Roxana Daneshjou, MD on AI research’s incentive problem.

Imaging Wire Sponsors

annalise.ai  •  Arterys  •  Bayer  •  Blackford  •  Canon Medical  •  CARPL.ai  •  Change Healthcare  •  Enlitic  •  GE Healthcare  •  Hyperfine  •  Intelerad  •  Novarad  •  Riverain Technologies  •  Siemens Healthineers  •  United Imaging  •  Us2.ai

We’re excited to share The Imaging Wire’s interview with United Imaging CEO, Jeffrey Bundy, who details company culture’s central role in medical imaging and how to build, improve, and maintain culture. If you’re ready to improve your organization’s culture, this interview is a great way to start.

Artificial Intelligence

Plaque AI’s First Reimbursement

The small list of cardiac imaging AI solutions to earn Medicare reimbursements just got bigger, following CMS’ move to add an OPPS code for AI-based coronary plaque assessments. That represents a major milestone for Cleerly, who filed for this code and leads the plaque AI segment, and it marks another sign of progress for the business of imaging AI.

With CMS’ October 1st OPPS update, Cleerly and other approved plaque AI solutions now qualify for $900 to $1,000 reimbursements when used with Medicare patients scanned in hospital outpatient settings. 

• That achievement sets the stage for plaque AI’s next major reimbursement hurdle: gaining coverage from local Medicare Administrative Contractors (MACs) and major commercial payers.

Cleerly and its qualifying plaque AI competitors join a growing list of Medicare-reimbursed imaging AI solutions, headlined by HeartFlow’s FFRCT solution ($930-$950) and Perspectum’s LiverMultiScan MRI software ($850-$1,150), both of which have since expanded their reimbursements across MAC regions and major commercial payers. 

• The last few years also brought temporary NTAP reimbursements for Viz.ai (LVO detection / coordination), Caption Health (echo AI guidance), and Optellum (lung cancer risk assessments), plus a growing number of imaging AI CPT III codes that might lead to future reimbursements.

The new reimbursement should also drive advancements within the CCTA plaque AI segment, giving providers more incentive to adopt this technology, and providing emerging plaque AI vendors (e.g. Elucid, Artrya) a clearer path towards commercialization and VC funding.

The Takeaway

CMS’ new plaque AI OPPS code marks a major milestone for Cleerly’s commercial and clinical expansion, and a solid step for the plaque AI segment. 

The reimbursement also adds momentum for the overall imaging AI industry, which finally seems to be gaining support from CMS. That’s good news for AI vendors, since it’s pretty much proven that reimbursements drive AI adoption and are often necessary to show ROI.

Ready to overcome the worklist paradox of choice?

See how GE Healthcare’s Intelligent Workload Manager eliminates case selection decision-making burdens and helps reduce radiologist stress.

What’s Next for Imaging AI Regulations?

Healthcare AI’s rapid evolution continues to challenge FDA regulators, leading to new AI frameworks and action plans, and a growing list of questions from AI developers and users. In this editorial, Intelerad’s A.J. Watson answers those questions and details a path forward that supports both AI regulations and innovations.

The Wire

• Yunu Unifies: Clinical trials imaging company Yunu announced the completion of its Series A round and revealed its ambitious plan to solve clinical trials’ imaging problem. Yunu’s client roster already includes 16 cancer centers and one pharma company, who are using its platform across over 2,500 clinical trials and 8,000 connected sites. That’s a fast start for a company that just came out of stealth, although its leadership team definitely aren’t imaging workflow newcomers.

• Simultaneous CTs: A new Nature study highlighted a German hospital’s innovative dual-room CT setup, that uses a movable sliding CT gantry to diagnose and treat two trauma patients simultaneously (check out the study’s images). The 46 patients who were examined simultaneously (10.9% of patients) and 377 patients examined individually had similar median times from arrival to CT (8 vs. 6 min) and times to emergency surgery (99 vs. 90 min), with no significant differences in treatments, mortality rates, and delayed and missed diagnoses.

