“This is becoming a pandemic of the unvaccinated.”
CDC director, Dr. Rochelle Walensky, at least week’s White House COVID-19 Response Team briefing.
Check out the latest Imaging Wire Show, featuring Zebra Medical Vision’s CMO and strategy leader, Dr. Orit Wimpfheimer. We discuss building an international telerad practice, what’s wrong with triage AI, and Zebra-Med’s population health AI pivot.
Imaging Wire Sponsors
Arterys | Bayer Radiology | Canon Medical Systems
Fujifilm Healthcare Americas | GE Healthcare |
Healthcare Administrative Partners | Novarad | Nuance
Riverain Technologies | Siemens Healthineers
United Imaging | Zebra Medical Vision
The Imaging Wire
Viz.ai and Avicenna.AI Coordinate Care
Viz.ai will make Avicenna.AI’s detection tools for pulmonary embolism and aortic dissection available on the Viz Intelligent Care Coordination platform, representing a new and interesting kind of AI alliance.
- The Combined Solution – The two Avicenna.AI tools will become part of Viz.ai’s Aortic and PE modules, with Avicenna.AI handling detection and Viz.ai supporting downstream clinical communications and decision making.
- Viz.ai, a Care Coordination Company – In the announcement, Viz.ai dubbed itself “the world leader in AI-driven intelligent care coordination,” suggesting that Viz.ai plans to keep adding to its portfolio of care coordination modules and partners. That strategy makes sense, given that Viz.ai already has a proven care coordination platform that could apply to a wide range of acute findings.
- An AI Alliance Trend – We’re starting to see more complementary AI alliances that either combine triage/detection with care coordination (like Avicenna.AI & Viz.ai) or combine triage/detection with downstream analysis/assessment (Aidoc & icometrix’s new stroke suite). This trend also makes sense, given that partnerships like these could help make AI solutions more compressive and actionable.
Regulating Service with Bayer & MITA
Check out this Imaging Wire Q&A, where Bayer Radiology’s Dennis Durmis and MITA’s Peter Weems discuss the medical device service debate and how ongoing legislation and regulation efforts could impact patients, clinicians, and OEMs.
About the AI CPT Codes
When the AMA announced its first imaging AI CPT codes earlier this month, it generated a lot of excitement and also led to some confusion about what these codes mean for providers and developers. Here’s some clarifications:
- Data Collection Codes – The Category III CPT codes are intended to help collect clinical data for emerging technologies / procedures (including AI). This data would be used to support future coverage and regulatory decisions.
- No RVUs – These codes don’t have assigned RVUs, and reimbursements would be up to the payors. However, some online reports suggest that physicians can reference similar Category I procedures when reporting Category III CPT codes.
- Still an AI Milestone – This is definitely still a milestone for imaging AI, as clinical data collection will be crucial for qualifying for CPT Category I codes in the future.
CVIS’ Cloud Advantages
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.
- MIT’s Double Agent: MIT researchers created a new diagnostic nanoparticle that can detect cancer when used both in a PET imaging agent and in a urine test. Recovering cancer patients would regularly undergo urine tests, and if they receive a positive result, they’d undergo a PET exam to confirm if or where the cancer has spread. Their initial study showed that this approach can effectively monitor colon cancer progression (including metastasis to lung and liver), and they hope it can eventually be used in population-scale routine cancer screening.
- Canon & Cleerly: Canon Medical Systems and Cleerly launched a partnership that will combine Cleerly’s heart disease digital care pathway with Canon’s cardiac CT systems, offering the solution through Canon’s US salesforce. Cleerly launched last month with the goal of bringing heart disease diagnosis and prevention into the twenty-first century, and now it has a very big partner to help work towards that goal.
- CAC Categorization: CTC-based coronary artery calcium (CAC) scoring could be a valuable supplement to traditional cardiovascular disease risk factors (e.g. family history, kidney disease, etc.) for identifying patients who would benefit from statin therapy. That’s from a new JAMA study (n = 1,688 w/ intermediate risk) that found CAC scoring would significantly improve cardiovascular risk assessments. For example, patients with CAC scores of 0 experienced <7.5 cardiovascular incidents per 1k years, even if other traditional factors would have miscategorized these patients as higher-risk.
- Probo on the Block: Probo Medical’s PE parent company, Varsity Healthcare, is reportedly making the imaging parts/service/device company available for acquisition. Probo hits the market as a much different company than when Varsity acquired it in late 2018. Probo’s six acquisitions since then expanded the ultrasound and U.S.-focused company into new modalities, service lines, and geographies, while significantly increasing its EBITDA (~$7m to ~29m).
- DVT Agent Breakthrough: Penn State researchers developed a new ultrasound agent that could improve deep vein thrombosis imaging, and might even become a DVT treatment. The new nanopeptisome-based agent binds to the surface of blood clots, creating “excellent” image contrast during ultrasound exams. During testing, they found that the novel agent also counteracted the enzymes used to create blood clots in clinical trials, indicating that it could also stop blood clot growth.
