|
A Lung CT Alliance | The Who & How of AI Implementations
August 3, 2022
|
|
|
|
|
Together with
|
|
|
|
“Radiology is 5% finding things, and 95% knowing what to look for.”
|
|
A tweet from Memorial Sloan Kettering’s Anton Becker, MD, PhD.
|
|
|
|
RevealDx and contextflow announced a new alliance that should advance the companies’ product and distribution strategies, and appears to highlight an interesting trend towards more comprehensive AI solutions.
The companies will integrate RevealDx’s RevealAI-Lung solution (lung nodule characterization) with contextflow’s SEARCH Lung CT software (lung nodule detection and quantification), creating a uniquely comprehensive lung cancer screening offering.
contextflow will also become RevealDx’s exclusive distributor in Europe, adding to RevealDx’s global channel that includes a distribution alliance with Volpara (exclusive in Australia/NZ, non-exclusive in US) and a platform integration deal with Sirona.
The alliance highlights contextflow’s new partner-driven strategy to expand SEARCH Lung CT beyond its image-based retrieval roots, coming just a few weeks after announcing an integration with Oxipit’s ChestEye Quality AI solution to identify missed lung nodules.
In fact, contextflow’s AI expansion efforts appear to be part of an emerging trend, as AI vendors work to support multiple steps within a given clinical activity (e.g. lung cancer assessments) or spot a wider range of pathologies in a given exam (e.g. CXRs):
- Volpara has amassed a range of complementary breast cancer screening solutions, and has started to build out a similar suite of lung cancer screening solutions (including RevealDx & Riverain).
- A growing field of chest X-ray AI vendors (Annalise.ai, Lunit, Qure.ai, Oxipit, Vuno) lead with their ability to detect multiple findings from a single CXR scan and AI workflow.
- Siemens Healthineers’ AI-RAD Companion Chest CT solution combines these two approaches, automating multiple diagnostic tasks (analysis, quantification, visualization, results generation) across a range of different chest CT exams and organs.
The Takeaway
contextflow and RevealDx’s European alliance seems to make a lot of sense, allowing contextflow to enhance its lung nodule detection/quantification findings with characterization details, while giving RevealDx the channel and lung nodule detection starting points that it likely needs.
The partnership also appears to represent another step towards more comprehensive and potentially more clinically valuable AI solutions, and away from the narrow applications that have dominated AI portfolios (and AI critiques) before now.
|
|
|
University of Colorado’s Case for ClearRead Bone Suppress
This Riverain Technologies case study details how the University of Colorado Hospital enhanced its chest X-ray workflow with ClearRead Bone Suppress.
|
|
DASA and CARPL.ai’s Pediatric AI Evaluation
When Sao Paolo’s Diagnosticos da America SA (DASA, the world’s 4th largest diagnostics company) set out to evaluate Qure.ai’s QXR solution for their pediatric chest X-ray workflows, they leveraged CARPL.ai’s platform to streamline their evaluation. See how it worked here.
|
|
- MIT’s Ultrasound Patch: MIT researchers developed a stamp-sized ultrasound patch that provides continuous imaging of blood vessels and internal organs. The researchers had volunteers wear the ultrasound patch for 48 hours while they performed various activities such as sitting and jogging, finding that it maintained adhesion and produced high-resolution images throughout the study. The team will next focus on supporting wireless operation, as it works towards its goal of making the patch as accessible as “Band-Aids at the pharmacy.”
- AI Implementation Roadmap: Some of the biggest names in imaging AI just published what might be the most well thought out framework for implementing clinical AI. The RSNA Special Report is worth a complete review for anyone implementing AI, with details on infrastructure requirements, governance, AI tool decision making, and ongoing monitoring and maintenance.
- Low Portal Engagement: A study out of UAB found that patients often skip the radiology report area of their online patient portals. Analysis of 139k patients who accessed UAB’s portal found that only 27% interacted with its radiology report section, while 47% accessed the portal’s lab results section. Although certain groups were more likely to use the patient portal (white, female, more educated), researchers couldn’t identify demographic explanations for why patients accessed the radiology and lab report sections.
- Ultrasound X-Rays: A team of China-based researchers developed an AI algorithm called UXGAN (Ultrasound to X-ray Generative Attentional Network) that creates X-ray-like images from ultrasound exams. In their study of 200 children, the researchers found that the ultrasound-synthesized X-rays produced scoliosis measurements that were comparable to actual X-ray images (r = 0.95).
- Cleerly Closes Series C (Again): Even though we called Cleerly’s $192M Series C “colossal” in our original coverage last week, the heart attack prediction startup wasn’t done yet, and has now officially closed the funding round after bumping the total raise to $223M. Cleerly plans to use the investment to expand the commercial reach of its AI software that evaluates noninvasive CT angiograms for plaque build-up to enable earlier detection of heart disease and calculate the likelihood of a patient having a heart attack.
