Explainable multimodal AI for diagnosing early gastric cancer from endoscopic images
Official title: Development and Validation of an Explainable Artificial Intelligence Model for Early Gastric Cancer Diagnosis Using Multimodal Endoscopic Imaging
Run by The First Affiliated Hospital of Soochow University · NCT07551466 · Data updated 2026-11-12
This project will try an explainable AI that combines white-light and image-enhanced endoscopy pictures plus clinical data to help detect early gastric cancer in adults with suspicious gastric lesions who underwent endoscopic submucosal dissection.
Quick facts
| Study type | Observational |
|---|---|
| Ages | 18 Years to 80 Years |
| Sex | All |
| Enrollment | 100 (estimated) |
| Sponsor | The First Affiliated Hospital of Soochow University Academic / other |
| Locations | 1 site (Suzhou) |
| Status | Recruiting |
| Started | May 1, 2026 |
| Main results expected | December 1, 2026 |
| Study ends | February 1, 2027 |
| Registry record updated | April 24, 2026 |
| Trial ID | NCT07551466 on ClinicalTrials.gov |
Is this trial a fit for you?
✓Likely a good fit
Adults (≥18 years) with suspicious gastric lesions who had both white-light imaging and magnifying endoscopy with narrow-band imaging and subsequently underwent endoscopic submucosal dissection with available histopathology are ideal candidates.
✕Probably not a fit
Patients without adequate WLI or ME‑NBI imaging, those who did not undergo ESD, or those with non-adenocarcinoma histologies or deeply invasive lesions are unlikely to benefit from this model.
A plain-English reading of the study's rules. Only the study team can confirm whether you qualify.
What this trial studies
This observational project will collect endoscopic images (white-light and image-enhanced/NBI) and clinical data from adults who underwent endoscopic submucosal dissection for suspicious gastric lesions. A lesion detection model will first identify regions of interest, then quantitative image features (color, texture, morphology, mucosal structure) and deep-learning–derived features will be extracted from both imaging modalities. These imaging features will be integrated with clinical variables to build a multimodal, explainable prediction model. Model performance will be tested on held-out data and reported using AUROC, sensitivity, specificity, accuracy, and calibration metrics.
Why it matters
Potential benefit: If successful, the model could improve accuracy of early gastric cancer detection and give interpretable decision support to endoscopists, potentially enabling earlier and more appropriate treatment.
How similar studies have gone: Previous AI models have improved endoscopic detection of gastric neoplasia, but most relied on single-modality images and lacked interpretability, while multimodal explainable approaches remain relatively novel.
Who can join: the full rules
Show full inclusion / exclusion criteria
Inclusion Criteria: * Age ≥18 years * Suspicious gastric lesions identified on white-light imaging (WLI) * Preoperative biopsy indicating precancerous lesions (dysplasia or intraepithelial neoplasia) or adenocarcinoma, with preoperative magnifying endoscopy with narrow-band imaging (ME-NBI) performed * Patients meeting the absolute indications for endoscopic submucosal dissection (ESD) and who underwent ESD Exclusion Criteria: * Non-adenocarcinoma histological types (e.g., lymphoma) * Patients who did not undergo ME-NBI examination or did not receive ESD * Lesions invading the muscularis propria or deeper layers * Missing or indeterminate postoperative histopathological results
Where it's running
-
The First Affiliated Hospital of Soochow University
Suzhou, China Recruiting
Study contacts
- Study coordinator: Li he Liu
- Email: lhliu2024@stu.suda.edu.cn
- Phone: +8615943593759
Similar studies
Other studies for the same condition or treatment. Recruiting studies are listed first.
-
SPADE procedure for upper stomach cancer
A multicenter study will test the SPADE operation, a special stomach reconnection technique, in patients with early upper-stomach cancer undergoing proximal gastrectomy to see if it is safe and feasible.
-
LECS with sentinel node navigation for early gastric cancer
This study tests whether combining LECS with sentinel node navigation can treat early gastric cancer while preserving stomach function in eligible patients.
-
Image-guided platform helps find sentinel lymph nodes in early gastric cancer
This study tests whether an image-guided platform with a deep learning model can find and retrieve sentinel lymph nodes better than standard palpation in people with early gastric cancer undergoing LECS-SNNS.
-
Early Gastric Cancer in China: Real-World Outcomes by Treatment Type
This project will look at real-world outcomes for about 5,000 Chinese patients with early gastric cancer treated with endoscopic resection, laparoscopic surgery, open surgery, or a combined approach to see how treatments relate to survival and recurrence.
-
H. pylori status and tissue features to predict gastric cancer behavior after endoscopic treatment
This study tests whether current H. pylori infection status and tissue features can help predict how early gastric cancer will behave after endoscopic treatment.
-
Dual-endoscope Sentinel Lymph Node Navigation for Early Gastric Cancer
This study tests whether using two endoscopes to guide sentinel lymph node navigation during laparoscopic surgery is safe and effective for people with early gastric cancer who need additional surgery after initial endoscopic treatment.
How to take part
- Review the eligibility criteria above with your treating physician.
- Check the official listing on ClinicalTrials.gov for the latest contact details and recruitment status.
- Contact the study coordinator or principal investigator to ask for pre-screening. Pre-screening is free and never obligates you to enroll.