Skip to content

Deep learning-based detection of acute pancreatitis on abdominal contrast-enhanced CT

Deep learning-based detection of acute pancreatitis on abdominal contrast-enhanced CT

Status
Active, not recruiting
Phases
Unknown
Study type
Observational
Source
DRKS
Registry ID
DRKS00041124
Enrollment
600
Registered
2026-07-29
Start date
2023-10-01
Completion date
Unknown
Last updated
2026-08-03

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

Conditions

K85

Interventions

Group 1: Patients with clinically suspected acute pancreatitis and a clinical indication for a contrast-enhanced CT scan of the abdomen to confirm or rule out the diagnosis. The study period covers pa

Sponsors

Universitätsklinikum Bonn
Lead Sponsor

Eligibility

Sex/Gender
All
Age
18 Years to No maximum

Inclusion criteria

Inclusion criteria: Inclusion criteria for the pancreatis group • Patients with clinically suspected acute pancreatitis • Elevated serum lipase levels above the reference range (defined as an increase in serum lipase to more than three times the normal range of 13 to 60 U/L) • Documented pancreatitis-specific ICD code in the discharge summary (K85, K86 in combination with K85) • Existing contrast-enhanced CT scan of the abdomen in the PACS • Imaging findings consistent with acute pancreatitis in the radiological report • Adequate image quality Inclusion criteria for the control group • Patients with an initial clinical suspicion of acute pancreatitis • Unremarkable imaging findings/exclusion of acute pancreatitis in the radiological report • No ICD code

Exclusion criteria

Exclusion criteria: • No documented ICD code specific to pancreatitis (K85, K86) • Ambiguous imaging findings suggestive of pancreatitis • Native CT scan only • Poor image quality • Incomplete organ coverage • History of partial pancreatic resection • Suspected pancreatic malignancy • Technical errors in organ segmentation

Design outcomes

Primary

MeasureTime frame
Development and evaluation of deep learning model for image-based detection of acute pancreatitis.

Countries

Germany

Contacts

Public ContactAlois Martin Sprinkart

Universitätsklinikum Bonn

Alois.Sprinkart@ukbonn.de+49 228 287 38531

Outcome results

None listed

Source: DRKS (via WHO ICTRP) · Data processed: Aug 10, 2026