Researchers have created a new method using artificial intelligence (AI) to analyze heart MRI scans.
This breakthrough can save the National Health Service (NHS) valuable time and resources while improving patient care.
Teams from the Universities of East Anglia (UEA), Sheffield, and Leeds worked together to develop an intelligent computer model. This model uses AI to examine heart images from MRI scans, focusing on a specific view called the four-chamber plane.
Their study, “Development and validation of AI-derived segmentation of four-chamber cine CMR,” was published in the European Radiology Experimental journal.
Dr. Pankaj Garg, a lead researcher from the University of East Anglia’s Norwich Medical School and a cardiologist at the Norfolk and Norwich University Hospital, led this innovative project.
His team has developed advanced 4D MRI imaging technology, which helps diagnose heart failure and other cardiac conditions more quickly and accurately.
Dr. Garg explained that the AI model accurately measured the size and function of the heart’s chambers. It produced results comparable to those done manually by doctors but much faster.
Traditional manual MRI analysis can take up to 45 minutes, but the new AI model completes the task in just a few seconds. This automated technique provides quick and reliable evaluations of heart health, potentially improving patient care.
The study involved analyzing data from 814 patients from Sheffield Teaching Hospitals NHS Foundation Trust and Leeds Teaching Hospitals NHS Trust to train the AI model.
To ensure the accuracy of the model’s results, scans and data from another 101 patients from the Norfolk and Norwich University Hospitals NHS Foundation Trust were used for testing.
While other studies have explored AI in interpreting MRI scans, this new AI model stands out. It was trained using data from multiple hospitals and different types of scanners.
The testing was also conducted on a diverse group of patients from another hospital. Unlike earlier studies that focused only on the heart’s two main chambers, this AI model provides a complete analysis of the entire heart, showing all four chambers.
Ph.D. student Dr. Hosamadin Assadi from UEA’s Norwich Medical School highlighted the benefits of this AI innovation. Automating the process of assessing heart function and structure saves time and resources and ensures consistent results for doctors.
This can lead to quicker diagnoses, better treatment decisions, and improved outcomes for patients with heart conditions. The AI’s ability to predict mortality based on heart measurements also shows its potential to revolutionize cardiac care.
The researchers suggest that future studies should test the AI model with larger groups of patients from various hospitals and with different types of MRI scanners.
Including other common diseases seen in medical practice will help determine if the model works well in a broader range of real-world situations.
Additionally, recent research from UEA, Leeds, and Sheffield has improved the use of heart MRI scans for female patients, especially those with early or borderline heart disease. This advancement has enabled 16.5% more females to be diagnosed.
This research was a collaborative effort involving the University of East Anglia, the University of Leeds, the University of Sheffield, 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.
If you care about heart health, please read studies that yogurt may help lower the death risks in heart disease, and coconut sugar could help reduce artery stiffness.
For more information about health, please see recent studies that Vitamin D deficiency can increase heart disease risk, and results showing vitamin B6 linked to lower death risk in heart disease.
The research findings can be found in European Radiology Experimental.
Copyright © 2024 Knowridge Science Report. All rights reserved.
