Veye Validation | RTs on AI | UHR-CTA

“Did they think I had surgery?”

An Arizona-based retiree after receiving a $14.5k MRI bill.

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

Veye Validation

A team of Dutch radiologists analyzed Aidence’s Veye Chest lung nodule detection tool, finding that it works “very well,” while outlining some areas for improvement.

The Study – After using Veye Chest for 1.5 years, the researchers analyzed 145 chest CTs with the AI tool and compared its performance against three radiologists’ consensus reads, finding that:

  • Veye Chest detected 130 nodules (80 true positive, 11 false negative, 39 false positives)
  • That’s 88% sensitivity, a 1.04 mean FP per-scan rate, and 95% negative predictive value
  • The radiologists and Veye Chest had different size measurements for 23 nodules
  • Veye Chest tended to overestimate nodule size (bigger than rads w/ 19 of the 23)
  • Veye Chest and the rads’ nodule composition measurements had a 95% agreement rate

The Verdict – The researchers found that Veye Chest “performs very well” and matched Aidence’s specifications. They also noted that the tool is “not good enough to replace the radiologist” and its nodule size overestimations could lead to unnecessary follow-up exams.

The Takeaway – This is a pretty positive study, considering how poorly many recent commercial AI studies have gone and understanding that no AI vendor would dare propose that their AI tools “replace the radiologist.” Plus, it provides the feedback that Aidence and other AI developers need to keep getting better. Given the lack of AI clinical evidence, let’s hope we see a lot more studies like this.

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.

ETMC and Bayer’s Contrast Reduction

See how East Texas Medical Center reduced its abdominal CT contrast volumes by 30% after adopting Bayer Radiology’s contrast dose management software.

– Sponsored.

The Wire

  • RTs & RTTs on AI: A new Radiography study found that many Radiographers and Radiation Therapists in Ireland (n = 318 RTs & 77 RTTs) believe AI will improve care (64.9% & 70.6%) and are in favor of adopting AI (86.1% & 94%), even though most aren’t currently using the technology (27.6% & 40.3%). The surveyed RTs logically approved of AI that would automate technical processes (67% – device QA, 61% – post-processing, 53% – clinical audits), but believed many autonomous diagnostic or patient-facing AI use cases were inappropriate.
  • Securing the Mo-99: The U.S. Department of Energy awarded $37m to NorthStar Medical Radioisotopes to help increase its molybdenum-99 (Mo-99) production capacity, with the end goal of establishing a reliable domestic Mo-99 source that doesn’t use highly enriched uranium. NorthStar, which has already raised $80.5m from venture capital, will be required to match the government funding.
  • The GE AMX Navigate: GE Healthcare introduced its new AMX Navigate portable X-ray, which launches with a major focus on reducing technologists’ physical and workflow requirements. The AMX Navigate’s physical improvements largely come from its new Free Motion telescoping column, which reduces technologists’ required lift force by up to 70%. GE’s new Zero Click Exam feature provides its workflow improvements, matching each patient to the worklist and automatically selecting the correct exam protocol (eliminating all typical UI interactions). Like GE’s previous portable X-rays, the AMX Navigate comes with a suite of embedded AI algorithms.
  • SubtlePET Validated: Subtle Medical’s SubtlePET image reconstruction solution allows 4x faster or lower-dose PET scans, and generalizes well (across sites, scanners, patients), while maintaining image quality and SUV accuracy. That’s from a new NP Digital Medicine study that had blinded radiologists review SubtlePET and standard PET scans from 50 oncology patients at 3 hospitals. The SubtlePET-enhanced scans matched the standard PET scans for diagnostic image quality, overall diagnostic confidence, tumor detection, and uptake value accuracy.
  • Is CMS Unfair to Imaging? Medical imaging didn’t contribute to the rise in Medicare Part B expenditures between 2009 and 2019, but it might have been disproportionately affected by CMS’ cost containment policies. Case Western Reserve researchers found that medical imaging represented an average of 8% of total Medicare Part B expenditures during the 10-year period (so roughly: 1.4% of Medicare, 0.05% of total National Healthcare Expenditures). During this period, medical imaging expenditures didn’t grow (Medicare, Part B, and NHE all did) and imaging’s -3.5% CAGR was lower than all other major service line categories.
  • DoubleVision: ContextVision might spin-off its Digital Pathology unit and list it on the Oslo Stock Exchange, separating Digital Pathology and Medical Imaging into two separate companies. ContextVision suggested that the ability to focus on its “core” image enhancement tech/products would outweigh the synergy benefits of keeping the units connected (the capital from the IPO should help too).
  • A Case for UHR-CTA: A new Johns Hopkins study found that ultra-high-resolution Coronary CT Angiography (UHR-CT) could improve assessments of patients with severe coronary artery calcification, overcoming conventional CT’s limitations. The researchers performed UHR-CT exams on 15 patients (53–79yrs) who also underwent invasive coronary angiography. UHR-CT detected stenosis with 86% sensitivity and 88% specificity, while achieving high diagnostic confidence and image quality scores (4.3 & 4.1 out of 5).
  • Centaur’s $15.9m: Healthcare AI labeling startup Centaur Labs quietly raised $15.9m that it will presumably use to further develop its data labeling services and fund its commercial activities. We haven’t covered Centaur Labs often, but they solve a key AI data problem, have a solid list of advisors, and just landed an 8-digit funding round, so we should hear more from them going forward.
  • Closing The Follow-up Gap: A new study in Current Problems in Diagnostic Radiology (n = 375) found that 66% of surveyed radiologists’ practices don’t track incidental follow-ups, with the remaining practices relying on closed-loop software or non-radiologist team members (67% & 29%). The authors encouraged radiologists to adopt tracking systems and increase referrer collaboration to ensure that the appropriate follow-ups take place, even if many rads think incidental management should be the PCP’s responsibility.
  • MindRhythm Funded: MindRhythm announced a $5m Seed round that it will use to complete clinical trials for its stroke triage technology. Although it technically doesn’t use imaging, MindRhythm’s pulse monitoring tech noninvasively detects / categorizes suspected strokes, so EMS teams can decide what level of stroke center to bring a patient (much like imaging). It also communicates patient data / location to hospital teams so they can prepare accordingly.
  • Dark-Field X-Ray, Quantified and Qualified: A team of German researchers performed the first human Dark-Field X-ray exams, revealing the techniques’ qualitative and quantitative characteristics. The researchers scanned 40 healthy adults using a Dark-Field scanner prototype, finding that lungs have a high signal in Dark-Field images, surrounding osseous structures have a very low signal, and soft tissue has no signal. They also found that total Dark-Field signal correlates with lung volume, while patient profiles didn’t influence Dark-Field signals (gender, age, weight, height).

