a-neural-network-based-identification-developmentally-competent-or

A Neural Network-Based Identification of Developmentally Competent or Incompetent Mouse Fully-Grown Oocytes

Infertility clinics would benefit from the ability to select developmentally competent vs. incompetent oocytes using non-invasive procedures, thus ...

University of Pavia

University of Helsinki

Full-grown mouse antral oocytes are classified as surrounding nucleolus (SN) or not-surrounding nucleolus (NSN), depending on the respective presence or absence of a ring of Hoechst-positive chromatin surrounding the nucleolus. In culture, both types of oocytes resume meiosis and reach the metaphase II (MII) stage, but following insemination, NSN oocytes arrest at the two-cell stage whereas SN oocytes may develop to term. By coupling time-lapse bright-field microscopy with image analysis based on particle image velocimetry, we provide the first systematic measure of the changes to the cytoplasmic movement velocity (CMV) occurring during the germinal vesicle-to-MII (GV-to-MII) transition of these two types of oocytes. Compared to SN oocytes, NSN oocytes display a delayed GV-to-MII transition, which can be mostly explained by retarded germinal vesicle break down and first polar body extrusion. SN and NSN oocytes also exhibit significantly different CMV profiles at four main time-lapse intervals, although this difference was not predictive of SN or NSN oocyte origin because of the high variability in CMV. When CMV profile was analyzed through a trained artificial neural network, however, each single SN or NSN oocyte was blindly identified with a probability of 92.2% and 88.7%, respectively. Thus, the CMV profile recorded during meiotic resumption may be exploited as a cytological signature for the non-invasive assessment of the oocyte developmental potential, and could be informative for the analysis of the GV-to-MII transition of oocytes of other species.

Thi Thu Hien Bui

Biography

JoVE Journal Publications

Other Publications