Butterfly Goes Home | Questioning CAD | Right to Repair

“The Future of Medicine is Here.”

Butterfly Network setting a high bar for its new home use ultrasound TeleGuidance platform.


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



Butterfly Goes Home

In an announcement that began with the proclamation that “The Future of Medicine is Here,” Butterfly Network officially expanded its ultrasound systems to patients’ homes.

  • Home TeleGuidance – The new home version of Butterfly Network’s TeleGuidance platform allows doctors to guide patients through their ultrasound exams remotely, potentially without either of them leaving their homes.
  • Emergency Tele-Guidance – This has surely been in the works for some time. However, the new TeleGuidance platform’s quick approval was made possible by the FDA’s COVID-19 Emergency Guidance, noting the transmission and workflow benefits of home ultrasound during the CV19 emergency.
  • Democratizing Imaging – Home use ultrasound has an unproven use case, but this could represent a major milestone for telemedicine and a big step towards Butterfly Network’s goal of democratizing imaging. It also exponentially increases the company’s addressable market to include households across America.



Questioning CAD

A new study from a team of University of Utah cognitive neuroscientists suggests that historical criticisms against mammography CAD systems could be because CAD has been “aiding” radiologists the wrong way.

  • Second Reader CAD Theory – The team suggests that a high prevalence of CAD marks can actually disrupt radiologists’ visual attention and cause rads to miss targets, especially when the CAD system misses them first. Because of this, they argue that withholding CAD findings until after the radiologist has a chance to read each image could actually improve their accuracy.
  • The First Study – To support this theory, the researchers produced 384 mammography-adjacent images organized into blocks with 50% or 10% target prevalence rates. Thirty students inspected the images with and without CAD, proving to be far less likely to spot a target if the CAD software didn’t detect it first (especially when reviewing low prevalence blocks of images).
  • The Second Study – To back that up, the researchers rigged a CAD system to only show findings in a text box after the radiologist clicked on that part of the mammography image. When 31 students reviewed these images, the researchers found that the students were less likely to miss a target when the CAD system also missed it.



The Right to Repair

The in-house medical device service movement got an unlikely boost from the DIY electronics repair website IFIXIT after it released the “most comprehensive medical equipment service database in the world.”

  • IFIXIT’s Healthcare Pivot – IFIXIT has traditionally advocated for the public’s ability to perform their own device repairs, but recently shifted its focus to the healthcare industry in response to the COVID-19 emergency. Within two months IFIXIT and 200 volunteers collected and released a crowdsourced database featuring about 13,000 medical device repair manuals (yes, including imaging systems), positioning it as a resource for biomedical engineering technicians to handle more repairs in-house.
  • Public Pressure – OEMs have long controlled much of the medical device repair infrastructure and policies, and it’s going to take a lot to change that dynamic. However, the new IFIXIT database comes at a vulnerable time for longstanding (and potentially inefficient) healthcare policies and the successful creation of this massive database suggests that the in-house repair movement has plenty of grassroots support.

