There are 15 million infants born prematurely each year worldwide. Of these, about 1 million will die of complications from reduced gestation (37 weeks and less) before the age of five. Cervical remodeling, which is the transformation of the cervix from a firm structure to a soft one, is essential for both term and preterm birth (PTB). Monitoring the uterine cervix remodeling and particularly the arrangement of the cervix primary structural components (elastin and collagen) is of great interest to researchers studying PTB. We have utilized a Self-validating Mueller Matrix Micro-Mesoscope (SAMMM) with convolutional neural networks (CNN) and K-nearest neighbor (K-NN) for classification of elastin and collagen fibers in the mouse cervix. In this work, we proposed that an independent polarized microscope can be used for collagen and elastin classification leveraging the previously developed classifier. The Mueller matrix and decomposition parameters of depolarization, retardance and diattenuation obtained with this system are fed to the previously developed classifier. Excised cervical tissues (50 μm thickness) were used in this study including samples obtained at different gestation days.
Along with second harmonic generation and two-photon excited fluorescence measured with Non-Linear Microscopy, polarization properties measured with Mueller Matrix Polarimetry Microscopy can improve our understanding of the remodeling process in preterm pregnancy. This is critical to define therapeutic targets and to develop clinical tools for early and accurate detection of preterm risks. While manual analyzing and classifying individual cervical samples is time-consuming, automated algorithms can be advantageous when the number of samples is large. To such extent, we demonstrate the use of Convolutional Neural Networks (CNN) for feature extraction and K-Nearest Neighbor (KNN) for classification as an alternative to manual assessment.
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.