JUN 30, 2021 7:00 AM PDT

A Deep Learning Tool for Faster, Better Heart Disease Diagnoses

WRITTEN BY: Tara Fernandez

A new deep learning tool could help slash the time it takes to interpret cardiology scans to diagnose obstructive coronary artery disease by 75 percent. The study, featured in the European Journal of Radiology, describes how this new technology, powered by artificial intelligence (AI) can not only accelerate processing times but also assist radiologists in identifying potential problem areas in the patients’ major arteries.

In obstructive coronary arterial disease, the blood vessels that supply the heart gradually narrow, and in severe classes, can even close completely. This happens as a result of the accumulation of plaque in a process called atherosclerosis.

Checking for obstructions and blockages in coronary scans can be challenging—radiologists require specialized training and extensive experience in order to be able to interpret these scans correctly.

According to Chun Yu Liu, lead author of the study, AI can complement scan interpretation by trained medical staff, speeding it up and improving accuracy.

The new diagnostic platform was built on scan data from 165 patients, with a threshold of at least 50 percent of luminal stenosis as a reference level for a positive diagnosis.

The team’s analysis revealed that the AI system proved to be reliable, diagnosing coronary artery disease with 90.5 percent sensitivity and 82.3 percent specificity. Most promisingly, it sped up processing times from 8.5 to 3.7 minutes.

Coronary artery calcification, or the buildup of calcium deposits on the inner walls of arteries, didn’t affect the software’s performance, and similarly, it was not impacted by differences in input image quality.

“Image quality and calcification burden did not negatively affect the diagnostic performance of AI,” explained Liu. “Thus, AI may be an efficient tool for the diagnosis of coronary artery stenosis.”

 

 

Sources: Diagnostic Imaging, European Journal of Radiology.


 

About the Author
  • Tara Fernandez has a PhD in Cell Biology and has spent over a decade uncovering the molecular basis of diseases ranging from skin cancer to obesity and diabetes. She currently works on developing and marketing disruptive new technologies in the biotechnology industry. Her areas of interest include innovation in molecular diagnostics, cell therapies, and immunology. She actively participates in various science communication and public engagement initiatives to promote STEM in the community.
You May Also Like
MAY 31, 2021
Clinical & Molecular DX
Researchers Create the First Saliva Wiki
MAY 31, 2021
Researchers Create the First Saliva Wiki
A new digital platform, developed by researchers at the University at Buffalo, is answering the question: what’s o ...
JUN 02, 2021
Genetics & Genomics
A Genetic Form of ALS is Discovered
JUN 02, 2021
A Genetic Form of ALS is Discovered
Some medical mysteries have become much easier to solve because of advanced genetic techniques that have enabled researc ...
JUN 15, 2021
Clinical & Molecular DX
An Early Warning System for Type 1 Diabetes in Children
JUN 15, 2021
An Early Warning System for Type 1 Diabetes in Children
In type 1 diabetes, or T1D, the body’s own immune system mistakenly launches an aggressive attack on insulin-produ ...
JUN 15, 2021
Cardiology
A Common Thread Among 20% of Sudden Cardiac Deaths
JUN 15, 2021
A Common Thread Among 20% of Sudden Cardiac Deaths
It's estimated that 450,000 Americans die from sudden heart conditions, and in about one in ten cases, the cause is unex ...
JUL 29, 2021
Clinical & Molecular DX
Sewage Sleuths: Tracking COVID Variants in Wastewater
JUL 29, 2021
Sewage Sleuths: Tracking COVID Variants in Wastewater
Since the dawn of the pandemic, one of the biggest challenges has been monitoring the crowned enemy as it spread through ...
AUG 19, 2021
Clinical & Molecular DX
Biosensor Illuminates Growing Tumors and Healing Wounds
AUG 19, 2021
Biosensor Illuminates Growing Tumors and Healing Wounds
Cancerous tissues can be difficult to spot, particularly at the early stages. The malignant cells are sometimes indistin ...
Loading Comments...