APPLAUSE: Automatic Prediction of PLAcental health via U-net Segmentation and statistical Evaluation

Abstract

PurposeArtificial-intelligence population-based automated quantification of placental maturation and health from a rapid functional Magnetic Resonance scan. The placenta plays a crucial role for any successful human pregnancy. Deviations from the normal dynamic maturation throughout gestation are closely linked to major pregnancy complications. Antenatal assessment in-vivo using T2* relaxometry has shown great promise to inform management and possible interventions but clinical translation is hampered by time consuming manual segmentation and analysis techniques based on comparison against normative curves over gestation.MethodsThis study proposes a fully automatic pipeline to predict the biological age and health of the placenta based on a rapid (sub-30 second) T2* scan in two steps: Automatic segmentation using a U-Net and a Gaussian Process regression model to characterize placental maturation and health. These are trained and evaluated on 110 3T MRI placental data sets including 20 high-risk pregnancies diagnosed with pre-eclampsia and/or fetal growth restriction.ResultsAutomatic segmentation achieves comparable performance to human experts (mean DICE coefficients automatic-manual 0.76, Pearson Correlation Coefficient 0.986 for mean T2* within the masks). The placental health prediction achieves an excellent ability to differentiate early cases of placental in-sufficiency before 32 weeks. High abnormality scores correlate with low birth weight, premature birth and histopathological findings. Retrospective application on a different cohort imaged at 1.5T illustrates the ability for direct clinical translation.ConclusionThe presented automatic pipeline facilitates a fast, robust and reliable prediction of placental maturation. It yields human-interpretable and verifiable intermediate results and quantifies uncertainties on the cohort-level and for individual predictions. The proposed machine-learning pipeline runs in close to real-time and, deployed in clinical settings, has the potential to become a cornerstone of diagnosis and intervention of placental insufficiency.