Google researchers trained an algorithm to set apart two types of lung cancer

Almost every industry is using AI nowadays; those that don’t, have little time left to adapt. From speech and face recognition to spam filtering, we are so used to AI features in our lives, that we sometimes don’t even realize they are present. In the healthcare system, artificial intelligence is used to more quickly find solutions to medical problems, help doctors identify and treat diseases, discover new drugs, and to dig through medical data.


The same type of AI that Google uses to identify faces, animals and objects in pictures uploaded to Google’s online services has been used to help doctors diagnose medical conditions, such as diabetic blindness.

Now, the same Google algorithm is being used to tell the difference between two nearly identical types of lung cancer. New York University scientists published the results of their innovative research about a Google deep learning algorithm in the September 17th issue of Nature. The computer was presented with varied images of lung tumors, training it to tell the difference between two of the most common types of lung cancers. Since diagnosing and beginning cancer treatment as soon as possible is crucial for patient survival, this is good news for the more than 200,000 people who are diagnosed with cancer each year, according to the American Cancer Society and the Cancer Statistics Center.

Beyond telling the difference between the two most common types of lung cancer, NYU’s neural network is doing something completely new that even the scientists involved can’t fully explain. Using pictures, the neural network can now pinpoint genetic mutations occuring inside tumor cells.

This is not the first time Google AI has been used for medical purposes. One of the company’s subsidiaries, DeepMind, has proved a machine learning algorithm can correctly recommend treatment for more than 50 eye diseases in 94 percent of all cases.

The medical field is not the only area for which Google designed AI tools. In early September, Google released a free artificial intelligence tool that will help companies identify child abuse cases on the internet, by analyzing images.

“We, and in particular our expert analysts, are excited about the development of an artificial intelligence tool which could help our human experts review material to an even greater scale and keep up with offenders, by targeting imagery that hasn’t previously been marked as illegal material,” said Susie Hargreaves of the Internet Watch Foundation, a U.K.-based organization that fights against abuse material.

Bottomline: AI innovation will significantly advance the digital transformation of healthcare by streamlining diagnoses while ensuring greater accuracy, ultimately benefiting patients as well as care providers.  

Read the ultimate list of best healthcare startups

Comments are closed.