- Value-Based Time-Out: A provocative opinion piece in STAT made waves last week after calling for a “time-out” for value-based care experimentation. The authors make the case that current approaches to value-based care have ambiguous quality metrics that do little to improve outcomes but plenty to incentivize reducing care and upcoding.
- GE’s Premium Definium 656 HD: GE Healthcare launched its Definium 656 HD X-ray system, positioning it at the top of its fixed overhead tube suspension X-ray lineup. Continuing GE’s recent focus on improving imaging team workflows, much of the Definium 656 HD’s highlighted features focus on automating technologists’ tasks, either through direct workflow enhancements (e.g. auto-positioning, image consistency tools, in-room workflows) or through image quality features that cut ‘repeat and reject’ rates (e.g. new detectors, image processing, image creation apps).
- NY Imaging Center Fraud: A New York imaging center owner is facing federal and civil charges related to operating a referral kickback scheme and performing unnecessary exams. For years, Payam Toobian MD and his company America’s Imaging allegedly bribed other physicians to refer patients for exams and performed additional procedures that weren’t included in the referral orders (including contrast-enhanced MRIs), leading to over $1M in false Medicaid claims.
- CXR + VBC Mortality Predictions: A new PLOS Digital Health study detailed a creative chest X-ray-based AI system that accurately predicted COVID patients’ comorbidities and mortality, and could be used to guide treatment decisions. The researchers trained the model using 14k non-COVID CXRs to predict a range of data points (sex, age, value-based care HCC codes, RAF risk scores) and tested it against 900 COVID patients’ CXRs (487 external), predicting six different comorbidities with a 0.85 AUC. They then applied those biomarkers to a logistic regression model, which predicted patient mortality with a 0.84 AUC.
- Hospital Margin Loss Streak: Patient volume and expense improvements haven’t been enough to offset the hospital industry’s growing cost of care, as US hospitals’ median operating margin is now officially in the red through the first six months of the year (-0.09%). Kaufman Hall’s latest National Hospital Flash Report showed positive month-over-month trends for both outpatient revenue (up 2.6%) and operating room minutes (up 2.4%), but margins are still “nowhere near pre-pandemic levels” and “will likely end up with historically low margins for the remainder of the year.”
- Family Medicine POCUS: A new Michigan Medicine study revealed promising point-of-care ultrasound adoption trends within US family medicine departments, while also highlighting key POCUS adoption barriers. The 2021 survey of 96 family medicine leaders found that 81% of their departments have at least one POCUS-trained faculty member and 44% use POCUS in outpatient care, but only 6% are billing for these exams. The respondents cited faculty time and funding as their two main POCUS training barriers (48% & 15%), while describing equipment purchasing and POCUS exam billing as “difficult” (70% & 73%).
|
|
Geisinger’s Case for the syngo Virtual Cockpit
When Geisinger Health set a goal to improve access to care, it leveraged Siemens Healthineers’ syngo Virtual Cockpit to ensure that its expert radiologic technologists were accessible to all 11 of its radiology facilities. Hear what Geisinger’s technologists and administrators had to say about how the remote scanning solution allowed them to extend hours and improve patient throughput.
|
|
Canon Across America
We’re excited to share the latest Imaging Wire Show, featuring Canon Medical Systems’ David Hashimoto. We explore Canon’s new approach to connecting with imaging teams, important insights into what imaging teams need, and how Canon is working to address those needs. Whether you’re on an imaging team or you work with them, you should check out this interview!
|
|
- Us2.ai recently announced the global launch of its flagship echocardiography AI solution, leveraging a new $15M Series A round, and its unique abilities to completely automate echo reporting (complete editable/explainable reports in 2 minutes) and analyze every chamber of the heart (vs. just left ventricle with some vendors).
- Ready to Update Your PACS? This Novarad blog outlines the product, vendor, future-proofing, and support considerations to help make sure you select the right system.
- Change Healthcare’s cloud-native, zero-footprint Stratus Imaging PACS is now live in clinical use. See how Stratus Imaging PACS is helping radiology practices improve productivity and patient care, while eliminating the cost and resource constraints of on-premise systems.
- Take the AiCE challenge and see why half the radiologists in a recent study “had difficulty differentiating” images from Canon Medical Systems’ Vantage Orian 1.5T MR using its AiCE reconstruction technology compared to standard 3T MRI images.
- The Hyperfine Swoop Portable MR’s accessibility advantages can translate to significant clinical and operational value, particularly for hospital emergency and intensive care departments. See how bringing MRI to the point-of-care can impact hospitals’ operational costs, quality of care, and revenue potential.
|
|
|
|
|
