Israel’s Zebra gets FDA nod for AI-based software that helps spot breast cancer

‘HealthMammo’ solution aims to support radiologists in their tumor diagnoses by identifying and prioritizing suspicious mammograms

Shoshanna Solomon was The Times of Israel's Startups and Business reporter

An illustrative image of a mammogram (Courtesy)
An illustrative image of a mammogram (Courtesy)

Zebra Medical Vision, a kibbutz-based startup that uses artificial intelligence technology to help read medical scans, said it has received US Food and Drug Administration clearance for use of its algorithm to read mammograms.

The FDA nod follows the European CE approval for its “HealthMammo” mammography solution, which supports radiologists in their search for breast tumors by prioritizing and identifying suspicious mammograms.

The suspicious mammograms are identified faster and read earlier than the current standard of care, Zebra said in a statement on Monday.

This is Zebra Medical Vision’s first oncology solution to get FDA clearance, the company said. The FDA clearance is only for prioritization of cases, while in Europe the approval allows the software to be used as an additional safety net for radiologists, as a second reader of the scans.

Zebra Medical also said it is the first AI startup to receive six FDA clearances for AI-based technology across three imaging platforms – CTs, x-rays and mammography. This provides coverage for roughly 80 percent of the total volume of imaging, the statement said.

Zebra Medical has received FDA nod for its mammography AI-based solution (Courtesy)

About one in eight women in the US — some 12% — will develop invasive breast cancer and in 2020 an estimated 276,480 new cases of invasive breast cancer are expected to be diagnosed in women in the US, along with 48,530 new cases of non-invasive (localized) breast cancer, according to Breastcancer.org. About 42,170 women in the US are expected to die in 2020 from breast cancer, though the overall death rate has declined over the years, mainly due to treatment advances and earlier detection through screening.

According to the FDA’s Mammography Quality Standards program (MQSA), some 40 million mammograms are performed in the US every year. However, with the outbreak of the coronavirus, annual mammography tests during lockdown were postponed or canceled.

As a result, patients waiting to be tested were running the risk of missing the early detection component of annual screening that could result in an undetected cancer that keeps growing, the statement said.

Because it helps with detection, Zebra Medical Vision’s HealthMammo product is also helping healthcare providers better handle the backlog, the statement said.

“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 (BMC), Massachusetts. “Zebra Medical Vision’s HealthMammo may help radiologists deal with the screening management strategy of the post COVID backlog and triaging.”

“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,” says Ohad Arazi, CEO of Zebra Medical Vision. “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.”

Founded in 2014 by Eyal Gura, Eyal Toledano and Benjamin Elad, the Shefayim, Israel-based company has raised some $57 million in funding to date. Investors include US fund Khoshla Ventures, US health fund Intermountain Investment Fund, Israel’s OurCrowd, Aurum, venture firm aMoon, Nvidia, J&J, Dolby ventures, and US entrepreneur Marc Benioff.

The company’s software is already installed in hospitals in Australia, India, Europe, the US, and Latin America. Last year the firm got grants from the Israel Innovation Authority to deploy its technology at health providers.

Most Popular
read more: