BioCentury
ARTICLE | Tools & Techniques

Researchers develop AI tool to improve screening for cervical cancer

January 16, 2019 12:04 AM UTC

A team from NCI and Intellectual Ventures Global Good Fund released a paper Thursday detailing an image-based, machine-learning algorithm that improves screening accuracy for precancerous cervical lesions. The tool could help reduce the incidence of cervical cancer.

In the paper, published in the Journal of the National Cancer Institute, the researchers described an automated visual evaluation machine-learning algorithm that evaluates pictures to calculate the probability of patients having cervical intraepithelial neoplasia grade 2 lesions or worse (CIN 2+). CIN 2 lesions can progress to cervical cancer if left untreated...