Retrace cites study on deep fake tech helping predict disease

A study by Retrace found that deep fake technology improves the diagnostic accuracy of artificial intelligence algorithms in identifying periodontal disease, the results of which were published in the August issue of the Journal of Dentistry.

Periodontal disease simulation using generative adversarial networks. Image and video courtesy of Retrace AI.

The blinded study looked at 10,687 radiographs, with independent validation from clinicians and research scientists at the University of California, San Francisco. Retrace said the study showed the superiority of using a generative adversarial network -- also known as deep fake -- to improve AI accuracy in predicting clinical attachment levels from bitewing and periapical images (J Dent, August 2022, Vol. 123, 104211).