University of Cambridge > > CMIH Hub seminar series > Deep learning in Endovascular Aneurysm Repair Surveillance

Deep learning in Endovascular Aneurysm Repair Surveillance

Add to your list(s) Download to your calendar using vCal

If you have a question about this talk, please contact J.W.Stevens.

Abdominal aortic aneurysm (AAA) is a condition in which the abdominal aorta, a large artery, dilates gradually, secondary to a degenerative process within its wall. AAA can cause fatal rupture of the vulnerable wall leading to exsanguination. AAAs can be surgically repaired by Endovascular Aneurysm Repairs (EVAR), the standard treatment for AAA in most patients. EVAR is a minimally invasive technique by inserting an artificial device (stent-graft) within the aortic lumen. However, often due to the failure of stent graft’s position, there are concerns regarding the long-term durability of stent-grafts. Some patients require further surgery to correct stent-graft complications in the period after the first EVAR surgery. Therefore, standard international practice is to keep patients are life-long surveillance after EVAR surgery. Stent-grafts are visible on plain abdominal radiographs. By comparing series of radiographs taken over time, it is possible to diagnose stent-graft migration problems. Stent-graft migration is often due to failure of the integrity of the stent-graft or movement from its original location of implantation. The main challenge is that these changes can be subtle on plain radiographs and difficult to spot, even to the most trained radiologists. Therefore, for monitoring the stent-graft durability, automated post-EVAR surveillance may help diagnose stent-graft migration. This talk will explore AI’s potentials in spatial and temporal analysis of plain abdominal radiographs for automated post-EVAR surveillance.

Join Zoom Meeting Meeting ID: 921 3393 8858 Passcode: 453608

This talk is part of the CMIH Hub seminar series series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.


© 2006-2024, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity