From 13 mins to 4 seconds: Significant gains for Cardiac MRI with machine learning and AI

According to a new study, cardiac magnetic resonance imaging (MRI) analysis can be done much faster and accurately while using artificial intelligence and machine learning.

Currently, human-read cardiac MRI’s take around 13 minutes. Findings published in the journal Cardiovascular Imaging suggest that comparably precise scans be done via AI in approximately four seconds.

MRI machines are low in number in India and technology like this could greatly increase the efficiency of the existing machines.

In the UK, however, where the study was conducted, it is estimated that more than 150,000 cardiac MRI scans are performed each year.

Researchers believe that using AI to perform scans could lead to saving 54 clinician days per year at each UK health centre.

In this study, a neural network was trained to read the cardiac MRI scans and results of almost 600 patients. Researchers found no significant difference in its analysis as compared to human-experts.

The study underlines the potential that AI has to act as a force multiplier in clinical decision-making for heart patients.

Sign Up for nextbigwhat newsletter

The smartest newsletter, partly written by AI.

Download, the short news app for busy professionals