Skip to content

Preoperative Imaging Analysis and Local Progression Risk Prediction of Pancreatic Cancer Driven by Deep Learning

Preoperative Imaging Analysis and Local Progression Risk Prediction of Pancreatic Cancer Driven by Deep Learning

Status
Active, not recruiting
Phases
Unknown
Study type
Observational
Source
ChiCTR
Registry ID
ChiCTR2500111137
Enrollment
Unknown
Registered
2025-10-27
Start date
2025-10-31
Completion date
Unknown
Last updated
2025-11-03

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

Conditions

Pancreatic ductal adenocarcinoma

Interventions

Gold Standard:For the diagnosis of pancreatic ductal adenocarcinoma (PDAC), the gold standard will be pathological examination (such as tissue biopsy), confirmed through surgical resection and histopa
Index test:Diagnostic Tests: 1. Preoperative CT Imaging Analysis Combined with Deep Learning Models Sensitivity: This metric evaluates the true positive rate of the deep learning model in predicting l

Sponsors

Ruijin Hospital, Shanghai Jiao Tong University School of Medicine
Lead Sponsor

Eligibility

Sex/Gender
All

Inclusion criteria

Inclusion criteria: 1. Diagnosis of Pancreatic Cancer (PDAC): The patient must be diagnosed with pancreatic cancer through pathological or radiological examination. 2. Availability of Preoperative Imaging Data: The patient must provide complete preoperative CT imaging data, and the quality of the images must meet the requirements for deep learning analysis. 3. Age Requirement: Patients must be 18 years or above Clear Clinical and Pathological Characteristics: The patient must have accessible clinical and pathological data, such as tumor location, size, degree of differentiation, etc. Informed Consent: The patient or their legal representative must agree to participate in the study and sign an informed consent form.

Exclusion criteria

Exclusion criteria: 1. Non-pancreatic Cancer Patients: Patients with an unclear or undiagnosed pancreatic cancer diagnosis. 2. Incomplete or Poor-quality Preoperative Imaging Data: Patients whose preoperative imaging data is missing or of insufficient quality to meet the requirements for deep learning analysis. 3. Severe Comorbidities: Patients with serious systemic diseases, such as severe heart disease or liver/kidney failure, that may affect postoperative treatment and prognosis. 4. Inability to Cooperate with the Study: Patients who are unable to understand the study requirements or cooperate due to language, cognitive, or other barriers.

Design outcomes

Primary

MeasureTime frame
Sensitivity;Specificity;Accuracy;PPV;NPV;Receiver Operating Characteristic Curve;

Countries

China

Contacts

Public ContactNing Wen

Ruijin Hospital, Shanghai Jiao Tong University School of Medicine

wn124wn12479@rjh.com.cn+86 133 0161 8359

Outcome results

None listed

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