A recent study in The Lancet Oncology showed that AI found 20 percent more cancers on mammogram screens than radiologists alone.
The Lancet Oncology
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.
Adobe Stock
It's all part of balancing bureaucracy with research goals for Williams, a leading expert on racial trauma and psychedelic medicine, as well as obsessive compulsive disorder (OCD), at the University of Ottawa. She's exploring the use of hallucinogenic substances like MDMA and psilocybin — commonly known as ecstasy and magic mushrooms, respectively — to help people of color address the psychological impacts of systemic racism. A prolific researcher, Williams also works as an expert witness, offering clinical evaluations for racial trauma cases.
Scientists have long known that psychedelics produce an altered state of consciousness and openness to new perspectives. For people with mental health conditions who haven't benefited from traditional therapy, psychedelics may be able to help them discover what's causing their pain or trauma, including racial trauma—the mental and emotional injury spurred by racial bias.
"Using psychedelics can not only bring these pain points to the surface for healing, but can reduce the anxiety or response to these memories and allow them to speak openly about them without the pain they bring," Williams says. Her research harnesses the potential of psychedelics to increase neuroplasticity, which includes the brain's ability to build new pathways.
"People of color are dealing with racism all the time, in large and small ways, and even dealing with racism in healthcare, even dealing with racism in therapy."
But she says therapists of color aren't automatically equipped to treat racial trauma. First, she notes, people of color are "vastly underrepresented in the mental health workforce." This is doubly true in psychedelic-assisted psychotherapy, in which a person is guided through a psychedelic session by a therapist or team of therapists, then processes the experience in subsequent therapy sessions.
"On top of that, the therapists of color are getting the same training that the white therapists are getting, so it's not even really guaranteed that they're going to be any better at helping a person that may have racial trauma emerging as part of their experience," she says.
In her own training to become a clinical psychologist at the University of Virginia, Williams says she was taught "how to be a great psychologist for white people." Yet even people of color, she argues, need specialized training to work with marginalized groups, particularly when it comes to MDMA, psilocybin and other psychedelics. Because these drugs can lower natural psychological defense mechanisms, Williams says, it's important for providers to be specially trained.
"People of color are dealing with racism all the time, in large and small ways, and even dealing with racism in healthcare, even dealing with racism in therapy. So [they] generally develop a lot of defenses and coping strategies to ward off racism so that they can function." she says. This is particularly true with psychedelic-assisted psychotherapy: "One possibility is that you're going to be stripped of your defenses, you're going to be vulnerable. And so you have to work with a therapist who is going to understand that and not enact more racism in their work with you."
Williams has struggled to find funding and institutional approval for research involving psychedelics, or funding for investigations into racial trauma or the impacts of conditions like OCD and post-traumatic stress disorder (PTSD) in people of color. With the bulk of her work focusing on OCD, she hoped to focus on people of color, but found there was little funding for that type of research. In 2020, that started to change as structural racism garnered more media attention.
After the killing of George Floyd, a 46-year-old Black man, by a white police officer in May 2020, Williams was flooded with media requests. "Usually, when something like that happens, I get contacted a lot for a couple of weeks, and it dies off. But after George Floyd, it just never did."
Monnica Williams, clinical psychologist at the University of Ottawa
Williams was no stranger to the questions that soon blazed across headlines: How can we mitigate microaggressions? How do race and ethnicity impact mental health? What terms should we use to discuss racial issues? What constitutes an ally, and why aren't there more of them? Why aren't there more people of color in academia, and so many other fields?
Now, she's hoping that the increased attention on racial justice will mean more acceptance for the kind of research she's doing.
In fact, Williams herself has used psychedelics in order to gain a better understanding of how to use them to treat racial trauma. In a study published in January, she and two other Black female psychotherapists took MDMA in a supervised setting, guided by a team of mental health practitioners who helped them process issues that came up as the session progressed. Williams, who was also the study's lead author, found that participants' experiences centered around processing and finding release from racial identities, and, in one case, of simply feeling wholly human without the burden of racial identity for the first time.
The purpose of the study was twofold: to understand how Black women react to psychedelics and to provide safe, firsthand, psychedelic experiences to Black mental health practitioners. One of the other study participants has since gone on to offer psychedelic-assisted psychotherapy to her own patients.
Psychedelic research, and psilocybin in particular, has become a hot topic of late, particularly after Oregon became the first state to legalize it for therapeutic use last November. A survey-based, observational study with 313 participants, published in 2020, paved the way for Williams' more recent MDMA experiments by describing improvements in depression, anxiety and racial trauma among people of color who had used LSD, psilocybin or MDMA in a non-research setting.
Williams and her team included only respondents who reported a moderate to strong psychoactive effect of past psychedelic consumption and believed these experiences provided "relief from the challenging effects of ethnic discrimination." Participants reported a memorable psychedelic experience as well as its acute and lasting effects, completing assessments of psychological insight, mystical experience and emotional challenges experienced during psychedelic experience, then describing their mental health — including depression, anxiety and trauma symptoms — before and after that experience.
Still, Williams says addressing racism is much more complex than treating racial trauma. "One of the questions I get asked a lot is, 'How can Black people cope with racism?' And I don't really like that question," she says. "I think it's important and I don't mind answering it, but I think the more important question is, how can we end racism? What can Black people do to stop racism that's happening to them and what can we do as a society to stop racism? And people aren't really asking this question."