and provided explanations to prediction. We further evaluated its predictive performance in prognosis and chemotherapy response. Results: The developed radiomics signature had a consistently high accuracy in predicting PR in the training cohort (area under the curve: 0.732), internal and SYSUCC validation cohorts (0.721 and 0.728). The radiomics signature was the most important feature in Shapley interpretation. The diagnostic accuracy of PR with the radiomics signature assistance was improved by 10.13% to 18.86% for clinicians (P<0.001). Furthermore, it was also applicable in the survival prediction. In multivariable analysis, the radiomics signature remained an independent predictor for PR and prognosis (P<0.001 for all). Importantly, patients with predicting high risk of PR from radiomics signature, could gain survival benefit from adjuvant chemotherapy. By contrast, chemotherapy had no impact on survival for patients with a predicted low risk of PR. Conclusion: The noninvasive and explainable model developed from preoperative CT images could accurately predict PR and chemotherapy benefit in patients with GC, which will allow the optimization of individual decision-making. Export

Background: Current TNM staging systems insufficiently predict individual prognosis and chemotherapy response in gastric cancer (GC). We aimed to develop and validate a radiopathomics signature (RPS) integrating computed tomography (CT) and pathological features to improve prognostic stratification and guide treatment decisions. A preliminary evaluation of the immunotherapy response was also conducted. Methods: This retrospective multicenter analysis included 1133 GC patients across three Chinese institutions. We integrated features extracted from CT images and H&E stain slides using ResNet-50 and HoverNet, encompassing radiomics, pathomics microenvironment, single-cell spatial distribution, and pathomics nucleus data, to develop the RPS. Prognostic performance was evaluated using the area under the time-dependent curve (AUC) and C-index. Chemotherapy and immunotherapy benefits were determined using Kaplan–Meier analysis. Results: The RPS demonstrated strong performance in predicting 5-year overall survival (OS), with AUCs of 0.928 (95% CI: 0.899–0.956) in the training cohort and 0.857–0.917 in internal and external validation cohorts, showing improved prognostic accuracy compared with single-modality radiomics and pathomics models. The model can identify patients who could benefit from postoperative chemotherapy (HR: 11.751, P < 0.0001). Moreover, the RPS showed a preliminary but significant association with treatment response in the immunotherapy cohort ( n = 64; HR: 3.651, P = 0.009). The nomogram combining RPS and TNM stage yielded good C-indexes of 0.79–0.84 for OS across cohorts. Conclusions: The RPS robustly predicts prognosis and chemotherapy benefit in GC patients and provides preliminary insights into immunotherapy response prediction, complementing the TNM staging system and helping to guide patient-specific treatment strategies.

INTRODUCTION: Gastric cancer (GC) is a leading cause of cancer-related deaths worldwide, with delayed diagnosis often limiting effective treatment options. This study introduces a novel, noninvasive radiomics-based approach using [18F] FDG PET/CT (fluorodeoxyglucose positron emission tomography/computed tomography) to predict vascular endothelial growth factor (VEGF) status and survival in patients with GC. The ability to noninvasively assess these parameters can significantly influence therapeutic decisions and outcomes. METHODS: We conducted a retrospective study involving patients diagnosed with GC, stratified into training, validation, and test groups. Each patient underwent a [18F] FDG PET/CT scan, and radiomic features were extracted using dedicated software. A Radiomics Score (RS) was calculated, serving as a predictor for VEGF status. Statistical analyses included logistic regression and Cox proportional hazards models to evaluate the predictive power of RS on survival outcomes. RESULTS: The developed radiomics model demonstrated high predictive accuracy, with the RS formula achieving an area under the receiver operating characteristic curve of 0.861 in the training cohort and 0.857 in the validation cohort for predicting VEGF status. The model also identified RS as an independent prognostic factor for survival, where higher RS values correlated with poorer survival rates. DISCUSSION: The findings underscore the potential of [18F] FDG PET/CT radiomics in transforming the management of GC by providing a noninvasive means to assess tumor aggressiveness and prognosis through VEGF status. This model could facilitate earlier and more tailored therapeutic interventions, potentially improving survival outcomes in a disease marked by typically late diagnosis and limited treatment success.