Value-Based Radiology | Mini Magic MRI | Density and Risk

“Hope that you can disrupt health care, but remember that UnitedHealth Group’s revenue is $220 billion and CMS spends $900 billion a year and they both appear mostly powerless to make anything better.”

This is rule number 12 in the THCB’s 12 rules for health tech startups. The other 11 follow a similar theme.


Imaging Wire Sponsors

  • Carestream – Focused on delivering innovation that is life changing – for patients, customers, employees, communities and other stakeholders
  • Focused Ultrasound Foundation – Accelerating the development and adoption of focused ultrasound
  • Medmo – Helping underinsured Americans save on medical scans by connecting them to imaging providers with unfilled schedule time
  • Nuance – AI and cloud-powered technology solutions to help radiologists stay focused, move quickly, and work smarter
  • Pocus Systems – A new Point of Care Ultrasound startup, combining a team of POCUS veterans with next-generation genuine AI technology to disrupt the industry
  • Qure.ai – Making healthcare more accessible by applying deep learning to radiology imaging

The Imaging Wire


Four Steps to Value-Based Radiology


An article from a Philips Healthcare team published on healthdatamanagement.com shared four steps to accelerate imaging’s shift to value-based care, noting that although radiology is among the most affected by the value-based shift, many value based imaging metrics are still undefined. Here’s what they suggest:

  • Start with How – Focus on “how” to move to value-based care rather than “why” to make the move, with a focus on improving health outcomes, patient and staff experiences, and cost of care.
  • Define Metrics – Radiology departments should identify and track leading indicators related to outcomes and productivity, figure out how to overcome challenges, and establish ownership.
  • Improve Patient Experiences – Noting the correlation between positive patient experiences and clinical effectiveness and patient safety, the patient experience should be the focus of all value-based imaging initiatives.
  • Collaborate – Collaboration is crucial given imaging’s broad reach within health systems and the numerous opportunities to improve outcomes and efficiency.
  • Get the Econometrics – It’s important to take into account the local market’s economic pressures and healthcare policies in understanding the “econometrics” of radiology’s role in value-based care, adapting to local models accordingly.



Mini Magic MRI


An Imperial College London team developed a prototype Mini MRI scanner that fits around a patient’s leg, using the ‘magic angle’ effect to potentially diagnose knee injuries faster and more effectively. Here’s how:

  • The Magic Angle – Noting that tendon and ligament brightness is greatest at the “magic angle” of 55 degrees, the system is designed to easily change the orientation of its specially-designed magnet, which can rotate around the patient’s leg while they remain seated. So far the team confirmed the magic angle’s effectiveness on goats and dogs using a conventional MRI and these results make the team encouraged about using this same positioning on humans with the new Mini MRI.
  • All in The Rotation – In addition to increased brightness, the MRI’s rotating magnet can allow physicians to identify collagen fiber patterns, which is important for repairing a torn meniscus and other treatments.
  • Small is Good – The Mini MRI’s small size could expand where MRI systems are available, including local clinics and even in GP surgeries, while potentially reducing NHS waiting times for MRI scans.
  • Next Steps – Noting that this is an early-stage proof-of-concept study, their plan is to advance the new MRI to human trials and potentially evaluate effectiveness for other joints (ankles, wrists and elbows).



RPI’s Imaging Blockchain


Researchers from Rensselaer Polytechnic Institute (RPI) are developing a medical image sharing system that uses IBM’s open source Hyperledger blockchain tech to transfer imaging data between different healthcare entities to support patient care and AI development. Here’s their goal and plan:

  • Defragmenting Imaging Data – The RPI team is trying to evolve the traditionally fragmented way imaging data has been stored and managed, suggesting that a centralized imaging data library could drive greater AI innovations and allow for faster decisions at the point of care.
  • Privacy Focused – Noting the complex role of patient privacy in image transfer and AI, the RPI blockchain platform will develop privacy-preserving techniques to safeguard patient identity, while maintaining flexibility and enforcing data sovereignty.
  • Up Next – The team just gained approval to access data and images from the National Lung Screening Trial (NLST), allowing them to test the system’s performance and impact.

During the California Gold Rush (1849-1850) some people made their fortunes by finding gold, but the greatest success stories were from folks who set up businesses to supply the many hopeful miners (shovels, wheelbarrows, clothes, banks, etc.). That might not be RPI’s goal here, but you can start to see parallels in AI infrastructure projects like this and the suppliers of the gold rush, understanding that not every AI development company is going to make it big but they’re all going to need “supplies” to support their AI rush efforts (GPUs, image sharing, data libraries, marketplaces, etc.). Whether or not you wear Levis Strauss jeans or bank with Wells Fargo (both gold rush success stories), there’s a lot of reasons to view AI infrastructure as a good long term play.



