Nigam Shah, MBBS, PhD and Michelle Mello, PhD, JD, in a commentary on a JAMA Network Open study on discrepancies between AI regulatory clearances and marketing materials.

Imaging Wire Sponsors

Annalise.ai  •  Arterys  •  Bayer  •  Blackford  •  CARPL.ai  •  Change Healthcare  •  Clearpath  •  Enlitic  •  GE HealthCare  •  Intelerad  •  Medality  •  Merge by Merative  •  Nuance  •  PocketHealth  •  Riverain Technologies  •  Siemens Healthineers  •  Subtle Medical  •  United Imaging  •  Us2.ai  •  Visage Imaging

Artificial Intelligence

Can You Believe the AI Hype?

Can you believe the hype when it comes to marketing claims made for AI software? Not always. A new review in JAMA Network Open suggests that marketing materials for one-fifth of FDA-cleared AI applications don’t agree with the language in their regulatory submissions. 

Interest in AI for healthcare has exploded, creating regulatory challenges for the FDA due to the technology’s novelty. This has left many AI developers guessing how they should comply with FDA rules, both before and after products get regulatory clearance.

This creates the possibility for discrepancies between products the FDA has cleared and how AI firms promote them. To investigate further, researchers from NYU Langone Health analyzed content from 510(k) clearance summaries and accompanying marketing materials for 119 AI- and machine learning (ML)-enabled devices cleared from November 2021 to March 2022. Their findings included:

• Overall, AI/ML marketing language was consistent with 510(k) summaries for 80.67% of devices
• Language was considered “discrepant” for 12.61% and “contentious” for 6.72% 
• Most of the AI/ML devices surveyed (63.03%) were developed for radiology use; these had a slightly higher rate of consistency (82.67%) than the entire study sample

The authors provided several examples illustrating when AI/ML firms went astray. In one case labeled as “discrepant,” a developer touted the “cutting-edge AI and advanced robotics” in its software for measuring and displaying cerebral blood flow with ultrasound. But the product’s 510(k) summary never discussed AI capabilities, and the algorithm isn’t included on the FDA’s list of AI/ML-enabled devices.

In another case labeled as “contentious,” marketing materials for an ECG mapping software application mention that it includes computation modeling and is a smart device, but require users to request a pamphlet from the developer for more information.

The Takeaway 

So, can you believe the AI hype? This study shows that most of the time you can, with a consistency rate of 80.67% – not bad for a field as new as AI (a fact acknowledged in an invited commentary on the paper). But the study’s authors suggest that “any level of discrepancy is important to note for consumer safety.” And for a technology that already has trust issues, it’s probably best that developers not push the envelope when it comes to marketing.

Maximizing AI to Streamline CT Workflow

Increasing demand for healthcare has led to a boom in imaging exam volume, with studies such as CT requiring complex scanning protocols. Learn how GE HealthCare is evolving CT workflows with its efficient scanning solutions.

Disaster Recovery for the 21st Century

Are you sure your imaging archive is safe and recoverable? See how Intelerad’s Cloud DR disaster recovery solution mitigates the many risks facing your archive by securely storing copies of every image.

Precision Imaging’s Accelerated Enhancement

When one of Precision Imaging Centers’ 3T MRIs wasn’t meeting their requirements, they implemented Subtle Medical’s SubtleMR solution, rather than purchasing a new scanner or an expensive upgrade. See how SubtleMR enhanced Precision’s patient throughput and comfort, without compromising image quality in this case study.

The Wire

• AI for Echo Gets Outpatient Code. Is the dam holding back reimbursement for AI in medical imaging starting to break? This week Ultromics said CMS has established a new HCPCS outpatient code (C9786) for the use of echo image processing for computer-aided detection of heart failure with preserved ejection fraction (HFpEF), a difficult-to-diagnose condition that makes up some 50% of heart failure cases in the US. Ultromics said the move will apply to its EchoGo Heart Failure software, which got FDA clearance in December 2022. 

