If you would like to submit a blog post for consideration, please email [email protected]
Detecting Skin Cancer with Artificial Intelligence
Artificial intelligence has the capacity to revolutionise skin cancer medicine, with multiple programs in development that aid in the early detection of the disease. One such program is Doctor Hazel – a platform that could someday identify cancerous moles with a success rate of 90 percent, provided it attracts enough user submissions.
Still in its infancy, Doctor Hazel was demonstrated earlier this week by a team of engineers at TechCrunch’s Disrupt San Francisco 2017 hackathon. The artificial intelligence program currently identifies cancer at an 85 percent success rate; however, the team has launched a beta and is inviting users to submit their own photos to improve the platform’s performance.
The technology relies on people sharing their medical images so it can learn the difference between a cancerous and non-cancerous mole. However, it can be difficult to persuade people to share such pictures, developers said.
Doctor Hazel gauges 8,000 variables when viewing a sample to determine whether the image is of a mole, melanoma, another type of cancer, or nothing. The team plans to have an app accompany the platform, as well as an image capturing device that could someday be made available for sale.
However, such apps need to be rigorously validated. In 2015, the Federal Trade Commission acted against the melanoma detection apps MelApp and Mole Detective. The Commission alleged that the photography-based apps “deceptively claimed to accurately analyse melanoma risk,” and that the marketers had insufficient evidence to make these claims.
Programs similar to Doctor Hazel include iDoc24’s smartphone-connected dermatoscope that sends pictures of users’ moles to a dermatologist for clinical evaluation, and VisualDX’s app — designed to support non-dermatological physicians by quickly categorising skin images — which will debut in Apple iOS 11.
Earlier this year, Stanford’s Artificial Intelligence Laboratory released a study describing a convolutional neural network that matched the performance of 21 board-certified dermatologists. The Stanford researchers said that they hope to bring their platform to smartphones and the general population.
Learn more about the early detection of melanoma here.
Muoio, D. (18 September, 2017.) Doctor Hazel, an AI aimed at skin cancer detection, is latest in a long line. Mobi Health News.