How this AI mammogram could help detect breast cancer years in advance – National

A new AI tool for mammograms is expected to help doctors and healthcare providers detect breast cancers in patients more quickly and effectively.

Health Canada approved ProFound Risk technology earlier this summer amid a health care crisis that has seen hospitals, specialists and providers across the country pushed to the breaking point and scrambling to meet demand in recent years.

The device uses artificial intelligence (AI) to provide patients with personalized risk estimates, even when a current mammogram comes back clear. It was founded by the American technology company iCAD, which specializes in breast cancer detection and treatment solutions.

iCAD founder and CEO Dana Brown says the device can dramatically change a patient’s care pathway once breast cancer risk is detected.

“The peace of mind that this technology can bring to the patient and the provider, allowing them to be on track for the next couple of years and be very vigilant about this, I think is just amazing ” Brown told PKBNEWS.

Brown explains that the device detects not only the risk of cancer, but also where it may appear specifically in the body. Both of these details are important so providers can better keep tabs on a patient and provide advice on lifestyle risk mitigation factors, such as diet and exercise.

Brown says it’s also “empowering” for individuals to be able to take control of their own health.

“Cancer is often something you feel like you have no control over,” she said.

Breast cancer accounts for about 25 percent of new cancer cases and 13 percent of cancer deaths among Canadian women, according to the Government of Canada website.

One in eight women are expected to develop breast cancer in their lifetime, and one in 33 will die from it.

“We are pleased that Canadian regulators see the urgent need and are working with us to get this technology approved for use, because I believe it can make a huge difference in saving more lives, and that is something Canadian women really need. » said Brown.

The new mammogram has a higher area under the curve (AUC) than other risk a*sessment devices, a measure used to show the accuracy of these technologies.

1.0 is considered a perfect score. While other devices hover around the 0.60 mark, ProFound Risk has a score of 0.80.

Canadians should have access to ProFound Risk mammography within one to two years.

The device, available for 2D and 3D mammography, has also been cleared for use in the European Union. The device is offered in the United States, but currently only for investigational purposes.

Dr. Mark Traill is one of the radiologists participating in the experimental study. He has been using the device for five years while overseeing the development of artificial intelligence in the Department of Radiology at University of Michigan Health-West.

Traill has been in the industry for 35 years, but he says it wasn’t until he saw the iCAD device in action that he understood the true value of AI in radiology.

“At that time, what I thought was the outcome came (to reality): AI algorithms are extremely capable of detecting cancer on a mammogram,” Traill told PKBNEWS.

“The stress I feel during the day, looking at literally thousands of photos, is much less now because I know I have an algorithm that is looking at the images with me and will actually capture over 90% of the images . the cancers I’m going to see that day,” he said.

Traill says its net performance in cancer detection has increased since using AI-based mammography.

“For me, being able to see a change in risk category is like, ‘Hey, something’s happening in this breast that might indicate cancer is on the horizon,'” he said. -he declares.

According to Traill, cancer goes unnoticed on a mammogram 10 to 30 percent of the time when it is read only by humans.

One experience particularly stood out to Traill, he said.

He says a woman came to him one day complaining of being full, but mentioned that her child had repeatedly slammed his head on her chest. Traill did a preventative mammogram that came back clear, but her risk score was incredibly high.

Traill told her to come back for another mammogram in three months. When he returned, not only was the risk score higher, but there were very small cancer findings.

“If I didn’t have the risk score available, I would have considered this a trauma with swelling and bruising,” Traill said.

“I didn’t in this case, so we were able to move forward…and get him treatment before things went too far.”

This system is not the first risk model available, but it is the only one not to base its results on genetic history. Traill says these latest models don’t address the vast majority of at-risk women.

According to the U.S. Centers for Disease Control and Prevention (CDC), only five to ten percent of breast cancers are hereditary.

Traill says it’s also beneficial that the device doesn’t rely on human intervention – where patients have to remember their family history – because the information isn’t always accurate. Instead, ProFound Risk’s AI uses an algorithm directly integrated into the mammogram to a**lyze risk.

Previous models also only provided an a*sessment of lifetime breast cancer risk, but knowing a person’s short-term risk allows them to better plan and make lifestyle changes accordingly.

Traill says it has been difficult to get more radiologists to use AI in their practice.

“There is sometimes a real prejudice among radiologists against this. You have to develop trust with the algorithm like in any type of relationship, and that takes time,” says Traill.

“But from what I’ve experienced over the years, it’s essential. I would never practice without it,” he says.

Traill also says it’s important for radiologists and patients to realize that AI does not replace doctors, but rather acts as a “complementary function.”

“Humans just can’t do it (alone), that’s the whole point of studies,” he says.

AI has made great strides in the detection and treatment of breast cancer in recent years.

A recent preliminary study on The Lancet Oncology found that AI is a safe and effective tool for breast cancer detection and improving diagnostic accuracy.

The AI ​​used in the study was able to cut the screen reading workload of medical mammograms in half, by 44.3%.

A study published in January 2020 by the journal Nature also found that AI can predict breast cancer more accurately than humans.

AI reduced false positives by 5.7 percent in the US and 1.2 percent in the UK. It also reduced false negatives by 9.4 percent in the US and 2.7 percent in the UK, meaning it detected cancers that humans had missed.

Alexander Wong, professor and Canada Research Chair in artificial intelligence and medical imaging at the University of Waterloo, is part of a Waterloo, Ont., lab that works to help patients get appropriate treatment through to new technology based on AI.

“It’s actually very exciting,” Wong said of ProFound Risk.

“AI helps a lot, but that said, there’s still a lot of information that’s not being leveraged, so that’s where the clinician really comes in to use these technologies as a second opinion or as additional information for help treat patients better,” he told PKBNEWS last week.

Wong also says there is intangible information useful for a*sessing risks that only doctors may encounter when treating a patient.

“So that’s where the combination of the clinician…and the AI ​​can really provide a benefit,” he said.

Traill says he would recommend patients avoid mammography centers that don’t use some sort of AI.

“I think it’s extremely important that women know that this is an option available to them.”

Traill says he is very excited about the future.

“I don’t think it’s not the future of diagnostic radiology.”