AI-assisted endoscopic ultrasound to grade how deep early esophageal cancer has grown
AI-assisted Endoscopic Ultrasound Grading of Early Esophageal Cancer Invasion Depth: A Multicenter, Prospective, Randomized Cohort Study
This study will test whether an AI tool used during endoscopic ultrasound can more accurately determine how deep early esophageal cancer has grown to help guide treatment decisions.
Quick facts
| Phase | Not applicable |
|---|---|
| Study type | Interventional |
| Enrollment | 200 (estimated) |
| Ages | 18 Years and up |
| Sex | All |
| Sponsor | Fujian Provincial Hospital Academic / other |
| Drugs / interventions | chemotherapy |
| Locations | 5 sites (Fuzhou, Fujian and 4 other locations) |
| Trial ID | NCT07251114 on ClinicalTrials.gov |
What this trial studies
This multicenter, prospective, randomized cohort study compares an AI-assisted endoscopic ultrasound (EUS) approach with conventional EUS interpretation for grading invasion depth in early esophageal squamous cell carcinoma. Approximately 200 eligible patients will be centrally randomized into an AI group or a conventional group, with about 100 patients per arm. The main outcome is grading accuracy of invasion depth compared with pathological results, with additional focus on pathological consistency and implications for preoperative T staging. Allocation is centrally randomized and labeled as A or B for operating physicians, and procedures occur at three participating hospitals in Fujian Province.
Who should consider this trial
Good fit: Adults over 18 with suspected or confirmed early esophageal squamous cell carcinoma or related precancerous lesions who have endoscopic and detailed pathological records and agree to participate are the intended candidates.
Not a fit: Patients who have had prior esophageal cancer surgery, prior radiotherapy or chemotherapy for esophageal cancer, those with missing key data, or those with more advanced disease are unlikely to benefit from this intervention.
Why it matters
Potential benefit: If successful, this approach could provide more accurate preoperative staging, helping patients receive the most appropriate treatment and potentially avoiding unnecessary procedures.
How similar studies have performed: Preliminary AI work in endoscopic imaging has shown promise, but applying AI specifically to EUS invasion-depth grading is relatively novel and still needs validation.
Eligibility criteria
Show full inclusion / exclusion criteria
Inclusion Criteria: * Satisfy ①⑧⑨ and one of the following conditions simultaneously: ②③④⑤⑥⑦ ① Age over 18 years old, ② Esophageal ulcer, ③ low-grade intraepithelial neoplasia, ④ high-grade intraepithelial neoplasia, ⑤ patients with esophageal squamous cell carcinoma, ⑥ white patches of esophageal mucosa, ⑦ esophageal polyps, ⑧ with endoscopic examination records and detailed pathological records, ⑨ agree to participate in the study; Exclusion Criteria: * ① Patients who have undergone esophageal cancer surgery, ② those with a history of radiotherapy and chemotherapy for esophageal cancer, ③ patients with missing data.
Where this trial is running
Fuzhou, Fujian and 4 other locations
- Fujian provincial hospital — Fuzhou, Fujian, China (Recruiting)
- Affiliated Hospital of Putian University — Putian, Fujian, China (Not_yet_recruiting)
- Putian First Hospital — Putian, Fujian, China (Not_yet_recruiting)
- Putian Hospital of Traditional Chinese Medicine — Putian, Fujian, China (Not_yet_recruiting)
- Xianyou County General Hospital — Putian, Fujian, China (Not_yet_recruiting)
Study contacts
- Principal investigator: Wei Liang, MD — Fujian Provincial Hospital
- Study coordinator: Wei Liang, MD
- Email: fjsllw@163.com
- Phone: +86 -18120888996
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.