zebra medical imaging

2021/05/21

ZebraMedicalVision has 7 FDA approved solutions heres how they did it. For example, 50% of patients who fracture a hip die of complications in the next 10 years. Radiology images in many different modalities (X-Ray, CT, MRI, Mammography, PET, and Nuclear Medicine); Clinical outcomes (meaning how patients fared after discharge, possibly years later). This error is much less problematic the doctor will cross-check the scan because the system flagged it, and will discover it was a false alarm. The hospital only has to install an agent in their local system once, and this agent deals with privacy, security, and anonymity, as well as providing a local user interface. In the past, a researcher might take the time to design the perfect experiment, implement it, and then assess whether their approach solves the problem. Unfortunately, the buildup of calcifications in coronary arteries is often only diagnosed after a heart attack or similar cardiac event. The deal consists of $21m of Nanox shares and $9m in cash. Eyal calls this unique interdisciplinary team the band: different talents, same clinical mission. Thats why, for the first two years, Zebra Medical Vision hardly did any machine learning at all. With all this infrastructure and this team in place, Zebra Medical Vision can move at a dazzling pace. Today this is one of Zebra Medical Visions leading solutions, and its proven to be effective on a large part of the population. Many research studies have shown that machine learning models can perform as well as trained doctors on a range of tasks especially in radiology and can even find patterns a human doctor would miss. Many companies talk about feedback loops where the model improves via user feedback. 2022 by Mercom Capital Group, LLC. In university studies, the problem youre working on is often fixed. This mindset pushed them on through myriad challenges. Product definition and system requirements. Now lets look at two examples of diagnostic solutions Eyal and his team developed, and find out what they learned along the way. 2022 MJH Life Sciences and Diagnostic Imaging. In addition, the transaction will enable both firms to create the next generation of AI-enabled hardware and software devices. Now we covered partnerships, data, integration, and the technical backbone. Not only were they small, but they also didnt represent the variety of patient cases clinicians see in hospitals on a day-to-day basis. At first sight this might seem very useful. Can deep learning extract new insights from basic H&E stains? This means hospitals dont need to do anything to receive updates. Our plan is to double down on Zebra-Meds AI and cloud platform effort, strengthen the industry-leading team even further, and solidify Zebra-Meds leadership position in the radiology space. Zebra Medical Vision has always operated to expand the use of AI in medical imaging to improve health outcomes for patients worldwide, said Zohar Elhanani, CEO of Zebra Medical Vision. (Credit: Business Wire). Due to this change if you are seeing this message for the first time please make sure you reset your password using the Forgot your password Link. Oops! Plus a lot of the software is quite old. So far, this is just a proof-of-concept youve demonstrated that an algorithm can process radiology images and differentiate between two clearly described groups of patients. And therefore, this would not help all the other patients who are at risk but have no symptoms yet. But overall, the false positive rate still determines whether the system saves the doctor time. A total of 136 digital health companies were acquired in the first half of 2021, Total Corporate Funding for Solar Sector Totaled $12 Billion in 1H 2022, Mirova Acquires SunFunder to Expand Clean Energy Investments, Zerigo Health Raises $43 Million for Connected Skin Therapy Device, Oak Street Health Acquires Telehealth Company RubiconMD for $130 Million, Workit Health Raises $118 Million for Addiction Care Platform, Modern Age Raises $27 Million for Digital Aging Wellness Platform, Bardavon Health Innovations Raises $90 Million in Funding, Insurights Raises $22 Million in Seed Funding, SPR Therapeutics Raises $37 Million for Wearable Neurostimulation Device, GoCheck Raises $10 Million for Vision Screening App, Top Doctors Raises $13 Million for Healthcare Booking Platform, Insiteflow Raises $2.3 Million for EHR Workflow Interoperability Platform. That's a fantasy. They are all necessary. Models trained on datasets that represent the population; Seamless integration into clinical workflows; A technology platform to connect research and hospitals. The problem with this approach: This particular CT scan protocol is something you would only run on a patient who is already known to have a risk of a heart attack. The more practical approach: Zebra Medical Vision realized that patients get CT scans for many other diseases. It should only require the exact data in the exact format thats already produced in the hospitals normal diagnostic workflow. But it wouldnt be useful in a hospital. One reason is Zebra Medical Visions technological backbone, which allows them to work fast and to easily modify and rerun experiments without starting from scratch. But academic research leaves this issue unresolved. This system automatically alerts them if a patient is high risk even though they took the scan for another reason and may never have looked at the heart. In this case, it doesnt matter how much more quickly the AI can make a single assessment if the doctor has to spend extra time checking and refuting most of the cases the AI flagged. Osteoporotic fractures affect nearly 50 percent of men and 25 percent of women during their lifetimes, resulting in 2 million broken bones annually and an estimated $52 billion cost to the U.S. healthcare system. This helps the clinicians who really care, who deal with osteoporosis prevention and treatment programs, to identify patients with VCFs. For example, you might develop a very accurate machine learning model that only performs well when the image is taken with specific machine settings settings a doctor wouldnt normally use in a routine exam. A proficient data science and research team is essential, but its not sufficient. Code is for vertebral compression fracture detection with CT scans. Nanox said the acquisition of Zebra Medical Vision would help achieve both companies shared goal of forming the next generation of AI-enabled hardware and software devices to set a new standard in the medical devices sector. report covering solar, storage & the grid. All rights reserved. The latest development regarding the CPT code approval by the AMA is an industry milestone in the effort to boost the adoption of AI in imaging for VCFs and other under-diagnosed chronic conditions for which can help reveal and drive care, said Zohar Elhanani, Zebra Medical Vision chief executive officer. Then theres also the immense burden of rehabilitation. A diagnostic model is considered a medical device, and any change has to go through the process of regulatory approval.

