Towards Deep Cellular Phenotyping in Placental Histology
This work addresses the challenge of automating cellular phenotyping in placental histology for population-scale studies, which could improve understanding of placental biology and its role in predicting adverse birth outcomes, though it appears incremental as it applies existing deep learning methods to a new medical domain.
The researchers tackled the problem of analyzing placental histology at the cellular level by developing an open-source deep learning pipeline that localizes and classifies placental cells into five classes with 89% accuracy, while also learning deep embeddings to stratify cell populations and capture intraclass variance.
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.