|
Imaging in 2022 | CovBaseAI January 3, 2022
|
|
|
|
Together with
|
|
|
“What I’ve learned in the last 24 hours is that radiologists think they are Ernest Hemingway when they are really Great Value brand Dan Brown.”
|
A Tweet from Brent Weinberg, MD on radiologists’ Walmart-brand semantic debates.
|
|
|
Happy New Year, and welcome to the first Imaging Wire of 2022. For those of you working on your annual gameplans, here are some major imaging themes to keep in mind.
COVID Wave Watch – Nothing will have more influence on imaging in 2022 than how / when the COVID pandemic subsides, and how many more waves and variants emerge until we get there.
Efficiency Focus – It’s abundantly clear that imaging must become more efficient, making workflow improvements arguably the top priority for radiology teams and the folks who sell to them.
AI Matures – Imaging AI should mature at an even faster pace this year, bringing greater clinical adoption (and expectations), better workflow integration, improved use cases and business models, and the emergence of clear AI leaders. We’ll also likely see an initial wave of consolidation due to acquisitions and/or VC-prompted shutdowns.
More M&A – Imaging’s extremely active M&A climate should continue into 2022. Based on recent trends, this year’s M&A hotspots are likely to include PE-backed rad practice and imaging center acquisitions, enterprise imaging vendors adding to their tech and “ology” stacks, and more modality and solution expansions from the major OEMs.
Advanced Imaging Advancements – 2022 is shaping up to be a milestone year for MR and CT technology. On the MRI side, recent breakthroughs in magnet strength, helium requirements, portability, and image enhancement (among others) should lead to big changes in how / where MRI can be used. On the CT side, we’ll see OEMs increase their focus on achieving photon-counting CT leadership, even if most of that focus will be from their R&D and future product marketing teams in 2022.
The Patient Engagement Push – Digital patient engagement continues to gain momentum across healthcare, placing pressure on radiology teams to keep up. In 2022, that might mean getting better at radiology’s current patient engagement methods (e.g. image sharing, patient-friendly reporting, follow-up management), although patients’ expectations will likely evolve at an even faster pace.
Imaging Leaves the Hospital – A lot more imaging exams could be performed outside hospital walls in 2022, as payors continue to incentivize outpatient imaging (and image-related procedures) and at-home care continues its massive growth.
While it’s hard to say which, if any, of these trends will be the top story of the next 12 months, it seems likely that we’re heading into another year with more big news than can fit into a seven-bullet roundup. Wishing you the best in 2022, Imaging Wire readers!
|
|
|
Salem Regional’s Case for Bayer
Learn how Salem Regional Medical Center improved its radiology workflows and cut service and syringe expenses after adopting Bayer’s MEDRAD Stellant FLEX system.
|
|
Blackford’s AI Value Matrix
Working out your AI business case? Check out this helpful Blackford Analysis post detailing how to create your AI Value Matrix based on your organizational objectives and value indicators.
|
|
- Annalise.ai Usefulness: A new “real-world usefulness” study (prospective, multi-center, in daily workflow) showed that Annalise.ai’s CXR AI solution led to significant diagnostic changes and was positively viewed by radiologists. Eleven radiologists used Annalise CXR to review 2,972 CXR cases, resulting in 92 significant reporting changes (3.1%) and 43 changes in patient management (1.4%), although the rads rejected 390 AI findings (13%). This was enough for 90% of the radiologists to state that Annalise CXR increased their accuracy and improved their opinions about AI.
- Brain Ultrasound Breakthrough: Penn State and University of Illinois at Urbana-Champaign researchers developed a new ML-based brain ultrasound technique that might lead to more-accessible and radiation-free neuroimaging applications (e.g. vascular maps, active imaging). The researchers recorded ultrasound echos using a model skull and fed it into their ML system, producing skull measurements that closely matched CT for skull thickness (mean error: 0.2mm; 1%) and sound speed (mean error: 25 m/s; 3%).
- Sectra Lands MUSC Health: Sectra announced an enterprise imaging contract with MUSC Health that includes Sectra’s radiology and breast imaging modules, system-wide Epic integration, and a subscription-based structure. This MUSC Health deal wraps up a solid year for Sectra USA that included quite a few new health system logos (MUSC, UNC, Emory, Mary Washington, UCSD Health).
- No GBCA Neurotoxicity: A new Radiology Journal study suggests that gadolinium retention might not have a neurological impact, at least on rats. During a 4-week period, the researchers injected 183 rats 20 times with commercial GBCAs in extremely high doses (80x human equivalent doses) or with saline. In 6- and 34-week follow-up exams, they found no clinical evidence of neurotoxicity, and the highest gadolinium retention among the rats exposed to linear GBCAs.
