SEP 04, 2020 4:41 PM PDT

Machine Learning May Protect Future Pregnancies

WRITTEN BY: Nouran Amin

It is critical for doctors to examine a placenta after the birth of a baby to determine a mothers health risks for any future pregnancies. The process is often a long and time-consuming, and despite its important to examine, may placentas go unchecked. Sometimes, a woman may have blood vessel lesions called decidual vasculopathy (DV) that goes unchecked and places a future pregnancy at risk for preeclampsia.

To address such a challenge, researchers at Carnegie Mellon University (CMU) and the University of Pittsburgh Medical Center (UPMC) developed a machine learning approach to examine placental slides and decrease the likelihood of failed future pregnancies.

"Pathologists train for years to be able to find disease in these images, but there are so many pregnancies going through the hospital system that they don't have time to inspect every placenta," said Daniel Clymer, PhD, alumnus, Department of Mechanical Engineering, CMU, Pittsburgh, PA, USA. "Our algorithm helps pathologists know which images they should focus on by scanning an image, locating blood vessels, and finding patterns of the blood vessels that identify DV."

Findings were reported in the American Journal of Pathology.

"This algorithm isn't going to replace a pathologist anytime soon," Dr. Clymer explained. "The goal here is that this type of algorithm might be able to help speed up the process by flagging regions of the image where the pathologist should take a closer look."

Learn more about placental complications:

 

 

Source: Science Daily

About the Author
  • Nouran earned her BS and MS in Biology at IUPUI and currently shares her love of science by teaching. She enjoys writing on various topics as well including science & medicine, global health, and conservation biology. She hopes through her writing she can make science more engaging and communicable to the general public.
You May Also Like
MAY 26, 2020
Technology
An App That Detects Retinal Damage
MAY 26, 2020
An App That Detects Retinal Damage
The most common cause of blindness in working-age adults is retinal damage as a result of diabetes. To address this prob ...
JUN 12, 2020
Technology
How A Computer Sea Slug Can Get Addicted To A Drug
JUN 12, 2020
How A Computer Sea Slug Can Get Addicted To A Drug
Sea slugs have long been used to study brain models especially in research concerned with memory and learning. Now, rese ...
JUL 24, 2020
Drug Discovery & Development
Profiling Technology Provides Rapid Drug Discovery
JUL 24, 2020
Profiling Technology Provides Rapid Drug Discovery
Rapid drug discovery saves lives and new technology is aiming to do just that in the fight against tuberculosis. Learn m ...
AUG 17, 2020
Clinical & Molecular DX
Smartphone Cameras Detect Signs of Diabetes
AUG 17, 2020
Smartphone Cameras Detect Signs of Diabetes
In the future, detecting the early signs of diabetes could be as simple as picking up your smartphone. A new study, rece ...
AUG 20, 2020
Technology
How Routing Apps Can Fix The Traffic Problem?
AUG 20, 2020
How Routing Apps Can Fix The Traffic Problem?
  Routing apps, such as Google Maps, are always on the go to capture detailed information that could help pin emiss ...
SEP 15, 2020
Chemistry & Physics
Chemistry Grad Students Be Warned: a Robotic Takeover?
SEP 15, 2020
Chemistry Grad Students Be Warned: a Robotic Takeover?
In a recent news release, the research arm of IBM announced that their Zurich team has developed an autonomous ...
Loading Comments...