A newly developed tool that leverages computer vision and artificial intelligence (AI) can help doctors quickly evaluate placentas at birth, potentially improving maternal and neonatal care, according to new research from Northwestern Medicine and Penn State scientists. .
The study, which was published December 13 in the print edition of the journal Patterns and which appears on the magazine’s cover, describes a computer program called PlacentaVision that can analyze a simple photograph of the placenta to detect abnormalities associated with infection and neonatal sepsis, a life-threatening condition that affects millions of newborns worldwide. .
“The placenta is one of the most common specimens we see in the laboratory,” said study co-author Dr. Jeffery Goldstein, director of perinatal pathology and associate professor of pathology at Northwestern University Feinberg School of Medicine. “When the neonatal intensive care unit treats a sick child, even a few minutes can make a difference in medical decision-making. With a diagnosis from these photographs, we can have an answer days earlier than we would have in our normal process”.
Northwestern provided the largest image set for the study, and Goldstein led the development and troubleshooting of the algorithms.
Alison D. Gernand, lead contact researcher for the project, conceived the original idea for this tool through her global health work, particularly with pregnancies where women give birth at home due to lack of care resources medical.
“Discarding the placenta without examining it is a common but often overlooked problem,” said Gernand, an associate professor in the Department of Nutritional Sciences at Penn State’s College of Health and Human Development (HHD). “It is a missed opportunity to identify concerns and provide early intervention that can reduce complications and improve outcomes for both mother and baby.”
Why early placental examination is important
The placenta plays a vital role in the health of both the pregnant woman and the baby during pregnancy, but is often not thoroughly examined at birth, especially in areas with limited medical resources.
“This research could save lives and improve health outcomes,” said Yimu Pan, a doctoral candidate in the computer science program at the College of Information Science and Technology (IST) and lead author of the study. “It could make placental screening more accessible, benefiting research and care of future pregnancies, especially for mothers and babies at higher risk of complications.”
Early identification of placental infection through tools like PlacentaVision could allow doctors to take immediate action, such as giving antibiotics to the mother or baby and closely monitoring the newborn for signs of infection, the scientists said.
According to the researchers, PlacentaVision is designed for use in a variety of medical demographics.
“In low-resource areas (places where hospitals don’t have pathology labs or specialists) this tool could help doctors quickly detect problems such as placental infections,” Pan said. “In well-equipped hospitals, the tool can eventually “help doctors determine which placentas need further examination, making the process more efficient and ensuring the most important cases are prioritized.”
“Before such a tool could be deployed globally, the main technical hurdles we faced were making the model flexible enough to handle various placenta-related diagnoses and ensuring that the tool can be robust enough to handle various conditions. delivery, including variation in lighting conditions, image quality, and clinical settings,” said James Z. Wang, distinguished professor at Penn State’s College of IST and one of the study’s principal investigators. “Our AI tool needs to maintain accuracy even when many training images come from a well-equipped urban hospital. It was essential to ensure PlacentaVision could handle a wide range of real-world conditions.”
How the tool learned to analyze images of placentas
The researchers used cross-modal contrastive learning, an artificial intelligence method for aligning and understanding the relationship between different types of data, in this case visual (images) and textual (pathology reports), to teach a computer program how to analyze images. of placentas. They assembled a large, diverse dataset of placental images and pathology reports spanning a 12-year period, studied how these images relate to health outcomes, and built a model that could make predictions based on new images. The team also developed several image alteration strategies to simulate different shooting conditions in order to properly evaluate the strength of the model.
The result was PlacentaCLIP+, a robust machine learning model that can analyze photographs of placentas to detect health risks with high accuracy. It was internationally validated to confirm consistent performance across populations.
According to the researchers, PlacentaVision is designed to be easy to use, potentially running through a smartphone app or integrated into medical records software so doctors can get quick answers after delivery.
Next step: an easy-to-use app for medical staff
“Our next steps include developing an easy-to-use mobile application that can be used by medical professionals (with minimal training) in low-resource clinics or hospitals,” Pan said. “The easy-to-use application would allow doctors and nurses to photograph placentas and get immediate feedback and improve care.
The researchers plan to make the tool even smarter by including more types of placental characteristics and adding clinical data to improve predictions while contributing to long-term health research. They will also test the tool in different hospitals to ensure it works in a variety of settings.
“This tool has the potential to transform the way placentas are examined after birth, especially in parts of the world where these examinations are rarely performed,” Gernand said. “This innovation promises greater accessibility in low- and high-resource settings. With further refinement, it has the potential to transform maternal and neonatal care by enabling early, personalized interventions that prevent serious health outcomes and improve the lives of mothers and babies all over the world.”
This research was supported by the National Institute of Biomedical Imaging and Bioengineering of the National Institutes of Health (grant R01EB030130). The team used supercomputing resources from the Advanced Cyber Infrastructure Coordination Ecosystem: Services and Support (ACCESS) program, funded by the National Science Foundation.