Bharadwaj P et al, in a new study in JACR on the economic value of AI.

Imaging Wire Sponsors

Bayer  •  Blackford  •  CARPL.ai  •  Clearpath  •  DeepHealth  •  Enlitic  •  Gleamer  •  Intelerad  •  Medality  •  Merge by Merative  •  Nuance  •  PocketHealth  •  Riverain Technologies  •  Siemens Healthineers  •  SpinTech MRI  •  TeraRecon  •  United Imaging  •  Us2.ai  •  Visage Imaging

Artificial Intelligence

Study Shows AI’s Economic Value

One of the biggest criticisms of AI for radiology is that it hasn’t demonstrated its return on investment. Well, a new study in JACR tackles that argument head on, demonstrating AI’s ability to both improve radiologist efficiency and also drive new revenues for imaging facilities. 

AI adoption into radiology workflow on a broad scale will require significant investment, both in financial cost and IT resources. 

• So far, there have been few studies showing that imaging facilities will get a payback for these investments, especially as Medicare and private insurance reimbursement for AI under CPT codes is limited to fewer than 20 algorithms. 

The new paper analyzes the use of an ROI calculator developed for Bayer’s Calantic platform, a centralized architecture for radiology AI integration and deployment. 

• The calculator provides an estimate of AI’s value to an enterprise – such as by generating downstream procedures – by comparing workflow without AI to a scenario in which AI is integrated into operations.

The study included inputs for 14 AI algorithms covering thoracic and neurology applications on the Calantic platform, with researchers finding that over five years … 

• The use of AI generated $3.6M in revenue versus $1.8M in costs, representing payback of $4.51 for every $1 invested
• Use of the platform generated 1.5k additional diagnoses, resulting in more follow-up scans, hospitalizations, and downstream procedures
• AI’s ROI jumped to 791% when radiologist time savings were considered
• These time savings included a reduction of 15 eight-hour working days of waiting time, 78 days in triage time, 10 days in reading time, and 41 days in reporting time  

Although AI led to additional hospitalizations, it’s possible that length of stay was shorter: for example, reprioritization of stroke cases resulted in 264 fewer hospital days for patients with intracerebral hemorrhage. 

• Executives with Bayer told The Imaging Wire that while the calculator is not publicly available, the company does use it in consultations with health systems about new AI deployments. 

The Takeaway

This study suggests that examining AI through the lens of direct reimbursement for AI-aided imaging services might not be the right way to assess the technology’s real economic value. Although it won’t settle the debate over AI’s economic benefits, the research is a step in the right direction.

All-In with United Imaging

United Imaging’s “all-in” approach means that every system ships with its entire suite of features and capabilities (no options), giving its clients more clinical flexibility and predictability.

The Difference Is in the Details

Riverain Technologies has developed the capability to create synthetic nodules automatically and place them in relevant anatomical contexts. Hear Chief Science Officer Jason Knapp explain the company’s unique position in this video.

The Wire

• PocketHealth Raises $33M: Medical image sharing firm PocketHealth has raised $33M in a massive Series B funding round, bringing the firm’s total equity funding to $56M to date. Founded in 2016, the company now manages images for 1.5M patients at 775 healthcare providers across the US and Canada. PocketHealth’s most recent product launches include MyCare Navigator and Follow-Up Navigator, and the company said it plans to leverage AI to help create healthcare experiences that are personalized for each patient. 

• News from NVIDIA’s GTC 2024: GPU giant NVIDIA this week is holding its GTC conference as an in-person event in San Jose, California for the first time since the COVID-19 pandemic. NVIDIA makes the microchips that serve as the backbone for compute-intensive applications like AI, so GTC is a closely watched event. Top news from GTC 2024 includes NVIDIA’s launch of the new Blackwell processing chip, as well as NIMs, a set of microservices designed to help developers accelerate the creation of applications in areas such as generative AI. 

• Microsoft, NVIDIA Expand Partnership: In related news, NVIDIA and Microsoft are expanding their relationship in a move that will benefit healthcare and imaging providers. The extended collaboration covers a variety of clinical and drug discovery uses; for example, they will offer a combination of Microsoft’s Azure cloud platform with NVIDIA’s MONAI algorithm development framework and Nuance’s Precision Imaging Network (PIN). The partnership should promote faster AI algorithm development and deployment, with Flywheel also providing its services for research-based AI. 

