Placental parenchymal lesions are commonly encountered and carry significant clinical associations. However, they are frequently missed or misclassified by general practice pathologists. Interpretation of pathology slides has emerged as one of the most successful applications of machine learning (ML) in medicine with applications ranging from cancer detection and prognostication to transplant medicine. The goal of this study was to use a whole-slide learning model to identify and classify placental parenchymal lesions including villous infarctions, intervillous thrombi (IVT), and perivillous fibrin deposition (PVFD).
We generated whole slide images from placental discs examined at our institution with infarct, IVT, PVFD, or no macroscopic lesion. Slides were analyzed as a set of overlapping patches. We extracted feature vectors from each patch using a pretrained convolutional neural network (EfficientNetV2L). We trained a model to assign attention to each vector and used the attentions as weights to produce a pooled feature vector. The pooled vector was classified as normal or 1 of 3 lesions using a fully connected network. Patch attention was plotted to highlight informative areas of the slide.
Overall balanced accuracy in a test set of held-out slides was 0.86 with receiver-operator characteristic areas under the curve of 0.917-0.993. Cases of PVFD were frequently miscalled as normal or infarcts, the latter possibly due to the perivillous fibrin found at the periphery of infarctions. We used attention maps to further understand some errors, including one most likely due to poor tissue fixation and processing.
We used a whole-slide learning paradigm to train models to recognize three of the most common placental parenchymal lesions. We used attention maps to gain insight into model function, which differed from intuitive explanations.

The placenta is at the core of many pregnancy pathologies, but we have limited knowledge about placental function because of two key research barriers: 1) lack of guidelines for sample collection and pathologic diagnosis; and 2) limited tools are available for molecular analysis of stored placental samples. We aimed to create a searchable, population-based placental database of pathologic diagnoses, and to validate molecular methods for gene expression studies of matching formalin fixed paraffin embedded (FFPE) placental blocks. Our database has over 1000 pregnancies coded for clinical diagnosis with corresponding FFPE blocks that are available for gene expression studies. RNA harvested from FFPE tissues is of sufficient quality for downstream applications. We successfully used this pipeline to identify FFPE placenta from term and preterm pregnancies, and compared their gene expression. The establishment of this platform, which links clinicopathological data and molecular gene expression, will increase our understanding of obstetrical diseases.

BACKGROUND: Implementation of universal antiretroviral therapy (ART) has significantly lowered vertical transmission rates but has also increased numbers of human immunodeficiency virus (HIV)-exposed uninfected children, who remain vulnerable to morbid effects. In the current study, we investigated whether T-cell alterations in the placenta contribute to altered immune status in HIV-exposed uninfected.
METHODS: We analyzed T cells from term placenta decidua and villous tissue and paired cord blood from pregnant women living with HIV (PWH) who initiated ART late in pregnancy (n = 21) with pregnant women not living with HIV (PWNH) (n = 9).
RESULTS: Placentas from PWH showed inverted CD4/CD8 ratios and higher proportions of tissue resident CD8+ T cells in villous tissue relative to control placentas. CD8+ T cells in the fetal capillaries, which were of fetal origin, were positively correlated with maternal plasma viremia before ART initiation, implying that imbalanced T cells persisted throughout pregnancy. In addition, the expanded memory differentiation of CD8+ T cells was confined to the fetal placental compartment and cord blood but was not observed in the maternal decidua.
CONCLUSIONS: T-cell homeostatic imbalance in the blood circulation of PWH is reflected in the placenta. The placenta may be a causal link between HIV-induced maternal immune changes during gestation and altered immunity in newborn infants in the absence of vertical transmission.

