Novel Artificial Intelligence Technology Shows Promising Results for Earlier and More Accurate Breast Cancer Detection

Kathy Schilling, M.D.

 

Data from the Centers for Disease Control and Prevention highlight that Breast Cancer is second most common form of cancer among women in the U.S. with approximately 240,000 new breast cancer diagnoses each year. Although breast cancer incidence is on the rise, its associated mortality has steadily declined over the last decade due to early detection via screening, and advancements in therapeutic options.

Mammograms remain the standard diagnostic tool for detection of breast cancer. Innovators in the field are now exploring assistive machine learning and articial intelligence (A.I.) to help healthcare providers assess mammograms and detect breast cancers earlier and more efficiently. Dr. Kathy Schilling, MD., Medical Director, Lynn Women’s Health & Wellness Institute, is one of the early adopters of this technology and continues to pave the way for improvements in the field. A.I. technology was first implemented at the Lynn Cancer Institute in 2020 during the COVID-19 pandemic. Dr. Schilling conducted a retrospective evaluation of the institute’s results since adopting this technology, presenting her study findings at the 2023 European Congress of Radiology in Vienna on March 3rd , 2023. Dr. Schilling found that cancer detection rates rose from 5.77 per 1000 women to 7.8 per 1000 women screened. Furthermore, each of the nine dedicated breast radiologists at the center improved in accuracy with a pooled increase of 23%. Dr. Schilling expressed her amazement at the impact A.I. had on her practice. ‘That’s huge, I was so shocked.” said Dr. Schilling. “If you had found 100 cancers before using A.I., we found 123 after using A.I. The increase in number of cancers detected occurred without having an increase in false positives or recalls. We became more accurate in those we recalled."

A.I. systems are trained for specificity and sensitivity in identifying cancer in a mammogram. This is done using hundreds and thousands of images from previous mammograms. Once ready for use, the system can scan the images from a mammogram and notify the radiologist of possible cancer spots. Acting like a second set of eyes. Each image is still examined by the radiologist who utilizes their expertise and a patient’s risk factors to determine if further evaluation is needed. The A.I. system not only reduces the burden on radiologists, who can often get fatigued looking at hundreds of images in a single shift, it also makes it easier to detect possible signs of cancer that the human eye might miss. “This is signicant” says Dr. Schilling. “The types of cancers we are currently finding are smaller and of lower stage, reducing the need for advanced treatments.”

Lynn Cancer Institute’s A.I. assistive technology system has led to an increase in cancer detection rate and helped many patients to avoid aggressive therapies. Beyond diagnostics, A.I. is also being studied and adapted for patient-centered therapies. Researchers in Florida are looking into how AI can assist in creating customized combinations of chemotherapy and immunotherapy to combat aggressive breast cancer. Patient safety and care are the foremost concern within the Baptist Health system. Providers can rest assured that their patients will receive the safest, most innovative, and state-of-the-art care at Lynn Cancer Institute.