Bots on Dots: Machines Screen for Melanoma

Source: Medpage Today, June 2018

A study suggests that a machine-learning algorithm may be just as good as trained dermatologists for determining whether suspect lesions are melanomas or not. In this 150-Second Analysis, F. Perry Wilson, MD, looks to a future where these algorithms are as ubiquitous at CT scanners are today.

Telling the difference between a benign mole (the first and third images) and a melanoma like image number two requires significant training.

And even the best dermatologists make mistakes. But rapidly developing research in the field of computer vision may give us a new weapon in the fight against this deadly disease. The most compelling data to date, comes from this paper, appearing in the Annals of Oncology.

http://www.onclive.com/onclive-tv/dr-postow-discusses-combination-therapy-for-melanoma" target="_blank"]read the original full article[/button]