A team of researchers from the Universities of East Anglia (UEA), Sheffield, and Leeds has developed a groundbreaking method for analyzing heart MRI scans using artificial intelligence (AI). This innovative approach promises to save valuable NHS time and resources while improving patient care.
The intelligent computer model, created by the research teams, utilizes AI to examine heart images from MRI scans specifically in the four-chamber plane. This method allows for a comprehensive analysis of the heart’s structure and function, providing rapid and accurate diagnoses of heart conditions.
“Unlike a standard manual MRI analysis, which can take up to 45 minutes or more, the new AI model takes just a few seconds. This automated technique could offer speedy and dependable evaluations of heart health, with the potential to enhance patient care.
[block_2]The retrospective observational study included data from 814 patients from Sheffield Teaching Hospitals NHS Foundation Trust and Leeds Teaching Hospitals NHS Trust, used to train the AI model. To ensure accuracy, scans and data from another 101 patients from the Norfolk and Norwich University Hospitals NHS Foundation Trust were used for testing.
While previous 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 and tested on a diverse patient group from another hospital. Additionally, it provides a complete analysis of the entire heart, showing all four chambers, unlike earlier studies that focused on the heart’s two main chambers.
[block_4]Dr. Hosamadin Assadi, a PhD student at UEA’s Norwich Medical School, highlighted the significance of this development: “Automating the process of assessing heart function and structure will save time and resources and ensure consistent results for doctors. This innovation could lead to more efficient diagnoses, better treatment decisions, and ultimately, improved outcomes for patients with heart conditions.”
The researchers emphasize the potential of AI to predict mortality based on heart measurements, which could revolutionize cardiac care and improve patient prognosis. Future studies will test the model on larger groups of patients from different hospitals, using various types of MRI scanners, and including other common diseases to validate its effectiveness in a broader range of real-world scenarios.
Additional research from the teams at UEA, Leeds, and Sheffield has also refined the use of heart MRI scans for female patients, particularly those with early or borderline heart disease, leading to a 16.5% increase in diagnoses among females.
This research was a collaborative effort between UEA, 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. The study was supported by funding for Dr. Pankaj Garg from the Wellcome Trust Clinical Research Career Development Fellowship.
The findings are published in the European Radiology Experimental under the title “Development and validation of AI-derived segmentation of four-chamber cine CMR.”