• GE Leverages NVIDIA Tech for US App: NVIDIA tools were used by GE HealthCare to develop an AI algorithm for segmenting objects like lesions and organs on ultrasound images. Called SonoSAMTrack, GE’s large vision model app was rapidly developed thanks to NVIDIA’s TensorRT software development kit, and the project represents an elevated level of collaboration between the companies. SonoSAMTrack is currently in testing on a research basis, but could become a clinical application once regulatory clearances are received.

• Dental Gadolinium Build-Up: In a new study in AJR, researchers used mass spectrometry to detect gadolinium accumulation in extracted teeth of young adults who had received MRI scans with gadolinium-based contrast agents. The small study included just 10 patients, but showed a correlation between GBCA exposure and retention in the dentin and enamel, with higher doses correlating to higher concentrations. While there are no known health effects due to retention of small amounts of gadolinium, the study is a disturbing reminder of gadolinium’s environmental persistence, even as radiology reduces reliance on the material. 

• ‘Havana Syndrome’ Doesn’t Appear on MRI: An NIH team was unable to find evidence on brain MRI scans of “Havana Syndrome,” a mysterious ailment that affected workers at the US embassy in Havana, Cuba starting in 2016. Embassy workers reported a variety of symptoms like headaches and forgetfulness; speculation on their cause ranged from pesticides to a “sonic weapon.” But in a study this week in JAMA, NIH researchers said there was no difference in brain structure on MRI between government personnel and normal controls. The mystery deepens ….

• Ultrasound Contrast Partnership: Bracco Imaging and Samsung Medison have forged a partnership to develop ultrasound contrast agents. In an announcement at ECR 2024, the companies said their collaboration would focus on developing protocols for high-frequency and super-resolution diagnostic ultrasound, and would also include provider education, global marketing, and joint participation at events. Bracco’s quantitative diagnostic analysis software will also be integrated with Samsung Medison’s equipment to improve image reporting. Future research could focus on ultrasound-targeted delivery of therapeutic drugs. 

• Top Influencers at ECR 2024: Who were the most prominent social media influencers at ECR 2024? A new report from analytics firm GemSeek documented the heavy influence of imaging OEMs at the show, with GE HealthCare, Siemens Healthineers, Philips, and Canon Medical Systems dominating the report’s “brand buzz” section. Imaging executives filled most of the top 10 influencers section, with Roland Rott of GE the top influencer, followed by Samuel Oliveira of Everything MRI, Philipp Fischer of Siemens, Bruno Triaire of Canon, and radiologist Amine Korchi, MD, rounding out the top five. The number of LinkedIn posts rose 99% over 2023 (2.4k  vs. 1.2k), while X/Twitter posts fell 32% (1.5k vs. 2.2k), perhaps due to controversies dogging the Elon Musk-owned channel. 

• NEJM AI to Require AI Trial Registration: As a condition for publication, NEJM AI will require that clinical trials involving AI-based interventions be registered in a trial database that meets WHO standards. The new rules apply to any trial that starts enrolling patients after January 1, 2025, and are designed to ensure that AI trials “meet the same bar for clinical evidence as other clinical interventions.” The move comes amid concerns about the transparency of AI performance, especially with the rise of large language model generative AI algorithms.

• AI’s Effect on Radiologists Varies: How does AI affect radiologist performance in reading medical images? A new study in Nature Medicine addresses this question, but results were mixed. Researchers had 140 radiologists perform 15 tasks in reading chest X-rays with AI assistance; factors such as experience, subspecialty, and familiarity with AI tools failed to predict whether AI helped their interpretations – and in some cases AI hurt their performance. The take-home message? AI developers should work with radiologists to personalize their tools and ensure a beneficial impact. 

• Simpler AI Breast Cancer Risk Prediction: MIT’s Mirai AI algorithm has shown value for predicting five-year breast cancer risk. In a new paper in Radiology, Duke University researchers tested a Mirai variant they developed called AsymMirai that’s simpler and easier to understand, calculating risk by analyzing breast bilateral dissimilarity. In tests on mammograms of 82k patients, AsymMirai performed almost as well as Mirai in predicting a woman’s risk of breast cancer over one year (AUC=0.79 vs. 0.84) and five years (AUC=0.66 vs. 0.71).   

