| Objective: To assess oocyte quality to improve assisted reproductive technologies and high quality embryo
production using image processing methods.
Design: A cross-sectional study.
Setting: Pasteur Institute, Iran.
Subject(s): 6 microscopic graphs (including 31 oocytes) of the NMRI mice oocytes that were recorded
with a stereomicroscope (Olympus, CX21, Tokyo, Japan).
Intervention(s): To apply image processing techniques for oocyte quality assessment.
Main outcome measure(s): oocyte areas segmentation using Moore neighborhood contour tracking
method and, oocytes clustering in terms of the number of particles in the cytoplasm with the gray-level
co-occurrence matrix texture features.
Result(s): The success rate of the proposed algorithm is 82/48% and 91/00% in segmentation and clustering
stages, respectively.
Conclusion(s): The results of the evaluation criteria also reflect the proper functioning of the proposed
algorithm. The three obtained clusters provided the following classification of oocyte images.
Oocytes with medium or high granularity and eventually some anomalies such as inclusions or vacuoles,
oocytes with medium granularity, oocytes with low granularity are oocyte’s clusters. |