|
Real-World Stroke AI | GE/DeepHealth AI Alliance
November 11, 2024
|
|
|
|
|
Together with
|
|
|
|
“Comparing the polls to the actual results I have realized that it’s ok to ask for a chest CT after ordering a chest radiograph.”
|
|
RogueRad, in a post to X on November 7.
|
|
|
As healthcare providers struggle to manage a growing number of cyberattacks, many are turning to cloud-based operations for help. In this Imaging Wire Show, we talked to Vikram Chhabra of Microsoft to learn how migrating to the cloud has cybersecurity benefits for radiology.
You’ve got a few days left to reserve your seat for the first-ever Imaging Wire webinar, Transforming Radiology Reporting, at 12 pm ET on Wednesday November 13. We’ve put together a great panel of key opinion leaders to discuss the new technologies revolutionizing radiology reporting, so don’t miss out!
|
|
|
|
Time is brain. That simple saying encapsulates the urgency in diagnosing and treating stroke, when just a few hours can mean a huge difference in a patient’s recovery. A new study in Clinical Radiology shows the potential for Nicolab’s StrokeViewer AI software to improve stroke diagnosis, but also underscores the challenges of real-world AI implementation.
Early stroke research recommended that patients receive treatment – such as with mechanical thrombectomy – within 6-8 hours of stroke onset.
- CT is a favored modality to diagnose patients, and the time element is so crucial that some health networks have implemented mobile stroke units with ambulances outfitted with on-board CT scanners.
AI is another technology that can help speed time to diagnosis.
- AI analysis of CT angiography scans can help identify cases of acute ischemic stroke missed by radiologists, in particular cases of large vessel occlusion, for which one study found a 20% miss rate.
The U.K.’s National Health Service has been looking closely at AI to provide 24/7 LVO detection and improve accuracy in an era of workforce shortages.
- StrokeView is a cloud-based AI solution that analyzes non-contrast CT, CT angiography, and CT perfusion scans and notifies clinicians when a suspected LVO is detected. Reports can be viewed via PACS or with a smartphone.
In the study, NHS researchers shared their experiences with StrokeView, which included difficulties with its initial implementation but ultimately improved performance after tweaks to the software.
- For example, researchers encountered what they called “technical failures” in the first phase of implementation, mostly related to issues like different protocol names radiographers used for CTA scans that weren’t recognized by the software.
Nicolab was notified of the issue, and the company performed training sessions with radiographers. A second implementation took place, and researchers found that across 125 suspected stroke cases …
- Sensitivity was 93% in both phases of the study.
- Specificity rose from the first to second implementation (91% to 94%).
- The technical failure rate dropped (25% to 17%).
- Only two cases of technical failure occurred in the last month of the study.
The Takeaway
The new study is a warts-and-all description of a real-world AI implementation. It shows the potential of AI to improve clinical care for a debilitating condition, but also that success may require additional work on the part of both clinicians and AI developers.
|
|
|
Register Today for a Visage 7 Priority Demo
Visage continues to lead imaging’s managed services SaaS move to the cloud with their Visage 7 CloudPACS solution. Register today for a priority demo at RSNA 2024 at booth #4329.
|
|
Learn How Industry Leaders Are Improving the Patient Experience
Join industry leaders at RSNA for a Lunch & Learn hosted by PocketHealth where they’ll share real-world strategies for enhancing patient engagement, tackling interoperability challenges, and reducing costs despite budget and staffing constraints. RSVP required!
|
|
Come See Enlitic at RSNA 2024
Visit Enlitic at RSNA 2024 at booth #4365 to learn how the company is revolutionizing radiology with its data standardization solutions, including data migration technology through its acquisition of Laitek. Book a demo today.
|
|
- GE/DeepHealth AI Alliance: GE HealthCare and DeepHealth are collaborating in an alliance to combine AI algorithms with big-iron hardware under the branding “SmartTechnology.” In the partnership’s first step, they are integrating GE’s Senographe Pristina mammography system with DeepHealth’s SmartMammo AI-powered workflow and image review tools as well as Smart Alerts software for alerting clinicians quickly to suspicious results. GE will distribute SmartMammo and other DeepHealth solutions in the U.S., and the companies will pursue other collaborations under the SmartTechnology umbrella.
