Health TrialsbyHealthPanel

AI-Assisted Detection and Staging of Gastric Cancer Using Contrast-Enhanced CT

ConditionsGastric Cancer StageGastric Cancer Patients Undergoing Gastrectomy
Trial statusRecruiting
Trial phaseNot listed
Trial typeObservational
Biological sexAll
Age18-85
SponsorThe First Affiliated Hospital with Nanjing Medical University

About this trial

Accurate preoperative assessment of gastric cancer stage guides eligibility for endoscopic resection, extent of gastrectomy and lymphadenectomy, selection for neoadjuvant therapy, and use of staging laparoscopy. Contrast-enhanced CT (CECT) is guideline-endorsed for initial staging, yet performance varies across institutions and readers. This study will evaluate an artificial-intelligence (AI) system that analyzes routine CECT to detect gastric cancer and assign four-class T stage (T1-T4) and N stage (N0-N3) .

Eligibility criteria

This trial does not accept healthy volunteers

Qualifiers

pathologically confirmed gastric cancer;

preoperative contrast-enhanced CT performed;

no evidence of distant metastasis on baseline staging;

curative-intent management with complete postoperative histopathology.

Disqualifiers

prior treatment before surgery;

non-diagnostic or poor-quality CT precluding evaluation.

Trial population

This study will enroll adult patients (≥18 years old) with a confirmed diagnosis of gastric cancer (adenocarcinoma) who have undergone contrast-enhanced CT (CECT) as part of their standard preoperative evaluation. Participants will be selected from both internal and external cohorts, with inclusion from multiple centers to assess cross-site reproducibility and generalizability of the AI model.

Trial design

Design model

Case-only

Time perspective

Retrospective

Treatments tested in this trial

  • CT scan

    Diagnostic test

    preoperative contrast-enhanced CT

Treatment groups

8,000 Participants
are divided into 3 treatment groups
Group A: Cohort 1 (Internal Derivation Cohort)1 intervention
Group B: Cohort 2 (External Validation Cohort A)1 intervention
Group C: Cohort 3 (External Validation Cohort B)1 intervention

Trial outcomes

Primary outcomes

1

Diagnostic performance of the AI model for staging

The primary outcome is the diagnostic accuracy of the AI system for four-class T staging (T1-T4) and N staging (N0-3) based on contrast-enhanced CT. The AI performance will be assessed using accuracy, area under the receiver operating characteristic curve (AUC), and micro-AUC for internal and external cohorts.

Time frame
3 years

Secondary outcomes

1

Reader Accuracy with AI Support

This outcome measures the accuracy of radiologists in classifying gastric cancer stagewhen aided by the AI system compared to manual classification without AI assistance. Accuracy will be compared between different radiologist experience levels.

Time frame
3 years
2

Survival time

Calculate the survival time of gastric cancer patients from the point of diagnosis and treatment initiation.

Time frame
3 years

Other outcomes

Sponsors and contacts

Click on the lead sponsor to view all of their trials.

The First Affiliated Hospital with Nanjing Medical University

Lead sponsor

Jiangsu Cancer Institute & Hospital

Collaborator

Zhengzhou University

Collaborator

Peking University First Hospital

Collaborator

Source ClinicalTrials.gov
Apply now