US COVID Test| LEGO MRI | AI Framework


“Why? It’s just an X-ray?”

Federal Judge, David Tatel, asking an AHA litigator why the negotiated rates for X-rays and many other medical services are “unknowable.”


Know anyone who made outstanding contributions to radiology practice and outcomes this year? Nominate them for an Imaging Wire Award.


Imaging Wire Sponsors

  • Arterys – Transforming medical imaging by reducing the tedium of interpretation and empowering physicians with our web-based AI platform.
  • Bayer Radiology – Providing a portfolio of radiology products, solutions, and services that enable radiologists to get the clear answers they need.
  • GE Healthcare – Enabling clinicians to make faster, more informed decisions through intelligent devices, data analytics, applications and services.
  • Healthcare Administrative Partners – Empowering radiology groups through expert revenue cycle management, clinical analytics, practice support, and specialized coding.
  • Hitachi Healthcare Americas – Delivering best in class medical imaging technologies and value-based reporting.
  • Nuance – AI and cloud-powered technology solutions to help radiologists stay focused, move quickly, and work smarter.
  • Riverain Technologies – Offering artificial intelligence tools dedicated to the early, efficient detection of lung disease.
  • Siemens Healthineers – Shaping the digital transformation of imaging to improve patient care.

The Imaging Wire



The Ultrasound COVID Test

Lung ultrasound’s role in assessing and managing COVID-19 is well documented at this point, and a new study out of Italy found that it could even help make sure patients with false negative RT-PCR results are correctly diagnosed. Here’s some details:

  • The Study – The Turin-based team integrated lung ultrasound (LUS) into its COVID-19 evaluation process, performing LUS immediately after initial assessments in the hospital’s ED. The study reviewed the processes’ performance with 228 patients with suspected COVID-19 (107 were CV19-positive).
  • The Results – The LUS-integrated clinical assessments had higher sensitivity (94.4% vs. 80.4%) and negative predictive value (95% vs. 85.2%) than the patients’ RT-PCR tests. Most notably, all 21 patients who had false negative RT-PCR tests were correctly identified as COVID-positive through their LUS-integrated assessments.
  • The Takeaway – RT-PCR tests have a bad reputation for false negative rates (one study says 38% false negates rates on the first day of symptoms, 20% on the 8th day) and this study shows that lung ultrasound might help catch these false negatives. Considering that most in radiology admit imaging shouldn’t be relied on for COVID-19 diagnosis, lung ultrasound’s role as a false negative safety net might make it the exception to this rule.

