Medical Imaging in 2022

For our final issue of 2022 we’re reflecting on some of the year’s biggest radiology storylines, including some trends that might have a major impact in 2023 and beyond.

“Post-COVID” – Radiology teams thankfully scanned and assessed far fewer COVID patients in 2022, but the pandemic was still partially responsible for most of the trends included in this recap.

Imaging Labor Crunch – Many organizations still didn’t have enough radiologists and technologists to keep up with their imaging volumes this year, driving up labor costs and making efficiency even more important.

Hospital Margin Crunch – There’s a very good chance that the hospitals you work for or sell to had a tough financial year in 2022, placing greater importance on initiatives/technologies that earn or save them money (and address their labor challenges).

AI Evolution – If a radiology outsider read a random Imaging Wire issue they might think that radiologists already use AI every day. We know that isn’t true, but imaging AI’s 2022 progress suggests that we’re slowly heading in that direction.

New Mega Practice Paradigm – After years of massive national expansions, recent unfavorable shifts in surprise billing reimbursements, radiologist staffing (costs & shortages), and the lending environment seemed to have caused large PE-backed radiology groups to pivot their 2022 strategies from practice growth to practice optimization.

The Patient Engagement Push – Radiology patient engagement gained momentum in 2022, as imaging teams and vendors worked to make imaging more accessible and understandable, more patient-centric imaging startups emerged, and radiology departments continued to get better at follow-up management.

The AI Shakeup – Everyone who has been predicting AI consolidation took a victory lap in 2022, which brought at least two strategic pivots (MaxQ AI & Kheiron) and the acquisitions of Aidence and Quantib (by RadNet), Nines (by Sirona), Arterys (by Tempus), MedoAI (by Exo), and Predible (by nference). This trend should continue in 2023, as VCs remain selective and larger AI players extend their lead over their smaller competitors.

Imaging Leaves the Hospital – Between the surge of hospital-at-home initiatives and payors’ efforts to move imaging exams to outpatient settings, imaging’s shift beyond hospital walls continued throughout 2022 and doesn’t seem to be slowing as we head into 2023.

Spotlight on ED Diagnostics

A new U.S. federal government study made emergency department diagnostic accuracy a mainstream news story, showing that although ED diagnostic errors are somewhat rare, they occur in high volumes and can carry serious consequences. 

The U.S. Agency for Healthcare Research and Quality and Johns Hopkins University teamed up to analyzed 279 international studies published between 2001 and 2021, finding that:

  • Diagnostic errors occur in an estimated 5.7% of ED visits
  • Generalized to the U.S., ED diagnostic errors impact 7.4M patients annually
  • Those diagnostic errors lead to “preventable harms” in roughly 2.6M patients, and “serious harms” in 371k patients, including 250k deaths
  • The top 5 and 15 diseases account for 39% and 68% of “serious misdiagnosis-related harms” 

Although “not all diagnostic errors are preventable,” error rate variations revealed key areas for improvement:  

  • Women and people of color were 20% to 30% more likely to be misdiagnosed
  • Misdiagnosis is far more common among patients with “atypical” and “subtle” disease presentation
  • Hospital and disease-specific error rates varied widely

Imaging played a major role in the study, as most of the top-15 diseases associated with “serious misdiagnosis-related harms” are typically diagnosed with imaging exams (including all of the top-5), and the report mentioned “radiology,” “imaging,” “image,” “scan,” or “ultrasound” a whopping 419 times.

Emergency medicine societies objected to these results, but the consensus among study authors and most observers was that more efforts are needed to understand and address ED diagnostic errors, with a specific focus on the diseases associated with serious misdiagnosis harms.

The Takeaway

Most efforts to improve ED safety over the last 20 years have targeted glaring mistakes (e.g. wrong medications, ED-acquired infections), but this report clearly calls for increased focus on improving EDs’ diagnostic accuracy. 

Those efforts would start at the bedside, but they would definitely involve medical imaging (and potentially error-catching AI tools), especially considering that most of the diseases associated with “serious misdiagnosis-related harms” are diagnosed via imaging.

Federated Learning’s Glioblastoma Milestone

AI insiders celebrated a massive new study highlighting a federated learning AI model’s ability to delineate glioblastoma brain tumors with high accuracy and generalizability, while demonstrating FL’s potential value for rare diseases and underrepresented populations.

The UPenn-led research team went big, as the study’s 71 sites in 6 continents made it the largest FL project to-date, its 6,314 patients’ mpMRIs created the biggest glioblastoma (GBM) dataset ever, and its nearly 280 authors were the most we’ve seen in a published study. 

The researchers tested their final GBM FL consensus model twice – first using 20% of the “local” mpMRIs from each site that weren’t used in FL training, and second using 590 “out-of-sample” exams from 6 sites that didn’t participate in FL development.

These FL models achieved significant improvements compared to an AI model trained with public data for delineating the three main GBM tumor sub-compartments that are most relevant for treatment planning.

  • Surgically targetable tumor core: +33% w/ local, +27% w/ out-of-sample
  • Enhancing tumor: +27% w/ local, +15% w/ out-of-sample
  • Whole tumor: +16% w/ local, +16% w/ out-of-sample data

The Takeaway

Federated learning’s ability to improve AI’s performance in new settings/populations while maintaining patient data privacy has become well established in the last few years. However, this study takes FL’s resume to the next level given its unprecedented scope and the significant complexity associated with mpMRI glioblastoma exams, suggesting that FL will bring a “paradigm shift for multi-site collaborations.”

Canon’s Meaningful RSNA Innovations

After taking a virtual approach to RSNA last year, Canon Medical Systems made its presence felt at RSNA 2022, unveiling an interactive “digital patient journey” booth that featured an interesting mix of new products and business model innovations. 