Separately, Nanox has also agreed to acquire US-based radiologist-run and operated full-service subspecialty radiology and teleradiology company USARAD and its related entity Medical Diagnostics Web (MDW) for $30m. Each clinical mission also needs a project manager, a research engineer, and an operations engineer. Eyal and his team found an approach where they could take these much more frequent scans and still achieve a similar accuracy - in predicting risk for heart disease - to the model that the researchers build for the targeted scans. If the doctor doesnt look at a scan because the system says the patient is healthy when they arent, then the patient might miss their chance to get treated. But this doesnt work for machine learning: there are so many ways to slice the data and build a model, you would never reach the end. Siemens' ARTIS Icono Ceiling Angiography System Wins FDA Clearance, Study Suggests AI Enhances Non-Contrast CT Detection of Large Vessel Occlusion, FDA to Allow Bracco to Import Iomeron Iodinated Contrast Media as Shortage Drags On. And weve shown that simply having an automated diagnostic model doesn't necessarily mean youre saving a doctor time seamless integration and a manageable false-positive rate are essential. Essentially this is a segmentation problem: you segment the white clouds of calcification in the coronary arteries.

Theyre already on their way to their seventh FDA-approved diagnostic solution, with more coming soon. Zebra Medical Vision announced July 7 it has received approval of its CPT application for using artificial intelligence (AI) with CT scans to detect vertebral compression fractures (VCF) from the American Medical Association (AMA). If you continue using our website, we'll assume that you are happy to receive all cookies on this website. So lets say youve managed to build a model that accurately represents the population, seamlessly integrates into diagnostic workstations, and fits the doctors workflow. But this is just one of the hurdles of working in a regulated environment. Nanox Acquires Medical Imaging Company Zebra Medical Vision for $200 Million. It also offers a 3D modeling solution for x-ray images used for orthopaedic surgery pre-operative planning. This strategic move represents an end-to-end, globally-connected medical imaging solution.. In the end, even if it took a bit longer, it would be an extremely meaningful challenge, and the impact and value of the project would be undeniable. Zebra Medical Vision didnt build a new software tool for doctors to add to their workflow. Something went wrong while submitting the form. The company has received honours and awards, including being named a Top 5 global AI company by Fast Company. USARAD operates a network of 300 radiologists. Why not? Under the deal, Zebra-Med will receive up to $100m as an upfront payment, as well as an additional $100m based on the achievement of certain milestones. To put it another way: the data you train the diagnostic model on needs to represent the population you expect to see in the clinic.

Solving the problem in this way is certainly a valuable research result, but its still far from a workable diagnostic model for clinical practice, because it requires a non-standard workflow. The academic research approach: When Zebra Medical Vision looked into this problem, they found an academic paper saying that if you manually segment the areas of interest, and have a gated CT scan (a scan focused only on the heart), and measure with and without contrast in a specific protocol, then you could build a model that can provide the equivalent of the Agatston score (a risk measurement from 0 (low risk) to 400 (very high risk)). Its more likely that a patient comes to you because they have some symptoms already, and you need to diagnose the cause: ground-glass opacity, pulmonary embolism, COPD, emphysema, and lung cancer might all present similar symptoms. Enjoy your vacation, go back to Israel, and find something else to do..

This is the first AI CPT code specific to radiology. This also makes it very simple for Eyal and his team to roll out new versions of the model. To assess whether an AI solution can truly speed up a particular diagnostic workflow, you need to consider: So far, weve highlighted how important it is to get real clinical data as the basis for building a model that can perform on the exact population and data present in the clinic. As Eyal says, Sometimes we look at the problems that are meaningful and not sexy. This is exactly the kind of opportunity you find when you look at large datasets with an exploratory mindset a data scientists mindset. Early diagnosis and treatment for osteoporosis is essential. Your submission has been received! For their studies, Zebra Medical Vision had to coordinate support from up to 60 different expert annotators worldwide all working on the same clinical mission. Zebra Medical Vision uses artificial intelligence and deep learning to create and provide next generation products and services to the healthcare industry. Once Eyal and his team had both the data and a means of getting solutions into clinicians hands, they had to build a highway on top of this bridge: the technological backbone that would make everything else possible. For real-world diagnostic solutions, representative data is absolutely crucial. Instead they partnered with diagnostic workstations and integrated their predictions directly into the software tools the doctors were already familiar with. Founded in 2014, Zebra Medical Vision has 7 FDA-approved and 10 CE-marked AI solutions for medical imaging, with a recently introduced 3D modeling solution for x-ray images used for orthopedic surgery pre-operative planning. Hence many patients are diagnosed earlier and receive preventive treatment. Plus Zebra-Med calculates the predictions in advance, so when a physician clicks on an image, they can see the result immediately. Imagine you see that a scan is flagged. Zebra Medical Vision needed someone with clinical trials management experience someone who could speak the languages of both the clinicians and the data scientists. The false-negative rate. If this happens in the arteries that supply blood to the heart muscle, then it can limit or stop the supply of oxygen to the heart and cause a heart attack. There is a firewall between them, and theyre even hosted in two separate physical locations. Get our leading market intelligence Both deals are subject to satisfaction of the conditions to closing in the definitive agreements, regulatory approvals, and other customary conditions.

In fact, this isnt a question that comes up in a hospital.