Background: Early recurrence in patients with locally advanced gastric cancer (LAGC) portends aggressive biological characteristics and a dismal prognosis. Predicting early recurrence may help determine treatment strategies for LAGC. The goal is to develop a deep learning model for early recurrence prediction (DLER) based on preoperative multiphase computed tomography (CT) images and to further explore the underlying biological basis of the proposed model.
Materials and methods: In this retrospective study, 620 LAGC patients from January 2015 to March 2023 were included in three medical centers and The Cancer Image Archive (TCIA). The DLER model was developed using DenseNet169 and multiphase 2.5D CT images, and then crucial clinical factors of early recurrence were integrated into the multilayer perceptron (MLP) classifier model (DLER MLP ). The area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity were applied to measure the performance of different models. The log-rank test was used to analyze survival outcomes. The genetic analysis was performed using RNA-sequencing data from TCIA.
Results: Using the MLP classifier combined with clinical factors, DLER MLP showed higher performance than DLER and clinical models in predicting early recurrence in the internal validation set (AUC: 0.891 vs. 0.797, 0.752) and two external test sets: test set 1 (0.814 vs. 0.666, 0.808) and test set 2 (0.834 vs. 0.756, 0.766). Early recurrence-free survival, disease-free survival, and overall survival can be stratified using the DLER MLP (all P < 0.001). High DLER MLP score is associated with upregulated tumor proliferation pathways (WNT, MYC, and KRAS signaling) and immune cell infiltration in the tumor microenvironment.
Conclusion: The DLER MLP based on CT images was able to predict early recurrence of patients with LAGC and served as a useful tool for optimizing treatment strategies and monitoring.