“For clinicians and patients, we believe this will quite simply change everything.”
Lumitron chief technical officer and UC Irvine professor, Chris Barty, has big expectations for the company’s HyperVIEW imaging system.
The Imaging Wire
Imaging AI developers suddenly have a lot more to work with following the National Institutes of Health’s public release of 32,000 annotated and anonymized CT images from 4,400 patients. The NIH’s “DeepLesion” dataset far outnumbers existing medical imaging datasets (most less than 1k) and features data on a variety of lesion types (vs. one type per dataset), potentially allowing developers to train a deep neural network and create a large-scale universal lesion detector that can help radiologists identify all lesion types. From there, the universal lesion detector could serve as an initial image screening tool, sending detection results to other specialist systems trained on certain types of lesions. It could also allow scientists to study the relationship between different types of lesions, potentially leading to new medical discoveries. That was a lot of “coulds,” but there is no doubt that the NIH’s massive image release helps overcome one of the main medical imaging artificial intelligence hurdles, leading to new and more-effective algorithms. This release is also an example of the growing role that government entities are playing in AI development, as the NIH released 10,000 chest X-ray images last year and 2018 already brought major public medical imaging AI initiatives in France, the UK, and Korea.
Lumitron’s Game Changer
Lumitron announced plans to develop HyperVIEW imaging systems that boast 100x greater image resolution than current CT scanners and a 1000x resolution advantage versus traditional X-rays. That’s quite a jump, especially considering that the systems will operate with lower radiation doses than X-ray and fit into a CT-size footprint. The HyperVIEW systems are expected to allow much earlier cancer diagnostics and treatment, while also supporting a range of new applications outside of medicine (e.g. aerospace, security, mining), making Lumitron believe HyperView “will quite simply change everything” in medical imaging. Lumitron is already collaborating with major medical imaging players in anticipation of commercialization, although there are no details on when the HyperVIEW systems will hit the market. Still, even with lingering questions about how and when the HyperVIEW platform will be ready to go, there is little doubt that the systems would have a big impact on the market.
Siemens’ New Technologist Services
Siemens Healthineers launched a pair of services intended to support healthcare providers’ radiologic and laboratory technologist workforce, with a side goal of making sure its client workforce is full of Siemens experts. With FlexForce Coach, a Siemens consultant works with a healthcare provider’s technologist teams to improve imaging system care procedures, standardize processes, and drive adoption of more advanced applications. Siemens’ FlexForce Tech is a staffing service, making trained and licensed technologists available to healthcare providers if they have a technologist workforce shortage.
GE Latin America Back in Cartel Headlines
Turns out GE Latin America may have been involved in the Rio de Janeiro-area bribery and price fixing scheme that recently brought down its CEO, Daurio Speranzini Jr. The executive’s illegal activities were previously believed to take place when he worked at Philips. However, prosecutors now claim that GE was indeed among the “cartel” of at least 33 companies funneling bribes through a politically connected local medical supply firm. Making matters (much) worse for GE, the court papers suggest that Speranzini joined GE just two months after an internal corruption probe brought his departure from Philips, adding that Speranzini continued the scheme upon joining GE. This revelation brought a shift in PR messaging from GE, which initially claimed that Speranzini’s involvement exclusively took place when he was at Philips, and has since adopted a more cautious position that the company is “currently not aware of any improper conduct.” The silver lining for GE is that they are still in less trouble than Philips, which is now relying on the “many years ago” defense.
Once again, stuff like this is more common in Latin America than most northern hemisphere Imaging Wire readers may believe, and this Brazilian crackdown isn’t really a condemnation of GE or Philips’ global business ethics. Still, it appears that the corruption headlines will get worse for GE and Philips before they get better.
- Carestream Health announced a big leadership change, naming David Westgate as its new chairman, president, and CEO, replacing Kevin Hobert after 11 years atop Caresteam. Westgate is an industry outsider, previously serving as CEO of Jason Industries, but has plenty of leadership experience and a proven EBITA record (a big focus of PE-owned companies like Carestream).
