Skip to content

Study on lesion boundary of early esophageal cancer based on Artificial Intelligence

Study on lesion boundary of early esophageal cancer based on Artificial Intelligence

Status
Active, not recruiting
Phases
Early Phase 1
Study type
Observational
Source
ChiCTR
Registry ID
ChiCTR2300069009
Enrollment
Unknown
Registered
2023-03-03
Start date
2019-12-01
Completion date
Unknown
Last updated
2023-05-22

For informational purposes only — not medical advice. Sourced from public registries and may not reflect the latest updates. Terms

Conditions

early esophagealcancer

Interventions

Gold Standard:WHO standards:Early esophageal cancer means that the depth of cancer invasion is in the mucosa and submucosa, and there is no lymph node metastasis Digestive endoscopy doctor's diagnosis

Sponsors

The First Affiliated Hospital of Shandong First Medical University
Lead Sponsor

Eligibility

Sex/Gender
All
Age
18 Years to 80 Years

Inclusion criteria

Inclusion criteria: Inclusion criteria: People between 18 and 80 years old Experimental group: Patients with early esophageal cancer diagnosed by endoscopy and pathology Control group: (1) Gastroscopy showed no gastrointestinal tumor; (2) No obvious lesion was found in the esophagus.

Exclusion criteria

Exclusion criteria: Exclusion criteria: 1.At present, antiplatelet drugs and anticoagulants are being used, so it is not suitable for endoscopic biopsy; 2. Patients with esophageal stenosis, obstruction, perforation or partial esophagectomy; 3. Patients allergic to iodine solution.

Design outcomes

Primary

MeasureTime frame
Consistency of AI model diagnosis and pathology;F1/Dice radio;IoU/Jaccard ratio;

Secondary

MeasureTime frame
The consistency between the diagnosis boundary of AI model and the diagnosis result of doctors;

Countries

China

Contacts

Public ContactZhangZhen

The First Affiliated Hospital of Shandong First Medical University(Shandong Qianfoshan hospital)

zzhhee99@163.com15628781588

Outcome results

None listed

Source: ChiCTR (via WHO ICTRP) · Data processed: Feb 4, 2026