An Automatic Method for Morphological Abnormality Detection in Metaphase II Human Oocyte Images

Abstract

The morphological evaluation of metaphase II (MII) oocytes before Intra-Cytoplasmic Sperm Injection (ICSI) can help to know and predict their developmental potential, the ICSI outcomes, and transfer the best embryo. The main morphometric features of MII oocytes are the thickness of zona pellucida, the width of perivitelline space, and the area of ooplasm and oocyte. Manual characterization of the MII oocytes can be prone to high inter-observer and intra-observer variability. In this study, we propose a fully automatic algorithm to identify malformations in images of human oocytes. 1500 images of MII oocytes were taken using inverted microscope before the ICSI process to build a dataset, namely the Human MII Oocyte Morphology Analysis Dataset (HMOMA-DS). The three main components of these prepared oocytes are analyzed. As the first step, we eliminated the noise and enhanced the quality of our input image. Further the regions were detected and segmented. Finally, the quality of the oocyte was assessed in terms of measuring the size and area of its main components. We have applied our method to the prepared dataset. It has been able to achieve an accuracy of 98.51% for the thickness of zona pellucida and area of oocyte. The accuracy values for measuring the area of ooplasm and the width of perivitelline space were 99.25% and 91.08%, respectively. The proposed fully automatic method performs effectively before ICSI due to its high accuracy and low computation time. It can help embryologists to select the best-qualified embryo based on the available analyzed parameters from injected oocytes in real-time.