- Healthcare AI company, Viz.ai, got a funding and credibility boost, completing a $21 million Series A round that included an investment from GV, formerly known as Google Ventures. The new funding will be used to drive market expansion and extend Viz.ai’s portfolio beyond stroke care.
- Researchers from NVIDIA, MIT, and Aalto University (Finland) developed a deep learning technique that can improve flawed images (removing artifacts, noise, and grain), without requiring a noise-free image for AI training. This new technique could be applied to a number of image applications, including MR imaging.
- Research from UC San Francisco reveals that many low-risk breast cancer patients are receiving high-cost and high-radiation imaging procedures that generally aren’t recommended for their condition. The research studied data on 36,045 women who had surgery for cancer in one breast between 2010 and 2012, finding that over an 18-month period nearly 32% underwent at least one high-cost/dose imaging procedure and 12.5% had at least one PET scan, neither of which are recommended.
- Analogic named Peter Granick as vice president of operations, taking over leadership of the company’s entire global operations, after leaving a global supply services VP role at Thermo Fisher Scientific.
- EOS imaging took a “significant equity investment” from Fosun Pharmaceutical AG (subsidiary of Shanghai Fosun Pharmaceutical), issuing 3,446,649 new shares to Fosun for a total investment of €15.1 million (€4.37 per share). The investment gives Fosun a 13.2% stake in EOS imaging, making it EOS’ largest shareholder. In addition to funding future growth, the investment will be used to help EOS expand its presence in the Asia-Pacific region, particularly in China.
- A survey of 263 German medical students revealed an overall optimistic view of medical imaging artificial intelligence, as the vast majority of students believed AI would improve radiology (83%), could detect pathologies on radiological exams (83%), and will revolutionize radiology (77%). Just as notably, 83% did not believe that AI would replace radiologists.
- A National Cancer Institute study suggests that CT scans may increase the risk of cancer, particularly in children. The study looked at records from 168,394 Dutch children who received one or more CT scans between 1979 and 2012, finding that these children had a 1.5x greater likelihood of getting brain cancer. This is awful, and it’s not the only study linking CT and cancer.
- The good news is, researchers from UCSF developed a clinical decision-making tool, called the Pediatric NEXUS Computed Tomography Decision Instrument, that could reduce the use of CT scanning on low-risk pediatric patients by 34%. The tool identifies blunt trauma patients who would most benefit from CT screening and prompts healthcare providers to consider other methods for low-risk patients.
- The Israeli government issued a $33 million grant (paid over 6 years) to GE Healthcare, Medtronic, and Change Healthcare to increase their R&D activities in the country, with the goal of establishing Israel as a biotechnology and medicine research hub.
The Resource Wire
– Future home of sponsored content. Maybe yours.
- Agfa Enterprise Imaging integrates clinical videos and images into a single application
- Analogic’s BK Ultrasound bkSpecto urology ultrasound system combines image quality, speed, usability, and small footprint
- Canon Aquilion Precision, the world’s first Ultra-High Resolution CT system
- Caresteam touts benefits of weight bearing CT imaging
- Fujifilm’s FDR AQRO mobile x-ray combines high sensitivity with small size and low-dos
- GE’s Every woman. Every body. Every town. roadshow brings the company’s breast health technologies and message to centers across the country.
- Hitachi white paper on the business benefits of high-field MRI.
- Hologic’s 3Dimension Mammography System leads with 3D imaging and patient comfort.
- IBM Watson Imaging Clinical Review cognitive data review tool for more accurate patient records.
- Konica Minolta publishes latest Kontours issue.
- Philips’ new HealthSuite Insights AI platform curates and analyzes healthcare data and offers tools to build and operate AI-based solutions.
- Samsung’s RS85A premium ultrasound combines image quality with advanced ergonomics
- Shimaduz MobileDaRt Evolution MX8 premium mobile x-ray
- Siemens’ new Somatom Go CTs add cardiac and image-guided capabilities