- Radiology’s Breakthrough Breakdown: Only 3% of FDA Breakthrough Device designations (32 products) have come from radiology – at the lower end of medical specialties. Cardiology dominates the program, with 21% of over 1k breakthrough designations made by the agency since 2015. The numbers are in stark contrast to FDA authorizations for AI devices, where radiology had a 73% share in the most recent update. Breakthrough designation is no sure sign of commercial success, however, with only 128 products (12%) going on to secure marketing authorization so far.
- China Woes Sink Vendor Results: Weakness in medical equipment purchasing in China related to the country’s anti-corruption campaign weighed down financial results for several imaging vendors in the most recent quarter. Revenues were reported for Siemens Healthineers Imaging division (+7.7% to $3.83B), GE HealthCare Imaging and Advanced Visualization Solutions divisions (flat to $3.45B), Philips Diagnosis & Treatment division (-1% to $2.23B), Fujifilm healthcare division (-3.6% to $1.59B), Canon Medical Systems (-0.1% to $865M), Hologic Breast Health division (+6.4% to $376M), United Imaging Healthcare (-25% to $227M), Guerbet (+5.4% to $217M), and Konica Minolta Healthcare (+2.2% to $148M).
- Siemens CEO Addresses China Tariffs: In related news, the CEO of Siemens Healthineers in an investor call addressed the prospect of higher tariffs that the incoming Trump Administration might impose on medical equipment manufactured in China. Trump has threatened to impose 60% tariffs on products entering the U.S. from China, where many imaging manufacturers have factories. But Bernd Montag said Siemens is “very, very well positioned” because it has set up factories to deliver products in the countries where they are made.
- United Imaging to Enter Canada: United Imaging is poised to enter the Canadian market after getting Health Canada marketing authorization for several PET/CT scanners in its uMI Panorama product line. The company noted that uMI Panorama scanners sport 2.9mm NEMA PET resolution, 200-picosecond time-of-flight resolution, and 0.25-second CT rotation. United is looking for channel partners in Canada to help market the scanners.
- DeepHealth Lands First AI Platform User: DeepHealth landed the first customer for its new DeepHealth OS AI operating system. Imaging center operator ONRAD will deploy DeepHealth OS and its full suite of AI solutions, including image viewers and smart reporting features. ONRAD manages over 1.4M exams annually and serves 120 hospitals through its network of imaging centers. Implementing DeepHealth OS enables it to integrate AI algorithms from DeepHealth and third-party developers in a single cloud-based diagnostic workspace.
- Low-Value Back Imaging Fail: An initiative to get physicians to order fewer imaging exams for low back pain – a potential example of low-value healthcare – failed to work in a new study in JAMA Network Open. Researchers deployed instructors posing as patients to meet clinicians and advocate for watchful waiting without imaging. But across 53 clinicians, those who got the visits ordered almost as many lumbar imaging scans as clinicians who didn’t (16% vs. 17%), with no statistically significant difference in follow-up imaging for acute neck pain or overall imaging.
- Mach7 Joins AWS Network: Mach7 Technologies has joined the AWS Partner Network, a community of over 130k partners from more than 200 countries working on the Amazon Web Services cloud platform. Mach7’s eUnity enterprise diagnostic viewer will be able to leverage AWS services from across healthcare enterprises, while also giving healthcare providers a complete view of patient imaging histories regardless of the data source or location where images were acquired.
- Bayer Contrast Injector Cleared: The FDA cleared Bayer’s newest CT contrast injector, Centargo. First introduced at ECR 2019, Centargo has been sold in international markets and with the FDA clearance will now be marketed in the U.S. Bayer designed Centargo to improve radiology workflow and adapt to technologist shortages by automating previously manual processes and reducing patient set-up times. The injector’s multi-patient design also makes it well-suited for high-volume CT environments, with piston-based technology that enables dual-flow simultaneous delivery of both contrast and saline.
- MeVis Gets Clearance for Mammoscape: Another medical product that’s received FDA clearance is MammoScape from German breast imaging software developer MeVis BreastCare. MammoScape provides a multimodality image review workspace for breast images, with AI-assisted workflows for both 2D and DBT mammography systems. With clearance in hand, MeVis will begin selling MammoScape in the U.S. market.
- Hyperfine Updates Software in Europe: Hyperfine’s Swoop portable MRI scanner received the CE Mark for an update to its system software. Hyperfine’s initial CE Mark was in 2023, but the new authorization positions the scanner for a broader European launch, and it has secured distribution partners in 13 European countries. Hyperfine is positioning the ultra-low-field Swoop as an option that can be transported to the patient bedside for brain scans.
