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.
Sammy Basso is one of around 400 young people in the world with progeria.
Just 400 or so people in the world live with progeria: The mutation that causes it usually arises de novo, or "of new," meaning that it is not inherited but happens spontaneously during gestation. The challenge, as with all rare diseases, is that few cases means few treatments.
"When we first started, there was absolutely nothing out there," says Leslie Gordon, a physician-researcher who co-founded the Progeria Research Foundation in 1999 after her own son, also named Sam, was diagnosed with the disease. "We knew we had to jumpstart the entire field, so we collected money through road races and special events and writing grants and all sorts of donors… I think the first year we raised $75,000, most of it from one donor."
"We have not only the possibility but the responsibility to make the world a better world, and also to make a body a better body."
By 2003, the foundation had collaborated with Francis Collins, a geneticist who is now director of the National Institutes of Health, to work out the genetic basis for progeria—that single mutation Sammy has. The discovery led to interest in lonafarnib, a drug that was already being used in cancer patients but could potentially operate downstream of the mutation, preventing the buildup of the defective progerin in the body. "We funded cellular studies to look at a lonafarnib in cells, mouse studies to look at lonafarnib in mouse models of progeria… and then we initiated the clinical trials," Gordon says.
Sammy Basso's family had gotten involved with the Progeria Research Foundation through their international patient registry, which maintains relationships with families in 49 countries. "We started to hear about lonafarnib in 2006 from Leslie Gordon," says Sammy's father, Amerigo Basso, with his son translating. "She told us about the lonafarnib. And we were very happy because for the first time we understood that there was something that could help our son and our lives." Amerigo used the Italian word speranza, which means hope.
Still, Sammy wasn't sure if lonafarnib was right for him. "Since when I was very young I thought that everything happens for a reason. So, in my mind, if God made me with progeria, there was a reason, and to try to heal from progeria was something wrong," he says. Gradually, his parents and doctors, and Leslie Gordon, convinced him otherwise. Sammy began to believe that God was also the force behind doctors, science, and research. "And so we have not only the possibility but the responsibility to make the world a better world, and also to make a body a better body," he says.
Sammy Basso and his parents.
Courtesy of Basso
Sammy began taking lonafarnib, with the Progeria Research Foundation intermittently flying him, and other international trial participants, to Boston for tests. He was immediately beset by some of the drug's more unpleasant side effects: Stomach problems, nausea, and vomiting. "The first period was absolutely the worst period of my life," he says.
At first, doctors prescribed other medicines for the side effects, but to Sammy it had as much effect as drinking water. He visited doctor after doctor, with some calling him weekly or even daily to ask how he was doing. Eventually the specialists decided that he should lower his dose, balancing his pain with the benefit of the drug. Sammy can't actually feel any positive effect of the lonafarnib, but his health measurements have improved relative to people with progeria who don't take it.
While they never completely disappeared, Sammy's side effects decreased to the point that he could live. Inspired by the research that led to lonafarnib, he went to university to study molecular biology. For his thesis work, he travelled to Spain to perform experiments on cells and on mice with progeria, learning how to use the gene-editing technique CRISPR-Cas9 to cut out the mutated bit of DNA. "I was so excited to participate in this study," Sammy says. He felt like his work could make a difference.
In 2018, the Progeria Research Foundation was hosting one of their biennial workshops when Francis Collins, the researcher who had located the mutation behind progeria 15 years earlier, got in touch with Leslie Gordon. "Francis called me and said, Hey, I just saw a talk by David Liu from the Broad [Institute]. And it was pretty amazing. He has been looking at progeria and has very early, but very exciting data… Do you have any spaces, any slots you could make in your program for late breaking news?"
Gordon found a spot, and David Liu came to talk about what was going on in his lab, which was an even more advanced treatment that led to mice with the progeria mutation living into their senior mouse years—substantially closer to a normal lifespan. Liu's lab had built on the idea of CRISPR-Cas9 to create a more elegant genetic process called base editing: Instead of chopping out mutated DNA, a scientist could chemically convert an incorrect DNA letter to the correct one, like the search and replace function in word processing software. Mice who had their Lamin-A mutations corrected this way lived more than twice as long as untreated animals.
Sammy was in the audience at Dr. Liu's talk. "When I heard about this base editing as a younger scientist, I thought that I was living in the future," he says. "When my parents had my diagnosis of progeria, the science knew very little information about DNA. And now we are talking about healing the DNA… It is incredible."
Lonafarnib (also called Zokinvy) was approved by the US Food and Drug Administration this past November. Sammy, now 25, still takes it, and still manages his side effects. With luck, the gift of a few extra years will act as a bridge until he can try Liu's revolutionary new gene treatment, which has not yet begun testing in humans. While Leslie Gordon warns that she's always wrong about things like this, she hopes to see the new base editing techniques in clinical trials in the next year or two. Sammy won't need to be convinced to try it this time; his thinking on fate has evolved since his first encounter with lonafarnib.
"I would be very happy to try it," he says. "I know that for a non-scientist it can be difficult to understand. Some people think that we are the DNA. We are not. The DNA is a part of us, and to correct it is to do what we are already doing—just better." In short, a gene therapy, while it may seem like science fiction, is no different from a pill. For Sammy, both are a new way to think about fate: No longer something that simply happens to him.