This study proposes to establish a CT radiomics-based prediction model for identifying metastasis of each station lymph nodes in gastric cancer.

This is a prospective, multi-center trial conducted at 4 high-volume gastric cancer centers in China (Nanfang Hospital of Southern Medical University; Sun Yat-Sen University Cancer Center; First Affiliated Hospital, Sun Yat-Sen University; The Third Affiliated Hospital, Sun Yat-Sen University) designed to determine the predicted performance of radiomics-based prediction model for identifying metastasis of each station lymph nodes by enhanced CT for preoperative noninvasive assessment of the lymph node status in patients with gastric cancer. The study includes the construction of CT radiomics-based prediction model and the validation of the prediction model.

Inclusion Criteria:

• Age >18 years;
• Patients providing written informed consent;
• Pathologically proven gastric cancer scheduled to preoperative enhanced abdomen CT and undergo gastrectomy with type D2 lymphadenectomy;
• Has undergone > 64 multi-detector row CT within 14 days prior to surgical resection; .No receipt of preoperative therapy (radiotherapy, chemotherapy or chemoradiotherapy).

Exclusion Criteria:

• Preoperative therapy (radiotherapy, chemotherapy or chemoradiotherapy);
• Failed to receive preoperative enhanced abdomen CT or undergo gastrectomy with type D2 lymphadenectomy;
• Inavailable pathological results for local lymph node status;
• Inquality of CT images for feature extraction; .Patient quit.

pathologically proven gastric cancer patients who receive preoperative CT and surgical resection in these hospitals.