Zebra Medical Vision has announced its latest Food and Drug Administration 510(k) clearance for HealthMammo, an artificial intelligence tool that helps radiologists identify suspicious mammograms.
The AI tool works by automatically sending mammograms to the analytic platform to be searched for breast lesions. HealthMammo then marks each mammogram as either “suspicious” or “not suspicious” for the radiologist to inspect further.
The tool can help radiologists speed up the diagnosis process and reduce missed cases, according to Zebra Medical Vision.
WHY THIS MATTERS
In 2020 there will be an estimated 276,480 new cases of invasive breast cancer diagnosed in women, and over 42,000 deaths caused by breast cancer in women, according to the American Cancer Society's "Cancer Facts and Figures 2020" report.
Mammograms offer a way to detect breast cancer at an early stage. However, they aren’t always perfect.
“It can miss cancer (false negative) or appear abnormal in the absence of cancer (false positive); about 12% of women who are screened have an abnormal mammogram, but only 5% of women with an abnormal mammogram have cancer,” the American Cancer Society said in its report.
There were approximately 40 million mammograms performed in 2019, according to the FDA Mammography Quality Standards Act and Program (MQSA).
However, due to the COVID-19 pandemic, many mammogram screenings were postponed. According to a study in the Journal of the American College of Radiology, there was a 94% decrease in mammograms during the pandemic.
Now, as some facilities begin performing nonemergency services, radiologists are facing a backlog of screenings.
THE LARGER TREND
Zebra Medical Vision has now received six FDA 510(k) clearances for its medical imaging technologies.
One of these came last year for HealthPNX, which can read medical imaging to identify potential cases of pneumothorax – a build-up of gas between a lung and the chest wall.
The company also received clearance for its algorithm that helps physicians quantify a patient’s coronary artery calcification. The Coronary Calcium Scoring algorithm automatically calculates a calcification rating equivalent to those derived using the Agatston Coronary Artery Calcium Scoring method.
Google is also making strides in using AI to detect breast cancer. In a study, the system was able to reduce the number of false positives and false negatives in breast cancer detection.
ON THE RECORD
“Our work is twofold: supporting the medical team’s overload and ensuring the well-being of patients, by supporting early detection and reducing the anxiety surrounding uncertainty,” said Ohad Arazi, CEO of Zebra Medical Vision, in a statement. “The fact that during initial testings we were able to identify two cases that were missed, and to have these women be recalled and diagnosed with cancer, shows the vast impact and potential contribution of AI in Oncology. With this fully commercial and regulated product, we aim to provide even more value and help patients and providers navigate the new COVID effected reality we are all facing. We’re proud of the achievements we’ve made in the past few months, providing U.S. healthcare with a growing portfolio of automatic solutions to enhance patient care, especially during these times.”
