Effect of left ventricular longitudinal axis variation in pathological hearts using Deep learning

EasyChair Preprint 648

Abstract

Cardiac disease is a primary cause of death worldwide. Prior study has indicated that the dynamics of the cardiac left ventricle (LV) during diastolic filling is a major indicator of cardiac viability. Hence, studies have aimed to evaluate cardiac health based on quantitative parameters unfolding LV function. In this research, it is demonstrated that major aspects of the cardiac function (Ejection Fraction) are reflected abnormalities of the left ventricular on longitudinal axis variation. We used deep learning algorithms on classifications and found that the LV correlates well with existing measures of cardiac health such as the LV ejection fraction. Our results reveal the relations among the wall regions of the data using a structure learning algorithm. This research could potentially be used as determination value to predict patients with future cardiac disease problems leading to heart failure.

Keyphrases: Cardiac wall motion, Ejection Fraction, Pathological heart, deep learning

@booklet{EasyChair:648,
  author    = {Yashbir Singh and Deepa S and Shi Yi Wu and João Manuel R. S. Tavares and Michael Friebe and Weichih Hu},
  title     = {Effect of left ventricular longitudinal axis variation in pathological hearts using Deep learning},
  howpublished = {EasyChair Preprint 648},
  year      = {EasyChair, 2018}}