How can we ensure that placental pathology plays a greater role in treating neonatal morbidity?

Mapping cell-to-tissue graphs across human placenta histology whole slide images using deep learning with HAPPY

Accurate placenta pathology assessment is essential for managing maternal and newborn health, but the placenta's heterogeneity and temporal variability pose challenges for histology analysis. To address this issue, we developed the 'Histology Analysis Pipeline.PY' (HAPPY), a deep learning hierarchical method for quantifying the variability of cells and micro-anatomical tissue structures across placenta histology whole slide images. HAPPY differs from patch-based features or segmentation approaches by following an interpretable biological hierarchy, representing cells and cellular communities within tissues at a single-cell resolution across whole slide images. We present a set of quantitative metrics from healthy term placentas as a baseline for future assessments of placenta health and we show how these metrics deviate in placentas with clinically significant placental infarction. HAPPY's cell and tissue predictions closely replicate those from independent clinical experts and placental biology literature.

Criteria for placental examination for obstetrical and neonatal providers

Pathologic examination of the placenta can provide insight into likely (and unlikely) causes of antepartum and intrapartum events, diagnoses with urgent clinical relevance, prognostic information for mother and infant, support for practice evaluation and improvement, and insight into advancing the sciences of obstetrics and neonatology. Although it is true that not all placentas require pathologic examination (although alternative opinions have been expressed), prioritization of placentas for pathologic examination should be based on vetted indications such as maternal comorbidities or pregnancy complications in which placental pathology is thought to be useful for maternal or infant care, understanding pathophysiology, or practice modifications. Herein we provide placental triage criteria for the obstetrical and neonatal provider based on publications and expert opinion of 16 placental pathologists and a pathologists' assistant, formulated using a modified Delphi approach. These criteria include indications in which placental pathology has clinical relevance, such as pregnancy loss, maternal infection, suspected abruption, fetal growth restriction, preterm birth, nonreassuring fetal heart testing requiring urgent delivery, preeclampsia with severe features, or neonates with early evidence of multiorgan system failure including neurologic compromise. We encourage a focused gross examination by the provider or an attendant at delivery for all placentas and provide guidance for this examination. We recommend that any placenta that is abnormal on gross examination undergo a complete pathology examination. In addition, we suggest practice criteria for placental pathology services, including a list of critical values to be used by the relevant provider. We hope that these sets of triage indications, criteria, and practice suggestions will facilitate appropriate submission of placentas for pathologic examination and improve its relevance to clinical care.