New AI approach outperforms human experts in identifying cervical pre-cancer


Cervical cancer is the fourth most common cancer in the world, with 570,000 cases per year in 2018 according to the World Health Organization (WHO).

"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, M.D., M.P.H., of the NCI's Division of Cancer Epidemiology and Genetics, senior author of the study, in a release.

The AI solutions which are called automated visual evaluation now has the potential to revolutionize the cervical cancer screening, in the low resource settings, according to the NCI press statement.

"Cervical cancer is almost 100 percent preventable, yet every year, IN women die from this awful disease", said State Health Commissioner Kris Box, M.D., FACOG.

Such changes include normal glandular cells transforming into squamous cells, which are more sensitive to the effect of the human papillomavirus (HPV), according to the Canadian Cancer Society. "So we're concerned that since only a little more than half to two-thirds of women are having regular screening, that could have consequences down the road in terms of cervical abnormalities, and pre-cancerous changes". Healthcare workers in these settings now use visual inspection with acetic acid (VIA), a screening method.

'Cervical cancer has become a health disparity issue, ' said Dr Schiffman.

In a study done in Costa Rica in the 1990s, photos were taken of visual inspections of more than 9,400 women. This technology also helps in improving the quality of treatment for the disease.

"Machine learning actually outperformed human experts by a considerable margin". And it has the advantage of requiring very little resources.

More news: VLC Hits 3 Billion Downloads, Will Soon Add AirPlay Support For Android
More news: Mookie Betts settles with Red Sox on $20M salary for 2019
More news: Withdrawal from Syria begun

"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", said Maurizio Vecchione, executive vice president of Global Good.

Dr. Jennifer Wu is an obstetrician-gynecologist at Lenox Hill Hospital in New York City.

Bangabandhu Sheikh Mujib Medical University gynecological oncology professor Sabera Khatun said the human papillomavirus is a very common virus caused by intercourse, but nearly 90 per cent of human papillomavirus is cleared naturally by women's immune system.

Schiffman said this method probably wouldn't replace methods now used in the United States.

While VIA is convenient and low-priced, this method is known to be inaccurate.

If high-grade lesions or cancer are suspected, the women can have excisions of the abnormal area right then, without waiting for Pap screening or biopsy results, she explained. "Study results were published January 10 in the Journal of the National Cancer Institute..."

The health department, along with the Sampson County Breast and Cervical Cancer Control Program (BCCCP) Advisory Board will promote the "Teal Ribbon Campaign" which serves as a reminder for all women to get cervical screenings.