New technique surpasses manual assessment of thoracic aortic aneurysm growth

The researchers developed a new method for measuring thoracic aortic aneurysm growth, which they believe could significantly improve the accuracy and reliability of aortic measurements compared to standard measurement techniques.

The technique, known as vascular strain mapping, measures changes in the thoracic aorta, using high-resolution computed tomography (CT) imaging to calculate three-dimensional changes in the aortic wall.

The technique outperforms standard manual evaluation methods performed by experts, according to study authors Zhnangxing Bian (University of Michigan, Ann Arbor, USA) and colleagues, who evaluated the performance of the mapping of vascular deformities in an article published in Radiology and medical physics.

“The technique used in this algorithm has been around for a while, but no one has ever used it to see the three-dimensional growth of a thoracic aortic aneurysm,” said Nicholas Burris (University of Michigan, Ann Arbor, United States United States), corresponding author of the article. “This is a promising step towards technology that pushes measurement accuracy beyond what human evaluators can achieve, allowing clinicians to get the best possible picture of a patient’s condition.”

For about 3% of adult patients over the age of 50 with thoracic aortic aneurysms, doctors recommend having regular tests, often with CT scans, to measure aortic growth and determine if surgical repair is needed.

Currently, the standard practice for measuring growth is with human “evaluators” aligning two images and drawing a line through two points to find the change. Burris says this process is error-prone, and in many cases doctors can’t tell for sure if the thoracic aorta is growing, creating uncertainty about the best treatments and follow-up plan.

“The challenge we face clinically is that a typical aortic aneurysm will only grow a fraction of a millimeter each year, and the process of hand drawing such precise diameters is very difficult to replicate” , did he declare. “You have a lot of variability in the standard measurements versus a very small amount of actual aneurysm growth. Basically, you rarely end up getting a reliable assessment of the growth, which can make it hard to know what the risk is. real patient and how closely it needs to be followed up with repeat CT scans.

The vascular deformity mapping technique developed by Burris’ team relies on an image analysis technique known as image registration, which aligns the anatomy shown in multiple CT scans by taking any which pixel on the first scan and relating its exact position to the pixel on the second scan. . When they are all lined up, a three-dimensional color map of the aorta shows how far and where the thoracic aorta has grown.

For these studies, the researchers used scans of nearly 50 aortic aneurysm patients and 75 reference models with varying aortic wall growth. They tested the automated program against two expert manual raters and found that vascular strain mapping outperformed humans with greater accuracy and lower variability in growth measurements. Mapping of vascular deformations achieved an accuracy of less than 1 mm in all cases, even the most experienced human analysts had measurements with errors of up to 3 mm.

“Recent advances in artificial intelligence have sparked a lot of interest in AI as it relates to automating radiology tasks,” said Charles Hatt, co-author of the paper and assistant adjunct research professor. in radiology at Michigan Medicine. “It turns out that replacing human radiologists is no simple task, and a more realistic goal for AI is to speed up workflows and help radiologists perform quantitative measurements of objects that are otherwise cumbersome to perform and inherently subjective. In this regard, vascular deformity mapping is a perfect and concrete example of how AI and quantitative imaging can improve clinical care by empowering clinicians rather than trying to replace them.

Although these reports show that vascular deformity mapping may be more useful than human assessment in determining whether surgery is needed on an aortic aneurysm, the researchers say the approach needs further study in large groups of patients. patients in a clinic. According to Burris, the vascular deformity mapping technique can be performed on routine CT scans of the aorta, making it easier to perform larger research studies.

“This is a whole new way of looking at aortic aneurysm growth,” he said. “As this develops, there is potential to deploy it in a wider range of diseases, such as abdominal aortic aneurysm. Moving from current one-dimensional measurements to a three-dimensional approach allows us to see the aneurysm growth patterns in a way never before possible and allows us to ask many new questions and learn how a highly accurate tracking tool like this can be used to ultimately improve patient care. patients.

About Irene J. O'Donnell

Check Also

Is trading with BitAlpha AI safer than manual trading? — Hometown Station | KHTS FM 98.1 & AM 1220 — Santa Clarita Radio

The Crypto market is progressing every day and the number of traders is constantly increasing. …