Predictive placentas that identify health risk in future pregnancies

Image used for representation purpose.

Image used for representation purpose.   | Photo Credit: Reuters

(Subscribe to our Today's Cache newsletter for a quick snapshot of top 5 tech stories. Click here to subscribe for free.)

Doctors examine the placenta after the baby is born to know whether the mother is at health risk in future pregnancies. This is a time-consuming process.

A team of researchers at Carnegie Mellon University (CMU) and the University of Pittsburgh Medical Center (UPMC) have made this process easier with a machine learning model.

The team’s algorithm will, instead of a specialist, examine placenta slides to know whether a mother is at risk.

“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 decidual vasculopathy,” former CMU Ph.D. student Daniel Clymer said.

Placenta is the organ that links a mother to a baby; it is examined to identify blood vessel lesions called decidual vasculopathy (DV). These indicate the mother is at risk for pre-eclampsia—a complication that can be fatal to the mother and the baby, in any future pregnancies. Once detected, pre-eclampsia can be treated, the researchers explained.

A sample revealing a decidual arteriole affected by early stage decidual vasculopathy.

A sample revealing a decidual arteriole affected by early stage decidual vasculopathy.   | Photo Credit: Carnegie Mellon Engineering


The team has trained the computer by showing numerous images of placenta while indicating whether the placenta is healthy or diseased.

The computer starts by spotting all the blood vessels in an image. It then analysis them individually and assesses if a blood vessel should be considered as healthy or diseased.

Further, the algorithm also takes into account features of the pregnancy including gestational age, birth weight, and any conditions the mother might have.

“This algorithm isn’t going to replace a pathologist anytime soon,” Clymer said. “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.”

Recommended for you
  1. Comments will be moderated by The Hindu editorial team.
  2. Comments that are abusive, personal, incendiary or irrelevant cannot be published.
  3. Please write complete sentences. Do not type comments in all capital letters, or in all lower case letters, or using abbreviated text. (example: u cannot substitute for you, d is not 'the', n is not 'and').
  4. We may remove hyperlinks within comments.
  5. Please use a genuine email ID and provide your name, to avoid rejection.

Printable version | Sep 18, 2020 9:20:58 PM |

Next Story