An automated artificial intelligence algorithm has been shown to accurately analyze digital images of a woman’s cervix and identify cervical precancer.
The AI approach, called automated visual evaluation, was developed by researchers at the National Cancer Institute and Global Good—a fund at Intellectual Ventures—whose results were published on Thursday in the Journal of the National Cancer Institute.
More than 60,000 cervical images from an NCI archive of photos—collected during a study conducted in Costa Rica from 1993 to 2000—were digitized and then used to train the AI algorithm to differentiate cervical conditions requiring medical treatment from those that did not.
“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,” says Mark Schiffman, MD, senior author of the study and senior investigator at NCI’s Division of Cancer Epidemiology and Genetics. “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).”
According to Schiffman and his co-authors, collaborators at the National Library of Medicine—part of the National Institutes of Health—independently checked their AI method and confirmed the study’s findings. As a result, they contend that the algorithm has the potential to revolutionize cervical cancer screening, particularly in low-resource settings.
“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,” says Maurizio Vecchione, executive vice president of Global Good.
Going forward, researchers plan to further train the AI algorithm on a sample of representative images of cervical precancers and normal cervical tissue collected from women in other regions of the world.
“We are currently working to transfer automated visual evaluation to images from contemporary phone cameras and other digital image capture devices to create an accurate and affordable point-of-care screening method that would support the recently announced World Health Organization initiative to accelerate cervical cancer control,” conclude the authors.