“Logically, overscanning”
A Twitter comment from UPenn’s Saurabh Jha on the main reason private practice scans have fallen by as much as 50% since CV19.
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.
- Nuance – AI and cloud-powered technology solutions to help radiologists stay focused, move quickly, and work smarter.
- Qure.ai – Making healthcare more accessible by applying deep learning to radiology imaging .
- Riverain Technologies – Offering artificial intelligence tools dedicated to the early, efficient detection of lung disease.
The Imaging Wire
The SOLUS Scanner
A team of scientists from the European Horizon2020 SOLUS project developed a multi-modal breast imaging system that they say might make many biopsies unnecessary.
- The Tech – The new SOLUS Scanner combines ultrasound and diffuse optical imaging technologies within a single handheld ‘smart optode’ probe to capture blood and tissue data. Scientists (and potentially clinicians) can then use this data to track clinical changes in tumors (oxygenated and deoxygenated haemoglobin, collagen, lipids, water, stiffness) and differentiate between benign and malignant lesions (targeting: 95% sensitivity and 90% specificity).
- Advantages – The researchers suggest that the SOLUS Scanner could result in fewer false positives and therefore reduce unnecessary biopsies, while shortening the time between screening and results.
Creative CV19 Imaging
It’s become quite clear that non-essential imaging should be delayed until we’re rebounding from CV19 — and it’s also very clear that this is having a massive financial impact on imaging centers and radiology practices. As a result, we are seeing a new wave of organizational and PR efforts from local radiology companies/ departments to help boost their imaging volumes.
- The Radiology Annex – PennState Health transformed an offsite storage area to create a Radiology Annex dedicated to patients suspected to be CV19-positive with the goal of “safely imag[ing] a high volume of intermediate-risk patients.” In addition to separating its CV19 and non-CV19 imaging operations and protecting against transmission, the new Annex is specifically designed to increase PennHealth’s imaging bandwidth by reducing decontamination times (it has a plexiglass wall between patients and the X-ray, can scan one patient every 8 minutes).
- Don’t Delay Essential Imaging, Please – Kern Radiology (a Bakersfield, CA RadNet company) worked with a local news station to remind patients not to delay “necessary medical imaging” and to reassure them of the safety steps Kern is taking to keep its centers safe.
- Outpatient Option – Buffalo NY’s Windsong Radiology took a similar approach, positioning its imaging centers as a CV19-safe alternative to hospital imaging for patients who require imaging for “urgent elective” procedures.
The Wire
- Riverain & LucidHealth Partner Up: Riverain Technologies and LucidHealth announced a new alliance that will combine Riverain’s ClearRead CT early lung disease detection software with LucidHealth’s RadAssist workflow. The partnership will also make ClearRead CT available to LucidHealth’s network of radiology practice/department customers that operate over 148 Midwest sites.
- How CV19 Will Impact Ultrasound: A new post from Informa Tech (formerly IHS Markit) suggested that although some ultrasound segments are valuable for CV19 care, the overall ultrasound market will decline until the pandemic subsides. Informa Tech was most bullish about CV19-driven demand for point-of-care and primary care ultrasound systems, and saw some upsides for general US, but expects “drastically” lower demand for larger dedicated US systems (e.g. OB/GYN and cardiovascular). These segments have a much higher-share and are much higher-priced than the POCUS/primary segments, making these declines much more significant.
- Hitachi’s New R/F: Hitachi announced the Japan launch of its new CURE VISTA Open X-ray fluoroscopy system, which launches with a similar 2-way arm as Hitachi’s previous R/F models, and features an improved image processor, a new tomography application, an updated UI, and a new long-length imaging application (among other upgrades).
- Tomographic CV19 Imaging: A team of Spanish scientists began work on a new imaging technique intended to measure CV19 pulmonary involvement. The system will combine tomosynthesis and AI with the goal of achieving the accuracy of CT at the cost and flexibility / portability / availability of X-ray systems.
- Re-purposing qXR: Qure.ai opened up about how it repurposed its qXR chest X-ray AI tool to detect signs of COVID-19 (now in use at 28 global sites). This blog version of “transparent AI” revealed that Qure.ai tuned its new CV19 tool on 300 CV19-positive and 300 CV19-negative CXRs and validated it on 11,479 CXRs (w/ 515 COVID-19 positive cases). The new CV19 tool achieved an AUC of 0.9 on the test set (95% CI : 0.88 – 0.92), while working with a sensitivity of 0.912 and a specificity of 0.775 when performing at its common operating threshold.
