Researchers from the National Institutes of Health and Global Good have developed an artificial intelligence (AI) based computer algorithm that can identify cervical pre-cancer with greater accuracy than a human expert.
The algorithm, called automated visual evaluation, can analyse digital images of a cervix and accurately identify precancerous changes that require medical attention, an advance the researchers say could revolutionise screening, particularly in low-resource settings.
The new method 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.
According to the researchers, automated visual evaluation is easy to perform. Health workers can use a cell phone or similar camera device for cervical screening and treatment during a single visit.
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.
“Our findings show that a deep learning algorithm can use images collected during routine cervical cancer screening to identify pre-cancerous changes that, if left untreated, may develop into cancer,” said senior author of the study, Dr Mark Schiffman from the National Cancer Institute’s (NCI) Division of Cancer Epidemiology and Genetics.
“In fact, the computer analysis of the images was better at identifying pre-cancer than a human expert reviewer of Pap tests under the microscope (cytology),” continued Dr Schiffman.
To develop the algorithm, the researchers used more than 60,000 cervical images from an NCI archive of photos collected during a cervical cancer screening study that was carried out in Costa Rica in the 1990s.
More than 9,400 women participated in that population study, with follow up that lasted up to 18 years.
The photos were digitised and then used to train a deep learning algorithm so that it could distinguish cervical conditions requiring treatment from those not requiring treatment.
Overall, the algorithm performed better than all standard screening tests at predicting all cases diagnosed during the Costa Rica study.
“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,” said Executive Vice President of Global Good, Maurizio Vecchione.
The researchers plan to further train the algorithm on a sample of representative images of cervical pre-cancers and normal cervical tissue from women in communities worldwide, using a variety of cameras and other imaging options.