• Reducing Contrast Dose with Photon-Counting CT: German researchers reduced contrast dose on photon-counting CT while maintaining image quality. In a paper in Heliyon, researchers say that during the 2022 contrast shortage they tested a protocol with Siemens Healthineers’ Naeotom Alpha scanner using 50-70% contrast dose in 83 patients; image quality at 70% dose was indistinguishable from full-dose scans, and SNR and CNR were less affected by less contrast than conventional energy-integrating CT. They said a virtual monoenergetic imaging protocol at 50 keV boosted image quality of low-dose photon-counting CT.

CARPL Adopted in Singapore

When it began implementing its AimSG nationwide AI program, Singapore’s Synapxe health technology agency relied on the CARPL.ai platform to make everything work. Learn more in this article.

Delighting Patients with Medical Image Sharing

A new platform from Clearpath now enables healthcare providers to delight their patients by sharing images and medical records digitally. Find out how it integrates simply into your practice.

The Resource Wire

• AI Helps Residents Detect Fractures: Gleamer’s BoneView AI algorithm helped radiology residents detect fractures on adult and pediatric radiographs. Learn more about how it worked in this research summary. 

• Best in KLAS for Image Exchange: With over 15k connected facilities and a dedicated outreach team building new connections every day, it’s no wonder Nuance PowerShare Image Sharing was named #1 Best in KLAS 2024 for image exchange. Learn more about this award-winning solution. 

• Your Single Solution for AI, 3D, and Full Interoperability: Realize immediate value across your organization with subscription-based advanced visualization and AI from TeraRecon that accelerates imaging workflows and improves patient outcomes. Schedule a demo today. 

• The UK’s Lung Cancer Screening Rollout: The UK has launched a targeted lung cancer screening program to improve lung cancer outcomes through earlier detection. Learn how DeepHealth’s Saige Lung is the preferred AI solution in this case study. 

• Home-Based Cardiac Ultrasound: How is home-based AI-aided cardiac ultrasound poised to change global healthcare? In this article from Us2.ai, hear from Izabella Uchmanowicz, RN, on how the CUMIN study is empowering nurses to perform AI-POCUS. 

• The Present and Future of Lung Cancer Screening: What is the latest evidence to support lung cancer screening, and what role will AI play? Watch this on-demand Bayer webinar to learn about evidence-based recommendations for the diagnosis and management of lung cancer. 

• Embrace the Cloud: The right partner for cloud-based PACS can change everything. Find out how Intelerad can help you optimize the benefits of cloud technology and scalability without sacrificing the performance of onsite architecture.

• Start at the Source to Improve MRI: Looking for ways to improve MRI speed and image quality while addressing broader concerns in healthcare? The answer may lie in proven MRI physics in your existing scanner – learn how to unlock it with STAGE from SpinTech MRI. 

• The Essence of Visage: What impact is Visage 7 Enterprise Imaging Platform having on healthcare enterprises? Find out from Visage customers in their own words how Visage 7 can help you eliminate your legacy PACS.

• Expanding Your Talent Pool with Teleradiology: Teleradiology can be a force multiplier in radiology. Watch this Medality webinar recording with Daniel Corbett of Radiology Business Solutions to learn the pros, cons, and essential factors for private practice leaders considering teleradiology integration.

• Simplifying Patient Access to Imaging: A major U.S. healthcare provider faced challenges simplifying imaging workflows and reducing costs. Learn how PocketHealth improved patient experience and efficiency, and saved $130,000 in annual costs. 

• Make Health Smarter with Merge: Address your imaging needs today and face the future with confidence with Merge by Merative. Learn more about enabling better outcomes for your physicians and patients with Merge Imaging Suite.

• Radiology Data Standardization with AI: Enlitic offers healthcare providers a transformative approach to patient care, operational efficiency, and resource utilization. Learn how the company’s ENDEX solution can help you generate a return on investment through AI-based radiology data standardization. 

• Top 5 Obstacles to Radiology AI Adoption: AI is reshaping healthcare, but some healthcare providers are encountering hurdles that demand strategic approaches for successful implementation. Learn the top 5 obstacles to radiology AI adoption – and how to avoid them – in this blog post from Blackford.

• Going Mobile with MRI Just Got Easier: Mobile MRI can help you deliver healthcare to your patients wherever they are. Find out in this article how the new MAGNETOM Viato.Mobile scanner from Siemens Healthineers makes going mobile with MRI easier than ever.