fbpx

Screening Efficiencies | Consumer Imaging | AI Beta Testers

“They should understand that they are early adopters, potentially on the cutting edge of technology but also in part beta testers for these new solutions.

Renato Cuocolo and Massimo Imbriaco, warning early AI adopters about the other role they could play in the AI evolution.


Imaging Wire Sponsors

Arterys | Bayer Radiology | Canon Medical Systems | GE Healthcare
Healthcare Administrative Partners | Hitachi Healthcare Americas
Novarad | Nuance | Riverain Technologies | Siemens Healthineers
United Imaging | Zebra Medical Vision



The Imaging Wire


AI-Aided Screening Efficiencies

New research out of Spain suggests that integrating AI into breast cancer screening programs could safely and significantly reduce radiologist workloads, potentially making these programs far more efficient and scalable.

  • The Study – The researchers simulated an AI-aided screening program, using ScreenPoint Transpara to triage 15,987 DM and DBT exams (w/ 98 screening-detected cancers, 15 interval cancers).
  • The Program – The simulated program excluded exams that Transpara found to be “least suspicious” (scores: 1-7) from radiologist reading workflows, while the radiologists read all other exams using their standard processes (Transpara scores: 8-10). The simulation also recalled all exams that Transpara graded as “very suspicious” but weren’t recalled by the radiologists.
  • AI Triage Impact – This AI triage program would have significantly reduced radiologists’ screening workloads (DM: -71.5%, DBT -72.4%), while maintaining cancer detection accuracy (DM 78/113 vs. 76/113; DBT: 95/113 vs. 92/113), and reducing recalls (DM: -16.9%; DBT: -16.7%).
  • DBT Transition Path – Noting DBT’s 2x-longer reading times than DM, the researchers found that integrating AI into DBT screening programs would reduce workloads by 30%, while improving sensitivity by 25% and cutting recalls by 27% (versus double-read DM without AI).
  • The Takeaway – Even though many patients/providers aren’t ready for AI-only screening and these efficiency numbers are inflated by Europe’s double-reading practices, this study still shares a compelling example of how AI can provide the efficiency gains we keep talking about.

Zebra-Med’s Orthopedic Solution

With a post-COVID surge in orthopedic surgery looming, this Zebra Medical Solutions blog details how its 3D imaging orthopedic solution can help surgeons improve their preoperative efficiencies.

– This is sponsored content.



The DXA App

Medical imaging might be late to healthcare’s ongoing consumerization boom, but it at least became more involved this week with the launch of the FitTrace Sync DXA Apple Health app.

  • About FitTrace – FitTrace historically allowed individuals to understand and track their DXA body composition (connects them with DXA imaging providers, provides them with DXA analysis) and helped organizations distribute DXA analysis to their clients (e.g. radiology depts, imaging centers, bone density centers, athletic teams).
  • About the App – FitTrace took its already consumerized approach a step further with the launch of its new FitTrace Sync iPhone app, which integrates DXA body composition data into the Apple Health platform, allowing motivated individuals to track/analyze how their wellness activities (workouts, steps, diet, etc.) are affecting their DXA body composition.
  • The Takeaway – This integration isn’t likely to affect the daily work of many Imaging Wire readers. However, personalized digital health’s massive growth can’t be understated and it’s a safe bet that we’ll keep seeing efforts to integrate clinical and wellness data with varying levels of physician involvement.

GE Bridges the AI Startup Adoption Gap

With the gap between AI interest and AI adoption becoming increasingly clear, this GE Healthcare post details how AI startups can bridge that gap.

– This is sponsored content.



