Uncategorized

End-to-End AI | Robotic Ultrasound

“When did we learn to replace the prefrontal cortex with a tiny little radiologist?”

One gem from Dr. Glaucomflecken’s latest neurologist skit.


Check out the latest Imaging Wire Show, featuring good friend of TIW and the unofficial mayor of the PACS industry, Kyle Henson. This was a great conversation about PACS, informatics, the cloud, and understanding radiologist burnout, and it’s definitely worth a listen.



Imaging Wire Sponsors

Arterys | Bayer Radiology | Blackford Analysis
Canon Medical Systems | Fujifilm Healthcare Americas
GE Healthcare | Novarad | Nuance
Riverain Technologies | Siemens Healthineers
United Imaging | Zebra Medical Vision



The Imaging Wire


Aidoc and Subtle Medical’s End-to-End Alliance

Aidoc and Subtle Medical launched an interesting new partnership that will make Subtle’s image acquisition / enhancement software available on the Aidoc AI platform.

End-to-End Partnership – The addition of SubtlePET and SubtleMR to the Aidoc AI platform will create what Aidoc called an “end-to-end” solution and “the first joint offering of AI for both image acquisition and triage.” Some folks might mistake that to mean that they will create new combined image acquisition+triage solutions, but they won’t be specifically linked (Aidoc doesn’t have MRI or PET tools yet anyway).

Aidoc, a Platform Company – Aidoc seems to be increasingly positioning itself as an AI platform company, which is an understandable strategy given users’ need for comprehensive / consistent AI workflows. Aidoc’s initial partnerships also allow the triage-focused vendor to offer a far more comprehensive value proposition (Subtle for acquisition, icometrix for stroke analysis/assessment).

Subtle Upsides – The alliance introduces Subtle Medical to Aidoc’s sizable list of clients (used at >500 medical centers, a high profile partnership w/ RP), and adds to Subtle’s current alliances with AI marketplace vendors (e.g. Blackford, Nuance, Incepto) and complementary solutions companies (e.g. Cortechs.ai).

The Takeaway – Although AI platform alliance stories don’t usually earn a spot at the top of The Imaging Wire, this alliance is pretty notable given what it suggests about Aidoc’s AI platform strategy and about the growing trend towards complementary AI alliances. It’s also a nice way for Subtle Medical to expand its reach.


Scaling AI with the Cloud

Trying to figure out how your IT resources can handle increased AI adoption? This Blackford paper details how the cloud is helping radiology organizations scale their computing resources to support multiple AI applications or algorithms.

– Sponsored.


Why United Imaging’s DR (uDR)?

United Imaging’s uDR X-ray portfolio combines low radiation dosage and brilliant images with a focus on user automation and patient comfort. Like United Imaging’s other systems, the uDR lineup comes in all-inclusive configurations and software upgrades for life.

– Sponsored.


