Robotic arms have now helped patients with missing limbs. Robots are becoming a part of the surgery room. In the world of breast cancer, artificial intelligence (AI) is also becoming more prevalent.

When it comes to diagnosing breast cancer, new research shows that artificial intelligence machinery may be able to help doctors identify breast lesions that could turn cancerous, according to HealthDay News.

These high-risk breast lesions are usually found when women undergo a biopsy. The problem these type of abnormal cells pose for healthcare providers is that they aren’t cancerous but also aren’t healthy tissue.

While some of these lesions develop into tumors, the majority don’t. So how can doctors and patients know whether to undergo any treatment or surgery?

Often, oncologists decide to move forward to remove these lesions, explained study author Dr. Manisha Bahl.

“The decision about whether or not to proceed to surgery is challenging, and the tendency is to aggressively treat these lesions [and remove them],” said Dr. Bahl.

“We felt like there must be a better way to risk-stratify these lesions,” continued Bahl, Director of the Breast Imaging Fellowship program at Massachusetts General Hospital.

The researchers worked with computer scientists from the Massachusetts Institute of Technology and created a machine-learning system that can diagnose which type of lesions need to removed immediately versus others that can be tracked over time.

The way this machine works is by learning from prior experiences and enhancing the response over time. The machine was provided with information about the type of lesion, the biopsy report, and patient age.

The researchers used patient data from more than 1,000 women with a high-risk lesion.

Within this group of women, 4 percent didn’t have surgery to remove their lesions and needed a two-year follow-up for imaging and diagnostics. The rest – around 96 percent – needed to have their lesions cut out through surgery.

The next plan is to incorporate mammography results and pathology slides into the AI machinery.

“The model picked up on text in the biopsy report — the words severely and severely atypical conferred a higher risk of upgrade to cancer,” Bahl said. “Machine learning is a tool that we can use to improve patient care — whether that means reducing unnecessary surgeries or being able to provide more information to patients so they can make more informed decisions.”

As many as 335 high-risk lesions were found in this study and the number of unneeded surgeries was reduced by 30 percent, reports BBC News. With more than 40,000 women dying from breast cancer in the United States every year, early diagnosis is key.

However, overtreatment of abnormal breast cells that may not become cancerous is rather harmful to patients. This new technological advancement helps reduce  unnecessary treatment.

“Women should know that there is a new type of machine learning that’s helped us identify high-risk lesions at low risk of cancer. And, we may soon have more information for them when they’re faced with the decision of whether to have surgery to excise these high-risk lesions or not,” Dr. Bonnie Litvack, medical director of the women’s imaging center at Northern Westchester Hospital, told HealthDay News.

“Artificial intelligence is an exciting field that will help us give women more data and help with shared decision-making.”

This type of advancement is huge for women’s health especially in terms of decreasing the rate of unnecessary breast cancer treatment. Diagnostics are changing and improving for women.

During Breast Cancer Awareness Month, don’t forget to get your yearly mammogram if you are 40 years old or older. October 20 is National Mammography Day so be sure to make an appointment with your doctor.

Early diagnosis may save your life and artificial intelligence may save you from needless surgery as well.

Scientific Breakthroughs Start Here!

We believe there's a better way-- and we are going to find it! Join our mailing list to receive the latest news and updates from our team.

You have Successfully Subscribed!