Change Healthcare’s Sonia Gupta, MD on why providers should look beyond AI success stories when evaluating new AI solutions.

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

If you’re planning your first (or next) AI implementation, you should check out the latest Imaging Wire show featuring Change Healthcare CMO, Sonia Gupta, MD. We take a deep dive into AI adoption, including how to select and evaluate your AI tools, work with your vendors, and navigate the adoption process.

Cardiac Imaging

Echo AI Detects More Aortic Stenosis

A team of Australian researchers developed an echo AI solution that accurately assesses patients’ aortic stenosis (AS) severity levels, including many patients with severe AS who might go undetected using current methods.

The researchers trained their AI-Decision Support Algorithm (AI-DSA) using the Australian Echo Database, which features more than 1M echo exams from over 630k patients, and includes the patients’ 5-year mortality outcomes.

Using 179k echo exams from the same Australian Echo Database, the researchers found that AI-DSA detected…

• Moderate-to-severe AS in 2,606 patients, who had a 56.2% five-year mortality rate
• Severe AS in 4,622 patients, who had a 67.9% five-year mortality rate

Those mortality rates are far higher than the study’s remaining 171,826 patients (22.9% 5yr rate), giving the individuals that AI-DSA classified with moderate-to-severe or severe AS significantly higher odds of dying within five years (Adjusted odds ratios: 1.82 & 2.80).

AI-DSA also served as a valuable complement to current methods, as 33% of the patients that AI-DSA identified with severe AS would not have been detected using the current echo assessment guidelines. However, severe AS patients who were only flagged by the AI-DSA algorithm had similar 5-year mortality rates as patients who were flagged by both AI-DSA and the current guidelines (64.4% vs. 69.1%).

Takeaway

There’s been a lot of promising echo AI research lately, but most studies have highlighted the technology’s performance in comparison to sonographers. This new study suggests that echo AI might also help identify high-risk AS patients who wouldn’t be detected by sonographers (at least if they are using current methods), potentially steering more patients towards life-saving aortic valve replacement procedures.

Novarad VisAR’s Precision Guidance

Check out this Imaging Wire Show featuring Novarad founder and CEO, Wendell Gibby, MD, exploring Novarad’s technological evolution and how its recent augmented reality expansion is bringing medical imaging into completely new clinical settings.

Arterys’ Top 2022 Imaging Trends

With ongoing radiologist shortages and higher rates of burnout, there’s a great need for fast, effective, efficient medical imaging technologies – and those factors are driving 2022’s major medical imaging trends detailed in this Arterys report.

The Wire

• Down on MOCs: An ACR survey highlighted radiologists’ largely negative view of the ABR’s Maintenance of Certification program (n = 1,994). Although radiologists’ overall perception of the program seemed balanced (35% fair/poor, 27% neutral, 36% very good/excellent), only 16% believed it was “worth the money” and 23% felt it “improves patient care.” In fact, deeper analysis found that the program was “acceptable” to just 1.7% of respondents. Although there have been many ABR MOC critiques in recent years, the fact that this study was produced by the ACR’s Certification Task Force suggests that it might have a greater impact.

• Chiasm Emerges: Previously unknown radiology startup Chiasm unveiled its cloud-based appointment scheduling and image/results sharing platform, which is currently in use by beta partners in New York and California. Chiasm might not fit the profile of a radiology startup that will “change the healthcare landscape” (three employees with no imaging history, one is 17 years old), it is part of an interesting wave of early-stage startups focused on imaging scheduling and/or sharing. Since May we’ve seen company introduction or early-stage funding announcements from Aurabox (sharing), Agora Care (sharing), Scan.com (scheduling & viewing), and xWave (referrals).

• Predicting Pancreatic Metastasis: A China-based research team developed a CT AI model that accurately predicted lymph node (LN) metastasis among patients with pancreatic ductal adenocarcinoma. The algorithm was trained and validated using CTs from 734 patients (340 w/ LN metastasis), and detected LN metastasis more accurately than radiologists, a clinical model, and a radiomics model (AUCs: 0.92 vs. 0.65 & 0.77 & 0.68). The patients with AI-predicted LN metastasis also had higher risk of mortality (hazard ratio: 1.46).

• Imaging Attacks: The last week brought a surge of imaging provider cyberattack announcements, revealing breaches at Alabama-based Henderson & Walton Women’s Center (HWWC), Arizona’s Radiology Ltd., and Texas-based Gateway Diagnostic Imaging. HWWC is unsure of when their breach occurred, which potentially exposed data from 34k patients. Radiology Ltd. and Gateway, which are both part of US Radiology Specialists, were hacked in December 2021. At least 10 US radiology practices and imaging centers have disclosed security incidents since the start of 2021, a trend that might increase as hackers reportedly shift their focus to smaller “specialty clinics.”

• Flurpiridaz PET MPI’s CAD Evidence: GE Healthcare and Lantheus’s [18F]flurpiridaz Phase III Trial showed that the PET radiotracer can accurately detect coronary artery disease, while achieving “higher diagnostic efficiency” and image quality than SPECT MPI (n = >600). Noting [18F]flurpiridaz’s 2 hour half-life (12x longer than current cardiac PET radiotracers) and the wide use of SPECT MPI (6M exams annually in US), the radiotracer’s potential FDA approval could significantly expand PET MPI use. GE funded [18F]flurpiridaz’s development and would be its exclusive global distributor if it’s approved. 