Density and Risk


As the momentum behind breast density awareness and encouraging supplemental screening discussions hits its peak, a study from a UCSF-led team suggests that it’s more effective to discuss routine screening with women who have dense breasts and higher-risk profiles (vs. all women with dense breasts). The cohort study looked at the BI-RADS breast density ratings and BCSC 5-year breast cancer risk levels from 638,856 women aged 40 to 74 years, finding that:

  • Women with heterogeneously dense breasts and BCSC risk levels of 2.5% or higher (6% of screened women) and women with extremely dense breasts and a BCSC risk level of 1% or higher (6.5% of screened women) had the most cases of advanced breast cancer.
  • Women with heterogeneously dense breasts and a 5-year risk under 1.67% (21.7% of screened women) had high rates of false-positive follow-up recommendations.
  • Density-risk subgroups with high advanced cancer risks represented 12.5% of screened women, but 27.1% of advanced cancers.
  • By specifically targeting women with higher density and higher risk profiles for screening discussions it would prevent one case of advanced cancer for every 1,097 discussions (vs. one per 1,866 discussions with all women with dense breasts), while reducing unnecessary anxiety, false positives, and costs among lower-risk women.

Because of this, the study argues that women who have both dense breasts and higher breast cancer risks should be targeted for supplemental imaging discussions, while women with low risk profiles shouldn’t be targeted regardless of their density.


The Wire

  • This may not make it on to the new Bracco Diagnostics site. A new study from a Mayo Clinic team (n=158k patients, 281k GBCA injections) found that gadobenate (Bracco MultiHance) and gadobutrol (Bayer Gadavist) are more likely to be associated with allergic reactions than other GBCAs, while patient gender (female), age (20-50yrs), location (outpatient), and MRI type (abdomen or pelvis exams) also correlate with acute reaction rates.
  • A survey of 936 ACR members detailed teleradiology’s massive presence, with 77.7% performing teleradiology at their practice (more common at larger practices), 85.6% performing teleradiology within the past 10 years, and a notable 25.4% relying on teleradiology for a majority of their annual imaging volumes. Although 84.4% performed teleradiology for internal examinations, 45.7% of the practices support external examinations and between 76.9% and 86.2% of the respondents saw value in using teleradiology to overcome workflow issues (e.g. geographic, after-hours, multispecialty, faster turnarounds). The main teleradiology challenges include electronic health record access (62.8%), quality assurance (53.8%), and technologist proximity (48.4%).
  • OTech’s Herman Oosterwijk shared his takeaways from SIIM 2019, revealing plenty of “good vibes” and highlighting these top-six impressions: 1. AI is over its initial hype (less paranoia and greater understanding that there’s plenty of work to be done), 2. Enterprise imaging is still very challenging (still…), 3. Teleradiology workflow is also very challenging (few PACS vendors do it well, plenty of telerad firms DIYing their PACS), 4. CDs are here to stay (for a while), 5. Cybersecurity is a popular topic, and 6. New standards are supporting greater interoperability.
  • GE Healthcare officially opened its College of Health Technology Management (HTM) last week to address the HTM professional shortage, revealing plans to initially train GE Healthcare employees before expanding to external customers in 2020. The GE College of HTM is located at the GE Healthcare Institute in Waukesha, Wisconsin and features classrooms intended to replicate hospital settings (OR, ER, ICU, nurses’ station, biomed shop, etc.).
  • A new study in the New England Journal of Medicine highlighted MRI’s advantages for guiding revascularization in patients with stable angina, finding that in addition to being noninvasive (plus, faster and without radiation), MRI is as safe as FFR and results in less coronary revascularization. The trial of 918 at-risk patients found that fewer MRI patients were recommended revascularization (40.5% vs. 45.9%) or underwent revascularization (35.7% vs. 45%) than FFR, while MRI had equivalent levels of death, heart attack, or revascularization as FFR within a year (3.6% s. 3.7%).

The Resource Wire

– This is sponsored content.

  • This Qure.ai video details how its qXR TB chest X-ray tool is transforming tuberculosis screening.
  • This POCUS Systems video details how its forthcoming ultrasound helps patients and providers, and reduces reliance on MSK MRI use.
  • By partnering with Medmo, imaging centers can keep their schedules full and their equipment busy. Here’s where to learn more and get started.

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.