A new tool utilizing computer vision and artificial intelligence aims to improve neonatal and maternal care by rapidly evaluating placentas at birth. Researchers from Northwestern Medicine and Penn State have developed PlacentaVision, a program that analyzes photographs of placentas to detect abnormalities linked to infections and neonatal sepsis.
"Placenta is one of the most common specimens that we see in the lab,” said Dr. Jeffery Goldstein, director of perinatal pathology at Northwestern University Feinberg School of Medicine. He noted that quick diagnoses could expedite medical decision-making, providing answers days earlier than traditional methods.
The research was published on December 13 in the journal Patterns. Alison D. Gernand, an associate professor at Penn State College of Health and Human Development, initiated the idea for this tool through her work in global health, particularly in regions where women often deliver without healthcare resources.
“Discarding the placenta without examination is a common but often overlooked problem,” Gernand stated. She emphasized that examining placentas can identify concerns early, potentially reducing complications for mothers and babies.
The study highlights the importance of early placental examination, especially in low-resource areas lacking pathology labs or specialists. “This research could save lives and improve health outcomes,” said Yimu Pan, a doctoral candidate from Penn State's College of Information Sciences and Technology.
PlacentaVision is designed for use across diverse medical settings. In well-equipped hospitals, it may help prioritize which placentas need detailed examination. James Z. Wang from Penn State stressed ensuring the tool's accuracy across various conditions was essential.
The researchers employed cross-modal contrastive learning to teach the program how to analyze placental images effectively. The resulting model, PlacentaCLIP+, demonstrated high accuracy in detecting health risks.
“Our next steps include developing a user-friendly mobile app that can be used by medical professionals — with minimal training — in clinics or hospitals with low resources,” Pan explained.
Gernand concluded that this innovation promises greater accessibility in both low- and high-resource settings: “With further refinement, it has the potential to transform neonatal and maternal care by enabling early, personalized interventions.”
The research received support from the National Institutes of Health National Institute of Biomedical Imaging and Bioengineering (grant R01EB030130) and utilized supercomputing resources funded by the National Science Foundation's ACCESS program.