The Wire

  • LEGO MRI, in Review: UK-based MRI radiographer Apollo Exconde’s Open MRI LEGO design just got a step closer to being accepted as an official LEGO, after surpassing 10k votes. The next step for the LEGO MRI design is an official review by a LEGO team who will decide whether to produce the design as part of their LEGO Ideas lineup. It’s worth noting that Exconde won the 2019 Imaging Wire Cornerstone award, in part because of his LEGO MRI efforts.
  • Fixing the AI Frameworks: A new JACR paper from a team of imaging AI leaders identified a number of problems with the way regulators currently evaluate AI and shared four recommendations to address these issues. The paper suggests that regulators should: 1) Separate the algorithm and its diagnostic task, and standardized task definitions; 2) Evaluate more than just accuracy (e.g. reliability, applicability, auditability); 3) Divide evaluations into discrete steps (define task, test in lab, test in real world, test at local sites, measure performance over time); 4) Encourage assessments by third party evaluators, like pharma trials; 5) Integrate these steps into the AI development process.
  • COVID’s Abdominal Findings: A new study from a Northwell Health team detailed how COVID-19 presents in emergency abdominopelvic CT scans. The study (n = 597 patients, 44% w/ CV19) found that these patients have far more ground glass opacities at the lung bases (65.1% vs 12.4%) and more inflammation in organs with high expression of ACE2 receptors (e.g. bowel or pancreas; 58% vs. 29.8%), but have much less acute abdominal findings (23.8% vs. 45.5%).
  • GE’s Big St. Luke’s Ultrasound Deal: GE Healthcare announced a 76-unit, $11m ultrasound deal with St. Luke’s University Health Network, calling it the company’s largest ever ultrasound deal in the United States. The deal will allow St. Luke’s to standardize its ultrasound technology across 12 hospitals, which became diverse after recent acquisitions, while leveraging GE’s Viewpoint 6 reporting and post-processing system to achieve $300k in annual radiologist efficiency gains.
  • SWIR Imaging: A research team from Helmholtz Zentrum München and UCLA are exploring shortwave infrared imaging’s (SWIR imaging, commonly used in defense/astronomy) potential to be a new medical imaging modality. The team has reason to be optimistic, given that SWIR imaging’s unique list of capabilities (real-time imaging, multiplexing, high tissue penetration, adequate resolution) could allow it to distinguish different structures (e.g. nerves, blood vessels).
  • AI Liability Protection: Physicians who follow healthcare AI systems’ advice may face less risk of legal liability if the physician’s decision causes harm to the patient, compared to if the physician rejects AI advice (as long as they don’t follow “nonstandard” AI advice). This is from a recent study out of Georgetown University and ETH Zurich that described AI scenarios to 2k U.S. adults (representing potential jurors) and asked them to assess the physician’s liability.
  • Wrong CT Tragedy: A 28-year-old patient with Marfan syndrome who visited Queen Elizabeth Hospital (Norfolk, UK) in early 2019 with chest pain died after a radiologist mistakenly read another patient’s CT scan and missed the man’s ruptured aortic aneurysm. Another radiologist realized the mistake after reviewing the scan and called the patient back into the hospital, but he suffered a fatal heart attack before he could be treated. The hospital attributed the error in-part to its dated PACS system, revealing plans to replace it.
  • Pacemakers Safe for MRI: A St. Luke’s radiology team found that MRI exams (including thoracic MRIs) can be safely performed on patients with non–MRI-conditional devices (e.g. pacemakers and implantable defibrillators) with certain MRI settings applied (e.g. patients w/ pacemakers received asynchronous pacing). This is from a study of 532 patients with these devices who underwent 608 MRI examinations, finding that there were no complications, but the exams did lead to changes in suspected diagnosis (25% of scans), prognosis (26%), and medical/surgical plans (42%).
  • Canon Aquilion Exceed LB CT: Canon Medical unveiled its new Aquilion Exceed LB CT radiation therapy planning system (FDA pending), highlighting its AiCE reconstruction technology and industry-leading bore opening (90cm), field of view (90cm), and detector coverage (4cm). The Aquilion Exceed LB CT is built specifically for radiation therapy planning, which is still unique compared to many oncology CTs that are often derived from their diagnostic CTs.
  • Partial CT Recovery: After a massive drop in CT volumes during the initial COVID shutdown, we’ve seen a “partial recovery” in CT volumes. This is from a JACR study that reviewed CT volumes at 2,398 radiology practices (16.1m total CT exams, Jan -Sep 2020), finding daily CT volumes were down by 53% at the lowest point of the year (33.5k/day), but daily CT volumes were 16% below expected by September 30 (59,856/day).
  • Mindray’s New ME8: Mindray unveiled its new ME8 point of care ultrasound system, highlighting its small/light form factor (1.7” thick, 6.6 lb.), image quality, and usability (sealed user interface, AI-based tools, needle guidance). The ME8 appears to be a new addition to Mindray’s POCUS lineup, positioned below its laptop-style M9 system.
  • Brain PET Breakthrough: MGH scientists validated a new PET tracer molecule that could improve how we detect and characterize brain injury. The novel [18F]3F4AP PET tracer binds to potassium channels in the brain’s neurons, which become exposed when they lose their protective coating (myelin), due to a variety of neurodegenerative conditions (MS, TBI, spinal cord injuries, stroke, Alzheimer’s). After the team’s success testing with monkeys (high penetration, fast washout/clearance, excellent reproducibility) they now have FDA approval to test [18F]3F4AP with humans.
  • Getting More from Single-Source CT: An RPI research team developed a new process that uses deep learning to create single-source CT images that match the quality of dual-energy CT (DECT), while avoiding DECT’s higher complexity and dosage. The team developed a residual neural network (ResNet) model to map single-spectrum CT images to virtual monoenergetic (VM) images and trained it on DECT images, producing high-quality VM image “approximations” with similar accuracy as DECT images.
  • Siemens’ Indian Innovation Hub: Siemens Healthineers will open an innovation hub in Bengaluru, India, where it will spend €160m over the next five years to develop new AI/AR/VR/cloud-enabled precision medicine technologies. The innovation hub is located at Siemens’ Bengaluru imaging system manufacturing facility and plays a key role in the company’s ‘Strategy 2025’ plan. Siemens also has innovation hubs in United States, Germany and China.

The Resource Wire

– This is sponsored content.

  • Siemens Healthineers’ c.cam cardiac camera allows you to perform high-quality scans in a small space without costly renovation fees. Discover how quickly you could be up and running with a budget-friendly cardiac camera.
  • GE Healthcare and Riverain Technology’s upcoming AI roundtable will feature a discussion on using AI to help detect lung, musculoskeletal, and neurological diseases.
  • Radiologists have a new tool available that will potentially allow them to recover some of the added costs related to safety precautions taken during the COVID-19 PHE. Learn more about CPT code 99072 in this blog article from Healthcare Administrative Partners.
  • This Bayer Radiology case study details how its Certegra P3T Software automates contrast enhanced abdominal CT injection protocols based on patient characteristics and contrast concentration.
  • Hear Regional Health CIO and CMIO, Stephanie Lahr, MD, explain how Nuance PowerShare enables Regional Health to share diagnostic images across a large geographical region quickly and efficiently.
  • Learn more about how GE Healthcare helped St. Luke’s University Health Network achieve system-wide ultrasound consistency and $300k in annual efficiency gains.
  • This Hitachi Healthcare Americas blog details COVID-19’s recent and future impact, warning cardiac practices and clinics of an upcoming wave of patients with cardiovascular issues that worsened due to delayed treatments, followed by a “third wave” of patients who developed heart complications from COVID-19 infections. Hitachi also shared some guidance on how to manage and minimize the impact of these waves.


Leave a Reply

Basic HTML is allowed. Your email address will not be published.

Subscribe to this comment feed via RSS

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

Join thousands of imaging professionals.