Redefining maternal vascular malperfusion (MVM) placental disease by circulating placental growth factor (PlGF) level

Zur, Rebecca L.; McLaughlin, Kelsey; Aalto, Laura; Parks, W. Tony; Kingdom, John

doi:10.1016/j.ajog.2022.11.1217

Cited by 3 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Uterine spiral artery remodeling is vital for healthy pregnancy, and when disrupted, results in hypoxia-related placental injuries -observed visually as lesions of Maternal Vascular Malperfusion (MVM). It is estimated that ~ 60% of all cases of HDP and FGR demonstrate some evidence of placental MVM lesions at the time of delivery [1][4] [5] indicative of insufficient utero-placental blood flow as a contributory factor to the disease pathogenesis.…”

Section: Introductionmentioning

confidence: 99%

Automated Detection of Maternal Vascular Malperfusion Lesions of the Placenta using Machine Learning

Patnaik,

Khodee,

Vasam

et al. 2023

Preprint

View full text Add to dashboard Cite

Introduction: Hypertensive disorders of pregnancy (HDP) and fetal growth restriction (FGR) are common obstetrical complications, often with pathological features of maternal vascular malperfusion (MVM) in the placenta. Currently, clinical placental pathology methods involve a manual visual examination of histology sections, a practice that can be resource-intensive and demonstrate moderate-to-poor inter-pathologist agreement on diagnostic outcomes, dependant on the degree of pathologist sub-specialty training. Methods: This study aims to apply machine learning (ML) feature extraction methods to classify digital images of placental histopathology specimens, collected from cases of HDP [gestational hypertension (GH), preeclampsia (PE), PE + FGR], normotensive FGR, and healthy pregnancies, according to the presence or absence of MVM lesions. 159 digital images were captured from histological placental specimens, manually scored for MVM lesions (MVM- or MVM+) and used to develop a support vector machine (SVM) classifier model, using features extracted from pretrained ResNet18. The model was trained with and without data augmentation, and with and without data shuffling, and the performance of the classifiers assessed and compared through measurements of accuracy, precision, and recall using confusion matrices. Results: The SVM model demonstrated accuracies between 7-78% for WSI-level MVM classification, with poorest performance observed on images with borderline MVM presence, as determined through post hoc observation. Conclusion: The results are promising for the integration of ML methods into the placental histopathological examination process. Using this study as a proof-of-concept will lead our group and others to carry ML models further in placental histopathology.

show abstract

Section: Introductionmentioning

confidence: 99%