FindTrial
Sign In

Deep learning model based on ultrasound images for early differential diagnosis of pancreatic tumors

Deep learning model based on ultrasound images for early differential diagnosis of pancreatic tumors

Status
Active, not recruiting
Phases
Unknown
Study type
Observational
Source
ChiCTR
Registry ID
ChiCTR2600118220
Enrollment
Unknown
Registered
2026-02-03
Start date
2024-12-01
Completion date
Unknown
Last updated
2026-02-09

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

Conditions

Pancreatic tumor

Interventions

Gold Standard: pathological examination
Index test:A deep learning model based on ultrasound imaging

Sponsors

The First Affiliated Hospital of University of Science and Technology of China
Lead Sponsor

Eligibility

Sex/Gender
All
Age
18 Years to No maximum

Inclusion criteria

Inclusion criteria: 1. Patients admitted between January 2020 and September 2024, aged >=18 years, and pathologically confirmed as pancreatic ductal adenocarcinoma or pancreatic cystic diseases (including pancreatic serous cystadenoma, pancreatic solid pseudopapillary tumor, pancreatic mucinous cystadenoma); 2. with available pre-treatment hepatobiliary and pancreatic ultrasound images;

Exclusion criteria

Exclusion criteria: 1. Age < 18 years, or patients with an unclear pathological diagnosis; 2. absence of pre-treatment hepatobiliary and pancreatic ultrasound images.

Design outcomes

Primary

MeasureTime frame
Overall correct classification rate for distinguishing different types of pancreatic tumors;Agreement;—

Secondary

MeasureTime frame
Precision;Recall;F1 score;—

Countries

China

Contacts

Public ContactYue Yu

The First Affiliated Hospital of University of Science and Technology of China

yuyuemd@ustc.edu.cn+86 189 6378 8890

Outcome results

None listed

Source: ChiCTR (via WHO ICTRP) · Data processed: Feb 15, 2026