AI-assisted CT detection and staging of stomach cancer
Langue and Imaging-integrated Foundation Model for Gastric Cancer Detection and Staging Via Contrast-Enhanced CT: a Multicenter Study
This project will test an AI tool that reads routine contrast-enhanced CT scans to detect stomach cancer and assign T1–T4 and N0–N3 stages before surgery.
Quick facts
| Study type | Observational |
|---|---|
| Enrollment | 8000 (estimated) |
| Ages | 18 Years to 85 Years |
| Sex | All |
| Sponsor | The First Affiliated Hospital with Nanjing Medical University Academic / other |
| Locations | 1 site (Nanjing, Jiangsu) |
| Trial ID | NCT07250347 on ClinicalTrials.gov |
What this trial studies
Adults with pathologically confirmed gastric cancer who undergo pre-treatment contrast-enhanced CT and curative-intent surgery will be enrolled. The AI will analyze routine clinical CECT images to detect tumors and assign four-class T stage and N stage, and its outputs will be compared to surgical pathology supplemented by clinical follow-up. Radiologists will interpret scans with and without AI assistance in a prespecified reader study to measure changes in diagnostic accuracy, interpretation time, and inter-reader agreement. The primary outcomes are detection performance and multi-class staging accuracy (including AUC), with secondary outcomes including reader impact and cross-site reproducibility.
Who should consider this trial
Good fit: Ideal candidates are adults with pathologically confirmed gastric cancer who have preoperative contrast-enhanced CT and proceed to curative-intent gastrectomy with complete postoperative histopathology available.
Not a fit: Patients with distant metastases, prior treatment before surgery, or nondiagnostic/poor-quality CT scans are unlikely to benefit from this protocol.
Why it matters
Potential benefit: If successful, the AI could improve preoperative staging accuracy and help doctors choose the right extent of surgery or need for neoadjuvant therapy.
How similar studies have performed: Previous AI studies for CT-based tumor detection and staging have shown promising results, but robust, multi-center validation for four-class T/N staging and reader-assist workflows remains limited.
Eligibility criteria
Show full inclusion / exclusion criteria
Inclusion Criteria: 1. pathologically confirmed gastric cancer; 2. preoperative contrast-enhanced CT performed; 3. no evidence of distant metastasis on baseline staging; 4. curative-intent management with complete postoperative histopathology. Exclusion Criteria: 1. prior treatment before surgery; 2. non-diagnostic or poor-quality CT precluding evaluation.
Where this trial is running
Nanjing, Jiangsu
- The First Affiliated Hospital of Nanjing Medical University — Nanjing, Jiangsu, China (Recruiting)
Study contacts
- Principal investigator: Zhang Yudong — The First Affiliated Hospital with Nanjing Medical University
- Study coordinator: Zhang Yudong, PHD, MD
- Email: zhangyd3895@njmu.edu.cn
- Phone: +8618251966069
How to participate
- Review the eligibility criteria above with your treating physician.
- Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
- Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.