“Modern medicine pushes forward thanks to the efforts of doctors and scientists who develop new tools, techniques, and methods for diagnosing and treating ailments, but what happens when the tools become smarter than the humans?” Mike Wehner reports for BGR. “A new algorithm for detecting skin cancers might provide the answer to that question, as it just demonstrated it can outperform human doctors in spotting malignant melanomas.”
“In a new study published in the journal Annals of Oncology, a team of scientists asked trained dermatologists to face off against a neural network to see which one provided accurate diagnoses more often,” Wehner reports. “Spoiler: The humans didn’t win.”
“The numbers are quite stunning: 87 percent of melanomas were accurately diagnosed by the human doctors the first time around, and that number improved to 89 percent during the second round of examination,” Wehner reports. “The AI, on the other hand, nailed 95 percent of malignant growths.”
Read more in the full article here.
MacDailyNews Take: This is great news! Of course, AI is just another valuable tool for doctors to utilize. As Wehner also reports, “while the average of the doctors’ scores did fall below that of the AI, roughly 22% of the human doctors actually outperformed the AI in certain instances.”
AI’s good showing is hardly surprising as over four years ago, it was reported that the DermoScreen app for iPhone was found to be quite accurate.
SEE ALSO:
Early testing reveals iPhone app screens for skin cancer more accurately than your doctor – May 8, 2014
Detecting yes. Machines have better resolutions than humans senses. Nothing new there.
Telling a machine what skin cancer is and might look like is a human contribution.
AI and Neural Networks are still a ways off on reading Mammograms.
RSNA 2017
https://rsna2017.rsna.org/dailybulletin/index.cfm?pg=17thu05
I guess it won’t be long before we have an app that lets you get a quick first opinion on those suspicious moles and spots, assuming the ai is using camera imagery only.