• Merative & RackTop Systems: Merative (formerly part of Watson Health) announced a partnership with cyberstorage startup RackTop, integrating RackTop’s BrickStor SP product into Merative’s Merge enterprise imaging solution. The integrated solution will operate within a data-centric Zero Trust architecture, targeting end-to-end protection of Merge users’ healthcare data.

• Multi-Cancer Blood Test: The Galleri Multi-Cancer Early Detection blood test achieved its latest clinical evidence milestone, flagging potential cancer in 92 patients out of 6,621 participants, and leading to 35 cancer diagnoses. Many of the detected cancers were early stage and nearly three-quarters were cancers that are not routinely screened for. The Galleri blood test is at the forefront of the growing cancer blood testing movement, which also includes recent efforts from Cedars-Sinai (liver cancer), as well as MGH and MD Anderson (both lung cancer).

• United Imaging and Huntsman’s PET/CT Installs: United Imaging and the Huntsman Cancer Institute at the University of Utah announced the installation of their partnership’s first two United Imaging PET/CT scanners. Huntsman Cancer Institute will utilize its new United Imaging molecular imaging systems for both clinical research and patient care, with a focus on precision medicine treatment evaluations and monitoring.

• PSMA PET Upstaging: UCLA researchers found that PSMA PET is increasingly leading to prostate cancer upstaging, potentially creating a similar shift to more aggressive prostate cancer treatments. Their analysis of 45,772 men with high-risk prostate cancer found that the median risk of PSMA PET upstaging increased from 13% in 2010 to 17.6% in 2017 (16.3% overall). The risk of nodal and distant metastatic upstaging also increased significantly (11.7% to 15.4%; 3.6% to 4.7%).

• Koning’s Breast CT Partners: Breast CT startup Koning announced partnerships with healthcare consulting firm 11TEN Innovation Partners and teleradiology practice DocPanel that are intended to help expand Koning’s Breast CT through retail health channels. DocPanel’s telerad service will begin reading breast CT exams this month and 11TEN will promote Koning’s Breast CT within its healthcare innovation network.

• Healthcare Employment Gains: New data from the Bureau of Labor Statistics indicated that the healthcare sector added 48k jobs in August, led by gains in physician offices (+15k), hospitals (+15k), and nursing facilities (+12k). The only subsector to lose jobs was home health services (-1.8k). Despite this year’s gains now totaling 412k jobs, healthcare hasn’t fully recovered losses from the beginning of the pandemic, with employment trailing 37k jobs (-0.2%) behind February 2020 levels.

• CurveBeam AI’s Breakthrough: CurveBeam AI’s OssView bone fragility assessment solution gained FDA Breakthrough Device status, fast-tracking its path to Medicare coverage. Although OssView currently doesn’t have FDA clearance, the designation process found that OssView’s Structural Fragility Scores determine fracture risk more accurately than current methods. The designation comes just a few weeks after CurveBeam merged with StraxCorp, the original developer of OssView.

Us2.ai’s Echo Evidence

Have more echo studies than sonographers? See how Us2.ai was able to classify, segment, and annotate echocardiographic videos with similar accuracy as expert sonographers.

What it Means to be Built for the Modern World

Find out what built for the modern world means — and why it matters — in this Aunt Minnie profile on United Imaging’s more modern approach to vertical integration, leadership, and culture.

The Resource Wire

• annalise.ai’s Annalise CXR solution 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.

• 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.

• The flow of new AI applications makes it hard for radiology groups to determine which tools would help them and how IT teams can handle increased AI adoption. In this Blackford Analysis white paper, radiology and IT leaders from NYU and Canopy Partners share how a platform approach alongside a curated marketplace can help solve these challenges.

• 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.

• Enterprise Imaging has come a long way, and it has a long way to go. This Intelerad white paper details the five pillars organizations should prioritize in order to realize the full potential of EI’s next evolution.

• The Hyperfine Swoop Portable MR’s accessibility advantages can translate to significant clinical and operational value, particularly for hospital emergency and intensive care departments. See how bringing MRI to the point-of-care can impact hospitals’ operational costs, quality of care, and revenue potential.

• Today’s radiology departments are under pressure like never before, and so much of it is generated by rising CT volumes and complexity. See how clinicians view today’s CT challenges, and why they believe scalable CTs might be the solution in this GE Healthcare Report.

• Imaging AI deployments face a long list of challenges that often emerge before any value is delivered. This Enlitic post details the top 10 AI deployment challenges organizations must understand in order to make sure their own deployments are successful.

• Nuclear medicine teams are facing three significant SPECT/CT challenges: balancing dose with image optimization, addressing staffing constraints, and preparing for continued theranostics advances. See how redefining your SPECT/CT standards can address these challenges in this Siemens Healthineers report.

• When Sao Paolo’s Diagnosticos da America SA (DASA, the world’s 4th largest diagnostics company) set out to evaluate Qure.ai’s QXR solution for their pediatric chest X-ray workflows, they leveraged CARPL.ai’s platform to streamline their evaluation. See how it worked here.

• Check out this talk from Eliot Siegel, MD on the “Hype, Myth, Reality and Next Steps” of imaging AI, including a profile on Canon’s AiCE Deep Learning Reconstruction solution at around the 4-minute mark.

• Imaging’s cloud evolution didn’t happen all at once. This Change Healthcare animation details the history of digital imaging architectures, and how cloud-native imaging improves stability and scalability, ease of management, patient data security, and operating costs.