The Wire

  • RSNA 2021 Preview: RSNA just shared an early preview of their 2021 annual meeting, revealing understandable drops in total exhibitors (510 vs. 740), first-time exhibitors (71 vs. 157), and show floor footprint (336k vs. 452k sq feet) versus 2019. These numbers all seem high enough to make RSNA 2021 a valuable COVID-era event, but as we saw with HIMSS, the show’s actual turnout will depend on how the COVID pandemic evolves during the next few months.
  • Google’s CXR AI: Google reminded the world that it’s still very much committed to healthcare, detailing a new deep learning system for detecting CXR abnormalities. Noting the inconvenience of using multiple disease-specific CXR AI tools, the Google team developed this system to classify CXRs as normal or abnormal (its disease-agnostic). In a test against two international CXR datasets, the model detected abnormalities with relatively high accuracy and generalizability (dataset 1= 0.87, dataset 2 = 0.94), while allowing radiologists to prioritize and interpret abnormal cases 7% to 28% faster.
  • Vascular Ultrasound Robot: Previously unknown Australian imaging startup Vexev unveiled its “game-changing” tomographic ultrasound robot, which automatically produces 3D vascular scans when patients place their arm or leg on the device. Vexev believes this device could make vascular ultrasound far more accessible for patients and efficient for sonographers. It’s starting trials this month to try to prove those beliefs.
  • AHN’s Sleep Stoke Method: The Allegheny Health Network detailed the benefits of its MRI-based method for assessing patients who experience acute ischemic strokes (AIS) while asleep. Noting that up to 27% of AIS occur during sleep and tPA treatment is most effective within 4.5hrs of symptoms, AHN adopted a stroke age assessment method based on MRI (not CT) and adjusted its staffing and communication structure to support 24/7 MRI access / interpretations for these patients. Since then, AHN has been able to give 21 wake up stroke patients tPA treatments that otherwise wouldn’t have been possible.
  • Feedback & Qure.ai’s AI App: Feedback and Qure.ai are exploring integrating Feedback’s Bleepa medical imaging mobile app with Qure.ai’s AI workflows, potentially allowing clinicians to upload images and then receive AI-based analysis (all with their mobile devices). The companies will initially target India, where rural clinics often lack onsite radiologists and the IT infrastructure to support traditional image sharing.
  • UK LC Screening Evidence: A new study out of the UK shows that earlier lung cancer screening could reduce mortality by 16%, prompting calls for the UK NHS to adopt a national lung cancer screening program. The 2011-2013 UK Lung Cancer Screening Trial (n = 3,968 at-risk patients, 50-75yrs) screened half of the patients with LDCT and had half attend normal checkups. Analysis after seven years revealed that the LDCT-screened patients had more detected cancers (86 vs. 75) that were detected at earlier stages (Stage IA: 53% vs. 14.5%), and had far fewer deaths (30 vs. 46).
  • GE’s Supply Pressures: GE informed shareholders that it expects to face medical imaging scanner supply chain issues through the first half of 2022 due to pandemic-related labor and materials shortages (particularly: semiconductors, resins, logistics). GE Healthcare is far from the only tech company dealing with COVID-related shortages and it wouldn’t be surprising if other scanner OEMs will have similar challenges.
  • DVT AI Impact: A new NPJ Digital Medicine study detailed how ThinkSono’s ultrasound AI system allowed inexperienced ultrasound operators to detect deep vein thrombosis (DVT). The researchers tested the algorithm on DVT clinic patients in the UK and Germany (53 & 30), achieving mixed sensitivity (0.82, 0.94), specificity (0.70, 0.82), PPV (0.65, 0.89), and NPV (0.99, 1.00). By allowing less-experienced operators to perform DVT exams, they estimate that the software would eliminate £72 to £175 in healthcare costs per exam.
  • Nuance’s ANZ Expansion: Nuance expanded its cloud/AI PowerScribe One radiology reporting platform and mPower Clinical Analytics solution to Australia and New Zealand, targeting the same burnout and clinical quality value proposition that’s made these tools successful stateside. Even if ANZ is a natural extension for Nuance’s core diagnostic solutions, it’s worth noting that geographic expansion was also one of the key expected next-steps from Nuance’s acquisition by Microsoft.
  • LBP Translations: Patients often don’t understand common and usually non-serious terms in their lumbar imaging reports. That’s from a new BMJ study of 677 English speakers (577 w/ back pain, 251 who received LBP exams) that found low reported understanding of terms like disc degeneration (35%) and Modic changes (10.5%). The respondents also believed that most of the study’s 14 terms indicated a serious back problem (59%–71%) that back pain might persist (52%–71%).
  • Butterfly’s Big Cameo: Butterfly Network gained a whole lot more exposure after making an appearance on this week’s Apple Event (starts at 15:48 mark). Apple used the Butterfly iQ+ to highlight the iPad Mini’s added USB-C and 5G connectivity, suggesting that these new features can allow doctors in remote areas to conduct ultrasound exams. Apple might be the best technology marketer in the world (this event got >12m views within 4hrs…), but stuff like this certainly supports Butterfly’s case as the best brand marketer in medical imaging.
  • QReport Evidence gap: A new paper in neuroradiology provided a helpful breakdown of the available FDA/CE-approved quantitative MRI reporting tools for dementia diagnosis (aka QReports), finding significant validation evidence gaps. Among the paper’s 17 qualifying QReport products, 11 were supported with technical validation, but only four had clinical validation (CorTechs.ai, Jung, Brainreader, Combinostics), and 6 products had no validation at all. As you might expect, the authors called for more clinical validations.

Windsong’s Case for MEDRAD Stellant FLEX CT

Learn how Windsong Radiology Group used Bayer’s MEDRAD Stellant FLEX CT injection system to drive efficiencies and standardization across its imaging centers.

– Sponsored.



The Resource Wire

  • Canon’s Cartesion Prime is the only air-cooled digital PET/CT system, which means big reductions in service, chiller, and infrastructure costs. Check out Canon’s case for the air-cooled Cartesion Prime.
  • See how Novarad’s CryptoChart solution allowed Central Ohio Primary Care (COPC, 70 practices, 400 physicians) to make the transition to digital imaging sharing in this Healthcare IT News case study.
  • This Diagnostic and Interventional Cardiology article details the unique advantages of cloud-based CVIS systems (off-property access, team collaboration), with insights from one Mississippi-based cardiologist on the benefits of Fujifilm Healthcare’s VidiStar CVIS.
  • It says a lot when a solution works so well for a radiology department that they decide to perform a study to quantify its benefits. In this Imaging Wire Q&A, University Hospital of Zurich’s Thomas Frauenfelder discusses his experience and study on Riverain Technologies ClearRead CT.
  • This Arterys white paper details how cloud-based AI tools have become essential for streamlining and improving lung nodule detection and tracking.
  • Cardiovascular disease is the number one global cause of death, but it’s also preventable, which is one of the reasons why Zebra-Med views AI-powered cardiovascular screening as the next frontier in population health.
  • See Birmingham Radiological Group-GV radiologist, Joel Mixon, MD, describe their transition to Nuance PowerScribe One and how the platform improved their efficiency, consistency, and accuracy.


You're signed up!

It's great to have you as a reader. Check your inbox for a welcome email.

-- The Imaging Wire team