As artificial intelligence continues to get more impressive, a lab out of Waterloo, Ont., is taking breast cancer research to new heights by working to help patients get proper treatment with their new technology.
When patients get breast cancer, they typically undergo a type of imaging, like a magnetic resonance imaging or MRI, to look for cancerous tumors. The Waterloo lab has created “a synthetic correlate diffusion” MRI that is tailored to capture details and properties of cancer in a way that previous MRI systems couldn’t.
“It could be a very helpful tool to help oncologists and medical doctors to be able to identify and personalize the type of treatment that a cancer patient gets,” Alexander Wong, professor and Canada Research Chair in Artificial Intelligence and Medical Imaging at the University of Waterloo, told Global News.
Breast cancer is the second leading cause of death from cancer in Canadian women, according to the Canadian Cancer Society.
It is estimated that one in eight Canadian women will develop breast cancer during their lifetime and one in 34 will die from it.
Last year, it was also estimated that 28,600 Canadian women would be diagnosed with breast cancer, the society said.
How does it work?
Using synthetic correlate diffusion imagining data, the new AI-driven technology predicts whether a patient is likely to benefit from neoadjuvant chemotherapy – or chemotherapy that occurs before surgery, according to Wong.
Though the hardware of the actual MRI machine hasn’t changed in this model, what has altered is the way the technology sends “pulses” through the patient’s body and how it collects data, Wong noted.
“The cancer itself just lights up and really shows the different nuances and characteristics around it, which makes it very much easier to identify not only where the cancer is, the size of the cancer, but also the actual tissue characteristics of the cancer to help doctors make better decisions,” he said.
The AI can then analyze the MRI data to help learn whether breast cancer patients could benefit from chemotherapy before surgery in their treatment process.
“Now, with this rich information about tumor characteristics, the AI in this case is a deep neural network – a little bit kind of like how our brain works. It takes this information from this MRI system and learns to identify what are the key nuances or traits that lead us to a patient that would benefit from this form of chemotherapy,” Wong said.
“It’s essentially the combination of two types of technologies. One is the new MRI imaging technology to really capture the right information. The other is the AI advancement in terms of a deep neural network.”
Deep neural networks are able to continue improving as more information is captured, said Wong.
“The more examples it sees, the better it gets at really identifying these subtle patterns that differentiate from one another. As we train it with more and more data, it’s able to have higher levels of predictive accuracy,” he said.
How accurate is the new tech?
The technology has been tested through a prospective study of around 253 patient cases from a cohort in the United States who have chemotherapy before surgery, according to Wong.
“The AI, when using our new form of MRI, was able to identify and predict with over 87 per cent accuracy which patients would benefit from chemotherapy,” he said.
“Compared to the existing practice of a clinician – just looking at data and then trying to predict what might work or what might not – I think this could be a very powerful tool. Having a tool like this allows doctors to maximize the chances of picking the right type of treatment, in this case chemotherapy, that’s most likely to help this particular patient based on their own personal profile,” Wong said.
Given the “promising results,” the next steps include establishing a larger-scale study in Canada, according to Wong.
'Best possible treatment'
Amy Tai, a post-graduate student at the University of Waterloo’s visual and image processing lab, began working on the technology after she introduced the idea to the lab at the beginning of her course in May of 2022.
“It’s been a whirlwind. It feels a little like one of those dream moments. I did not think that we could get this much advancement in one year,” Tai said.
“We were super excited to see the results, especially seeing how high the accuracy was and that it has potential to really benefit patients. Patients, especially cancer patients, have very limited time and they want to make sure that they have the best possible treatment,” she said.
Tai explained that some types of treatments such as chemotherapy expose patients to radiation.
“If it’s predicted that they won’t recover from that or if a better treatment is out there that is more suited for their type of tumor or breast cancer stage, we would ideally want them to undergo that one instead,” she said.
Now, with hopes to expand its patient cohort to more people, Tai said connecting with a clinical doctor to learn more about successfully employing the technology in the clinical field is also a priority.
Responsible technology for the future
This AI tool wasn’t created to replace doctors but instead work as a complement to improve health care, said Wong.
“AI, in my opinion, is never really meant to replace anyone, especially in this case a doctor with years of experience treating patients,” he said.
“What we see is that AI is always there as a complementary tool or assistant doctor to help them make better decisions, more consistent decisions, as well as decisions in a more rapid fashion.”
According to Wong, doctors these days are becoming more comfortable with AI and incorporating it into health care.
“Now, as doctors learn more about what AI can do and more importantly, what AI cannot do, they’re a lot more comfortable with it and they’re actually very welcoming,” he said.
“We actually have a lot of doctors who want to work closely with us to see this type of technology being adopted for clinical care.”
As AI continues to develop and expand, Wong said the tool was created as part of building responsible technology for the future.
“AI has become a really powerful tool and you could use it for a lot of different purposes – for malicious purposes, for good purposes. I’m just very glad that we’re heading in the direction of really pushing for real world AI for good, especially for health care,” he said.
“One of the key things that we’ve done, especially with the AI that we’re building, is allowing it to explain itself so that a doctor can understand what is the rationale behind some of the recommendations and predictions that it makes. That makes it even more exciting because that’s how you really gain trust with doctors.”
After working in the industry for over a decade, Wong is “excited at the possibilities” of the tool and the impact it could have on Canada’s health care.
“We’re getting to the point where now we’re seeing a powerful enough combination with new medical imaging modalities that it’s really leading to really promising results that could really have a huge benefit for Canadian health care,” he said.