The Wire

  • AI Beta Testers: A new editorial in European Radiology warned imaging AI’s early adopters that they are also serving the role of AI “beta testers.” Written in response to a recent study detailing AI’s lack of clinical evidence, the editorial notes that despite growing interest in AI: 1) Many commercial imaging AI products are backed by limited evidence; 2) AI still has unsolved ethical and regulatory issues; 3) There’s a lack of AI implementation best practices; and 4) AI is still in its infancy.
  • Pulsify’s Wearable Funding: Wearable ultrasound startup Pulsify Medical just closed a €3.75m Series A round (increasing total to €6.35m) that it will use to fund the development of its ‘Smart Patch’ cardiac monitoring systems. Intended for home and hospital use, Pulsify’s Smart Patch systems continuously monitor cardiac function and notify both patients and physicians if an anomaly is detected.
  • Emory’s Lean CT Management: A new Emory paper detailed how lean management-based interventions improved the health system’s emergency CT workflows. After initial research, Emory launched four new processes/guidelines (ideal staffing model, patient flow worksheet, new CT patient screening forms, examination prioritization), reducing median CT turnaround times from 90–109 minutes to 82–106 minutes, and eliminated 268 hours of wasted technologist labor per year.
  • Ambra & Arterys’ Platform Partnership: Ambra Health and Arterys will integrate their respective image management and AI marketplace platforms, allowing providers to leverage Arterys’ AI tools within their Ambra platform workflows. The alliance significantly expands Ambra’s integrated AI solutions portfolio, while making Arterys’ AI platform available across Ambra’s large customer base.
  • A Case for Centralized Screening: Lung cancer screening adherence is higher when patients are managed through centralized screening programs. That’s from a new JAMA study (n = 2,283) that found patients who were referred through a lung cancer screening clinic or program (centralized programs; 46% adherence) were far more likely to attend their second annual screening than patients who were referred by a clinician (decentralized programs; 35.3% adherence).
  • Imaging’s Strong Q1: Imaging OEMs enjoyed very positive healthcare/imaging division performances during the January-March quarter, with every major player posting strong revenue growth and solid margins. The quarter featured year-over-year revenue growth from Canon Medical (+17.3% to $1.13b), Philips’ Diagnosis & Treatment division (+9% to $2.23b), Siemens Healthineers’ imaging business (+7.4% to $2.84b), Hologic’s breast imaging division (+7.9% to $269.9m), and GE Healthcare’s Systems division (+7% to $3.7b). This type of annual growth isn’t surprising considering what was happening in Q1 2020, but most of these OEMs have been trending upwards since last summer and that trend should continue into Q2.
  • U-Survival: MGH researchers were able to accurately predict COVID patients’ disease progression and mortality risk using a new model that integrates CT radiomic data with an established statistical predictive model. In an evaluation of 383 COVID-positive patients, their new “U-Survival” model was far more accurate than their existing disease progression (91.6% vs. 59%-69.8%) and mortality (88.7% vs. 53%-65.5%) predictive models.
  • RSIP’s Prostate MRI + Ultrasound Tool: RSIP Vision unveiled a new MRI-to-ultrasound registration tool that uses a registered prostate MRI scan to visualize information on top of an in-op ultrasound image, helping surgeons identify regions of interest. The vendor-neutral module is available to medical device and solutions manufacturers.
  • No Standards: The majority of hospitals give patients electronic access to their radiology reports, but embargo periods before the reports become available are very inconsistent. That’s from a new study out of Yale (n = 70 U.S. hospitals) that found 91% of hospitals make reports available online, with embargo periods ranging from 1–3 days (34%), 4–6 days (13%), 7–14 days (9%), and either “an indefinite period” or “unknown” (43%). This inconsistency might have to change with the upcoming 21st Century Cures Act.
  • OncoRes’ Breakthrough Designation: OncoRes Medical’s Quantitative Micro-Elastography (QME) Imaging System platform just received FDA Breakthrough Device designation for real-time tumor assessments during surgeries, fast-tracking its path to Medicare coverage. OncoRes achieved its new FDA designation by showing that the QME Imaging System improves outcomes and could reduce repeat breast-conserving surgeries.
  • Vertical Consolidation: A new Health Affairs study found that when hospitals acquired physician practices between 2013 and 2016, they were followed by notable in-hospital shifts for diagnostic imaging (in-hospital: +26.3 per 1k, non-hospital: -24.8 per 1k) and laboratory testing (in-hospital: +44.5 per 1k, non-hospital: -36 per 1k). Uncoincidentally, these shifts came with notable Medicare reimbursement increases (avg: +$6.38 imaging, $0.57 labs), translating to $40.2m and $32.9m overall Medicare spending increases over the four years.
  • Secondary Findings Companion: A new study out of Germany found that Siemens Healthineers’ AI-Rad Companion Chest CT could be used to catch secondary thoracic findings in emergency whole-body CT scans. The researchers analyzed 105 whole-body CTs with AI-Rad Companion Chest CT, finding that initial diagnoses missed 25 patients with cardiomegaly or borderline heart size, 17 with coronary plaques, 34 with aortic ectasia, 2 with significant lung lesions, and 13 missed vertebral fractures.

Hitachi on CVIS Must-Haves

It’s clear that structured reporting is a must for CVIS platforms, but they aren’t all created equal. This Hitachi article reveals what physicians and sonographers view as the “non-negotiable” CVIS structured reporting features.

– This is sponsored content.



The Resource Wire

– This is sponsored content.

  • In this quick video, Sharp Memorial Hospital interventional radiologist, Jim Lyon, MD, describes the image quality and dose advantages of Canon Medical Systems’ Alphenix Sky+ system.
  • “Work-flow validation should happen very early in the AI development cycle…” Read on to learn about “Building Radiology AI that Works” featuring Babak Rasolzadeh, Sr. Director of Product & Machine Learning at Arterys.
  • See how Einstein Healthcare Network reduced its syringe costs, enhanced its syringe loading, and improved its contrast documentation when it upgraded to Bayer Radiology’s MEDRAD Stellant FLEX CT Injection System.
  • United Imaging’s approach to brain imaging in molecular imaging puts the patient first, with a focus on reducing scan times and correcting for patient motion to avoid repeat studies, while supporting interpretation with high resolution images and quantitative values.
  • This AI economics overview from Healthcare Administrative Partners details the various AI ROI scenarios and ways that AI can contribute to radiology practices until reimbursements become more of a reality.
  • Watch Jared Christensen, MD, MBA explain how Duke University Health uses Riverain Technology’s ClearRead CT Vessel Suppress and ClearRead CT Detect in its daily practice.
  • In this Novarad video, interventional oncologist Gary M. Onik, MD shares how Novarad’s AR surgical navigation system, OpenSight, helps his team accurately assess and treat tumors
  • See how Nuance’s mPower Clinical Analytics helped Summa Health improve its incidental lung nodule follow-up rates by nearly 8x.
  • This new ebook looks at how you can empower your CT technologist team and set up your department for success by looking at four key areas.