A recent study in The Lancet Oncology showed that AI found 20 percent more cancers on mammogram screens than radiologists alone.
Published in The Lancet Oncology, the study analyzed the scans of 80,000 Swedish women with a moderate hereditary risk of breast cancer who had undergone a mammogram between April 2021 and July 2022. Half of these scans were read by AI and then a radiologist to double-check the findings. The second group of scans was read by two researchers without the help of AI. (Currently, the standard of care across Europe is to have two radiologists analyze a scan before diagnosing a patient with breast cancer.)
The study showed that the AI group detected cancer in 6 out of every 1,000 scans, while the radiologists detected cancer in 5 per 1,000 scans. In other words, AI found 20 percent more cancers than the highly-trained radiologists.
Scientists have been using MRI images (like the ones pictured here) to train artificial intelligence to detect cancers earlier and with more accuracy. Here, MIT's AI system, MIRAI, looks for patterns in a patient's mammograms to detect breast cancer earlier than ever before. news.mit.edu
But even though the AI was better able to pinpoint cancer on an image, it doesn’t mean radiologists will soon be out of a job. Dr. Laura Heacock, a breast radiologist at NYU, said in an interview with CNN that radiologists do much more than simply screening mammograms, and that even well-trained technology can make errors. “These tools work best when paired with highly-trained radiologists who make the final call on your mammogram. Think of it as a tool like a stethoscope for a cardiologist.”
AI is still an emerging technology, but more and more doctors are using them to detect different cancers. For example, researchers at MIT have developed a program called MIRAI, which looks at patterns in patient mammograms across a series of scans and uses an algorithm to model a patient's risk of developing breast cancer over time. The program was "trained" with more than 200,000 breast imaging scans from Massachusetts General Hospital and has been tested on over 100,000 women in different hospitals across the world. According to MIT, MIRAI "has been shown to be more accurate in predicting the risk for developing breast cancer in the short term (over a 3-year period) compared to traditional tools." It has also been able to detect breast cancer up to five years before a patient receives a diagnosis.
The challenges for cancer-detecting AI tools now is not just accuracy. AI tools are also being challenged to perform consistently well across different ages, races, and breast density profiles, particularly given the increased risks that different women face. For example, Black women are 42 percent more likely than white women to die from breast cancer, despite having nearly the same rates of breast cancer as white women. Recently, an FDA-approved AI device for screening breast cancer has come under fire for wrongly detecting cancer in Black patients significantly more often than white patients.
As AI technology improves, radiologists will be able to accurately scan a more diverse set of patients at a larger volume than ever before, potentially saving more lives than ever.
A fierce champion fighter in action, representing the incredible power of the human immune system.
It's vacation time. You and your family visit a country where you've never been and, in fact, your parents or grandparents had never been. You find yourself hiking beside a beautiful lake. It's a gorgeous day. You dive in. You are not alone.
How can your T cells and B cells react to a pathogen they've never seen?
In the water swim parasites, perhaps a parasite called giardia. The invader slips in through your mouth or your urinary tract. This bug is entirely new to you, and there's more. It might be new to everyone you've ever met or come into contact with. The parasite may have evolved in this setting for hundreds of thousands of years so that it's different from any giardia bug you've ever come into contact with before or that thrives in the region where you live.
How can your T cells and B cells react to a pathogen they've never seen, never knew existed, and were never inoculated against, and that you, or your doctors, in all their wisdom, could never have foreseen?
This is the infinity problem.
For years, this was the greatest mystery in immunology.
As I reported An Elegant Defense -- my book about the science of the immune system told through the lives of scientists and medical patients -- I was repeatedly struck by the profundity of this question. It is hard to overstate: how can we survive in a world with such myriad possible threats?
Matt Richtel's new book about the science of the immune system, An Elegant Defense, was published this month.
