Using AI to predict breast cancer and personalize care
New technology could predict cancer up to 5 years in advance.
Despite major advances in genetics and modern imaging, the diagnosis catches most breast cancer patients by surprise.
For some, it comes too late. Later diagnosis means aggressive treatments, uncertain outcomes, and more medical expenses. As a result, identifying patients has been a central pillar of breast cancer research and effective early detection.
With that in mind, a team from MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL) and Massachusetts General Hospital (MGH) has created a new deep-learning model that can predict from a mammogram if a patient is likely to develop breast cancer as much as five years in the future. Trained on mammograms and known outcomes from over 60,000 MGH patients, the model learned the subtle patterns in breast tissue that are precursors to malignant tumors.
MIT Professor Regina Barzilay, herself a breast cancer survivor, says that the hope is for systems like these to enable doctors to customize screening and prevention programs at the individual level, making late diagnosis a relic of the past.
Although mammography has been shown to reduce breast cancer mortality, there is continued debate on how often to screen and when to start. While the American Cancer Society recommends annual screening starting at age 45, the U.S. Preventative Task Force recommends screening every two years starting at age 50.
"Rather than taking a one-size-fits-all approach, we can personalize screening around a woman's risk of developing cancer," says Barzilay, senior author of a new paper about the project out recently in Radiology. "For example, a doctor might recommend that one group of women get a mammogram every other year, while another higher-risk group might get supplemental MRI screening." Barzilay is the Delta Electronics Professor at CSAIL and the Department of Electrical Engineering and Computer Science at MIT and a member of the Koch Institute for Integrative Cancer Research at MIT.
The team's model was significantly better at predicting risk than existing approaches: It accurately placed 31 percent of all cancer patients in its highest-risk category, compared to only 18 percent for traditional models.
Harvard Professor Constance Lehman says that there's previously been minimal support in the medical community for screening strategies that are risk-based rather than age-based.
"This is because before we did not have accurate risk assessment tools that worked for individual women," says Lehman, a professor of radiology at Harvard Medical School and division chief of breast imaging at MGH. "Our work is the first to show that it's possible."
Barzilay and Lehman co-wrote the paper with lead author Adam Yala, a CSAIL PhD student. Other MIT co-authors include PhD student Tal Schuster and former master's student Tally Portnoi.
How it works
Since the first breast-cancer risk model from 1989, development has largely been driven by human knowledge and intuition of what major risk factors might be, such as age, family history of breast and ovarian cancer, hormonal and reproductive factors, and breast density.
However, most of these markers are only weakly correlated with breast cancer. As a result, such models still aren't very accurate at the individual level, and many organizations continue to feel risk-based screening programs are not possible, given those limitations.
Rather than manually identifying the patterns in a mammogram that drive future cancer, the MIT/MGH team trained a deep-learning model to deduce the patterns directly from the data. Using information from more than 90,000 mammograms, the model detected patterns too subtle for the human eye to detect.
"Since the 1960s radiologists have noticed that women have unique and widely variable patterns of breast tissue visible on the mammogram," says Lehman. "These patterns can represent the influence of genetics, hormones, pregnancy, lactation, diet, weight loss, and weight gain. We can now leverage this detailed information to be more precise in our risk assessment at the individual level."
Making cancer detection more equitable
The project also aims to make risk assessment more accurate for racial minorities, in particular. Many early models were developed on white populations, and were much less accurate for other races. The MIT/MGH model, meanwhile, is equally accurate for white and black women. This is especially important given that black women have been shown to be 42 percent more likely to die from breast cancer due to a wide range of factors that may include differences in detection and access to health care.
"It's particularly striking that the model performs equally as well for white and black people, which has not been the case with prior tools," says Allison Kurian, an associate professor of medicine and health research/policy at Stanford University School of Medicine. "If validated and made available for widespread use, this could really improve on our current strategies to estimate risk."
Barzilay says their system could also one day enable doctors to use mammograms to see if patients are at a greater risk for other health problems, like cardiovascular disease or other cancers. The researchers are eager to apply the models to other diseases and ailments, and especially those with less effective risk models, like pancreatic cancer.
"Our goal is to make these advancements a part of the standard of care," says Yala. "By predicting who will develop cancer in the future, we can hopefully save lives and catch cancer before symptoms ever arise."
- New therapy turns cancer into fat to stop its spread - Big Think ›
- Breast Cancer May be Linked to a Dad's Body Fat is at the Time of ... ›
To create wiser adults, add empathy to the school curriculum.
- Stories are at the heart of learning, writes Cleary Vaughan-Lee, Executive Director for the Global Oneness Project. They have always challenged us to think beyond ourselves, expanding our experience and revealing deep truths.
