A newly developed tool that harnesses computer vision and artificial intelligence (AI) may help clinicians rapidly evaluate placentas at birth, potentially improving neonatal and maternal care, based on latest research from scientists at Northwestern Medicine and Penn State.
The study, which was published Dec. 13 within the print edition of the journal Patterns and featured on the journal’s cover, describes a pc program named PlacentaVision that may analyze an easy photograph of the placenta to detect abnormalities related to infection and neonatal sepsis, a life-threatening condition that affects thousands and thousands of newborns globally.
“Placenta is one of the crucial common specimens that we see within the lab,” said study co-author Dr. Jeffery Goldstein, director of perinatal pathology and an associate professor of pathology at Northwestern University Feinberg School of Medicine. “When the neonatal intensive care unit is treating a sick kid, even a number of minutes could make a difference in medical decision making. With a diagnosis from these photographs, we are able to have a solution days sooner than we’d in our normal process.”
Northwestern provided the biggest set of images for the study, and Goldstein led the event and troubleshooting of the algorithms.
Alison D. Gernand, contact principal investigator on the project, conceived the unique idea for this tool through her global health work, particularly with pregnancies where women deliver of their homes as a consequence of lack of health care resources.
“Discarding the placenta without examination is a typical but often missed problem,” said Gernand, associate professor within the Penn State College of Health and Human Development (HHD) Department of Dietary Sciences. “It’s a missed opportunity to discover concerns and supply early intervention that may reduce complications and improve outcomes for each the mother and the newborn.”
Why early examination of the placenta matters
The placenta plays an important role within the health of each the pregnant individual and baby while pregnant, yet it is usually 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 within the informatics program from the College of Information Sciences and Technology (IST) and lead writer on the study. “It could make placental examination more accessible, benefitting research and take care of future pregnancies, especially for moms and babies at higher risk of complications.”
Early identification of placental infection through tools like PlacentaVision might enable clinicians to take prompt actions, resembling administering antibiotics to the mother or baby and closely monitoring the newborn for signs of infection, the scientists said.
PlacentaVision is meant to be used across a variety of medical demographics, based on the researchers.
“In low-resource areas — places where hospitals haven’t got pathology labs or specialists — this tool could help doctors quickly spot issues like infections from a placenta,” Pan said. “In well-equipped hospitals, the tool may eventually help doctors determine which placentas need further, detailed examination, making the method more efficient and ensuring a very powerful cases are prioritized.”
“Before such a tool will be deployed globally, core technical obstacles we faced were to make the model flexible enough to handle various diagnoses related to the placenta and to be certain that the tool will be robust enough to handle various delivery conditions, including variation in lighting conditions, imaging quality and clinical settings” said James Z. Wang, distinguished professor within the College of IST at Penn State and considered one of the principal investigators on the study. “Our AI tool needs to take care of accuracy even when many training images come from a well-equipped urban hospital. Ensuring that PlacentaVision can handle a wide selection of real-world conditions was essential.”
How the tool learned how one can analyze pictures of placentas
The researchers used cross-modal contrastive learning, an AI method for aligning and understanding relationship between several types of data — on this case, visual (images) and textual (pathological reports) — to show a pc program how one can analyze pictures of placentas. They gathered a big, diverse dataset of placental images and pathological reports spanning a 12-year period, studied how these images relate to health outcomes and built a model that would make predictions based on latest images. The team also developed various image alteration strategies to simulate different photo-taking conditions so the model’s resilience will be evaluated properly.
The result was PlacentaCLIP+, a strong machine-learning model that may analyze photos of placentas to detect health risks with high accuracy. It was validated cross-nationally to substantiate consistent performance across populations.
Based on the researchers, PlacentaVision is designed to be easy to make use of, potentially working through a smartphone app or integrated into medical record software so doctors can get quick answers after delivery.
Next step: A user-friendly app for medical staff
“Our next steps include developing a user-friendly mobile app that will be utilized by medical professionals — with minimal training — in clinics or hospitals with low resources,” Pan said. “The user-friendly app 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 kinds of placental features and adding clinical data to enhance predictions while also contributing to research on long-term health. They’ll also test the tool in several hospitals to make sure it really works in quite a lot of settings.
“This tool has the potential to remodel how placentas are examined after birth, especially in parts of the world where these exams are rarely done,” Gernand said. “This innovation guarantees greater accessibility in each low- and high-resource settings. With further refinement, it has the potential to remodel neonatal and maternal care by enabling early, personalized interventions that prevent severe health outcomes and improve the lives of moms and infants worldwide.”
This research was supported by the National Institutes of Health National Institute of Biomedical Imaging and Bioengineering (grant R01EB030130). The team used supercomputing resources from the National Science Foundation-funded Advanced Cyberinfrastructure Coordination Ecosystem: Services & Support (ACCESS) program.
