Researchers have developed a new computer algorithm, which they say can outperform experts in identifying cervical precancer.
Investigators used comprehensive datasets to "train" a deep learning algorithm to analyse digital images of the cervix and identify precancerous changes that require attention. In creating the algorithm, they used more than 60,000 cervical images collected during a cervical cancer screening study that was carried out in Costa Rica in the 1990s.
In a study, published in the Journal of the National Cancer Institute, researchers at the National Institutes of Health in the United States and Global Good found the computer analysis of the images was better at identifying precancer than original cervigram interpretation or conventional cytology.
The researchers now say the artificial intelligence approach, called automated visual evaluation, has the potential to revolutionise 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," said Maurizio Vecchione, executive vice president of Global Good.
The researchers now plan to further train the algorithm on a sample of representative images of cervical precancers and normal cervical tissue from women around the world.