Google AI can detect breast cancer more effectively than doctors
Lyra algorithm can successfully identify cancerous cells 99% of the time
Google has developed an artificial intelligence (AI) programme that is more effective at identifying signs of breast cancer than doctors.
Created by researchers at Google AI and the Naval Medical Center San Diego, the Lymph Node Assistant (Lyna) has been programmed to recognise the “characteristics” of tumours by analysing scans from real-world cancer patients, Engadget reports.
The process, commonly referred to as machine learning, allows the AI identify cancerous cells 99% of the time, the tech site says.
The Week
Escape your echo chamber. Get the facts behind the news, plus analysis from multiple perspectives.
Sign up for The Week's Free Newsletters
From our morning news briefing to a weekly Good News Newsletter, get the best of The Week delivered directly to your inbox.
From our morning news briefing to a weekly Good News Newsletter, get the best of The Week delivered directly to your inbox.
It could mean the Lyna is used as a virtual “spell check” for pathologists, says Business Insider, where the AI programme is used as a back-up tool to help medical professionals confirm whether a minute anomaly on a scan is either benign or malign.
The search engine’s researchers found that pathologists who used the tool “performed better” than those who didn’t use the programme, the news site says.
And according to Google, some pathologists claim the Lyra tool makes detecting small growths, an often “laborious task”, notably “easier”.
A member of the search giant’s AI team, Yun Liu, told Business Insider that the Lyna “represents a demonstration that people can work really well with AI algorithms than either one alone.”
A free daily email with the biggest news stories of the day – and the best features from TheWeek.com
But Google isn’t the only technology company looking to make inroads into the medical industry.
Last week, Chinese tech firm Tencent revealed that it is developing an algorithm to aid Parkinson’s disease patients record their symptoms. This would help doctors prescribe the correct amount of medication, cutting down the number of hospital visits for patients.
-
Spiralism is the new cult AI users are falling intoUnder the radar Technology is taking a turn
-
AI agents: When bots browse the webfeature Letting robots do the shopping
-
Is AI to blame for recent job cuts?Today’s Big Question Numerous companies have called out AI for being the reason for the culling
-
‘Deskilling’: a dangerous side effect of AI useThe explainer Workers are increasingly reliant on the new technology
-
AI models may be developing a ‘survival drive’Under the radar Chatbots are refusing to shut down
-
Saudi Arabia could become an AI focal pointUnder the Radar A state-backed AI project hopes to rival China and the United States
-
How the online world relies on AWS cloud serversThe Explainer Chaos caused by Monday’s online outage shows that ‘when AWS sneezes, half the internet catches the flu’
-
AI is making houses more expensiveUnder the radar Homebuying is also made trickier by AI-generated internet listings


