Automatic calculation of left ventricular volume in magnetic resonance imaging using an image-based clustering approach

Abstract

In this work we propose an algorithm to automate the process of left ventricular (LV) volume calculation during magnetic resonance imaging (MRI) analysis. The proposed algorithm does the LV segmentation, volume calculation, finds the time frames where the heart is in systole and diastole phase, and calculates LV ejection fraction. The proposed approach has been tested on a dataset containing MRI study results of 500 patients. According to experimental results the root mean square error of LV systolic volume calculation is 21.64 ml, LV diastolic volume - 44.92 ml, ejection fraction - 7.96 %.