“It’s not going away. You’re just going to keep hearing about it more and more.”
Hi everyone, we have a few big announcements that we’re excited to share with you…
First, we’re honored to welcome Blackford Analysis as an Imaging Wire sponsor. It’s become super clear that Blackford “gets” imaging AI from a business, clinical, and IT perspective and we’re really looking forward to sharing their insights with you.
We’re also thrilled to introduce our second newsletter, the Digital Health Wire. Starting today we’ll be delivering the most important news in digital health (e.g. telehealth, apps, platforms, patient engagement) — curated and written with the typical “Wire” style you’re familiar with.
The first edition hits inboxes in just a few hours, so if you’re interested in digital health, sign up to get the Digital Health Wire today.
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
The AI Patient Pipeline
Last week’s imaging news cycle revealed that there might be a growing trend towards alliances between AI developers and downstream pharma / medtech companies, where the primary goal is to drive treatment demand (more diagnoses = more patients to treat).
- A Big Alliance Week – Last Thursday’s Imaging Wire detailed alliances between Aidence and AstraZeneca (lung cancer detection + drug treatment) and Imbio and Olympus (emphysema detection & device treatment), plus a forecast from Signify Research suggesting that we’ll see more of these kinds of alliances.
- Pipeline Alliance History – Last week might be an outlier, but this trend has been forming for a while. Over the last few years, we’ve also seen AI diagnosis / treatment pipeline alliances from Qure.ai and AstraZeneca (also lung cancer), Viz.ai and Medtronic (stroke), RapidAI and Penumbra (pulmonary embolism), and almost certainly others.
Using AI to identify more patients in need of specific treatments is a much different type of ROI than the AI industry usually talks about (physician efficiency, patient outcomes, etc.), but it also makes a lot of sense given AI’s current reimbursements/evidence challenges, and it seems like a growing number of vendors agree.
Canon and UCD’s Ultra High Resolution CT Experience
See Dr. Brian Goldner, MD of UC Davis Sacramento detail his experience with Canon’s Ultra High Resolution CT and how it can be applied to cardiothoracic interpretations.
What to Expect from Fujifilm Healthcare Americas
Check out this Imaging Wire Show interview with Fujifilm Healthcare Americas’ Dave Wilson, detailing what we can expect as Hitachi Healthcare becomes part of Fujifilm.
- Exo’s $220m: Exo continued its impressive fundraising progress, completing a massive $220m Series C round (total now >$320m) that it will use to fund its handheld ultrasound’s commercial rollout. There are already some big names competing in the handheld ultrasound segment, but Exo contends that its ultrasound’s “unrivaled” advantages (image quality, definition/ depth, affordability, design) and straightforward workflow will allow it to lead handheld POCUS’ expansion across healthcare. It seems Exo’s VC backers agree.
- TB CAD Outcomes: A new McGill study found that CXR AI tools from Qure.ai, Delft Imaging, and Lunit detected Tuberculosis in four CXR datasets with high enough pooled sensitivity (90%) to suggest that these tools would produce similar outcomes as human readers (despite low specificity: 54.1% – 60.5%). Qure.ai’s qXR achieved slightly higher overall accuracy than the Delft and Lunit tools (AUCs: 0.85, 0.83, 0.83).
- Unnecessary Warming: A new AJR study suggests that warming the CT contrast agent, iohexol 350 (Omnipaque), to body temperature might not reduce adverse reactions enough to justify the required resources. The analysis of patients administered room and body-temperature Omnipaque (n = 3,933 & 3,939) revealed statistically similar adverse reaction rates (0.43% vs. 0.28%). However, all four “allergic/allergic-like” reactions occurred with room temperature contrast.
- ScreenPoint’s $28M: ScreenPoint Medical wrapped up a $28m Series C round (total now $33m) that it will use to “accelerate” its Transpara AI breast care software’s commercial growth, fund R&D, and expand its product portfolio. ScreenPoint’s list of Series C funders happens to include major U.S. radiology practice University Radiology Group (URG) and Siemens Healthineers, giving the startup additional industry and clinical clout as it works to further expand its US presence.
- X-Ray Plans: A new IMV Medical survey (n = 294) revealed that “most” US hospitals plan to acquire a new x-ray system in the next three years, although demand appears down from previous surveys. Eighty percent of these new x-ray systems will replace existing units, while “only a fraction” will go to locations that don’t currently have onsite X-rays.