Assisted reproductive technology including in vitro fertilization (IVF) and oocyte donation (OD) may increase risk for placenta-mediated diseases. Comprehensive analysis of histopathological placental lesions according to source of oocytes used in the IVF procedure - recipient derived (RD-IVF) vs oocyte donation (OD-IVF), has not been conducted in a population with a hypertensive disorder of pregnancy (HDP) and/or intrauterine growth restriction (IUGR).
A retrospective cohort study of archived placenta specimens from RD-IVF and OD-IVF pregnancies affected by HDP and/or IUGR was conducted with blinded histopathological placental examination. Three categories of lesions were differentiated and defined as main outcomes: maternal vascular malperfusion (MVM), chronic inflammation, and fetal vascular malperfusion (FVM). To determine the relationship between conception method and placental lesions, multivariable regressions were performed with maternal age, gestational age, HDP, birth and placental weight percentiles as model covariates.
115 placentas were included 83 (72.2%) RD-IVF, 32 (27.8%) OD-IVF. Adjusted OR (aOR) for conception method was 5.05 (95%CI 0.58-43.90, p=0.142) for MVM, 1.87 (95%CI 0.68-5.15, p=0.228) for chronic inflammatory and 0.61 (95%CI 0.15-2.37, p=0.471) for FVM lesions. Multiple gestation demonstrated borderline association with MVM (aOR=0.24, 95%CI 0.04-1.51, p=0.129) and total pathology score (aRR=0.79, 95%CI 0.62-1.01, p=0.058). Subgroup analysis suggested greater odds of villitis of unknown etiology (VUE) for OD-IVF (aOR=2.98, 95%CI 1.12-7.93, p=0.029).
Source of oocyte derivation demonstrated no evidence of association with main outcomes in cases of HDP and/or IUGR. Subgroup analysis demonstrated increased rates of inflammatory lesions for OD-IVF. Multiple gestation may be associated with decreased MVM and total lesions.

Objective  In this currently evolving coronavirus disease 2019 (COVID-19) pandemic, the evidence is scarce about the impact of COVID-19 infection on women in labor and neonates in an inner city African-Americans (AA) population. The objective of this study was to evaluate the clinical outcomes and placental pathology in mother-infant dyads in COVID-19 cases. Study Design  Retrospective chart review was conducted on 34 COVID-19 positive mother-infant dyads to study their baseline characteristics and outcomes. Placental pathology was reviewed by two perinatal pathologists. Results  COVID-19 was noted in 3% of pregnant women who delivered in our institution. The majority (82%) of them were asymptomatic. Out of the four mothers who were symptomatic, only three (9%) required supplemental oxygen. None of them required invasive ventilation. All the neonates tested negative for COVID-19 at 24 hours of age. There were no gross or microscopic pathological abnormalities detected that could be definitely associated with any COVID-19 related complications during pregnancy in any of the 34 placentas. Conclusion  COVID-19 does not appear to increase morbidity and mortality among pregnant women and their neonates in a predominantly AA population. Our study did not find any evidence of vertical transmission of COVID-19 infection nor any specific findings on placental pathology. Key Points Majority of women infected by coronavirus disease 2019 (COVID-19) during labor were asymptomatic.None of the newborns tested positive for COVID-19 at 24 hours of age.Placental pathology findings were nonspecific in COVID-19 mothers.

OBJECTIVE: To explore the clinical characteristics and placental pathological changes of pregnant women with 2019 novel coronavirus (CoV) disease (COVID-19) in the third trimester, and to assess the possibility of vertical transmission.
RESULTS: The placenta tissues were evaluated by using immunohistochemistry for inflammatory cells and Hofbauer cells, and using severe acute respiratory syndrome (SARS) CoV-2 RNA Fluorescence In-Situ Hybridization (FISH) and SARS-CoV-2 spike protein immunofluorescence (IF) double staining. All eight placentas from the third trimester pregnancy women were studied. All patients were cured, no clinical or serological evidence pointed to vertical transmission of SARS-CoV-2. Features of maternal vascular malperfusion (MVM) such as increased syncytial knots were present in all 8 cases (8/8), and increased focal perivillous fibrin depositions were presented in 7 cases (7/8). No significate chronic histiocytic intervillositis was noted in the placenta. The number of macrophages and inflammatory cells such as T cells, B cells and plasma cells in the placental villous was not significantly increased in all cases. Moreover, all of eight cases demonstrated negative results by FISH using a SARS-CoV-2 virus RNA probe and by IF using a monoclonal antibody against SARS-CoV-2 spike protein.
CONCLUSIONS: We found no evidence of vertical transmission and adverse maternal-fetal outcomes in the placentas of third trimester COVID-19 pregnancy women, which provided further information for the clinical management of those women in the third trimester. However, further studies are still needed for patients with infections in different stage of gestation, especially in first and second trimester.