- Funding The Non-Physician Fight: The ACR bolstered its efforts to protect radiology from non-physicians’ potential encroachment into image interpretation, establishing the ACR Scope of Practice (SOP) Fund. Starting with a $225k warchest, the SOP will lobby state and federal lawmakers about the risks of non-physician interpretations, noting that non-physician societies are similarly working to expand RNs and PAs into image interpretation.
- Multimodal COVID AI: A new study out of China detailed a COVID detection workflow that combines machine learning-based blood sample analysis with human radiologists’ CXR interpretations. The blood test ML model (Sensitivity: 55.5% – 77.8%; Specificity: 91.5% – 98.3%) and the human radiologists (Sensitivity: 53.8% – 55%; Specificity: 74.5% – 95.1%) struggled with sensitivity when used independently against three test sets. When they were combined, the workflow achieved significantly improved sensitivity (92.3% – 92.5%), but significantly lower specificity (52.7% – 66.7%).
- Imaging SPACs: PoC MRI leader Hyperfine and cardiac AI heavyweight HeartFlow will go public through a pair of SPAC mergers (SPAC = special purpose acquisition company), giving the companies significantly more funding and highlighting SPACs’ growing role as imaging startups’ path to public listings. Hyperfine will merge with non-invasive brain monitoring company Liminal Sciences and HealthCor Catalio Acquisition Corp, giving it a $580m enterprise value and $375m in the bank. HeartFlow will merge with Longview Acquisition Corp, giving a $2.4b enterprise value and $400m in the bank.
- COVID PE Prevalence: A new Radiology Journal study (n = 413) found that 25% of hospitalized COVID-19 patients with suspected pulmonary embolism were diagnosed with PE following CTPA or perfusion scintigraphy exams. The study also revealed that COVID-19 patients with D-dimer levels above 1600 ng/mL were far more likely to have PE (100% sensitivity, 62% specificity), suggesting that the blood test can help identify which COVID patients need CTPA.
- Female Physicians Order More Imaging: Female physicians order more imaging exams than their male colleagues. That’s from a new JAMA study out of Canada (n = 171k hospitalized patients, 171 physicians) that found female doctors ordered more CTs (54.8% vs. 52% of patients), MRIs (11.1% vs. 10.2%), X-rays (81.4% vs. 80.7%), and ultrasounds (31.7% vs. 29%). Female physicians also had lower in-hospital mortality rates (4.8% vs. 5.2%, statistically insignificant) and higher median costs per patient admission ($4.694 vs. $4,386).
- MPFS Cuts: CMS’s proposed 2022 MPFS would cut overall radiology reimbursements by 2%, with the greatest impact on interventional radiology (-9%). This is a lot better than the 10% cut radiology was supposed to receive in 2021 (revised to -4% due to COVID), although the ACR and other healthcare societies will fight these proposed cuts once again.
- Curbing CTPA Overuse: In order to curb CTPA overuse for suspected pulmonary embolism (PE), health systems should introduce strict D-dimer threshold requirements (vs. just recommendations). That’s from a new Hawaii Permanente study that measured its ED’s CTPA utilization and PE diagnosis rates after introducing a ≥ 1.0 μg/mL D-dimer recommended threshold (n = 6,013 CTPA studies). Over the next 8 years, 42.5% of patients didn’t receive pre-CTPA D-dimer tests (7.3% positive rate), 40.2% had D-dimer results above the 1.0 μg/mL recommended threshold (10.6% positive rate), 17.2% had D-dimer results below the 1.0 μg/mL threshold (0.6% positive rate).
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.
The Resource Wire
- This American College of Cardiology case report details how Arterys’ 4D flow enhances visualization of blood flow and pulmonary venous anatomy in cardiac MRI, improving diagnosis and surgical planning for partial anomalous pulmonary venous return.
- Check out this blog from the NIH’s Dr. Francis Collins, where he discusses how United Imaging’s “groundbreaking” Explorer total-body PET/CT “opens a new window into human biology.”
- Make quick and well-informed decisions by having a clear overview of your clinical and operational performance data with Siemens Healthineers’ teamplay.
- 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 than CDs).
- Tune into this Nuance and ITN webinar on August 5th, where they’ll discuss how AI is supporting radiologists, and how AI outputs are informing providers and specialists across the care continuum.
- Independent and staying that way? Healthcare Administrative Partners just released a helpful set of guidelines that radiology practices can follow to stay private despite ongoing consolidation pressures.
- See what early users of GE Healthcare’s new StarGuide SPECT/CT have to say about how the system is bringing quantitative SPECT/CT into routine clinical practice.
- 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.
- This Riverain Technologies case study details how the University of Colorado Hospital enhanced its chest X-ray workflow with ClearRead Bone Suppress.