AI Significantly Reduces the Time It Takes for Cardiac MRI
A study conducted in the UK found that by combining machine learning with Cardiac MRI analysis, the technique could be done at a faster rate and with similar results when compared to performing the imaging procedure manually.
September 25, 2019
Artificial intelligence can help Cardiac MRI analysis be performed at a faster rate and with similar precision to experts, a new study finds. The research was conducted in the U.K. and the results were published in Circulation: Cardiovascular Imaging, an American Heart Association journal.
Using AI, researchers were able to complete cardiac MRI scans in four seconds. This compares to the 13 minutes it takes humans to perform the cardiovascular imaging technique.
In the study, researchers trained a neural network to read the cardiac MRI scans and the results of almost 600 patients. When the AI was tested for precision compared to an expert and trainee on 110 separate patients from multiple centers, researchers found that there was no significant difference in accuracy.
Charlotte Manisty, M.D. Ph.D., the study’s author said, “Cardiovascular MRI offers unparalleled image quality for assessing heart structure and function; however, current manual analysis remains basic and outdated.
“Automated machine learning techniques offer the potential to change this and radically improve efficiency, and we look forward to further research that could validate its superiority to human analysis," Manisty said in a release. “Our dataset of patients with a range of heart diseases who received scans enabled us to demonstrate that the greatest sources of measurement error arise from human factors. This indicates that automated techniques are at least as good as humans, with the potential soon to be 'super-human' -- transforming clinical and research measurement precision."
Although the study did not demonstrate the superiority of AI over human experts and was not used prospectively for clinical assessment of patient outcomes, researchers said it highlights the potential that such techniques could have in the future to improve analysis and influence clinical decision making for patients with heart disease.
About the Author
You May Also Like