- Vaughan-Lee explains 6 ways that storytelling can foster empathy and deliver powerful learning experiences.
- Global Oneness Project is a free library of stories—containing short documentaries, photo essays, and essays—that each contain a companion lesson plan and learning activities for students so they can expand their experience of the world.
Philosophers like to present their works as if everything before it was wrong. Sometimes, they even say they have ended the need for more philosophy. So, what happens when somebody realizes they were mistaken?
Sometimes philosophers are wrong and admitting that you could be wrong is a big part of being a real philosopher. While most philosophers make minor adjustments to their arguments to correct for mistakes, others make large shifts in their thinking. Here, we have four philosophers who went back on what they said earlier in often radical ways.
Numerous U.S. Presidents invoked the Insurrection Act to to quell race and labor riots.
- U.S. Presidents have invoked the Insurrection Act on numerous occasions.
- The controversial law gives the President some power to bring in troops to police the American people.
- The Act has been used mainly to restore order following race and labor riots.
It looks like a busy hurricane season ahead. Probably.
- Before the hurricane season even started in 2020, Arthur and Bertha had already blown through, and Cristobal may be brewing right now.
- Weather forecasters see signs of a rough season ahead, with just a couple of reasons why maybe not.
- Where's an El Niño when you need one?
Welcome to Hurricane Season 2020. 2020, of course, scoffs at this calendric event much as it has everything else that's normal — meteorologists have already used up the year's A and B storm names before we even got here. And while early storms don't necessarily mean a bruising season ahead, forecasters expect an active season this year. Maybe storms will blow away the murder hornets and 13-year locusts we had planned.
NOAA expects a busy season
According to NOAA's Climate Prediction Center, an agency of the National Weather Service, there's a 60 percent chance that we're embarking upon a season with more storms than normal. There does, however, remain a 30 percent it'll be normal. Better than usual? Unlikely: Just a 10 percent chance.
Where a normal hurricane season has an average of 12 named storms, 6 of which become hurricanes and 3 of which are major hurricanes, the Climate Prediction Center reckons we're on track for 13 to 29 storms, 6 to 10 of which will become hurricanes, and 3 to 6 of these will be category 3, 4, or 5, packing winds of 111 mph or higher.
What has forecasters concerned are two factors in particular.
This year's El Niño ("Little Boy") looks to be more of a La Niña ("Little Girl"). The two conditions are part of what's called the El Niño-Southern Oscillation (ENSO) cycle, which describes temperature fluctuations between the ocean and atmosphere in the east-central Equatorial Pacific. With an El Niño, waters in the Pacific are unusually warm, whereas a La Niña means unusually cool waters. NOAA says that an El Niño can suppress hurricane formation in the Atlantic, and this year that mitigating effect is unlikely to be present.
Second, current conditions in the Atlantic and Caribbean suggest a fertile hurricane environment:
- The ocean there is warmer than usual.
- There's reduced vertical wind shear.
- Atlantic tropical trade winds are weak.
- There have been strong West African monsoons this year.
Here's NOAA's video laying out their forecast:
ArsTechnica spoke to hurricane scientist Phil Klotzbach, who agrees generally with NOAA, saying, "All in all, signs are certainly pointing towards an active season." Still, he notes a couple of signals that contradict that worrying outlook.
First off, Klotzbach notes that the surest sign of a rough hurricane season is when its earliest storms form in the deep tropics south of 25°N and east of the Lesser Antilles. "When you get storm formations here prior to June 1, it's typically a harbinger of an extremely active season." Fortunately, this year's hurricanes Arthur and Bertha, as well as the maybe-imminent Cristobal, formed outside this region. So there's that.
Second, Klotzbach notes that the correlation between early storm activity and a season's number of storms and intensities, is actually slightly negative. So while statistical connections aren't strongly predictive, there's at least some reason to think these early storms may augur an easy season ahead.
Image source: NOAA
Batten down the hatches early
If 2020's taught us anything, it's how to juggle multiple crises at once, and layering an active hurricane season on top of SARS-CoV-2 — not to mention everything else — poses a special challenge. Warns Treasury Secretary Wilbur Ross, "As Americans focus their attention on a safe and healthy reopening of our country, it remains critically important that we also remember to make the necessary preparations for the upcoming hurricane season." If, as many medical experts expect, we're forced back into quarantine by additional coronavirus waves, the oceanic waves slamming against our shores will best be met by storm preparations put in place in a less last-minute fashion than usual.
Ross adds, "Just as in years past, NOAA experts will stay ahead of developing hurricanes and tropical storms and provide the forecasts and warnings we depend on to stay safe."
Let's hope this, at least, can be counted on in this crazy year.
Got any embarrassing old posts collecting dust on your profile? Facebook wants to help you delete them.