- PDC vs. Duke: Duke University Health System is being sued by a physician from its associated physician group, Private Diagnostic Clinic (PDC, employs all Duke-associated physicians), claiming that Duke is trying to “destroy” PDC so its physicians have to work directly for Duke (with less pay and independence). After previous attempts to acquire PDC, Duke created an alternative system-owned practice that all Duke physicians must work for if they perform research. The lawsuit alleges that this requirement would initially cost PDC 400 of its 1,850 physicians, threatening PDC’s future viability.
- CovBaseAI: Noting COVID AI’s challenges with data availability and regional generalizability, carpl.ai took a different approach with its CovBaseAI tool, which uses three DL models and an expert decision system (EDS) trained on pre-COVID-19 data (all from outside of India). CovBaseAI was first validated against 1,401 annotated CXRs from Indian patients with suspected COVID, finding that it could triage serious COVID-pneumonia with 87% accuracy and a 98% NPV. Next, its diagnostic accuracy was validated against 905 CXRs from five different Indian datasets (434 diagnosed w/ COVID), achieving 0.66 to 0.90 sensitivity.
- RAYUS’ Twin Expansions: RAYUS Radiology (formerly CDI) continued its expansion, opening two new imaging centers in Minnesota and one new center in Maine. Interestingly, the new locations are in the two states’ respective Twin Cities areas (Maine’s Twin Cities = Auburn and Lewiston). RAYUS is wrapping up an active 2021 that included a big rebranding, at least four territory-expanding acquisitions, and the addition of 21 new imaging centers (now 150 nationwide locations).
- Density + BMI Risk Synergy: A new JAMA study (n = 7.6M South Korean women, 5-10yr study period) found that high breast density and high body mass index “interact synergistically” to increase breast cancer risk. Postmenopausal women with the highest BMI and density levels had a 6.31 adjusted relative risk of developing breast cancer (aRR). That’s 40% higher than postmenopausal women with BI-RADS 2 density and the highest BMI (4.49 aRR) and 25% higher than postmenopausal women with the highest density and normal BMI (5.06 aRR).
- Ezra Reporter: Direct-to-consumer cancer screening company, Ezra, launched its new Ezra Reporter solution that uses AI to convert radiology reports into easy-to-understand patient reports. Ezra will make its new Reporter available to its radiologist network, reducing report turnaround for patients who receive Ezra’s full-body MRI screening exams from 7 to 3 days.
- COVID’s Pediatric Imaging Impact: A new MGH study detailed major shifts in their pediatric imaging utilization during the first 1.5 months of the COVID lockdown. Analysis of 15,424 pediatric imaging exams between September 2019 and May 2020 (1,047 during COVID) revealed that a lower proportion of their COVID-era imaging exams were for adolescents (45.5% vs. 53.3%), used radiography (62.4% vs. 70.4%), or were for non-traumatic pain (39.1% vs. 46.3%). Instead, pediatric imaging shifted towards younger patients (24.3% vs. 17.7%), CT and ultrasound modalities (CT: 7.4% vs. 5.9%; US: 18.3% vs. 13.5%), and oncologic and congenital/developmental disorder indications (8.8% vs. 6.5%; 6% vs. 3.9%).
- EU Approves Microsoft + Nuance: The European Commission unconditionally approved Microsoft’s pending acquisition Nuance Communications, clearing the last major hurdle for the acquisition that is now expected to be finalized in the coming weeks. The investigation found that Nuance’s transcription software for end-users differs significantly from Microsoft’s speech recognition APIs targeted at developers, and that combining the two will not stifle competition.
|
|
What United Imaging’s Software for Life Meant in 2021
Last year, as part of their Software Upgrades for Life commitment, United Imaging upgraded its entire U.S. MR installed base with the latest major releases, including 12 new applications, Windows 10, and its United Compressed Sensing (uCS 2.0) platform.
|
|
- Check out this Imaging Wire Show, featuring Nanox AI strategy leader, Dr. Orit Wimpfheimer, where we discuss building an international telerad practice, what’s wrong with triage AI, and pivoting to population health AI.
- See why Children’s National Medical Center calls Arterys’ Cardio AI 4D flow “an important diagnostic tool that enhances diagnostic sensitivity and has the potential to improve surgical planning and patient outcomes” in this JACC study.
- In this Nuance Q&A, Open System Imaging’s medical director and CTO discuss how adopting PowerScribe One improved the California radiology practice’s efficiency and productivity.
- The USPSTF guidelines for lung cancer screening were updated in May 2021, and driving compliance to such guidelines is a long, slow, repetitive process. Because of that, the Riverain team put together a kit to help hospitals and imaging centers educate either referring physicians or patients on the new guidelines either via branded tools or through the media.
|
|
|
|
|