• AI Research’s RCT Gap: Out of over 28k healthcare AI studies performed from 2012 to 2021, only 41 were randomized clinical trials (RCTs), and none adhered to the CONSORT-AI reporting guidelines. The good news is AI RCTs are becoming more common (36 of the 41 were from 2019-2021) and most of the RCTs had a low risk of bias, although only 11 of the trials reported race/ethnic data. The study and some passionate online conversations blamed AI’s research-to-clinic translation gap on this lack of RCTs.

• GE’s AIR Recon DL Expansion: GE Healthcare’s AIR Recon DL gained an additional FDA clearance that covers 3D and PROPELLER imaging sequences, expanding the image reconstruction solution’s time and image quality advantages to “nearly all” MRI procedures. GE highlighted 3D sequences’ clinical efficiency advantages (eliminates need for multiple 2D acquisitions), and PROPELLER’s support for anatomies susceptible to motion and for patients who have difficulty remaining still (it’s a motion-insensitive sequence).

• CMRI LV Signature Risk Predictions: Machine learning-based cardiac MRI left ventricular (LV) shape signatures could help identify higher-risk atherosclerosis patients. Among 4.6k patients with atherosclerosis, analysis based on LV shape signatures and clinical risk factors was more accurate than standard cardiac MRI metrics for predicting heart failure (AUCs: 0.83 vs. 0.81), coronary heart disease (0.77 vs. 0.75), and cardiovascular disease (0.78 vs. 0.76) over 10 years. Patients who the LV signatures identified as “high risk” had far lower survival rates than “low risk” patients (56% vs. 95%).

• A Case for LiverMultiScan: A new BMJ study highlighted Perspectum Diagnostics’ mpMRI-based LiverMultiScan solution’s economic advantage for monitoring patients with autoimmune hepatitis (AIH). By reducing or eliminating regular biopsies over a five-year monitoring period, LiverMultiScan screening would avoid between £121k (10 scans in 5yrs) and £232k (5 scans in 5yrs) in healthcare costs for every 100 moderate/severe AIH patients, and between £73k (6 scans in 5yrs) and £139k (3 scans in 5yrs) for every 100 mild/moderate AIH patients

• Philips’ Compact US Clearance: Philips announced the FDA clearance of its 5000 Compact Series ultrasound system, highlighting its small size, high image quality, and clinical versatility (point of care, cardiology, general imaging, OBGYN). The 5000 Compact Series supports Philips’ tele-ultrasound solution and ultrasound workflows, and adopts many features found in Philips’ established EPIQ and Affiniti ultrasound lineups (e.g. UI, transducers, workflows).

• The EU’s Cancer Screening Ambitions: The EU unveiled an ambitious new cancer screening plan that covers a broader list of cancers, includes a wider group of patients, and should significantly increase screening volumes. The new approach expands breast cancer screening ages (45-75yrs vs. 50-69yrs), increases HPV and colorectal cancer screening frequency, and creates population screening programs for lung, prostate, and gastric cancers.

• ScreenPoint’s New Medical Advisory Board: ScreenPoint Medical announced the formation of its Medical Advisory Board, featuring breast imaging leaders who will share their expertise and help guide ScreenPoint’s products and strategy. The international advisory board will include Dr. Jennifer Harvey from the University of Rochester, Dr. Laurie Margolies from Mount Sinai Health System, and Dr. Ritse Mann from Radboud University Medical Center in the Netherlands. 

• FDA Final AI Guidance: The FDA meant business last week, releasing several dense documents outlining how it will regulate different medical technologies. The most notable was the agency’s final guidance on what kinds of clinical decision support software and AI tools fall under its jurisdiction, and it laid out four nuanced criteria to determine its oversight (section IV on page 3). Although the regulatory jargon is a little tough to wade through, medical imaging solutions and sepsis alerts tools are specifically called out as requiring oversight.

