Skip to Content

AI-supported mammogram screening increases breast cancer detection by 20%, study finds

Artificial intelligence found more breast cancers than doctors with years of training and experience and cut doctors’ mammogram reading workload almost in half, a new early-stage study found.
CNN
Artificial intelligence found more breast cancers than doctors with years of training and experience and cut doctors’ mammogram reading workload almost in half, a new early-stage study found.

By Jen Christensen, CNN

(CNN) — Artificial intelligence found more breast cancers than doctors with years of training and experience and cut doctors’ mammogram reading workload almost in half, a new early-stage study found.

This doesn’t mean your hospital will let a computer determine whether you have cancer any time soon. There’s still a lot more research to do, but the study, published Tuesday in the journal The Lancet Oncology, shows that AI is safe to use in breast cancer detection and could make doctors even more effective at finding cancer than they are now.

Other studies have shown that AI can be useful at predicting breast cancer risk, but they use models or have been focused on retrospective data. The new research is thought to be the first randomized control trial to compare AI-assisted breast cancer detection with detection done by well-trained humans alone.

The researchers looked at scans from more than 80,000 women in Sweden who underwent a mammogram between April 2021 and July 2022. Half of the women were assigned to a group in which AI read the mammogram before it was analyzed by a radiologist. The other group’s mammograms were read by two radiologists without the use of AI. All the radiologists in the study were considered highly experienced.

The group whose scans were read by a radiologist along with AI had 20% more cancers detected than the group whose mammograms were read by two radiologists without the additional technical assistance.

Overall, the screenings supported by AI resulted in a cancer detection rate of 6 per 1,000 screened women, compared with 5 per 1,000 with the standard approach.

But the researchers say they didn’t get the sense that the AI was too sensitive. It did not increase the number of false positives, when a mammogram is diagnosed as abnormal even though no cancer is present.

The group that used the AI had an additional benefit: a reduced reading workload of 44%. The trial didn’t measure the specific amount of time saved by AI, but the researchers calculated that if radiologists read about 50 mammograms an hour, it would have taken a single radiologist four to six months less to read about 40,000 screening exams with the help of AI than it would take two radiologists alone.

“The greatest potential of AI right now is that it could allow radiologists to be less burdened by the excessive amount of reading,” said study co-author Dr. Kristina Lång, an associate professor of radiology diagnostics from Lund University in Sweden.

In Europe, guidelines recommend that two radiologists screen a mammogram. The US does not have the same standard, so the workload issue might be different in different countries.

However, Europe and the US both have a shortage of radiologists, according to the Radiological Society of North America. If further research shows that this technology really works, it may help ease some of those staffing problems as well as making radiologists even better at their jobs.

The demand for radiologists is expected to increase as the global population ages and requires even more imaging.

Many radiologists see the possibilities as welcome news rather than as threats to their job security.

“With mammography, our goal is to detect breast cancer as early as possible, to give each patient the best prognosis, so anything that will make us more accurate is a wonderful thing,” said Dr. Stamatia Destounis, a radiologist specializing in breast imaging at Elizabeth Wende Breast Care in Rochester, New York, who was not involved with this study.

Any kind of technology that could help with breast screening could make a big difference. Breast cancer incidence has been increasing by 0.5% per year, according to the American Cancer Society, although there hasn’t been a corresponding increase in the number of deaths. While breast cancer is still the No. 2 killer of women who die from cancer, behind only lung cancer, more women have survived than decades ago, largely because of effective screening. When breast cancer is caught early, a person’s chance of survival increases significantly.

But mammography is not perfect, experts say. It’s a highly subjective skill. Overall, screening mammograms miss about 20% of breast cancers, according to the National Cancer Institute.

Detecting the complex pattern that is breast cancer is extremely difficult, even with years of specialized training. Essentially, a radiologist must spot a tumor that is white in the midst of a white background. AI may one day be able to help with that pattern detection, but a radiologist’s job is a lot more than pattern recognition, said Dr. Laura Heacock, a breast radiologist at NYU Langone Perlmutter Cancer Center who wasn’t involved with the new study.

“If you spend a day with a radiologist, you’ll see that how an AI looks at screening a mammogram is really just a faction of how radiologists practices medicine, even in breast imaging,” she said. “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.”

Heacock said that with more research, her colleagues may be using AI like this in the future. Radiologists already use a comparatively crude kind of computer image analysis called CAD, developed in the 1990s, that can recognize patterns in mammograms.

“AI algorithms are more flexible and trained with much more cutting-edge deep neural networks that allow advanced feature recognition and application, and they are cross-trained on all the commercial models, and the research models are externally validated,” Heacock said. An AI model looks at an image differently than a human eye would, is trained on different material and can give different predictions based on what it can and cannot see, she said.

Although AI is still an emerging technology, artificial intelligence has started to capture the imagination of scientists. It’s being used in drug discovery and development, and it’s helped doctors communicate better with patients. AI even passed the practice exam that doctors use to get their licenses, so it’s being used to help write better test questions.

Several AI programs are also under development to assist doctors in cancer detection. One program at MIT has been created to detect high risk of future breast cancer based on present mammograms, something doctors aren’t able to do right now.

Many of these programs show real promise, Heacock said.

“I think of AI as more validation. It doesn’t sleep. AI doesn’t get tired. The AI doesn’t get fatigued, and it’s been shown that it can tremendously augment our less-experienced doctors, like if you’re seeing something rare, the AI might be more likely to flag it if you haven’t seen It before,” she said.

She will also welcome the day when the research is further along.

“You wouldn’t turn down a stethoscope if it’s offered to you, you know?” she added.

The-CNN-Wire
™ & © 2023 Cable News Network, Inc., a Warner Bros. Discovery Company. All rights reserved.

Article Topic Follows: Health

Jump to comments ↓

Author Profile Photo

CNN Newsource

BE PART OF THE CONVERSATION

KIFI Local News 8 is committed to providing a forum for civil and constructive conversation.

Please keep your comments respectful and relevant. You can review our Community Guidelines by clicking here

If you would like to share a story idea, please submit it here.

Skip to content