Towards Deep Cellular Phenotyping in Placental Histology

TL;DR

This paper introduces a deep learning pipeline for cellular analysis of placental histology, enabling accurate cell classification and phenotypic characterization to advance understanding of placental biology and fetal health.

Contribution

It presents a novel open-source deep learning method combining CNNs and transfer learning for placental cell classification and phenotypic embedding.

Findings

Achieved 89% accuracy in classifying five placental cell types.

Developed embeddings that differentiate cell populations and phenotypic variance.

Potential to scale to population studies for better understanding of placental health.

Abstract

The placenta is a complex organ, playing multiple roles during fetal development. Very little is known about the association between placental morphological abnormalities and fetal physiology. In this work, we present an open sourced, computationally tractable deep learning pipeline to analyse placenta histology at the level of the cell. By utilising two deep Convolutional Neural Network architectures and transfer learning, we can robustly localise and classify placental cells within five classes with an accuracy of 89%. Furthermore, we learn deep embeddings encoding phenotypic knowledge that is capable of both stratifying five distinct cell populations and learn intraclass phenotypic variance. We envisage that the automation of this pipeline to population scale studies of placenta histology has the potential to improve our understanding of basic cellular placental biology and its variations, particularly its role in predicting adverse birth outcomes.