New York-based startup Ezra recently received FDA clearance for an AI tool it plans to use to launch “the world’s first 30-minute full body MRI scan.”
The tool, named Ezra Flash, allows radiologists to acquire MR images at a rate much faster than normal — which results in noisier images that lack sharpness. Ezra Flash’s AI quickly removes the noise and enhances the quality of these images. This reduces the amount of time needed to complete a high-quality scan, which therefore decreases MRI costs, said CEO Emi Gal.
Gal founded Ezra in 2018. The company’s name is the Hebrew word for help, which reflects the startup’s mission to help doctors detect cancer earlier, he said.
“’I’m personally at high risk for cancer and lost my mother to metastatic colon cancer, so I have a very personal motivation to help people find cancer early,” Gal declared.
He pointed out that screening tests exist for only about 50% of cancers — these include cancers of the breast, colon, prostate, uterus, lungs and skin. The other 50%, which include cancers in the pancreas, liver and gallbladder, lack screening procedures. This means that people really only discover they have these cancers once they’re symptomatic — when it’s generally too late.
Ezra’s full body MRI screens for cancer in all the organs that radiologists can’t currently screen for. The scan is designed to look for potential cancer and 500 other diseases across 13 organs, Gal explained.
A Deep-dive Into Specialty Pharma
A specialty drug is a class of prescription medications used to treat complex, chronic or rare medical conditions. Although this classification was originally intended to define the treatment of rare, also termed “orphan” diseases, affecting fewer than 200,000 people in the US, more recently, specialty drugs have emerged as the cornerstone of treatment for chronic and complex diseases such as cancer, autoimmune conditions, diabetes, hepatitis C, and HIV/AIDS.
“Our radiologists read Ezra Flash-powered scans similarly to the way they would read any MRI scans. The AI works in the background — as soon as an MR scan is acquired, it’s sent to the AI for enhancement. Within just a few minutes the AI returns the enhanced images to our routing system, which then passes it onto the radiologist’s reading list,” he said.
The AI tool enables Ezra to create MRI scanning protocols that are “twice as fast,” without compromising on image quality, according to Gal. Ezra will now offer a 30-minute full body scan using Flash that costs $1,350 — an almost 40% reduction in price from the startup’s 60-minute scan — he pointed out.
The company trained its AI tool using its proprietary longitudinal MRI dataset, which comprises hundreds of thousands of MR images taken of cancer patients and healthy subjects.
“We have multiple terabytes of data across millions of MRI images from over 5,000 individuals. Roughly half of our members have come back for at least a second annual scan, and some of them are on their third or fourth,” Gal explained.
This longitudinal dataset allows Ezra to find changes in the body “much earlier” than the startup would be able to by looking at a single data point. The company also continuously gathers downstream data regarding findings from its scans, as well as collects follow-up diagnostic scan and biopsy data when applicable, Gal said.
Ezra isn’t the only startup working to make MRI scans quicker and cheaper, though. Last year, Prenuvo raised $70 million in Series A funds for its MRI machine that promises to scan people about three to four times faster than a regular MRI.
CGToolbox, Getty Images
