Researchers create AI approach for cervical cancer screening

A computer algorithm which works on the Artificial Intelligence system had now typically screened and identified cervical cancer in a much better way than the trained experts, according got the report which has been revealed by the research scientist.

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.

The researchers work on the used comprehensive datasets to train, a machine learning algorithm to simply recognize the patterns in a much more complex visuals inputs such as the medical images. The approach was done by the investigators at the NCI and Global Good, and with the finding which was confirmed independently by some of the experts at the National Library of Medicine, the report said.

“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. 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),” said Mark Schiffman, senior author of the study and master of public health at NCI’s Division of Cancer Epidemiology and Genetics.

Nowadays the healthcare workers who are working in the low resource settings as of now use a screening method called the visual inspection with the acetic acid. In this form of approach, a health works apply the dilute acetic acid to the cervix, and the inspects the cervix with the help of a naked eye, looking for the ‘Aceto whitening’;, which reveals the possible disease.

To create such type of algorithm, the team of researchers has used more than 70000 cervical images from the NCI department archive of photos which is collected at the time of cervical cancer screening study that was also carried out in Costa Rica in the 1990s.