One of lung cancer’s most lethal attributes is its ability to trick radiologists. Some nodules appear threatening but turn out to be false positives. Others escape notice entirely, and then spiral without symptoms into metastatic disease.
On Monday, however, Google unveiled an artificial intelligence system that — in early testing — demonstrated a remarkable talent for seeing through lung cancer’s disguises.
A study published in Nature Medicine reported that the algorithm, trained on 42,000 patient CT scans taken during a National Institutes of Health clinical trial, outperformed six radiologists in determining whether patients had cancer. It detected 5% more cancers and cut false positives — when cancer is suspected though a nodule is harmless — by 11% from reviewing a single scan. It performed on par with the radiologists when prior images of patients were also included in the evaluation.
About the Author Reprints
As already stated in the article this new technology did not show any advantage regarding quality of life or preventing death.Hope that AI will develop a tridimensional vision of the social and genetic factors that can be usead for prevention.During the asymptomatic,clinical or laboratory(including imaging),of cancers.
As already stated in the article this new technology did not show any advantage regarding quality of life or preventing death.Hope that AI will develop a tridimensional vision of the social and genetic factors that can be used for prevention.During the asymptomatic,clinical or laboratory(including imaging),of cancers.
Great news ! Hope it’s available soon ..
What AI is showing, is that, physicians are not really good at their job!
This is a very encouraging first step. Imagine being able to scan an entire target area in 3 dimensions instantly. What a powerful new tool for radiologists. And we can expect the AI to get smarter and smarter every year.
Computers are becoming better then humans at doing a lot of jobs. I hope a computer replaces you because your bad at your job