Gestational Stage Prediction from Cervical Tissue Analysis Using Imaging Mueller Polarimetry Data

TL;DR

This study demonstrates that imaging Mueller polarimetry combined with deep learning can noninvasively predict gestational stages in cervical tissue by analyzing collagen microstructural changes, aiding preterm birth risk assessment.

Contribution

The paper introduces a novel application of Mueller polarimetry with CNNs to classify gestational stages based on collagen organization in cervical tissue.

Findings

Ensemble CNN achieved 70% accuracy in predicting gestational stage.

Spatial maps highlight collagen remodeling in the stroma as key for classification.

Deep learning outperformed traditional threshold methods.

Abstract

Preterm birth is associated with premature cervical remodeling, yet current clinical assessments cannot detect the underlying microstructural changes in collagen organization. We apply imaging Mueller polarimetry to murine cervical tissue at three gestational stages (early, mid, late) and develop classification methods to predict gestational stage from polarimetric maps. Using Lu-Chipman decomposition, we extract orientation and azimuth local variability maps that capture collagen fiber alignment and disorder. We evaluate two approaches under 20-fold leave-one-out cross-validation: an analytical threshold classifier on mean azimuth local variability, and a lightweight CNN ensemble (approximately 76k parameters) operating on spatially resolved maps. The ensemble achieves 70..0% sample-level accuracy, outperforming the analytical baseline (55.0%), with strong performance on early (71.0%) and late (86.0%) gestation. Spatial prediction maps confirm that classification accuracy is highest in the stroma, where collagen remodeling is most prominent. These results demonstrate that Mueller polarimetry combined with deep learning models can detect gestational collagen remodeling noninvasively, offering a potential pathway toward objective cervical assessment for preterm birth risk.