POCUS Alternative | CV19 PXS | Pain & Change

“Cancer and other diseases do not stop, and imaging should not either.”

MITA’s Patrick Hope, urging U.S. governors to keep screening going despite the pandemic.


Imaging Wire Sponsors

  • Focused Ultrasound Foundation – Accelerating the development and adoption of focused ultrasound.
  • GE Healthcare – Providing point of care ultrasound systems, from pocket-sized to portable consoles, designed to support your clinical needs and grow along with your practice.
  • 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.

The Imaging Wire



POCUS Alternative

When internal medicine doctors use point-of-care ultrasound, hospitals perform fewer medical imaging exams without increasing mortality. That’s from a new study out of Italy and here are some details:

  • The Study – The Milan-based internal medicine team used POCUS during alternating months (8 months total), then measured results from POCUS’ “on” and “off” months (n = 263 patients on, 255 patients off, 81yr median age).
  • The Results – The internists ordered far less imaging exams during the POCUS months (113 vs. 329 exams), finding that patients were 87% less likely to receive a chest X-ray, 78% less likely to receive a chest CT, and 68% less likely to have an abdominal ultrasound when internists use POCUS as a primary tool. However, abdominal CT was 41% higher during POCUS months.
  • The Significance – The study supports the use of POCUS in primary care and internal medicine settings (not just emergency), suggesting that it improves care, reduces downstream imaging, and does not result in unnecessary tests.



CV19 PXS

An MGH-led team developed a Siamese neural network that produces CXR-based COVID-19 pulmonary disease severity scores (PXS), helping clinicians monitor disease progression and predict intubation or death.

  • Training – The algorithm was trained using 160k CheXpert images with transfer learning from 314 COVID-19 patients’ frontal chest X-rays.
  • Testing – The team evaluated the algorithm using internal and external test sets from two hospitals (n = 154 & 113 CXRs), correlating PXS scores with radiographic severity scores produced by two thoracic radiologists and one in-training radiologist.
  • Results – The PXS scores correlated with the radiologists’ radiographic pulmonary disease severity scores on both the internal and external test sets, while predicting changes as well as the radiologists, including predicting intubation or death within three days of hospital admission with an 0.80 AUC.
  • Significance – An algorithm like this could help clinicians use CXRs to monitor COVID-19 disease progression, potentially helping overcome the subjectivity, workflow, and expertise challenges associated with manual chest X-ray assessments. PXS scores could also contribute to models that leverage a range of data sources for CV19 assessments (e.g. vital signs, lab values, and co-morbidities).

