Skip to main content
Move the World.
Scientists Are Using AI to Improve Breast Cancer Screening

Lead image courtesy of Sergey Tarasov / Adobe Stock, Jo Panuwat D / Adobe Stock.

For MIT computer scientist Adam Yala, improving breast cancer screening had a personal motivation.

Yala's academic mentor, Regina Barzilay, had a bout with breast cancer in 2014. The experience gave a glimpse into the subjective side of the healthcare system and how much work needed to be done to improve breast cancer screening. For many patients, their ability to receive effective pre-cancer screening varies based on where they live and who their doctor is.

Yala wanted to standardize this experience for patients everywhere. He put his computer science training to good use and — together with Barzilay and their team from MIT and Massachusetts General Hospital (MGH) — created a deep learning algorithm designed to predict whether or not a patient will develop breast cancer within the next five years.

Traditional Predictive Models are Flawed

Discovering early signs of breast cancer in women improves the odds of survival, but the methods for deciding who to screen are fuzzy. Traditional predictive models, based on broad demographic factors, accurately place patients in the highest-risk category at an 18% success rate; the MIT/MGH team has radically improved on that, predicting risk accurately in 31% of cases.

Why the difference in accuracy?

Traditional risk models are based on surface-level information, such as age and family history. While these models are certainly better than nothing, they miss really important information in a majority of the cases.

Current screening guidelines simply suggest more regular exams based on the patient's age. Doctors normally recommend biannual mammograms at age 40 or 50, because breast cancer risk increases with age. This is painting with too broad a brush, Yala says.

"What is age, really?" Yala says. "It's just a weak risk marker." Other weak risk markers in current models include breast density, family history, and a patient's hormones.

MIT’s model is able to spot those extremely early signs of cancer before a human eye is able to, thanks to big data and machine learning.

MIT's machine learning model is able to look past these weak predictors because it is based on mammograms of actual patients, recognizing patterns that are invisible to humans.

"Given a large amount of data, there might be some subtle signal that humans are overlooking," says Kun-Hsing Yu, a biomedical informatics instructor at Harvard Medical School. "And give a machine a lot of data, we can tease out those hidden associations."

MIT's model is able to spot those extremely early signs of cancer before a human eye is able to, thanks to big data and machine learning. The model used 60,000 mammograms — from patients whose outcome, cancer or not, was already known — to pick out small trends in the images that correctly predict if the patient would get breast cancer. 

When tested with black and white patients at MGH, the results were very promising for both cohorts, finding early signs of breast cancer in women up to five years in advance that humans could not see.

This could not only lead to more accurate screenings, giving patients more accurate readings of their individual mammograms, but also better screening guidelines, by helping doctors target screenings on those with the highest risk.

Improving Breast Cancer Screening Around the World

The next step is to refine and validate the model on other patient populations. Yala says that the current iteration of the model is much more accurate than it was before, but it needs to work that well for everyone. There is no guarantee the model can predict outcomes as accurately for different races or in other parts of the world.

"Cancer is a global problem," Yala says. "We want to do this at scale, across the world." The team at MIT is working hard to make their model accurate for every race and ethnicity.

The model has already performed well with patient data from a hospital in Sweden, and plans are being made to test it with data from other hospitals around the world. But medical data is sensitive, and ensuring the data is used responsibly is paramount — a challenge made even more difficult when working across various healthcare providers, systems, and countries.

“Cancer is a global problem...We want to do this at scale, across the world.”

Adam Yala MIT computer scientist

However, with vast troves of human-validated clinical data, the potential for machine learning to change the future of medicine is high, Barzilay says. "If you think about it, the whole calling of medicine is all about prediction."

"I'm very grateful that I had a chance to work on this topic and try to make a difference," Barzilay says. "I think all of us, when we go through some upsetting experience, really want to take something out of it and help others."

Up Next

The Sound of Science
Sifting Through Sound: Using Soundscapes to Understand Ecosystem Health
Sifting Through Sound: Using Soundscapes to Understand Ecosystem Health
The Sound of Science
Sifting Through Sound: Using Soundscapes to Understand Ecosystem Health
“Ecoacoustics” is an emerging field of research. Instead of chasing down isolated animal sounds, researchers are using all of the acoustic properties of a location to answer ecological questions.
By Teresa Carey

“Ecoacoustics” is an emerging field of research. Instead of chasing down isolated animal sounds, researchers are using all of the acoustic properties of a location to answer ecological questions.

Digital Detectives
Online Hackers Hunt Down Missing People
Online Hackers Hunt Down Missing People
Watch Now
Digital Detectives
Online Hackers Hunt Down Missing People
This search and rescue expert discovered that many missing people had nobody looking for them. Then he had an idea: what if hackers made a game out of finding missing people through the internet?
Watch Now

The latest hacker game: solving missing persons cases for points. It’s the brainchild of Rob Sell, founder of Trace Labs. Sell is a professional search and rescue tracker who has also worked in computer security. Frustrated at the enormous number of missing persons with nobody searching for them, he began crowdsourcing hackers’ skills in computer forensics to follow the digital footprints of cold cases from the missing...

Dispatches
"Q" Probably Won't Make You Rich, but It's an Experiment Worth Watching
"Q" Probably Won't Make You Rich, but It's an Experiment Worth Watching
Dispatches
"Q" Probably Won't Make You Rich, but It's an Experiment Worth Watching
It's not the next Bitcoin (or a path to riches), but it's an intriguing idea.
By Brendan Markey-Towler

It's not the next Bitcoin (or a path to riches), but it's an intriguing idea.

Dispatches
UV Robots Can Sterilize an ICU in 10 Minutes
UV Disinfection Robots
Dispatches
UV Robots Can Sterilize an ICU in 10 Minutes
UV light destroys bacterial DNA from the inside out, eradicating the toughest pathogens in minutes.

UV light destroys bacterial DNA from the inside out, eradicating the toughest pathogens in minutes.

Dispatches
New Tech Makes Fresh Produce Last Twice as Long
New Tech Makes Fresh Produce Last Twice as Long
Dispatches
New Tech Makes Fresh Produce Last Twice as Long
The plant-based preservative could radically change the game on food waste.

The plant-based preservative could radically change the game on food waste.

Could Growing Vaccines in Plants Save Lives?
Could Growing Vaccines in Plants Save Lives?
Watch Now
Could Growing Vaccines in Plants Save Lives?
Vaccines for influenza, polio, smallpox, even Ebola have all be grown … in plants.
Watch Now

This flu season has been nasty in large part because the vaccine didn’t work as well as past versions. So scientists like Professor George Lomonossoff of the John Innes Centre are on the hunt for new ways to make better vaccines and think they might have found one -- by growing them in plants.

On The Fringe
Growing Human Organs in Pigs
Growing Human Organs in Pigs
Watch Now
On The Fringe
Growing Human Organs in Pigs
Twenty people die every day in the U.S. waiting for an organ transplant. There aren’t enough organs for the 100,000...
Watch Now

Twenty people die every day in the U.S. waiting for an organ transplant. There aren’t enough organs for the 100,000 people waiting for one. And there likely never will be… unless we can find a better way to source them. Enter: the pigs. A team of scientists has figured out how to grow human organs in pigs. It might make you feel weird. But it also might save countless lives.