• Automated LDCT CAC Scoring: South Korean researchers demonstrated a commercially-available automated coronary artery calcium scoring solution’s ability to accurately produce CAC scores using low-dose CTs (LDCTs). The researchers performed automated CAC scoring on 567 ECG-gated CTs and LDCTs, finding that auto CAC scores from the gated CTs, LDCTs with 1mm slices, and LDCTs with 2.5mm slices closely matched manually-produced gated-CT CAC scores (ICCs: 1.000, 0.937, 0.955). The automated 1mm and 2.5mm LDCT CAC scores also accurately detected patients with ≥ 400 Agatston calcium scores (F1 scores: 0.929 & 0.855).

• ADMdx’s TBI Grant: ADM Diagnostics (ADMdx) secured a $1.96M, 2-year NIH grant to develop a diagnostic test that assesses the effects of repeated traumatic brain injuries and differentiates TBI from Alzheimer’s disease. ADMdx’s TBI tools will combine brain imaging and blood biomarkers, potentially allowing clinicians to detect early signs of TBI-driven diseases and evaluate progression, while supporting the development of new treatments.

Exploring Calantic Digital Solutions

Bayer’s cloud-based Calantic Digital Solutions AI platform features a suite of disease-specific AI apps that integrate into radiologist workflows, helping radiology teams scale AI deployment and improve efficiency and quality of care.

Scaling AI with the Cloud

Trying to figure out how your IT resources can handle increased AI adoption? This Blackford paper details how the cloud is helping radiology organizations scale their computing resources to support multiple AI applications or algorithms.

The Resource Wire

• See why radiologist Dr. Eleanna Saloura called Arterys’ Lung AI solution “a fast and reliable second opinion” for chest CT lung nodule analysis and tracking, allowing “more accurate diagnostic and treatment decisions.”

• Did you know one quarter of healthcare organizations have experienced a cyber-attack in the last year? This Change Healthcare animation explains how 3rd-party certified cloud-native enterprise imaging can help secure IT infrastructure that might be exposed with re-platformed imaging systems.

• When Geisinger Health set a goal to improve access to care, it leveraged Siemens Healthineers’ syngo Virtual Cockpit to ensure that its expert radiologic technologists were accessible to all 11 of its radiology facilities. See what Geisinger’s technologists and administrators had to say about how the remote scanning solution allowed them to extend hours and improve patient throughput.

• Check out this Imaging Wire Show featuring Us2.ai’s co-founders, James Hare and Carolyn Lam MBBS, PhD, detailing Us2.ai’s unique origins, impressive capabilities, and big goals to automate echocardiography reporting across the world.

• United Imaging’s “all-in” approach means that every system ships with its entire suite of features and capabilities (no options), giving its clients more clinical flexibility and predictability.

• See how Dubai-based healthcare leader Aster DM Healthcare leveraged the CARPL platform to connect its doctors, data scientists, and imaging workflows, and support its AI projects and development infrastructure.

• This Riverain Technologies case study details how Einstein Medical Center adopted ClearRead CT enterprise-wide (all 13 CT scanners) and how the solution allowed Einstein radiologists to identify small nodules faster and more reliably.

• See Dr. Brian Goldner of UC Davis Sacramento detail his experience with Canon’s Ultra High Resolution CT and how it can be applied to cardiothoracic interpretations.

• Do your patients text more than they use CDs? Find out how Novarad’s CryptoChart simplifies image access, combining secure QR codes and text and email communications to help providers and patients ditch the disk.

• Hyperfine’s Swoop Portable MR Imaging System is redefining MR accessibility, deploying MR-enabled decision-making across clinical settings within minutes. But do you know how the Swoop is actually being used? Check out this clinical case study detailing the settings and patient scenarios that the Swoop is supporting today.

• Annalise CXR detects up to 124 findings in a single chest X-ray. See how it detects such a wide range of abnormalities using these demo studies…  or upload your own CXR images.

• Discover how Enlitic’s Curie|ENDEX application transforms medical imaging data to a standard nomenclature to form a foundation for successful artificial intelligence strategies.