- Redundant Imaging: A new JACR study detailed the rise of “redundant” emergency imaging for patients with transient ischemic attack strokes (TIA, or “mini strokes”). The rate of redundant TIA brain imaging scans in US EDs increased from 2.3% of encounters in 2006 to 30% in 2017 (that’s 55k cases w/ redundant imaging in 2017), leading to $8.67m in additional charges.
- Volpara’s VIS 3.2 FDA: Volpara Health announced the FDA approval of its latest-generation Volpara Imaging Software for breast density assessments (VIS 3.2). The new version now incorporates AI learnings, expands compatibility to Giotto and Siemens systems, and includes Volpara’s Open Virtual Appliance (OVA) architecture (increases security, improves software monitoring / service / updating capabilities).
- Telerad Surge Predictor: A new Insights into Imaging study found that emergency CT teleradiology volumes can accurately predict regional COVID surges. The researchers compared central France’s COVID data and telerad CT volumes between March and November 2020, finding that the two trends “were almost perfectly superimposed.” For example, hospitalizations peaked (23,542 patients) one week after the highest weekly telerad CT volumes (1,086 exams).
- Lunit CXR Evidence: A new study from Lunit and MGH showed that Lunit’s INSIGHT CXR algorithm improved radiologists/residents’ ability to detect lung cancer in CXRs, leading to more accurate chest CT recommendations. The study had five radiologists and three residents interpret 519 images from the NLST dataset (with and without AI support), finding that Lunit CXR allowed the residents to recommend more chest CTs for patients with visible lung cancer (54.7% vs. 70.2%) and reduced the radiologists’ unnecessary chest CT recommendations (16.4% vs. 11.7%).
- MPFS 2022, Detailed: Healthcare Administrative Partners provided a complete overview of how CMS’ proposed 2022 Medicare Physician Fee Schedule (MPFS) might impact radiology, including more reimbursement cuts (diag. radiology -2%, IR -9%) but relatively few overall changes. HAP also highlighted potential changes to AUC penalties (delayed to 2023), PET imaging (expanded to non-oncologic patients), direct payments to Physician Assistants (CMS would allow it), and QPP weighting (more focus on cost).
- CB-CT for LVO: Performing Cone Beam CT scans on emergency stroke patients in the angiosuite (and skipping the CT room) could allow faster thrombectomies and improved outcomes. That’s from a new study out of Canada (pages 14-15) that compared CB-CT and CT scans from 105 patients with acute ischemic / large vessel occlusion strokes who received thrombectomies, finding that CB-CT effectively supports pre-treatment stroke assessments (excludes hemorrhages, defines stroke core, demonstrates brain perfusion & collaterals).
Arterys’ AI Journey
Check out this Imaging Wire Q&A, where Arterys CEO John Axerio-Cilies, PhD discusses medical imaging’s AI and cloud evolution and how Arterys works with its Center of Excellence partners to make AI real.
The Resource Wire
- 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.
- See how Einstein Healthcare Network reduced its syringe expenses, enhanced its syringe loading, and improved its contrast documentation when it upgraded to Bayer Radiology’s MEDRAD Stellant FLEX CT Injection System.
- Despite significant interest, there’s still confusion about the value of imaging AI. This Blackford Analysis white paper explores the key cost considerations and ROI factors that radiology groups can use to figure out how to make AI valuable for them.
- Are you at AHRA 2021? Swing by Riverain’s booth (#310) to learn how you can optimize your lung disease detection using your existing acquisition and workflow. Bonus: they’re near the dessert table.
- 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 peer-reviewed manuscript published in Magnetic Resonance in Medicine proposed a fast single-shot imaging technique, COEPI, demonstrating its SNR benefit with reduced TE at 1.5T and 3.0T. They also showed the feasibility of DWI using COEPI at 3.0T, while finding that COEPI’s reduced TE makes it a promising sampling technique for other MRI applications, including arterial spin labeling.
- Siemens Healthineers’ MAGNETOM Free.Max is the world’s first MRI with an 80 cm bore that is improving the patient experience. See how it is breaking barriers in MRI.
- 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.
- 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.