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

• Published in: Medical image analysis 2021-08, Vol.72, p.102145-102145, Article 102145
• Main Authors: Pietsch, Maximilian, Ho, Alison, Bardanzellu, Alessia, Zeidan, Aya Mutaz Ahmad, Chappell, Lucy C., Hajnal, Joseph V., Rutherford, Mary, Hutter, Jana
• Format: Article
• Language: English
• Subjects: Acquisition; Birth weight; Complications; Correlation coefficient; Correlation coefficients; Female; Fetal Growth Retardation; Fetuses; Gaussian process; Gestation; Humans; Image segmentation; Intelligence; Learning algorithms; Low birth weight; Machine learning; Magnetic Resonance Imaging; Maturation; Pipelines; Placenta; Placenta - diagnostic imaging; Placental MRI; Pre-eclampsia; Predictions; Preeclampsia; Pregnancy; Pregnancy complications; Premature birth; Regression; Regression models; Relaxometry; Retrospective Studies; Risk groups; Segmentation; Statistical analysis; Statistical prediction; Translation; U-Net
• ISSN: 1361-8415; 1361-8423
• DOI: 10.1016/j.media.2021.102145

•Automatic placental health prediction based on a 30 s MRI scan can identify early placental insufficiency (AUC = 0.95).•An abnormal automatic maturation marker is associated with low birth weight centile and premature birth.•The automatic maturation marker correlates with presence of maternal vascular malperfusion in the abnormal cohort.•Explicit uncertainty modeling and separation into human-interpretable steps facilitates clinical use and future extensions. [Display omitted] Purpose:Artificial-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. Methods:This study proposes a fully automatic pipeline to predict the biological age and health of the placenta based on a free-breathing 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 108 3T MRI placental data sets, the evaluation included 20 high-risk pregnancies diagnosed with pre-eclampsia and/or fetal growth restriction. An independent cohort imaged at 1.5 T is used to assess the generalization of the training and evaluation pipeline. Results: Across low- and high-risk groups, automatic segmentation performs worse than inter-rater performance (mean Dice coefficients of 0.58 and 0.68, respectively) but is sufficient for estimating placental mean T2* (0.986 Pearson Correlation Coefficient). The placental health prediction achieves an excellent ability to differentiate cases of placental insufficiency between 27 and 33 weeks. High abnormality scores correlate with low birth weight, premature birth and histopathological findings. Retrospective application on a different cohort imaged at 1.5 T illustrates the ability for direct clinical translation. Conclusion:The presented automatic pipeline facilitates a fast, robust and reliable prediction of placental maturation. It yields human-interpretable and verifia