Leveraging Pediatric Imaging AI

Check out this Blackford Analysis white paper detailing how children’s hospital imaging teams can leverage AI to improve modality throughput and imaging device availability.

– Sponsored.

Take the Canon AiCE Challenge

Take the AiCE challenge and see why half the radiologists in a recent study “had difficulty differentiating” images from Canon Medical Systems’ Vantage Orian 1.5T MR using its AiCE reconstruction technology compared to standard 3T MRI images.

– Sponsored.

The Resource Wire

  • This MDPI study details how imaging represents the most powerful tool for identifying patients at risk of arrhythmic mitral valve prolapse, noting Artery’s 4D-flow CMR’s “great promise” for assessing mitral regurgitation.
  • 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.
  • See how VidiStar users have benefitted from the Fujifilm Healthcare’s cardiovascular information system’s flexible SaaS-based model and leveraged its productivity advantages to increase reimbursements.
  • Canon Medical System’s new Aquilion Exceed LB CT radiation therapy planning system has a lot to boast about, combining AiCE reconstruction technology with an industry-leading bore opening (90cm), field of view (90cm), and detector coverage (4cm).
  • See how and why Zebra Medical Vision sees a much bigger future for public health AI than many of us imagine in this Imaging Wire Q&A with company CEO, Zohar Elhanani.
  • CD burning issues? Check out this one-minute video showing how Novarad’s CryptoChart image sharing solution allows patients to easily access and share their medical images using personalized, highly secure QR codes (not CDs).
  • Biogen’s new FDA-approved Alzheimer’s disease treatment, Aduhelm, targets and reduces amyloid-beta plaque build-ups in the brain. However, access to the amyloid PET scans needed to diagnose Alzheimer’s and monitor treatment remains insufficient. This GE Healthcare story details the current Alzheimer’s treatment barriers and how PET and Aduhelm could help Alzheimer’s patients avoid deterioration.

You might also like

You might also like..

Select All

You're signed up!

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

-- The Imaging Wire team

You're all set!