3 levels of artificial intelligence detect hundreds of diseases: ‘An end-to-end cancer screening platform’
Meet Ezra, the full-body cancer screener that just might save your life.
Combining MRI imaging technology with artificial intelligence, Ezra scans for possible cancer in the human body in up to 13 organs. It also monitors for hundreds of other conditions, such as brain aneurysms or fatty liver disease.The New York-based company just received FDA clearance to implement another level of AI — called Ezra Flash — that will enhance the imaging results of the scans to enable faster, higher-quality results at a lower cost.
Startup Ezra wins FDA clearance for AI that enhances MRIs
Ezra today announced it received FDA 510(k) clearance for its Ezra Flash AI platform that enhances the quality of MR images.
New York-based Ezra designed Ezra Flash to reduce the time needed to complete a high-quality scan with the hopes of reducing MRI costs. The company plans to use the technology to launch what it touts as the “world’s first 30-minute full body MRI scan.”
“Over 1.9 million people are expected to be diagnosed with cancer in the U.S. in 2023, according to the American Cancer Society. Our mission at Ezra is to detect cancer early for everyone in the world, and I’m really excited about this new AI enabling us to make our scan more affordable,” Founder and CEO Emi Gal said in a news release. “By boosting quality while reducing scan time, we’re decreasing our cost for a full body MRI by 30%, and we’re passing these cost savings to our customers.”
Ezra’s technology leverages AI across all three key components of the cancer screening process, which includes imaging, analysis and reporting. Ezra Flash AI enables Ezra to increase MR image quality, Ezra Prostate AI assists radiologists in the analysis of MR images of the prostate and Ezra Reporter AI creates an easily digestible translation of radiology reports that assist medical professionals in communicating screening results to people.
Ezra Flash has so far received FDA clearance for use in the brain.
To test the technology, the company created a fast MRI protocol that produces noisy images. The system was able to enhance the quality of the images. Ezra also trained the AI using its longitudinal MRI dataset, comprising hundreds of thousands of MR images in patients and healthy subjects.
Ezra also trained the AI to assess which elements of the MRI scan are essential to creating a complete and accurate image. This allowed Ezra to enhance image quality in high-speed MRI scans that are at the limits of the current standard of care, according to the company. It used a multi-step validation process in which a panel of five radiologists analyzed the performance of the AI both qualitatively and quantitatively.
“The FDA clearance of Ezra Flash is an important landmark – the beginning of a sea change in how medical imaging is used,” said Dr. Daniel Sodickson, chief of innovation and the director of the Center for Advanced Imaging Innovation and Research in the Department of Radiology at NYU, who also worked with Ezra’s team to develop the Ezra Flash. “Progressive increases in imaging speed over time have already resulted in myriad benefits to patients and physicians. Until now, though, imaging has principally been used for the diagnosis and characterization of disease once other signs and symptoms have already developed. Ezra, on the other hand, is using MRI as a tool for early detection of cancer prior to the development of symptoms – a safety net of proactive monitoring that has previously only been available to patients with certain well-established risk factors. Ezra Flash will increase the accessibility of early-warning MRI, and Ezra’s dataset of repeated scans over time will help it to prevent false positives and ensure that the warnings it provides are appropriate and actionable.”
The company said that its full Boyd MRI, which previously took one hour, is now available as a 30-minute MRI scan. Ezra’s ultimate goal is to reduce the time to 15 minutes.
_
With reports from FoxNews and +MassDevice
Gary P Hernal started college at UP Diliman and received his BA in Economics from San Sebastian College, Manila, and Masters in Information Systems Management from Keller Graduate School of Management of DeVry University in Oak Brook, IL. He has 25 years of copy editing and management experience at Thomson West, a subsidiary of Thomson Reuters.
