You’re back from a fun weekend at the beach and want to tag all your friends in the photos you took. That’s easy: Facebook’s facial recognition software does it automatically.
Or say, your doctor just took CAT-scan images of your chest and wants to tag everything that might be a lung tumor. Can computers do that, too?
Jeremy Howard says they can. The data scientist is the CEO of a just-launched company called Enlitic. He’s leveraging the power of a concept dubbed “deep learning” to develop ways for computers to spot injuries and diseases in X-rays, CAT scans, MRIs and other medical imaging, according to MIT Technology Review.
In the quest to make machines smarter, computers scientists have turned away from simply pumping the devices full of more and more facts and toward programming them to look for patterns and make connections on their own. This is deep learning — teaching computers to work the way the human brain does.
Deep learning is helping Google create self-driving cars and IBM make a computer that can win Jeopardy. Enlitic wants to use it to help doctors do their jobs better and faster.
Enlitic’s approach is to feed into a computer hundreds of pictures of, say, malignant liver growths, allowing the computer to identify the common characteristics they share. The computer can then begin to automatically tag tumors in medical images, highlighting areas for doctors to examine more closely.
Part of the venture’s appeal, for Howard, is that it’s a chance to apply data-mining techniques to a problem that’s more worthwhile than helping businesses figure out who your friends are or what you’ll want to watch next on Netflix.
“Data science is a very sexy job at the moment,” he tells Wired. “But when I look at what a lot of data scientists are actually doing, the vast majority of work out there is on product recommendations and advertising technology and so forth.”
Howard isn’t the only one working on ways to apply data science to medicine. Stanford University computer scientist Daphne Koller is training computers to analyze breast cancer scans. Her invention, Computational Pathologist (C-Path), also learns as it goes, figuring out which characteristics are the most important to look for.
Not only can Koller’s C-Path catch breast cancer tumors, it can also analyze them to predict patient survival rates.
Howard says his goal is not to replace radiologists and other doctors who examine medical images, but to help them be more efficient.
With deep learning computers on the rise in medicine, it may only be a matter of time before computers are tagging not only your vacation photos but your X-rays, too.
MORE: The Innovative Blood-Drawing Technique That’s Pain-Free and Saves Money
Tag: computer
Can Big Data Reshape City Governments?
When it comes to the nebulous term “big data,” U.S. cities are finally leaning in.
Though aggregating data and statistics seems to be a fool-proof trick to understanding the source of, and resolving urban problems like crime, traffic, pollution, and things of the like, city leaders have been slow to plug in.
“There was a time — the past 20 years, actually — when two large computer monitors in the mayor’s office would have been as welcome as a Walmart executive pitching a store in Boston,” Michael B. Farrell wrote for the Boston Globe last week. “Longtime occupant Thomas M. Menino famously shunned e-mail and didn’t even allow a PC to clutter his desk.”
How can a mayor get a full picture of his or her jurisdiction without even an e-mail address? Exactly. That’s not to say that Boston’s leadership has been completely in the dark, though. For years, Boston and other cities have been pored over crime, traffic, and potholes statistics to find areas for improvement. This kind of big data has been useful for enacting new laws and determining their effectiveness.
But Martin J. Walsh, Boston’s new mayor as of January 6, has embraced big data head on and brought it right onto his desktop. He has two 46-inch screens — called dashboards — that sit atop a metal stand, which display data about all things Boston — from the percentage of school buses arriving on schedule to how many potholes were filled in the past week to the number of calls flooding the city’s 24-hour hot line.
This way, he gets real-time reports from his city’s departments.“It’s really a way to have the department heads push to deliver better services to the city of Boston,” Walsh told the Globe. Watching his social media streams and hotline activity allows him to witness what issues need addressing right away and to see what’s working.
The dashboards originated with former New York City mayor Michael Bloomberg, who pushed his staff to use computers to discover previously overlooked issues and find solutions to ones that had long proved frustrating. The Globe found an instance in which this was particularly useful:
In one case, New York officials analyzed building data to determine which were more susceptible to fires, and then dispatched inspectors to those properties. Boston has undertaken similar efforts to target negligent landlords and to cut down on traffic congestion.
With Walsh’s term still in its infancy, his big data push will take time to truly manifest itself. But he has huge software and technological improvements to thank for enabling his mission. In a way, the true potential of big data couldn’t have been accessed during Menino’s long term, anyway. But today’s smartphones, powerful computers, and evermore effective data platforms make it easier to track trends. Even more exciting is the possibility of predictive data services, which may able to detect crimes before they happen.
Until then, Boston, along with other cities, as Government Technology outlines, may help lead the way in hacking into city problems — and how to fix them, stat.