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.
Unlike a standard manual MRI analysis, which can take up to 45 minutes or more, the new AI model takes just a few seconds.
It was then tested with data and scans from 101 additional patients at Norfolk and Norwich University Hospitals NHS Foundation Trust to verify the model’s predictive accuracy.
Moreover, while earlier research typically focused on a two-chamber view of the heart, this AI model employs a comprehensive approach, analyzing all four heart chambers to provide a more complete examination.
Automating the process of assessing heart function and structure will save time and resources and ensure consistent results for doctors.
Researchers from the University of East Anglia, Sheffield, and Leeds have created an innovative AI-based technique for analyzing heart MRI scans, potentially saving the NHS valuable time and resources while enhancing patient care. This study was published in the journal European Radiology Experimental.
Dr. Pankaj Garg, a Consultant Cardiologist at Norfolk and Norwich University Hospital and a Lecturer at the University of East Anglia's Norwich Medical School, is at the forefront of developing a groundbreaking 4D MRI imaging technology. This new method allows for the quick, non-invasive, and precise diagnosis of heart failure.
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. 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. Dr. Pankaj Garg, Study Lead Investigator and Lecturer, University of East Anglia
The AI model was developed through a retrospective observational study using data from 814 patients across Leeds Teaching Hospitals NHS Trust and Sheffield Teaching Hospitals NHS Foundation Trust. It was then tested with data and scans from 101 additional patients at Norfolk and Norwich University Hospitals NHS Foundation Trust to verify the model’s predictive accuracy.
This latest AI model has been trained with data from multiple hospitals and various scanner types, and tested on a diverse patient group from a different hospital.
Previous studies have explored AI's role in interpreting MRI scans. Moreover, while earlier research typically focused on a two-chamber view of the heart, this AI model employs a comprehensive approach, analyzing all four heart chambers to provide a more complete examination.
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. Moreover, the potential of AI to predict mortality based on heart measurements highlights its potential to revolutionise cardiac care and improve patient prognosis. Dr. Hosamadin Assadi, PhD Student, Norwich Medical School, University of East Anglia
The researchers recommend that future studies expand the testing of the model to include larger patient groups from various hospitals, different MRI scanner types, and a broader spectrum of common medical conditions to evaluate its effectiveness in more diverse real-world settings.
In other recent developments, teams from the University of East Anglia, the University of Leeds, and the University of Sheffield have improved the use of heart MRI scans for diagnosing women with early or borderline heart disease, resulting in a 16.5% increase in diagnoses among this demographic.
This research was a joint effort involving multiple institutions: the University of East Anglia, the University of Leeds, the University of Sheffield, Leiden University Medical Centre, Norfolk and Norwich University Hospitals NHS Foundation Trust, Sheffield Teaching Hospitals NHS Foundation Trust, and Leeds Teaching Hospitals NHS Trust.
Dr. Pankaj Garg's research was supported by a Wellcome Trust Clinical Research Career Development Fellowship.
Journal Reference:
Assadi, H., et al. (2024). Development and validation of AI-derived segmentation of four-chamber cine cardiac magnetic resonance. European Radiology Experimental. doi.org/10.1186/s41747-024-00477-7.