- SM Matches FFDM: A study out of Weill Cornell Medicine found that 2D synthetic mammography (SM) performs no worse than full-field digital mammography (FFDM) for the detection of microcalcifications during screenings. The retrospective multireader study (n = 160 cases, 70 with microcalcifications, 35 malignant, 3 readers) compared SM and FDM screenings and found SM to be non-inferior for diagnostic accuracy (91% and 88% AUCs), sensitivity (77% vs 73%), negative predictive value (84% vs 82%), although SM had lower specificity (91% vs 98%) and positive predictive value (87% vs 96%). The readers found calcifications to be more conspicuous on SM and reported no difference in diagnostic confidence between the two technologies.
- CAD4COVID: Dutch AI developers, Thirona and Delft Imaging, rolled out their new CAD4COVID AI solution that triages chest X-rays for COVID-19. The new solution leverages the core technology in Delft Imaging’s CAD4TB tuberculosis detection tool, generates a 0-to-100 CV19 score, displays CV19 abnormalities on a heatmap, and quantifies the percent of lung affected. CAD4COVID is available without charge, but because it hasn’t achieved regulatory approval it can only be used for research (at least officially).
- MRI for Femoral Fractures: A new study from UTHealth Houston’s McGovern Medical School found that rapid limited-sequence pelvic MRI scans could help identify femoral neck fractures that are missed with CT or X-ray. The researchers performed pelvic MRI on 33 out of 37 patients with suspected femoral shaft fractures, finding that MRI identified femoral neck fractures in 12.1% of these patients that were not identified in CT or X-ray.
- Mednax Cuts: Facing major CV19-driven imaging declines, Mednax announced a number of cost-reducing moves to help protect its businesses. These cuts include reducing executive and key management salaries by as much as 50%, suspending board bonuses/payments, reducing salaries and furloughing non-clinical employees, and significantly reducing third party expenditures. Mednax’s cuts are consistent with many other radiology and imaging companies, but Mednax has a much larger staff than most.
- Oregon’s Fluoroscopy Nurses: In anticipation of a CV19-driven fluoroscopy surge, the Oregon Board of Medical Imaging is temporarily allowing APRNs to perform/supervise all fluoroscopic procedures through September 1, even if they haven’t passed the ARRT fluoroscopy exam (they will have to participate in training/tests). Crisis or not, the ACR did its job and came out against this decision, arguing that it doesn’t appropriately address quality or safety issues.
- SonoVision: Tissue Differentiation Intelligence (TDi) announced the FDA approval of its SonoVision spinal surgery ultrasound system, calling it the first spinal ultrasound system to leverage machine learning and/or support intraoperative spinal access. SonoVision applies image-processing algorithms to its intraoperative ultrasound images to help visually differentiate nerve, muscle, bone, and vessels in real time.
- CV19 Physician Impact: A new MGMA survey (n = 774 practice leaders) found that 97% of physician practices experienced a negative financial impact from the CV19 pandemic (2% were unsure), with 55% reporting a reduction in revenue and 60% experiencing lower patient volumes since the crisis began. In response to these declines, many of the practices have already begun layoffs and furloughs (22% and 48% by April 8th) and even more plan cuts if the crisis persists (36% and 60% by May 8th).
- CV19 Lung US Training: Simbionix announced a lung ultrasound training module to help doctors diagnose COVID-19. The new training module was co-developed with Israel’s Ben-Gurion University and includes a range of cases presenting different ultrasound characteristics typically found in COVID-19 patients (B-lines, thickening of the pleura, and consolidated lung).
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.
- Learn how and why Seattle Children’s Hospital, Duke University Health System, and HCA Healthcare chose to ditch the disk by adopting Nuance’s PowerShare Network.
- This blog article from Healthcare Administrative Partners outlines the legislation passed that can help support radiology practices during the COVID-19 pandemic.
- This JAMA Current article details how Focused Ultrasound and other key therapies help treat Parkinson’s disease.
- Vessel suppression from Riverain Technologies’ ClearRead CT software was recently found to significantly improve nodule detection, interreader agreement, and reading time with oncologic chest CT scans.
- This Nature Research study found that Qure.ai’s qXR tool can identify TB-associated abnormalities in chest radiographs with over 95% accuracy, potentially eliminating 2 out of 3 Xpert MTB/RIF tests.