Artificial intelligence can detect breast cancer four years before it develops in patients

Artificial intelligence (AI) is here to stay. Not only can you power creative and entertainment tools, but in fields like productivity, work, science, and medicine you can achieve feats that previously seemed unattainable with other tools. Now, it can detect breast cancer four years before it develops in patients.

Hungarian doctors are using an artificial intelligence model to quickly detect the disease early, according to a report from The New York Times.

Inside a dark room in the Bács-Kiskun county hospital on the outskirts of Budapest, the doctor. Éva Ambrózay, a radiologist with more than two decades of experience, looked at a computer monitor displaying a patient’s mammogram.

Two radiologists had previously said that the x-ray did not show any signs that the patient had breast cancer. But Ambrózay was taking a close look at several areas of the scan circled in red, which the artificial intelligence software had flagged as potentially cancerous.

“This is something,” he said. He soon ordered the woman to be called in for a biopsy.

How does the AI ​​work?

The AI, called Computer Aided Detection, identifies spots on mammograms for doctors to closely inspect.

A partner study from the Massachusetts Institute of Technology (MIT) found that the technology could identify changes between mammograms and detect spots that were at risk of becoming cancer. Spots identified in patients turned into breast cancer years later.

Larry Norton, medical director of Lauder Breast Cancer at Memorial Sloan Kettering Cancer Center, told CNN: “AI is a tool that radiologists can use to create better treatment plans. After identifying trouble spots, radiologists can determine what additional tests may be appropriate for patients to lower their chances of developing cancer.”


The widespread use of cancer detection technology still faces many obstacles, doctors and AI developers told The New York Times. Additional clinical trials are needed before the systems can be more widely adopted as a second or third automated breast cancer screen reader, beyond the limited number of places now using the technology.

The tool must also demonstrate that it can produce accurate results in women of all ages, ethnicities and body types and must demonstrate that it can recognize more complex forms of breast cancer and reduce false positives that are not cancerous, the radiologists noted.