To study the association between placental pathology and neonatal birthweight and outcomes, and whether a combination of first trimester biomarkers and fetal growth velocity can predict placental lesions.
The presence of maternal vascular malperfusion (MVM) lesions (Amsterdam criteria) was recorded in a retrospective cohort of singleton pregnancies in the Maastricht University Medical Centre, 2011-2018. First trimester maternal characteristics and PAPP-A, PlGF and sFlt-1 levels were collected. Fetal growth velocities were calculated (mm/week) from 20 to 32 weeks for abdominal circumference, biparietal diameter, head circumference and femur length. Data were compared between neonates with \'small for gestational age\' (SGA < p10) and different categories of \'appropriate for gestational age (AGA)\': AGAp10-30, AGAp30-50 and AGA > p50 (reference), using one-way ANOVA and post hoc test.
There were significantly more MVM lesions in the SGA group (94.6% p < .0001), but also in the AGAp10-30 (67.3% p < .0001) and AGAp30-50 (41.6% p = 0.002), compared to the reference AGA group (19.3%). The prediction of MVM for a 20% false-positive rate, with maternal characteristics was25.2%. The addition of birthweight percentile gave a prediction of 51.7% for MVM. However adding placental biomarkers and fetal growth velocities (instead of birthweight percentile) to the maternal characteristics, gave a prediction of 81.8% (PPV 49.5%, NPV 53.7%).
Placental MVM lesions correlated inversely with birthweight even in AGA neonates, and was associated with slower fetal growth and more adverse outcome in SGA neonates. A combination of first trimester biomarkers and fetal growth velocity had good prediction of placental MVM lesions, as an indicator of fetal growth restriction irrespective of neonatal weight.

Preeclampsia is a life-threatening disorder of pregnancy, demonstrating a high degree of heterogeneity in clinical features such as presentation, disease severity, and outcomes. This heterogeneity suggests distinct pathophysiological mechanisms may be driving the placental disease underlying this disorder. Our group recently reported distinct clusters of placental gene expression in preeclampsia and control pregnancies, allowing for the identification of at least 3 clinically relevant gene expression-based subtypes of preeclampsia. Histopathological examination of a small number of samples from 2 of the gene expression-based subtypes revealed placental lesions consistent with their gene expression phenotype, suggesting that detailed placental histopathology may provide further insight into the pathophysiology underlying these distinct gene expression-based subtypes.
The objective of the study was to assess histopathological lesions in the placentas of patients belonging to each identified gene expression-based subtype of preeclampsia, characterized in our previous study. Our goal was to further understand the pathophysiologies defining these gene expression-based subtypes by integrating gene expression with histopathological findings, possibly identifying additional subgroups of preeclampsia patients.
Paraffin-embedded placental biopsies from patients included in the gene expression profiling study (n = 142 of 157, 90.4%) were sectioned, hematoxylin and eosin stained, and imaged. An experienced perinatal pathologist, blinded to gene expression findings and clinical information, assessed the presence and severity of histological lesions using a comprehensive, standardized data collection form. The frequency and severity scores of observed histopathological lesions were compared among gene expression-based subtypes as well as within each subtype using using Fisher exact tests, Kruskal-Wallis tests, and hierarchical clustering. The histological findings of the placental samples were visualized using t-distributed stochastic neighbor embedding and phylogenetic trees. Concordance and discordance between gene expression findings and histopathology were also investigated and visualized using principal component analysis.
Several histological lesions were found to be characteristic of each gene expression-based preeclampsia subtype. The overall concordance between gene expression and histopathology for all samples was 65% (93 of 142), with characteristic placental lesions for each gene expression-based subtype complementing prior gene enrichment findings (ie, placentas with enrichment of hypoxia-associated genes showed severe lesions of maternal vascular malperfusion). Concordant samples were located in the central area of each gene expression-based cluster when viewed on a principal component analysis plot. Interestingly, discordant samples (gene expression and histopathology not reflective of one another) were generally found to lie at the periphery of the gene expression-based clusters and tended to border the group of patients with phenotypically similar histopathology.
Our findings demonstrates a high degree of concordance between placental lesions and gene expression across subtypes of preeclampsia. Additionally, novel integrative analysis of scored placental histopathology severity and gene expression findings allowed for the identification of patients with intermediate phenotypes of preeclampsia not apparent through gene expression profiling alone. Future investigations should examine the temporal relationship between these 2 modalities as well as consider the maternal and fetal contributions to these subtypes of disease.