The Wire

  • Emergency Extended: A tweet from HHS Secretary Alex Azar officially extended the COVID-19 public health emergency last week, keeping hospitals’ emergency benefits / flexibilities in place for another 90 days (e.g. 20% additional Medicare payments for CV19 patients).
  • Pain Drives Change: Value-based care proponents are optimistic that the drop in patient volume during the COVID-19 pandemic will encourage more providers to adopt alternative payment models that compensate physicians on a per-patient basis (vs. per-service). Although not technically an imaging story, “alternative” per-patient models have been found to significantly reduce imaging volumes.
  • Cycloidal CT: A University College London team developed a new CT method that could improve image resolution and/or reduce dosage. The new cycloidal CT method uses a mask with small slits that reshapes X-ray beams into smaller “beamlets” and adopts a new X-ray beam motion (rotation + back & forth), increasing in-slice spatial resolution and reducing dosage. UCL also suggested that different mask apertures could be used to achieve different image resolution or dosage levels.
  • Home COVID X-Rays: New York’s Northwell Health launched a home care program for people with moderate to severe COVID-19, deploying nurses to provide a range of in-home services including oxygen and mobile X-ray imaging. Northwell’s Coronavirus Related Outpatient Work Navigators (CROWN) program is intended to care for homebound patients, reduce contamination risks, and preserve hospital capacity if a second COVID-19 surge develops.
  • Canon AiCE Cleared for 1.5T: Canon Medical’s Advanced intelligent Clear-IQ Engine (AiCE) image reconstruction technology is now cleared by the FDA for use with its Vantage Orian 1.5T MR system. About 1.5 years after debuting with Canon’s high-end CTs, its AiCE technology has now either been announced or approved for use with much of Canon’s CT (Aquilion ONE / GENESIS Edition, Aquilion Precision, Aquilion ONE / PRISM Edition, and Aquilion Prime SP) and MRI portfolios (Vantage Galan 3T, Vantage Orian 1.5T).
  • A Call to Continue Screening: A letter from seven of the major imaging organizations (ACR, MITA, ASRT, others) urged U.S. governors to continue cancer screenings during the COVID-19 pandemic, warning that delayed findings might lead to a second health crisis and 10,000 additional deaths. Although imaging organizations have their reasons to encourage continued screenings, this is the same warning issued by the National Cancer Institute last month.
  • Qlarity & Ikonopedia: Qlarity Imaging and Ikonopedia launched a partnership that will integrate Qlarity’s QuantX breast MRI CAD system and Ikonopedia’s breast reporting and risk assessment system. With the integration, information from QuantX (location, size, kinetics, QuantX score) is automatically transferred into Ikonopedia.
  • Reimbursements Down: A new JACR study revealed that inflation-adjusted Medicare reimbursement rates for diagnostic studies declined between 2007 and 2019 (92% of all study types declined), largely due to policy changes. Bone densitometry absorbed the greatest percentage decline (−70.5%), followed by MRI (-64%), MRA (-54%), CTA (-52.5%), CT (-45%), ultrasound (-22.9%), radiography (-14.6%), and mammography (-7.1%), while nuclear medicine got away with the smallest decline (−4.28%).
  • LUS for CV19: Spanish researchers published the latest study supporting lung ultrasound’s value for COVID-19 care (here’s another recent one). The new study found that lung ultrasound (LUS) detects abnormalities in COVID-19 patients with similar accuracy as chest CT, supporting LUS’ role as a first-line option for CV19 evaluation. The researchers performed CT and LUS exams on 51 patients. Two radiologists were able to identify all 40 CV19-positive patients using the LUS exams (vs. 37 with CT), while finding that LUS had better alignment with CT than CXR (LUS: 100% sensitivity, 79% specificity, 93% positive predictive value, 100% negative predictive value).
  • Educational Consequences: A new paper in Academic Radiology detailed the COVID-19 pandemic’s impact on radiology education, as DR and IR educational caseloads decreased significantly in April 2020 and numerous international conferences were cancelled. DR caseloads fell by between 39.3% (neuro) and 75.5% (women’s imaging) and IR caseloads fell by between 42.6% (core IR) to 62.6% (arterial IR), while online learning increased significantly. The Imaging Wire headquarters became an online kindergarten classroom in March, so we can relate.
  • MRI DL for Cervical Cancer: A new study in JAMA Network Open detailed a DL model that can use MRI scans to diagnose lymph node metastasis in patients with cervical cancer, helping reduce unnecessary surgeries and supporting treatment planning. The China-based research team developed the model using images from 479 patients (n = 338 training, 141 validation), finding that it can identify patients with lymph node metastasis with a 0.933 AUC when combined with MRI lymph-node status assessments.
  • CV19 CT Drapes: EDM Medical Solutions launched a portfolio of single-use CT scanner drapes intended to reduce COVID-19 infection risks and potentially ease decontamination labor. EDM’s new CT drapes join its existing portfolio of medical equipment covers for tablets, ultrasound machines, C-arms, and more.

The Resource Wire

– This is sponsored content.

  • As the world navigates the unprecedented challenge presented by the COVID-19 pandemic, GE Healthcare supports healthcare providers, partners, communities and patients around the world in addressing it. Find information on GE Healthcare’s COVID-19 Resources here.
  • This Hitachi blog details the benefits of multi-parametric MRI (mpMRI) for prostate imaging, including insights on how its Oasis 1.2T High Field Open MR allows more diagnostic-quality exams with reduced metal susceptibility artifacts on the diffusion sequence compared to a 3T magnet.
  • This Nuance white paper details how Baptist Health South Florida used PowerScribe Workflow Orchestration and PowerConnect Communicator to optimize its radiology workflow and streamline its communication.
  • Check out Riverain Technologies’ on-demand webinar demonstrating how its AI solutions integrated into LucidHealth’s radiology workflow and sharing best practices on how to combine AI with radiologist expertise.
  • If you’re in the mood for a good success story, this video details how MRI-guided focused ultrasound treatment helped one patient recover from essential tremor.

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. We will never sell or share your information.