This AI Approach Is More Accurate Than Doctors At Detecting Cervical Cancer

The algorithm, called automated visual evaluation, can analyse digital images of a cervix

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.