Neural Network Could Help Clinicians Look for "Ugly Duckling" Pre-Cancerous Skin Lesions (2 of 5) (IMAGE)
Caption
Example images with multiple lesions on the back of a subject. The neural network analyzes the images and classifies the lesions as nonsuspicious or suspicious (red). This material relates to a paper that appeared in the Feb. 17, 2021, issue of Science Translational Medicine, published by AAAS. The paper, by L.R. Soenksen at Massachusetts Institute of Technology in Cambridge, MA; and colleagues was titled, "Using deep learning for dermatologist-level detection of suspicious pigmented skin lesions from wide-field images."
Credit
L.R. Soenksen <i>et al., Science Translational Medicine</i> (2021)
Usage Restrictions
Please cite the owner of the material when publishing. This material may be freely used by reporters as part of news coverage, with proper attribution. Non-reporters must contact <i>Science</i> for permission.
License
Licensed content