To further underscore the quandary, the immune system has to neutralize threats without killing the rest of the body. If the immune system could just kill the rest of the body too, the solution to the problem would be easy. Nuke the whole party. That obviously won't work if we are to survive. So the immune system has to be specific to the threat while also leaving most of our organism largely alone.
"God had two options," Dr. Mark Brunvand told me. "He could turn us into ten-foot-tall pimples, or he could give us the power to fight 10 to the 12th power different pathogens." That's a trillion potential bad actors. Why pimples? Pimples are filled with white blood cells, which are rich with immune system cells. In short, you could be a gigantic immune system and nothing else, or you could have some kind of secret power that allowed you to have all the other attributes of a human being—brain, heart, organs, limbs—and still somehow magically be able to fight infinite pathogens.
Dr. Brunvand is a retired Denver oncologist, one of the many medical authorities in the book – from wizened T-cell innovator Dr. Jacques Miller, to the finder of fever, Dr. Charles Dinarello, to his eminence Dr. Anthony Fauci at the National Institutes of Health to newly minted Nobel-Prize winner Jim Allison.
In the case of Dr. Brunvand, the oncologist also is integral to one of the book's narratives, a remarkable story of a friend of mine named Jason. Four years ago, he suffered late, late stage cancer, with 15 pounds of lymphoma growing in his back, and his oncologist put him into hospice. Then Jason became one of the first people ever to take an immunotherapy drug for lymphoma and his tumors disappeared. Through Jason's story, and a handful of other fascinating tales, I showcase how the immune system works.
There are two options for creating such a powerful immune system: we could be pimples or have some other magical power.
Dr. Brunvand had posited to me that there were two options for creating such a powerful and multifaceted immune system: we could be pimples or have some other magical power. You're not a pimple. So what was the ultimate solution?
Over the years, there were a handful of well-intentioned, thoughtful theories, but they strained to account for the inexplicable ability of the body to respond to virtually anything. The theories were complex and suffered from that peculiar side effect of having terrible names—like "side-chain theory" and "template-instructive hypothesis."
This was the background when along came Susumu Tonegawa.
***
Tonegawa was born in 1939, in the Japanese port city of Nagoya, and was reared during the war. Lucky for him, his father was moved around in his job, and so Tonegawa grew up in smaller towns. Otherwise, he might've been in Nagoya on May 14,1944, when the United States sent nearly 550 B-29 bombers to take out key industrial sites there and destroyed huge swaths of the city.
Fifteen years later, in 1959, Tonegawa was a promising student when a professor in Kyoto told him that he should go to the United States because Japan lacked adequate graduate training in molecular biology. A clear, noteworthy phenomenon was taking shape: Immunology and its greatest discoveries were an international affair, discoveries made through cooperation among the world's best brains, national boundaries be damned.
Tonegawa wound up at the University of California at San Diego, at a lab in La Jolla, "the beautiful Southern California town near the Mexican border." There, in multicultural paradise, he received his PhD, studying in the lab of Masaki Hayashi and then moved to the lab of Renato Dulbecco. Dr. Dulbecco was born in Italy, got a medical degree, was recruited to serve in World War II, where he fought the French and then, when Italian fascism collapsed, joined the resistance and fought the Germans. (Eventually, he came to the United States and in 1975 won a Nobel Prize for using molecular biology to show how viruses can lead, in some cases, to tumor creation.)
In 1970, Tonegawa—now armed with a PhD—faced his own immigration conundrum. His visa was set to expire by the end of 1970, and he was forced to leave the country for two years before he could return. He found a job in Switzerland at the Basel Institute for Immunology.
***
Around this time, new technology had emerged that allowed scientists to isolate different segments of an organism's genetic material. The technology allowed segments to be "cut" and then compared to one another. A truism emerged: If a researcher took one organism's genome and cut precisely the same segment over and over again, the resulting fragment of genetic material would match each time.
When you jump in that lake in a foreign land, filled with alien bugs, your body, astonishingly, well might have a defender that recognizes the creature.
This might sound obvious, but it was key to defining the consistency of an organism's genetic structure.
