Clustering Based Fusion System for Blastomere Localization

Abstract

Microscopic digital image processing paves the way to deep study and evaluation of blastomere identification and/or localization to provide specific selection for in vitro fertilization (IVF) transfer. The main purpose of this thesis is to develop an automated image processing system which assist embryologists to study and investigate the behavior of developing pre implanted embryos wishing to improve IVF outcomes. The proposed method’s objective is calculate the number of blastomeres based on a clustering based fusion system, where the clustering algorithm enhance the results. Experimental results on a dataset of 50 embryo images with various blastomere numbers and sizes confirm that the proposed method identifies blastomeres with average Precision, sensitivity, and Overall Quality of 87.9%, 92.9%, and 82.3%, respectively.