Deep learning model provides rapid detection of stroke-causing blockages

September 29, 2020

OAK BROOK, Ill. - A sophisticated type of artificial intelligence (AI) called deep learning can help rapidly detect blockages in the arteries that supply blood to the head, potentially speeding the onset of life-saving treatment, according to a study published in Radiology.

Large vessel occlusions are blockages in the arteries that supply oxygenated blood to the brain. These occlusions account for a significant proportion of ischemic strokes, the most common type of stroke. Prompt diagnosis is critical in order to begin recanalization, or opening of the blocked artery, through a treatment known as endovascular therapy.

"Minutes matter in this time-sensitive diagnosis," said study lead author Matthew T. Stib, M.D., a radiology resident at the Warren Alpert Medical School at Brown University in Providence, Rhode Island. "Every minute that we reduce the time to recanalization extends the patient's disability-free life by a week."

CT angiography (CTA), a three-minute exam that provides detailed views of the blood vessels, is the gold standard for detecting these occlusions. Radiologists are highly accurate at identifying large vessel occlusions on CTA, but they are not always available, and any backlogs at the hospital can further delay care.

Dr. Stib and his colleagues at Brown explored the use of deep learning to help provide rapid detection of large vessel occlusions on CTA and reduce time to treatment.

Working closely with Brown's computer science department, the researchers developed a deep learning model from scratch. They used a large sample of CTA examinations for patients with suspected acute ischemic stroke to train the algorithm to recognize the appearance of large vessel occlusions and distinguish it from other conditions. Preprocessing of the CTA exams included the creation of maximum intensity projection images to emphasize the contrast-enhanced vasculature. The researchers also used multiphase CTA, a newer approach that provides more comprehensive information than the single-phase technique.

When they tested the deep learning model on multiphase CTA examinations of 62 patients, the model detected all 31 large vessel occlusions for a sensitivity of 100%, a statistically significant improvement over the 77% sensitivity rate of single-phase CTA. The use of multiphase CTA contributed to the improved performance.

"These results are quite promising," Dr. Stib said. "We really wanted to optimize the sensitivity of the model so that we were sure that we picked up every single case because missing a case has pretty dire consequences."

The study is the first to use multiphase CTA to look at occlusions in both the arteries of the front, or anterior, part of the head and neck and those in the back, or posterior.

"Posterior circulation occlusions have not been discussed much in machine learning literature," Dr. Stib said. "They're less common but have pretty profound clinical consequences if missed. It's important to have an algorithm that detects all categories of occlusion, both anterior and posterior."

The next step in the research is to validate the results using the algorithm in real time and see if it can improve outcomes for patients. If the results hold up, then the deep learning model could be a useful asset in medical centers or hospitals that don't have the expertise for reading large vessel occlusion CTA images.

"This algorithm is not replacing the ability of radiologists to do their job; rather, it's trying to speed up the time to diagnosis," Dr. Stib said. "So if the radiologist isn't around or there is a large workflow that is preventing someone from looking at the exam results quickly, there will be an alert that says an occlusion may be present and someone should look at this. That's where the value is in this kind of a model."

The team worked under the direction of the study's senior author Ryan A. McTaggart, M.D., a neuroradiologist specializing in interventional neuroradiology at Rhode Island Hospital in Providence, Rhode Island, and proponent of decreasing the time to treatment for large vessel occlusions.
"Detecting Large Vessel Occlusion at Multiphase CT Angiography by Using a Deep Convolutional Neural Network." Collaborating with Drs. Stib and McTaggart were Justin Vasquez, M.S., Mary P. Dong, Yun Ho Kim, Sumera S. Subzwari, Harold J. Triedman, Amy Wang, Hsin-Lei Charlene Wang, B.A., Anthony D. Yao, B.S., Mahesh Jayaraman, M.D., Jerrold L. Boxerman, M.D., Ph.D., Carsten Eickhoff, Ph.D., Ugur Cetintemel, Ph.D., and Grayson L. Baird, Ph.D.

Radiology is edited by David A. Bluemke, M.D., Ph.D., University of Wisconsin School of Medicine and Public Health, Madison, Wisconsin, and owned and published by the Radiological Society of North America, Inc. (

RSNA is an association of radiologists, radiation oncologists, medical physicists and related scientists promoting excellence in patient care and health care delivery through education, research and technologic innovation. The Society is based in Oak Brook, Illinois. (

For patient-friendly information on CT angiography, visit

Radiological Society of North America

Related Stroke Articles from Brightsurf:

Stroke alarm clock may streamline and accelerate time-sensitive acute stroke care
An interactive, digital alarm clock may speed emergency stroke care, starting at hospital arrival and through each step of the time-sensitive treatment process.

Stroke patients with COVID-19 have increased inflammation, stroke severity and death
Stroke patients who also have COVID-19 showed increased systemic inflammation, a more serious stroke severity and a much higher rate of death, compared to stroke patients who did not have COVID-19, according a retrospective, observational, cross-sectional study of 60 ischemic stroke patients admitted to UAB Hospital between late March and early May 2020.

'Time is vision' after a stroke
University of Rochester researchers studied stroke patients who experienced vision loss and found that the patients retained some visual abilities immediately after the stroke but these abilities diminished gradually and eventually disappeared permanently after approximately six months.

More stroke awareness, better eating habits may help reduce stroke risk for young adult African-Americans
Young African-Americans are experiencing higher rates of stroke because of health conditions such as high blood pressure, diabetes and obesity, yet their perception of their stroke risk is low.

How to help patients recover after a stroke
The existing approach to brain stimulation for rehabilitation after a stroke does not take into account the diversity of lesions and the individual characteristics of patients' brains.

Kids with headache after stroke might be at risk for another stroke
A new study has found a high incidence of headaches in pediatric stroke survivors and identified a possible association between post-stroke headache and stroke recurrence.

High stroke impact in low- and middle-income countries examined at 11th World Stroke Congress
Less wealthy countries struggle to meet greater need with far fewer resources.

Marijuana use might lead to higher risk of stroke, World Stroke Congress to be told
A five-year study of hospital statistics from the United States shows that the incidence of stroke has risen steadily among marijuana users even though the overall rate of stroke remained constant over the same period.

We need to talk about sexuality after stroke
Stroke survivors and their partners are not adequately supported to deal with changes to their relationships, self-identity, gender roles and intimacy following stroke, according to new research from the University of Sydney.

Standardized stroke protocol can ensure ELVO stroke patients are treated within 60 minutes
A new study shows that developing a standardized stroke protocol of having neurointerventional teams meet suspected emergent large vessel occlusion (ELVO) stroke patients upon their arrival at the hospital achieves a median door-to-recanalization time of less than 60 minutes.

Read More: Stroke News and Stroke Current Events is a participant in the Amazon Services LLC Associates Program, an affiliate advertising program designed to provide a means for sites to earn advertising fees by advertising and linking to