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."
- Researchers develop comprehensive new way to predict breast ... ›
- Breast Cancer Risk Assessment Tool ›
- Cancer What Do Breasts Look Like on a Mammogram? ›
At one point, America needed to be called a Judeo-Christian nation. Now, with growing populations of Muslims, Evangelicals, Sikhs, Atheists, and other faiths, what should America call itself next?
- America wasn't always known as Judeo-Christian nation. Rather, it used to be considered a Protestant nation.
- As Jews and Catholics began to represent a larger share of the nation, activists realized that America needed to reinvent itself if the voices of these growing groups were to be heard. In this way, the "Judeo-Christian" label was conceived. Today, that label doesn't quite fit anymore. What does?
- The opinions expressed in this video do not necessarily reflect the views of the Charles Koch Foundation, which encourages the expression of diverse viewpoints within a culture of civil discourse and mutual respect.
Researchers hope the technology will further our understanding of the brain, but lawmakers may not be ready for the ethical challenges.
- Researchers at the Yale School of Medicine successfully restored some functions to pig brains that had been dead for hours.
- They hope the technology will advance our understanding of the brain, potentially developing new treatments for debilitating diseases and disorders.
- The research raises many ethical questions and puts to the test our current understanding of death.
The image of an undead brain coming back to live again is the stuff of science fiction. Not just any science fiction, specifically B-grade sci fi. What instantly springs to mind is the black-and-white horrors of films like Fiend Without a Face. Bad acting. Plastic monstrosities. Visible strings. And a spinal cord that, for some reason, is also a tentacle?
But like any good science fiction, it's only a matter of time before some manner of it seeps into our reality. This week's Nature published the findings of researchers who managed to restore function to pigs' brains that were clinically dead. At least, what we once thought of as dead.
What's dead may never die, it seems
The researchers did not hail from House Greyjoy — "What is dead may never die" — but came largely from the Yale School of Medicine. They connected 32 pig brains to a system called BrainEx. BrainEx is an artificial perfusion system — that is, a system that takes over the functions normally regulated by the organ. The pigs had been killed four hours earlier at a U.S. Department of Agriculture slaughterhouse; their brains completely removed from the skulls.
BrainEx pumped an experiment solution into the brain that essentially mimic blood flow. It brought oxygen and nutrients to the tissues, giving brain cells the resources to begin many normal functions. The cells began consuming and metabolizing sugars. The brains' immune systems kicked in. Neuron samples could carry an electrical signal. Some brain cells even responded to drugs.
The researchers have managed to keep some brains alive for up to 36 hours, and currently do not know if BrainEx can have sustained the brains longer. "It is conceivable we are just preventing the inevitable, and the brain won't be able to recover," said Nenad Sestan, Yale neuroscientist and the lead researcher.
As a control, other brains received either a fake solution or no solution at all. None revived brain activity and deteriorated as normal.
The researchers hope the technology can enhance our ability to study the brain and its cellular functions. One of the main avenues of such studies would be brain disorders and diseases. This could point the way to developing new of treatments for the likes of brain injuries, Alzheimer's, Huntington's, and neurodegenerative conditions.
"This is an extraordinary and very promising breakthrough for neuroscience. It immediately offers a much better model for studying the human brain, which is extraordinarily important, given the vast amount of human suffering from diseases of the mind [and] brain," Nita Farahany, the bioethicists at the Duke University School of Law who wrote the study's commentary, told National Geographic.
An ethical gray matter
Before anyone gets an Island of Dr. Moreau vibe, it's worth noting that the brains did not approach neural activity anywhere near consciousness.
The BrainEx solution contained chemicals that prevented neurons from firing. To be extra cautious, the researchers also monitored the brains for any such activity and were prepared to administer an anesthetic should they have seen signs of consciousness.
Even so, the research signals a massive debate to come regarding medical ethics and our definition of death.
Most countries define death, clinically speaking, as the irreversible loss of brain or circulatory function. This definition was already at odds with some folk- and value-centric understandings, but where do we go if it becomes possible to reverse clinical death with artificial perfusion?
"This is wild," Jonathan Moreno, a bioethicist at the University of Pennsylvania, told the New York Times. "If ever there was an issue that merited big public deliberation on the ethics of science and medicine, this is one."
One possible consequence involves organ donations. Some European countries require emergency responders to use a process that preserves organs when they cannot resuscitate a person. They continue to pump blood throughout the body, but use a "thoracic aortic occlusion balloon" to prevent that blood from reaching the brain.
The system is already controversial because it raises concerns about what caused the patient's death. But what happens when brain death becomes readily reversible? Stuart Younger, a bioethicist at Case Western Reserve University, told Nature that if BrainEx were to become widely available, it could shrink the pool of eligible donors.
"There's a potential conflict here between the interests of potential donors — who might not even be donors — and people who are waiting for organs," he said.
It will be a while before such experiments go anywhere near human subjects. A more immediate ethical question relates to how such experiments harm animal subjects.
Ethical review boards evaluate research protocols and can reject any that causes undue pain, suffering, or distress. Since dead animals feel no pain, suffer no trauma, they are typically approved as subjects. But how do such boards make a judgement regarding the suffering of a "cellularly active" brain? The distress of a partially alive brain?
The dilemma is unprecedented.
Setting new boundaries
Another science fiction story that comes to mind when discussing this story is, of course, Frankenstein. As Farahany told National Geographic: "It is definitely has [sic] a good science-fiction element to it, and it is restoring cellular function where we previously thought impossible. But to have Frankenstein, you need some degree of consciousness, some 'there' there. [The researchers] did not recover any form of consciousness in this study, and it is still unclear if we ever could. But we are one step closer to that possibility."
She's right. The researchers undertook their research for the betterment of humanity, and we may one day reap some unimaginable medical benefits from it. The ethical questions, however, remain as unsettling as the stories they remind us of.
A large new study uses an online game to inoculate people against fake news.
- Researchers from the University of Cambridge use an online game to inoculate people against fake news.
- The study sample included 15,000 players.
- The scientists hope to use such tactics to protect whole societies against disinformation.
SMARTER FASTER trademarks owned by The Big Think, Inc. All rights reserved.