Tuesday, March 19, 2019
News

This AI approach accurate than doctors at detecting cervical cancer

   SocialTwist Tell-a-Friend    Print this Page   COMMENT

New York | Friday, 2019 5:15:05 PM IST
Researchers have developed a novel Artificial Intelligence (AI)-based computer algorithm that can identify cervical cancer with greater accuracy than a human expert, an advance that could revolutionise screening, particularly in low-resource settings.

The algorithm, called automated visual evaluation, can analyse digital images of a cervix and accurately identify precancerous changes that require medical attention.

It can be performed with minimal training, making it ideal for countries with limited healthcare resources where cervical cancer is a leading cause of illness and death among women.

Importantly, the automated visual evaluation identified precancer with greater accuracy than a human expert review or conventional cytology, the researchers said.

"Our findings show that a deep learning algorithm can use images collected during routine cervical cancer screening to identify precancerous changes that, if left untreated, may develop into cancer," said Mark Schiffman, from the National Cancer Institute in the US.

"In fact, the computer analysis of the images was better at identifying precancer than a human expert reviewer of Pap tests under the microscope (cytology)," Schiffman said.

Pap test is the cervical screening test.

To create the algorithm, the research team used more than 60,000 cervical images and included more than 9,400 women.

The findings, published in the journal of the National Cancer Institute, showed that overall, the algorithm also performed better than all standard screening tests at predicting all cases diagnosed.

"When this algorithm is combined with advances in HPV vaccination, emerging HPV detection technologies, and improvements in treatment, it is conceivable that cervical cancer could be brought under control, even in low-resource settings," the researchers said.

Further, the team plans to train the algorithm on a sample of representative images of cervical precancers and normal cervical tissue from women in communities worldwide, using a variety of cameras and other imaging options.

--IANS pb/rt/mag/sed

( 313 Words)

2019-01-11-16:50:05 (IANS)

 
  LATEST COMMENTS (0)
POST YOUR COMMENT
Comments Not Available
 
POST YOUR COMMENT
 
 
TRENDING TOPICS
 
 
CITY NEWS
MORE CITIES
 
 
 
MORE HEALTH NEWS
Coffee compounds may reduce prostate can...
Painkillers in pregnancy won't cause ast...
Origins and nature of 'math anxiety'...
Positive work environment leads to feeli...
Hormonal treatment may trigger depressio...
Researchers identify 9 genes behind eyeb...
More...
 
INDIA WORLD ASIA
Pramod Sawant to be sworn in as Goa CM...
Parrikar is the 'first victim' of Rafale...
K'taka Deputy CM rubbishes reports of 'p...
Pramod Sawant to succeed Manohar Parrika...
Asaduddin Owaisi files nomination from H...
Jana Sena announces candidates for 5 mor...
More...    
 
 Top Stories
K'taka Deputy CM rubbishes reports ... 
India lodges protest with Pak over ... 
Parrikar is the 'first victim' of R... 
Pramod Sawant to succeed Manohar Pa... 
One of 7 abducted Indians return ho... 
Advani, Mehta to clash in CCI snook... 
Miwaiz ready for NIA questioning, b... 
India, Maldives vow to combat terro...