Israeli med-tech startup earns FDA approval for AI breast cancer solution
The FDA approval for HealthMammo marks the companies first oncology solution to earn the coveted "go-ahead" from the US-based federal agency.
By ZACHARY KEYSERA radiologist examines a brain scan. (Illustrative)(photo credit: NanoxAI)
Israeli medical imaging technology start-up Zebra Medical Vision announced on Monday that it received US Food and Drug Administration approval for its mammography solution HealthMammo.HealthMammo, which had already earned the CE certification, is the company's sixth solution to earn FDA approval - six solutions spread across three modalities (CT, x-ray and mammography) – the first AI start-up to do so.The FDA approval for HealthMammo marks the company's first oncology solution to earn the coveted "go-ahead" from the US-based federal agency.The HealthMammo solution itself prioritizes and identifies "suspicious" mammograms for radiologists to focus their attention on instead of using the standard "first-in first-out" method to diagnose a patient, which in turn recognizes problematic readings ahead of time while alerting the radiologist to the issue - allowing for early detection and intervention following a positive breast cancer diagnosis.“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 CEO of Zebra Medical Vision Ohad Arazi. “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-affected reality we are all facing. We’re proud of the achievements we’ve made in the past few months, providing US healthcare with a growing portfolio of automatic solutions to enhance patient care, especially during these times.”Breast cancer is the most common form of cancer and the second-leading cause of cancer-related death among women in the United States, according to the National Cancer Institute. Approximately 2.1 million women worldwide are diagnosed each year with breast cancer.However, radiologists fail to notice 20% of breast cancers in mammograms, according to the American Cancer Society, and nearly half of all women who undergo mammography screenings over a 10-year period receive false positive results.Zebra Medical's HealthMammo attempts to combat this issue with their automatic AI tool, which has the ability to categorize mammograms as "suspicious" or "not suspicious" before reaching the eyes of the radiologist. Specifically, every x-ray performed is automatically uploaded and linked to Zebra Medical's imaging analytics platform, where they are processed and anatomized for suspected breast lesions.The early readings are then returned to the radiologist, through the work list or by notifying the user directly through an application dedicated to HealthMammo and its platform.
Amid the coronavirus pandemic, many annual breast cancer screening were either postponed or cancelled, resulting in a 94% drop in mammography imaging volumes during the onset of the outbreak.Within this, health care providers and patients are running the risk of foregoing the early detection benefit of annual mammography exams, which could result in the spread of an undetected cancer. At the moment, nearly 100,000 screens are being backlogged each day in the US to a later date. According to the FDA Mammography Quality Standards program, approximately 40 million mammograms are performed in the states each year.Zebra Medical is uniquely positioned to assist health care providers in minimizing the COVID-19-induced care gaps using their HealthMammo AI solution - rapidly identifying and recognizing suspected lesions, leading to an accelerated patient turnover rate.“As restrictions are lifted from the COVID-19 crisis, the backlog of mammograms has increased,” said Dr. Michael Fishman, Breast Imaging Section Chief at Boston Medical Center. “Zebra Medical Vision’s HealthMammo may help radiologists deal with the screening management strategy of the post COVID backlog and triaging.”Expanding on this, earlier this year a Google artificial intelligence system proved as good as expert radiologists at detecting which women had breast cancer based on screening mammograms and showed promise at reducing errors, researchers in the United States and Britain reported.The study, published in the journal Nature, is the latest to show that artificial intelligence (AI) has the potential to improve the accuracy of screening for breast cancer, which affects one in eight women globally.The findings of the study, developed with Alphabet Inc’s (GOOGL.O) DeepMind AI unit, which merged with Google Health in September, represented a major advance in the potential for the early detection of breast cancer, according to Mozziyar Etemadi, one of its co-authors from Northwestern Medicine in Chicago.The team, which included researchers at Imperial College London and Britain’s National Health Service, trained the system to identify breast cancers in tens of thousands of mammograms.They then compared the system’s performance with the actual results from a set of 25,856 mammograms in the United Kingdom and 3,097 from the United States.The study showed the AI system could identify cancers with a similar degree of accuracy to expert radiologists, while reducing the number of false positive results by 5.7% in the U.S.-based group and by 1.2% in the British-based group.It also cut the number of false negatives, where tests are wrongly classified as normal, by 9.4% in the U.S. group, and 2.7% in the British group.These differences reflect the ways in which mammograms are read. In the United States, only one radiologist reads the results and the tests are done every one to two years. In Britain, the tests are done every three years, and each is read by two radiologists. When they disagree, a third is consulted.Reuters contributed to this report.
