The paper presents an algorithm based on low order statistics for the informative feature extraction for Raman spectroscopy data. The proposed method was tested on mouse preimplantation embryos Raman spectra. Both supervised and unsupervised machine learning methods were applied to selected the most informative features to test the separability of the processed data.
The paper presents an analysis of the Raman spectra of mouse preimplantation embryos using machine learning for visualization, assessing the separability of classes, and highlighting informative areas of the spectrum. Separation of lipid reach areas and nucleus spectra was shown by principal component analysis coupled with a linear support vector machine.
The effect of the laser pulse energy and total expose of the energy incident on the embryo blastomere fusion probability was investigated. The probability of the four different events after laser pulse was determined: the fusion of two blastomeres with the following formation of tetraploid embryo, the destruction of the first blastomere occurs, the second blastomere conservation remains intact, the destruction and the death of both cells; two blastomeres were not fused, and no morphological changes occurred. We report on viability and quality of the embryo after laser surgery as a function of the laser energy incident. To characterize embryo quality, the probability of the blastocyst stage achievement was estimated and the blastocyst cells number was calculated. Blastocoel formation is the only event of morphogenesis in the preimplantation development of mammals, so we assumed it as an indicator of the time of embryonic “clocks” and observed it among fused and control embryos. The blastocoel formation time is the same for fused and control embryos. It indicates that embryo clocks were not affected due to blastomere fusion. Thus, the analysis of the fluorescence microscopic images of nuclei in the fused embryo revealed that nuclei fusion does not occur after blastomere fusion.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.