Artificial intelligence is reportedly advancing work in the fight against cancer.
Dr. Laurie Margolies, chief of breast imaging at Mount Sinai Health System, told CBS News this week the technology is being used to detect breast cancer.
“I think artificial intelligence has the ability to make us be even better physicians than we might otherwise be, by teaching us what are the risk factors, what makes a certain pattern of breast tissue be at high risk,” she explained, noting that AI can see things the naked eye might miss on a mammogram.
“It’s the AI that does the first pass. It puts a mammogram into one of three buckets. One bucket is the computer thinks has a very low chance that there’s a cancer on here, and then there’s a middle range where it says there may be a cancer here, look carefully. And then there’s a high range that says there’s an elevated risk of cancer on these mammograms. Look really carefully at the spots we’ve marked,” Margolies said.
The doctors look at the patient’s history and old mammograms with artificial intelligence as an integrated piece of information.
“AI doesn’t get tired. It doesn’t get distracted. There also is a type of error in radiology that we call ‘satisfaction of search,’ whereby if you find a cancer on one side, you sometimes are less likely to find a second cancer in the other breast or somewhere else in the same breath because you think, ‘Oh, I’m done. I found the cancer. I’m done,'” she added.
Koios DS Breast — an AI-powered, ultrasound-reading software platform that can spot cancer in two seconds — was gifted to the Department of Radiology.
Mount Sinai says the software ensures that physicians have advanced technology to aid them in making rapid and accurate diagnoses and in reducing biopsies.
Using artificial intelligence and machine learning algorithms, Koios DS Breast compares ultrasounds to an archive of hundreds of thousands of images from patients from around the world with confirmed benign or malignant diagnoses.
Such capability is key for women with dense breasts, which can make it harder to spot cancers.
Nearly 50% of women over the age of 40 have dense breast tissue, and mammograms miss more than half of cancers present in those individuals.
These women often require an ultrasound to capture images of areas of the breast that could be harder to see.
However, doctors say it is still crucial to keep up with annual screenings and mammograms.
Breast cancer is the second most common cancer among women in the United States.
Researchers are also using AI models to detect colorectal cancer, including a model with an average of 90% accuracy reported by the University of Minnesota.
In the U.K., AI advances are cutting wait times for radiotherapy treatments at a Cambridge hospital.
Microsoft said the system named “OSAIRIS” allows planning treatments more than twice as fast as if specialists were working alone.