, Sheffield, and Leeds have developed a groundbreaking artificial intelligence (AI) method for analyzing heart MRI scans.){kind=link}
Researchers from the Universities of East Anglia (UEA), Sheffield, and Leeds have developed a groundbreaking artificial intelligence (AI) method for analyzing heart MRI scans. This innovative approach promises to save valuable NHS time and resources while significantly improving patient care.
The research team, led by Dr. Pankaj Garg of UEA’s Norwich Medical School and a consultant cardiologist at Norfolk and Norwich University Hospital, has created an intelligent AI model that examines heart images from MRI scans using the four-chamber plane view. This pioneering 4D MRI imaging technology enables faster, non-invasive, and more accurate diagnoses of heart failure and other cardiac conditions.
Dr. Garg explained, “Our AI model precisely determines the size and function of the heart’s chambers, providing outcomes comparable to manual analysis by doctors but much quicker. Unlike traditional manual MRI analysis, which can take up to 45 minutes or more, the new AI model completes the task in just a few seconds. This automated technique offers speedy and dependable evaluations of heart health, potentially enhancing patient care.”
The retrospective observational study utilized data from 814 patients at Sheffield Teaching Hospitals NHS Foundation Trust and Leeds Teaching Hospitals NHS Trust to train the AI model. To ensure accuracy, the model was then tested using scans and data from an additional 101 patients at Norfolk and Norwich University Hospitals NHS Foundation Trust.
While previous studies have explored AI in MRI scan interpretation, this latest model stands out due to its training on data from multiple hospitals and various types of scanners. It also provides a comprehensive analysis of the entire heart, using a view that shows all four chambers, unlike earlier studies that focused on only two chambers.
Dr. Hosamadin Assadi, a PhD student at UEA’s Norwich Medical School, emphasized, “Automating the assessment of heart function and structure saves time and resources and ensures consistent results for doctors. This innovation could lead to more efficient diagnoses, better treatment decisions, and ultimately, improved outcomes for patients with heart conditions. Additionally, the AI’s potential to predict mortality based on heart measurements highlights its capability to revolutionize cardiac care and enhance patient prognosis.”
Future studies will test the AI model with larger patient groups from various hospitals, different MRI scanners, and include other common diseases to evaluate its effectiveness in a broader range of real-world situations.