Unsupervised fully automated inline analysis of global left ventricular function in CINE MR imaging

Area of Science:

• Cardiovascular imaging
• Medical image analysis
• Cardiac MRI techniques

Background:

• Accurate assessment of global systolic cardiac function and myocardial mass is crucial for diagnosing and managing cardiac disorders.
• Manual segmentation of cardiac MRI data is time-consuming and subject to inter-observer variability.
• Developing automated methods for inline analysis can improve efficiency and consistency in cardiac function assessment.

Purpose of the Study:

• To implement and evaluate the accuracy of unsupervised, fully automated inline analysis for global ventricular function and myocardial mass.
• To compare the accuracy of automated segmentation with manual segmentation in patients with cardiac disorders.
• To assess the correlation and agreement between automated and manual measurements of end-diastolic volume, end-systolic volume, ejection fraction, and myocardial mass.

Main Methods:

• Fifty patients underwent cine imaging of the left ventricle using an accelerated steady-state free precession sequence on a 1.5 Tesla MRI scanner.
• Fully automated segmentation and contouring were performed instantaneously after image acquisition.
• Cine datasets were also manually segmented using semi-automated postprocessing software for comparison.

Main Results:

• Automated inline analysis showed high correlation with manual segmentation for end-diastolic volume (r=0.96), end-systolic volume (r=0.95), ejection fraction (r=0.89), and myocardial mass (r=0.96).
• No significant differences were found between automated and manual evaluations for end-diastolic volume, end-systolic volume, and ejection fraction.
• Significant differences were observed for myocardial mass (P < 0.01), with automated analysis yielding higher values.
• Manual analysis averaged 15 minutes per patient, while automated analysis was performed instantaneously.

Conclusions:

• Unsupervised, fully automated segmentation and contouring during image reconstruction enable accurate evaluation of global systolic cardiac function.
• Automated inline analysis provides a rapid and reliable method for assessing cardiac function and myocardial mass.
• This automated approach has the potential to streamline cardiac MRI workflows and improve diagnostic efficiency.