NCT06957678

AI-Based Prediction of Lymph Node Metastasis in Gastric Cancer Using Preoperative Multimodal Data

Artificial Intelligence-Based Prediction of Lymph Node Metastasis and Nodal Station Involvement in Gastric Cancer Using Preoperative Multimodal Imaging and Pathology Data

• Status: Enrolling By Invitation
• Phase: —
• Study type: Observational
• Enrollment: 1,200 (estimated)
• Sponsor: Qun Zhao · Academic / Other
• Sex: All
• Age: 18 Years – 80 Years
• Healthy volunteers: —

Summary

This study aims to develop and validate an artificial intelligence (AI) system that can predict whether lymph node metastasis has occurred in patients with gastric cancer before surgery. Using preoperative imaging and pathology data, the AI models will not only predict if metastasis is present but also identify which specific lymph node stations or individual lymph nodes are involved. All lymph nodes will be carefully removed during surgery and examined one by one with detailed pathological methods to ensure accurate diagnosis. The goal is to improve the accuracy of lymph node assessment and assist doctors in making better treatment decisions.

Conditions

• Gastric Cancer Adenocarcinoma Metastatic
• Lymph Node Metastasis
• Artificial Intelligence (AI) in Diagnosis

Interventions

Type	Name	Description
DIAGNOSTIC_TEST	Artificial Intelligence-Based Predictive Model for Lymph Node Metastasis	The intervention is an artificial intelligence-based predictive model developed using preoperative multimodal data, including contrast-enhanced CT images, preoperative histopathological findings, and clinical features. The model is designed to predict (1) the presence or absence of lymph node metastasis, (2) the specific lymph node stations involved, and (3) the individual lymph nodes involved. Each lymph node's metastatic status is confirmed by serial pathological sectioning of surgically retrieved nodes, ensuring a highly accurate reference standard for model training and validation. This distinguishes the intervention from traditional imaging-based assessments and from other AI models that do not use individually validated lymph node pathology.

Timeline

• Start date: 2025-01-01
• Primary completion: 2025-12-31
• Completion: 2025-12-31
• First posted: 2025-05-04
• Last updated: 2025-05-04

Locations

1 site across 1 country: China