Oslo University Hospital · Fall 2025 · Completed

State of the art segmentation of AAA

Leveraging recent advances in medical image segmentation to identify potential abdominal aortic aneurysms from general abdominal CT scans acquired through the national screening program.

Medical imagingSegmentationClinical research
Axial abdominal CT scan showing an abdominal aortic aneurysm

This project and accompanying research paper leverage recent advances in medical image segmentation to generate accurate representations of a patient’s abdominal aorta, one of the body’s major blood vessels. The primary objective is to identify potential abdominal aortic aneurysms (AAA) from general abdominal CT scans acquired through the national screening program. Collaboration with OUS provides expert clinical insight into the condition as well as access to high-quality annotated training data. The goal is to develop an automated pipeline capable of alerting clinicians when further diagnostic evaluation is warranted, thereby reducing the likelihood of missed AAA cases in patients who have already undergone screening.

Data
Abdominal CT scans
Methods
medical image segmentation, preprocessing experiments, inference pipelines
Handoff
segmentation baselines, inference outputs, handoff notes for OUS review
Public limits
Clinical data is not shown publicly.
Back to projects