The Wire

  • Telerad Up and Staying Up: A new JACR paper detailed how internal teleradiology volumes increased significantly during the COVID-19 emergency and suggested that telerad rates probably won’t fall back to pre-CV19 levels. The survey of 174 radiology practices found that the CV19 emergency caused 65.2% of practices to buy new home workstations and 73.6% to switch normal daytime shifts to internal teleradiology. It appears that the respondents experienced the benefits of teleradiology, as 55.9% revealed that they will continue to perform internal teleradiology after the pandemic subsides (particularly private practices at 64.3%).
  • Zebra Cleared Again: Zebra Medical Vision announced the FDA approval of its Vertebral Compression Fractures (VCF) product (its 5th FDA approved product), an AI-based solution intended to help spot compression fractures and identify patients who are at risk of osteoporosis using abdominal or chest CT scans.
  • No Exemptions: A STAT News editorial by David Townsend (he co-invented the PET/CT scan) argued that hospitals shouldn’t be exempt from having to report faulty radioisotope injections. Townsend pointed out that the current exemption policy is antiquated (originally drafted in 1980) and inconsistent (spilling radioactive isotopes on a patient is a reportable event, but incorrect injections aren’t), and suggests that this issue will get worse as radioisotopes are increasingly used for imaging and treatment.
  • Fujifilm & Royal’s Informatics Partnership: Fujifilm Medical Systems U.S.A. announced a partnership with Royal Health that will make Royal’s patient engagement and revenue cycle management solutions available to Fujifilm’s Synapse customer base.
  • BI-RADS 3 at 6 Months: Women with BI-RADS 3 breast lesions should receive follow up imaging at six months. That’s from a recent study in the Radiology journal (n = 43k women w/ BI-RADS 3) that assessed outcomes at 6, 12, and 24-month follow ups, finding that 12% of the invasive cancers diagnosed within six months with node staging had spread to the lymph nodes. This “small but not insignificant risk that (BI-RADS 3) lesions are malignant” is enough to support their suggested 6 month follow up cadence.
  • Behold.ai Goes Big in India: Behold.ai announced a deal to provide its red dot COVID-19 X-ray detection solution to India’s Apollo Radiology International, calling it the “world’s largest deployment of a radiology-based AI diagnostic solution for COVID-19.” Behold.ai will provide its red dot ‘instant triage’ algorithm via Apollo Radiology International to Apollo Hospitals’ network of 71 hospitals in India as well as select government-run hospitals.
  • Life Image Patient Connect Portal: Life Image launched its new Patient Connect Portal, highlighting the portal’s ability to collect, assemble, store, and share diagnostic images (even from different locations), while giving patients control over their own images and data. The new portal is based on Life Image’s Mammosphere platform, expanding it to new modalities and clinical conditions.
  • RADLogics on Nuance Marketplace: RADLogics’ AI solutions for COVID-19 evaluations are now available on the Nuance AI Marketplace, expanding the solutions to Nuance’s massive PowerScribe customer base (80% of U.S. radiologists, over 7,000 connected healthcare facilities). RADLogics’ COVID-19 solutions provide triage and disease extent measurements from both CT and X-ray scans.
  • TBI AI: A study published in The Lancet: Digital Health detailed a new deep learning system that can accurately detect and quantify lesions associated with traumatic brain injury (TBI) in CT scans. The CNN was trained on images from 60 centers across Europe and tested on an independent set of 500 Indian patients, finding that the algorithm can detect the type, distribution, and extent of TBI injury as well manual assessments.
  • Mount Sinai’s CV19 AI: Mount Sinai developed an AI system that combines medical imaging (chest CT) and clinical data (symptoms, age, bloodwork, and contact tracing) to analyze and identify patients with COVID-19 as well as experienced radiologists (85% vs. 75% sensitivity). Mount Sinai is working to integrate the algorithm into its internal workflows and is making its AI toolkit available to other hospitals worldwide.
  • SyntheticMR & Philips: Philips Healthcare will integrate SyntheticMR’s SyMRI imaging software into its U.S. product catalog, allowing Philips MR users to generate multiple contrast-weighted images and volumetric data in a single 5-6 minute scan. SyntheticMR launched a similar deal with Siemens Healthineers U.S. last summer.

The Resource Wire

– This is sponsored content.

  • The introduction of ultrasound into musculoskeletal care has been a game-changer, revolutionizing the level of precision MSK physicians can bring to patient care. This GE Healthcare profile details how one physician used point of care ultrasound to help improve performance and effectiveness.
  • ClearRead Xray from Riverain Technologies includes the first FDA-cleared software solution to transform a chest x-ray into a soft-tissue image, providing unprecedented clarity for efficient, accurate, early detection of lung disease.
  • This Healthcare Administrative Partners blog post details how independent radiology practices can build upon their relationships with hospitals, referring physicians, and even neighboring radiology practices to remain strong and independent in the face of ongoing consolidation.
  • This Hitachi blog details how the COVID-19 pandemic created new urgency for healthcare systems to adopt and expand tele-health and tele-radiology, while outlining the key considerations for those about to make this transition.
  • In its latest Q&A, Nuance sat down with MaxQ AI’s Randy Rohmer to discuss how its AI platform helps hospitals reduce misdiagnosis and healthcare costs, and share about it’s AI Marketplace partnership with Nuance.

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.