Meeting Banner
Abstract #1248

Artificial Intelligent Technique for Measuring Heart Volume from MRI Images Using Iterative Salient Isolated Threshold Optimization Ant Algorithm (ISITOAA)

El-Sayed H. Ibrahim1, Shannon Birchell2, Sherif Elfayoumy2

1Department of Radiology, University of Florida, Jacksonville, FL, United States; 2School of Computing, University of North Florida, Jacksonville, FL, United States

Manual segmentation of MRI images is inefficient and inconsistent method for measuring ventricular volumes. In this study, new artificial intelligence technique (ISITOAA) is developed and implemented for measuring ventricular volumes. The technique is based on automatic delineation of blood-myocardium border using ant colony optimization with salient isolated thresholding. The technique was implemented on datasets from eight volunteers and the results were compared to manual segmentation. ISITOAA provided both left and right ventricular segmentation in single processing, and provided stability measure of the solution. ISITOAA showed good agreement with the gold standard and was faster and more consistent than manual segmentation.

Abstract PDF

Keywords

accordingly accurate actual adaptive adds agents agreement another ants artificial axis bias bland blood boundaries boundary cine coefficients colonies communicate computer computing conducted considered consistency contours converge core cross degrees delineate delineation describes detection detects deviations dies ding eight encounter food foraging gold good greater heart immediately implementation integration intelligence isolated iterative leads lied limit location long manual measure measured measuring minutes move movements myocardium north optimal parallel path personal pheromone pixel pixels process reached resolves respectively rules salient scanned scanner school segmentation segmentations severe share significantly simulating sing solution specified stability statistical stochastic task threshold trail transactions trapped traveled ventricular versus vision volume volumes