Gross appearance of the fetal membrane on the placental surface is associated with histological chorioamnionitis and neonatal respiratory disorders

Cross-modal contrastive learning for unified placenta analysis using photographs

The placenta is vital to maternal and child health but often overlooked in pregnancy studies. Addressing the need for a more accessible and cost-effective method of placental assessment, our study introduces a computational tool designed for the analysis of placental photographs. Leveraging images and pathology reports collected from sites in the United States and Uganda over a 12-year period, we developed a cross-modal contrastive learning algorithm consisting of pre-alignment, distillation, and retrieval modules. Moreover, the proposed robustness evaluation protocol enables statistical assessment of performance improvements, provides deeper insight into the impact of different features on predictions, and offers practical guidance for its application in a variety of settings. Through extensive experimentation, our tool demonstrates an average area under the receiver operating characteristic curve score of over 82% in both internal and external validations, which underscores the potential of our tool to enhance clinical care across diverse environments.

Placental pathology predicts infantile neurodevelopment

The aim of present study was to investigate the association of placental pathological findings with infantile neurodevelopment during the early 40 months of life. 258 singleton infants were enrolled in the Hamamatsu Birth Cohort for Mothers and Children (HBC Study) whose placentas were saved in our pathological division. To assess the infantile neurodevelopment, we used Mullen Scales of Early Learning (gross motor, visual reception, fine motor, receptive language, expressive language) at 10, 14, 18, 24, 32, and 40 months. For obtaining placental blocks, we carried out random sampling and assessed eleven pathological findings using mixed modeling identified ‘Accelerated villous maturation’, ‘Maternal vascular malperfusion’, and ‘Delayed villous maturation’ as significant predictors of the relatively lower MSEL composite scores in the neurodevelopmental milestones by Mullen Scales of Early Learning. On the other hand, ‘Avascular villi’, ‘Thrombosis or Intramural fibrin deposition’, ‘Fetal vascular malperfusion’, and ‘Fetal inflammatory response’ were significant predictors of the relatively higher MSEL composite scores in the neurodevelopmental milestones by Mullen Scales of Early Learning. In conclusion, the present study is the first to report that some placental pathological findings are bidirectionally associated with the progression of infantile neurodevelopment during 10–40 months of age.