Researchers from the Universities of East Anglia (UEA), Sheffield and Leeds developed the computer model that utilises AI to examine heart images from MRI scans in a specific view known as the four-chamber plane.
“The AI model precisely determined the size and function of the heart's chambers and demonstrated outcomes comparable to those acquired by doctors manually, but much quicker,” lead researcher Dr Pankaj Garg, of UEA’s Norwich Medical School and a consultant cardiologist at the Norfolk and Norwich University Hospital, said in a statement.
“Unlike a standard manual MRI analysis, which can take up to 45 minutes or more, the new AI model takes just a few seconds.”
The retrospective observational study consisted of data from 814 patients from Sheffield Teaching Hospitals NHS Foundation Trust and Leeds Teaching Hospitals NHS Trust, which was then used to train the AI model.
To ensure the model’s results were accurate, scans and data from another 101 patients from the Norfolk and Norwich University Hospitals NHS Foundation Trust were then used for testing.
While other studies have investigated the use of AI in interpreting MRI scans, the researchers said that this latest AI model was trained using data from multiple hospitals and different types of scanners, as well as conducting the testing on a diverse group of patients from a different hospital.
More from Medical and Healthcare
In addition, this AI model provides a complete analysis of the entire heart using a view that shows all four chambers, while most earlier studies focused on a view that only looks at the heart's two main chambers.
PhD student Dr Hosamadin Assadi, UEA’s Norwich Medical School, said: “This innovation could lead to more efficient diagnoses, better treatment decisions, and ultimately, improved outcomes for patients with heart conditions.
“Moreover, the potential of AI to predict mortality based on heart measurements highlights its potential to revolutionise cardiac care and improve patient prognosis.”
Looking ahead, the researchers said that future studies should test the model using larger groups of patients from different hospitals, with various types of MRI scanners, and including other common diseases seen in medical practice to see if it works well in a broader range of real-world situations.
The research was a collaboration between UEA, Leeds University, Sheffield University, Leiden University Medical Centre, the Norfolk and Norwich University Hospitals NHS Foundation Trust, Sheffield Teaching Hospitals NHS Foundation Trust and Leeds Teaching Hospitals NHS Trust.
The study was supported by funding for Dr Pankaj Garg from the Wellcome Trust Clinical Research Career Development Fellowship.
‘Development and validation of AI-derived segmentation of four-chamber cine CMR' was published in the European Radiology Experimental, and can be read in full here.
NESO report says clean grid achievable by 2030
This report shows a welcome increase in realism. They have realised that storage is not going to work and will be using gas to fill the holes. Gas...