3:27 PM Abstract No. 293 Effectiveness of a deep convolutional neural network in the identification of major vascular structures during digital subtraction angiography

With the increasing use of artificial intelligence (AI) and deep convolutional neural networks (DCNN) to accurately identify images in radiology, this technology has the potential to assist the interventional radiologist in real time during digital subtraction angiography (DSA) to identify pathology intraoperatively. DSA poses unique challenges to existing DCNNs, namely the apparent similarity of vascular beds, motion artifacts, and anatomy variability. As such, the ability of DCNN to identify major vascular structures on DSA is unknown.
Source: Journal of Vascular and Interventional Radiology : JVIR - Category: Radiology Authors: Tags: Scientific Session 32 Source Type: research