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

NCT06957678 | Enrolling By Invitation DMC

• 1 other identifier: GC-RAD-AI-2025-02
• Study Type: observational
• Target: 1,200
• Locations: 1 country
• Sites: 1

Brief 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

Outcome Measures

Primary Outcomes (1)

• Diagnostic Accuracy of the AI Model in Predicting Presence of Lymph Node Metastasis in Gastric Cancer

  From Preoperative Evaluation to Completion of Postoperative Pathological Analysis (Approximately 4-6 Weeks)

Interventions

Artificial Intelligence-Based Predictive Model for Lymph Node Metastasis DIAGNOSTIC_TEST

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.

Eligibility Criteria

• Age: 18 Years - 80 Years
• Sex: all
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Probability Sample

Study Population

The study will enroll adult patients diagnosed with gastric adenocarcinoma who are scheduled to undergo curative-intent gastrectomy with lymphadenectomy. Participants must have completed preoperative imaging studies and histopathological evaluation. All enrolled patients will have individually retrieved lymph nodes evaluated by detailed pathological examination to provide a definitive reference for lymph node metastasis status.

You may qualify if:

• Age 18 years or older
• Histologically confirmed gastric adenocarcinoma
• Scheduled for curative-intent gastrectomy with lymphadenectomy
• Completed preoperative imaging with contrast-enhanced CT or MRI
• Available preoperative biopsy pathology report
• Able and willing to provide written informed consent

You may not qualify if:

• Evidence of distant metastasis on preoperative imaging
• Prior chemotherapy, radiotherapy, or major abdominal surgery
• Severe comorbidities contraindicating surgery
• Incomplete or poor-quality preoperative imaging or pathology data
• Pregnancy or lactation

Sponsors & Collaborators

• Qun Zhao: lead
• Renmin Hospital of Wuhan University: collaborator
• Nanjing University School of Medicine: collaborator
• Baoding First Central Hospital: collaborator
• Hengshui People's Hospital: collaborator
• No.1 Hospital of Shijiazhuang City: collaborator
• The Second Affiliated Hospital of Xingtai Medical College: collaborator

Study Sites (1)

the Fourth Hospital of Hebei Medical University

Shijiazhuang, None Selected, 050011, China

Location

MeSH Terms

Conditions

Lymphatic Metastasis

Condition Hierarchy (Ancestors)

Neoplasm Metastasis; Neoplastic Processes; Neoplasms; Pathologic Processes; Pathological Conditions, Signs and Symptoms

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: PROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: SPONSOR INVESTIGATOR
• PI Title: Professor

Study Record Dates

• First Submitted: April 26, 2025
• First Posted: May 4, 2025
• Study Start: January 1, 2025
• Primary Completion: December 31, 2025
• Study Completion: December 31, 2025
• Last Updated: May 4, 2025

Record last verified: 2025-04

Locations

CN (1)