Then Tonegawa found the anomaly.
He was cutting segments of genetic material from within B cells. He began by comparing the segments from immature B cells, meaning, immune system cells that were still developing. When he compared identical segments in these cells, they yielded, predictably, identical fragments of genetic material. That was consistent with all previous knowledge.
But when he compared the segments to identical regions in mature B cells, the result was entirely different. This was new, distinct from any other cell or organism that had been studied. The underlying genetic material had changed.
"It was a big revelation," said Ruslan Medzhitov, a Yale scholar. "What he found, and is currently known, is that the antibody-encoding genes are unlike all other normal genes."
The antibody-encoding genes are unlike all other normal genes.
Yes, I used italics. Your immune system's incredible capabilities begin from a remarkable twist of genetics. When your immune system takes shape, it scrambles itself into millions of different combinations, random mixtures and blends. It is a kind of genetic Big Bang that creates inside your body all kinds of defenders aimed at recognizing all kinds of alien life forms.
So when you jump in that lake in a foreign land, filled with alien bugs, your body, astonishingly, well might have a defender that recognizes the creature.
Light the fireworks and send down the streamers!
As Tonegawa explored further, he discovered a pattern that described the differences between immature B cells and mature ones. Each of them shared key genetic material with one major variance: In the immature B cell, that crucial genetic material was mixed in with, and separated by, a whole array of other genetic material.
As the B cell matured into a fully functioning immune system cell, much of the genetic material dropped out. And not just that: In each maturing B cell, different material dropped out. What had begun as a vast array of genetic coding sharpened into this particular, even unique, strand of genetic material.
***
This is complex stuff. But a pep talk: This section is as deep and important as any in describing the wonder of the human body. Dear reader, please soldier on!
***
Researchers, who, eventually, sought a handy way to define the nature of the genetic change to the material of genes, labeled the key genetic material in an antibody with three initials: V, D, and J.
The letter V stands for variable. The variable part of the genetic material is drawn from hundreds of genes.
D stands for diversity, which is drawn from a pool of dozens of different genes.
And J is drawn from another half dozen genes.
In an immature B cell, the strands of V, D, and J material are in separate groupings, and they are separated by a relatively massive distance. But as the cell matures, a single, random copy of V remains, along with a single each of D and J, and all the other intervening material drops out. As I began to grasp this, it helped me to picture a line of genetic material stretching many miles. Suddenly, three random pieces step forward, and the rest drops away.
The combination of these genetic slices, grouped and condensed into a single cell, creates, by the power of math, trillions of different and virtually unique genetic codes.
In anticipation of threats from the unfathomable, our defenses evolved as infinity machines.
Or if you prefer a different metaphor, the body has randomly made hundreds of millions of different keys, or antibodies. Each fits a lock that is located on a pathogen. Many of these antibodies are combined such that they are alien genetic material—at least to us—and their locks will never surface in the human body. Some may not exist in the entire universe. Our bodies have come stocked with keys to the rarest and even unimaginable locks, forms of evil the world has not yet seen, but someday might. In anticipation of threats from the unfathomable, our defenses evolved as infinity machines.
"The discoveries of Tonegawa explain the genetic background allowing the enormous richness of variation among antibodies," the Nobel Prize committee wrote in its award to him years later, in 1987. "Beyond deeper knowledge of the basic structure of the immune system these discoveries will have importance in improving immunological therapy of different kinds, such as, for instance, the enforcement of vaccinations and inhibition of reactions during transplantation. Another area of importance is those diseases where the immune defense of the individual now attacks the body's own tissues, the so-called autoimmune diseases."
Indeed, these revelations are part of a period of time it would be fair to call the era of immunology, stretching from the middle of the 20th century to the present. During that period, we've come from sheer ignorance of the most basic aspects of the immune system to now being able to tinker under the hood with monoclonal antibodies and other therapies. And we are, in many ways, just at the beginning.
