RSNA 2020 News

Machine learning helps find vessel occlusions on CTA

By Kate Madden Yee, staff writer
December 7, 2020

A 3D convolutional neural network (CNN) helps find large-vessel occlusions (LVOs) on head and neck CT angiography (CTA) studies -- which could translate to better patient outcomes, according to research presented at the recent virtual RSNA 2020 meeting.

"Time is brain, so getting patients treated sooner will help them retain more neurologic function," presenter Dr. Ian Pan of Rhode Island Hospital in Providence told session attendees.

Almost 800,000 people in the U.S. have a stroke each year, and about 10% of those are due to large-vessel occlusions. The use of artificial intelligence (AI) for detecting stroke is gaining momentum; in fact, in September, the U.S. Centers for Medicare and Medicaid Services (CMS) approved reimbursement for use of software developer's artificial intelligence (AI) application for stroke images.

"[The clearance] is a first for radiology artificial intelligence, and very exciting," Pan said.

Pan and colleagues sought to assess the performance of a deep learning algorithm in identifying LVOs. They trained a CCN with more than 7,000 LVO studies from Rhode Island Hospital and tested it on a set that consisted of 10% of these studies; the exams were classified into three categories:

  • No LVO (83.5%)
  • Chronic LVO (13.6%)
  • Acute LVO (2.9%)

The team also used 683 positive LVO studies from the Hospital of the University of Pennsylvania as an independent test set.

Pan's group found that the CNN had a 96% accuracy rate and an area under the receiver operating curve (AUC) of 1 for categorizing LVOs and a 5% false-positive rate.

CNN performance in categorizing LVOs

Measure Acute LVO versus no LVO
AUC 0.824
Specificity 30%
Sensitivity 95%

"3D CNNs were effective in identifying series of interest and acute LVOs in CT angiography," Pan and colleagues wrote in their study abstract. "At a 5% false-positive rate, over 40% of acute LVOs would be successfully identified without manual intervention."

Additionally, the CNN had a 98.2% accuracy rate on the comparison data from the University of Pennsylvania, Pan noted.

Going forward, Pan hopes to develop the CNN's ability to localize LVOs rather than simply identifying if there is one or not -- research that could perhaps benefit from support from the RSNA, perhaps through its AI challenge initiative.

"Given that [the U.S. Centers for Medicare and Medicaid Services] is now reimbursing for [AI software for LVO], I'd love to see this as an RSNA AI challenge," he said.

COVID-19, AI, and dose reduction top RSNA's CT agenda
In 2020, the COVID-19 pandemic has shaped the practice of imaging across all modalities, and CT is no exception. At the upcoming RSNA 2020 meeting, attendees...
MRI at RSNA: COVID-19 and beyond
At RSNA 2020, MRI's value in coping with the pandemic will be a hot topic, with abstracts particularly focused on the modality's ability to diagnose and...
Algorithm detects LVO stroke on multiphase CTA
An artificial intelligence algorithm can be extremely sensitive for detecting large-vessel occlusion (LVO) on multiphase CT angiography (CTA) scans, potentially...
COVID-19 associated with large vessel strokes
Patients with COVID-19 who present with acute neurologic symptoms may be at risk for large-vessel occlusion (LVO) stroke, and thus need prompt workup,...
FDA OK's's CT software
The U.S. Food and Drug Administration (FDA) has cleared artificial intelligence healthcare company's Viz CTP image-processing software that views...

Copyright © 2020