- CT AI’s Predictive Promise: Cardiac CT analysis using Cleerly’s AI-based ISCHEMIA solution can predict serious cardiac events in patients with coronary artery disease symptoms. In results presented at TCT 2024, researchers found that among over 3.5k patients, the two strongest predictors of MACE were diameter stenosis percentage and noncalcified plaque volume (HRs: 1.251 and 1.069), the latter of which was linked to adverse patient outcomes. These two factors were more predictive than traditional clinical risk scores, suggesting AI-driven evaluations could help guide treatment decisions.
|
|
Connecting Patients to Exceptional Care
Mach7 Technologies’ enterprise imaging solutions connect patients and clinicians across the globe to enable exceptional care. As modern healthcare evolves, so should your strategies. Schedule a demo at RSNA 2024 or stop by booth #3953 to learn more.
|
|
Book an RSNA Meeting with Riverain
Riverain’s ClearRead technology with Clear Visual Intelligence can improve your ability to detect lung cancer with either CT or X-ray. Book at meeting with them at RSNA 2024 or drop by for a visit at booth #4523.
|
|
Get Your Head Around AI for Neuroradiology
Check out the latest blog from Blackford on how advances in deep learning algorithms for neurology imaging are improving outcomes and easing the burden on radiologists.
|
|
- Discover Prenuvo at RSNA 2024: Discover how Prenuvo is advancing research and redefining the future of healthcare at booth #1239 at RSNA 2024. Learn about their cutting-edge MRI technology first-hand and explore partnership opportunities.
- Request an RSNA Meeting with TeraRecon: RSNA 2024 will be here before you know it. Come explore TeraRecon’s latest updates and find out why the company is an award-winning solution provider for AI-empowered radiology, oncology, cardiology, neurology, and vascular surgery.
- Connect with United Imaging at RSNA 2024: United Imaging will be celebrating the theme of Building Intelligent Connections at RSNA 2024. Come visit the company at booth #1929 to learn about their imaging solutions and how they connect to United’s mission of Equal Healthcare for All.
- Meet Merge at RSNA 2024: Merge is looking forward to sharing a wide range of news, innovations, and updates at RSNA 2024. Join them at booth #6100 to explore how their imaging solutions put your workspaces, clinicians, and transformation into focus.
- Networked Radiology Empowers Radiologists: Join AGFA HealthCare at 11 am ET on November 12 for a webinar on how networked radiology can bridge health systems and empower radiologists. Learn about the role of networked radiology and get acquainted with new strategies for enterprise imaging implementation.
- Book an RSNA Meeting with CARPL: Explore radiology AI like never before by booking a meeting with CARPL at RSNA 2024, or drop by booth #5733 to tune in to any of seven research presentations across the show.
- Leading Radiology Forward at RSNA 2024: DeepHealth is leading radiology forward through AI-powered informatics and smart technology. Book a meeting today at RSNA 2024 booth #1340 to learn how they can help you achieve increased staff productivity and a better experience for patients and staff.
- Heart Failure Screening at Home and in Primary Care: Heart failure is the number one cause of hospitalization in people over 65. The SYMPHONY study is investigating a screening strategy of point-of-care AI echo and NT-proBNP in primary practice and general community settings. Learn more on this page from Us2.ai.
- Harnessing the Power of a Connected Network: Check out the next Road to RSNA virtual session from Microsoft at 2 pm ET on November 20 to discover how their network, powered by Microsoft Azure, can help increase efficiencies and improve patient care while building a scalable foundation for the future.
- 2 Questions about AI for Radiology Leaders: Are today’s radiology AI solutions solving the right problems? And are there other solutions available for AI of brain MRI? Read this article from SpinTech MRI to learn how their STAGE solution can optimize MRI utilization.
- A Sneak Peak at Intelerad for RSNA 2024: Join Intelerad for a webinar at 1 pm ET on November 19 to get a sneak peek at what they’ll be highlighting at RSNA 2024. Company executives will explore the transformative impact of AI and cloud technology on radiology.
- AI for Limb Fractures on X-Ray: AI can recognize limb fractures on X-rays and reduce interpretation discrepancies between radiology and emergency departments. Learn how Gleamer’s BoneView AI algorithm performed in this new research study.
|
|
|
|
|