SP MRIs – Canon unveiled SP-suffix configurations of its Vantage Orian and Galan MRIs (1.5T & 3T), adding new features intended to enhance MRI team efficiency (tablet UX interface, intelligent Ceiling Camera), while making a number of its image quality and productivity-focused solutions standard (AiCE DLR, Fast 3D acceleration, ForeSee View automation).

Mobile XR – The new Mobirex i9 brings a rare update to Canon’s U.S. mobile X-ray lineup, launching with an emphasis on its small size, mobile/flexible design, and its use of Canon’s next-gen CXDI-Elite wireless detectors.

Mobile MI – In a different type of mobile expansion, Canon launched a mobile version of its Cartesion Prime Digital PET/CT, which seems to be a good fit for mobile coaches given its Air Cooled technology and small footprint (fits in 3.15×7.1 meters).

Future Proof Packages – Canon rolled out its interesting new Non-Obsolescence Program, which allows CT and MRI customers to purchase an up-front package that gives them access to all future hardware, software, and service options as they become available. The program covers five years of upgrades, and is priced well below what users would pay if they ordered each item individually.

Glassbeam Clinsights – Canon’s Inclusive Analytics Suite added Glassbeam Clinsights Utilization Analytics, which analyzes DICOM and HL7 data to help Canon service customers understand imaging utilization and productivity levels across their fleets (multi-modalities and vendors).

GE Focuses on Efficiency at RSNA 2022

GE Healthcare had yet another busy RSNA, highlighted by several major launches, and its continued focus on helping imaging teams work more efficiently.

MRI Efficiency – GE’s biggest RSNA launches were in its MRI lineup, and those new launches placed a direct target on workflow, resource, and cost efficiency.

  • GE launched its SIGNA Experience MRI platform, which positions the new SIGNA One user interface as a “cornerstone” for managing a range of GE MRI technologies (AI, DLIR, technologist workflow solutions, AIR Coils), and simplifying MRI operations.
  • GE also unveiled its forthcoming SIGNA Victor MRI (1.5T, 60cm), which will feature the new SIGNA Experience platform, and consumes significantly less power and helium (-10% & -70%).

Future-Forward CT – While GE Healthcare’s CT booth was highlighted by the modular/scalable Revolution Apex platform that launched at RSNA 2021, this year’s event brought news that GE’s latest photon counting CT prototype is beginning clinical evaluations at the University of Wisconsin–Madison (its first U.S. evaluations).

Partnership Plays – GE also announced a pair of partnerships that expand its capabilities beyond the scanners and solutions that it’s known for.

  • GE Healthcare unveiled its OmnifyXR Interventional Suite augmented reality solution, which it co-developed with MediView to support IR visualization and remote collaboration.
  • GE also entered the contrast media injector segment, signing an agreement with ulrich medical that will allow GE to sell the GE-branded CT Motion multi-dose syringeless CT contrast injector in the US.

Much More – GE Healthcare has been busy throughout 2022, so although the other products in its booth were still quite new, they’ve already been detailed in recent Imaging Wire issues. That includes the Definium 656 HD X-ray system, Omni Legend PET/CT, LOGIQ Fortis ultrasound, and the PACS-based intelligent workload management solution.

The Imaging Wire’s RSNA 2022 Reflections

RSNA 2022 is officially a wrap. We hope you had a blast if you made it, and had a great week if you stayed home. We also hope you enjoy our recap of radiology’s most important event in at least three years.

Crowds & Conversations – RSNA’s attendance and overall energy continued to trend upward, as most of the 31k people on-site were super engaged and truly excited to be there. Although attendance was still well below RSNA 2019 (~49k on-site), it was a big jump from last year (~23k on-site), and infinitely better than 2020’s virtual RSNA.

Much Rad Love – If you had “I’m not a radiologist but…” on your RSNA bingo card you’d be in a good spot, because the exhibit hall was full of non-rads talking about how to help radiology teams be more effective and more satisfied.

Focus on Productivity – Perhaps due to all that vendor empathy, just about every new product (hardware and software) focused on eliminating steps / clicks / interruptions, improving workflow integration, alleviating burnout and labor challenges, and better matching diagnostic processes.

Getting Cloudy – There’s no debate that imaging’s shift to the cloud was one of RSNA’s top trends, as informatics vendors continued to strengthen their cloud capabilities and expand their list of cloud-based customers (especially if you include hybrid). There were, however, plenty of debates about who’s cloud tech is truly native and who’s aren’t.

AI’s Two Sides – It seems like many folks are still in AI’s “trough of disillusionment,” as conversations often drifted towards problems with AI’s performance, use cases, funding climate, and provider ROI. However, AI adoption has never been wider, AI products have never worked better, and there are plenty of AI trends to be excited about…

  • AI is becoming less narrow
  • AI workflow integration keeps getting better
  • More radiologists are interested in AI
  • There’s solid traction with operational and efficiency AI
  • We’re not talking about AI replacing radiologists (as much)

Modality Progress – Although there were only a handful of completely new scanners at RSNA, the major OEMs showed continued advancements in MR (image quality, low-helium, low-field, reconstruction, coils) and CT (spectral, photon-counting, upgradability), while nearly all scanners took big strides in operator efficiency.

The Takeaway

Radiology faces plenty of challenges, but it’s populated by some of the smartest people in medicine/medtech who are working hard to solve those challenges. Hats off to the RSNA team for getting all the smart people together every year to push those solutions forward.

Get every issue of The Imaging Wire, delivered right to your inbox.

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!