RecruitingNot Applicable

Multicenter Observational Study of Multimodal AI for Upper GI Mesenchymal Tumor Diagnosis

China130 participantsStarted 2025-07-28

Plain-language summary

This study develops a multimodal AI model using endoscopic ultrasound, white-light endoscopy, and clinical information to support the diagnosis of upper GI mesenchymal tumors and the risk stratification of gastric GISTs.

Who can participate

Age range18 Years

SexALL

See this in plain English?

AI-rewrites the medical criteria so a patient or caregiver can understand them. Always confirm with the trial site.

Inclusion criteria

✓. Equipment requirements: Olympus EU-ME2/ME1 processor (Olympus Medical Systems Corp., Tokyo, Japan); radial EUS scope (GF-UE260/GF-UE240; Olympus, Tokyo, Japan) or linear EUS scope (GF-UCT260/GF-UCT240; Olympus, Tokyo, Japan); miniature probe (UM2R/3R; Olympus, Tokyo, Japan); Pentax ARIETTA 850 processor (Pentax, Tokyo, Japan); radial EUS scope (EG-3670URK, Pentax, Tokyo, Japan); linear EUS scope (EG-3870UT, Pentax, Tokyo, Japan); Fujifilm SU-8000 or SU-9000 processor; linear EUS scope (EG-580UT, Fujifilm, Tokyo, Japan); radial EUS scope (EG-580UR, Fujifilm, Tokyo, Japan)
✓. EUS images clearly showing the lesion and surrounding tissue characteristics (at least 5 images or video); must include at least one image of the maximum lesion diameter, one image showing the layer of origin, and one image demonstrating the growth pattern (intraluminal/extraluminal)
✓. EUS images must not contain artificial annotations, such as measurement scales, biopsy needles, Doppler signals, or elastography overlays
✓. Image resolution must be at least 448 × 448 pixels

What they're measuring

Diagnostic accuracy of a multimodal AI model for differentiating gastrointestinal stromal tumors (GISTs) from other upper gastrointestinal mesenchymal tumors

Timeframe: After the training process of the multimodal AI model is completed，on average per year

Predictive accuracy of the multimodal AI model for risk stratification of GISTs

Timeframe: After the training process of the multimodal AI model is completed，on average per year

Trial details

NCT IDNCT07078136

SponsorHuazhong University of Science and Technology

Sponsor typeOTHER

Study typeOBSERVATIONAL

Primary completion2026-03

Contact for this trial

Bin Cheng

+8613986097542 b.cheng@tjh.tjmu.edu.cn

View on ClinicalTrials.gov More Submucosal Tumor trials

Who can participate

Age range18 Years

SexALL

See this in plain English?

AI-rewrites the medical criteria so a patient or caregiver can understand them. Always confirm with the trial site.

Inclusion criteria

✓. Equipment requirements: Olympus EU-ME2/ME1 processor (Olympus Medical Systems Corp., Tokyo, Japan); radial EUS scope (GF-UE260/GF-UE240; Olympus, Tokyo, Japan) or linear EUS scope (GF-UCT260/GF-UCT240; Olympus, Tokyo, Japan); miniature probe (UM2R/3R; Olympus, Tokyo, Japan); Pentax ARIETTA 850 processor (Pentax, Tokyo, Japan); radial EUS scope (EG-3670URK, Pentax, Tokyo, Japan); linear EUS scope (EG-3870UT, Pentax, Tokyo, Japan); Fujifilm SU-8000 or SU-9000 processor; linear EUS scope (EG-580UT, Fujifilm, Tokyo, Japan); radial EUS scope (EG-580UR, Fujifilm, Tokyo, Japan)
✓. EUS images clearly showing the lesion and surrounding tissue characteristics (at least 5 images or video); must include at least one image of the maximum lesion diameter, one image showing the layer of origin, and one image demonstrating the growth pattern (intraluminal/extraluminal)
✓. EUS images must not contain artificial annotations, such as measurement scales, biopsy needles, Doppler signals, or elastography overlays
✓. Image resolution must be at least 448 × 448 pixels

What they're measuring

Diagnostic accuracy of a multimodal AI model for differentiating gastrointestinal stromal tumors (GISTs) from other upper gastrointestinal mesenchymal tumors

Timeframe: After the training process of the multimodal AI model is completed，on average per year

Predictive accuracy of the multimodal AI model for risk stratification of GISTs

Timeframe: After the training process of the multimodal AI model is completed，on average per year