• AI of Brain MRI Gets CPT Code: In related news, reimbursement for the use of AI for brain MRI scans also got a boost when the AMA issued a Category III CPT code for AI-based brain quantification software, enabling users to request reimbursement from payers. AI developer icometrix said the code will apply to its application for analyzing neurological disorders such as multiple sclerosis, dementia, and traumatic brain injury. There are a limited number of radiology AI applications that have CPT III codes; limited reimbursement is one of the factors believed to be holding back wider adoption of AI in healthcare. 

• CMS Proposes New Breakthrough Device Pathway: Finally, FDA-cleared “breakthrough devices” could soon have a quicker path to reimbursement if CMS’ proposed Transitional Coverage for Emerging Technologies (TCET) pathway is enacted. With the goal of finalizing coverage within six months of FDA approval, the TCET pathway would give device makers access to CMS officials prior to FDA market authorization to review early evidence, help design studies to address payer concerns, and offer guidance on the best existing coverage areas. 

• AI Generates Synthetic CT: Maybe you’ve heard of synthetic digital breast tomosynthesis (DBT), but how about synthetic CT? In Radiology, researchers from France describe the effectiveness of their technique for using AI to create high-resolution synthetic CT lung images from MRI scans. In a dataset of 82 patients with cystic fibrosis, synthetic CT had similar SNR compared to real CT (88 vs. 88) and lower noise level (median score 26 vs. 42). They concluded that synthetic CT has almost perfect concordance with real CT, without the radiation.

• Us2.ai & Core Sound Imaging’s Mount Sinai Pilot: Echo AI company Us2.ai and PACS workflow company Core Sound Imaging announced that the Mount Sinai Health System will pilot Core Sound’s new Studycast Integration Program, bringing Us2.ai’s AI-automated analysis into Mount Sinai’s echo viewing and reporting workflows. Us2.ai’s echo analysis will be presented to clinicians directly within the Studycast interface, allowing them to review and apply results to their Studycast worksheets and reports. Core Sound Imaging is Mount Sinai’s longtime echo PACS provider.

• Model Predicts COVID Severity: Adding quantitative CT data and radiomics analysis to standard CT can better predict which COVID-19 patients with initially mild presentation will progress to severe disease. In a study in European Radiology, French researchers showed how they improved on the AUC of conventional CT by first adding quantitative data from Siemens Healthineers’ syngo.via Pneumonia Analysis software and then radiomics data from the open-source PyRadiomics software (AUC=0.70 vs. 0.73 vs. 0.77). 

• United Imaging Debuts New Scanners: United Imaging Healthcare is debuting three new scanners at AHRA 2023, July 9-12 in Indianapolis. They include uMR 680, a 1.5-tesla MRI scanner with fixed or detachable table; uCT ATLAS, a CT system with an 82cm bore available in up to 640 slices; and uDR 380i pro, a mobile DR unit with high-voltage generator and uVision remote console. The new systems join uMI Panorama, a new wide-bore PET/CT scanner that launched at SNMMI 2023, as new products in United Imaging’s catalog.  

• Bayer Studies New MRI Agent: Pharmaceutical giant Bayer is reporting progress on gadoquatrane, a new high-relaxivity gadolinium-based contrast agent (GBCA) it is developing for MRI. The company said it has started the QUANTI phase III clinical development program for the agent, particularly whether the GBCA can be used at a gadolinium dose that’s 60% lower than standard dosing of established MRI contrast. High-relaxivity MRI agents have begun entering the market, offering the prospect of lower risk of gadolinium contrast reactions. 

• Challenges of 7T MRI: What are the clinical benefits – and challenges – involved in the operation of a 7T MRI scanner? In a new study in AJR, a group from the University of Minnesota describes their experiences with Magnetom Terra, a commercially available 7T scanner from Siemens Healthineers installed in 2020. The group has seen gains in SNR and CNR, but this hasn’t necessarily translated into faster imaging, and specific absorption rate (SAR) must be carefully controlled. Siemens at RSNA 2022 introduced Magnetom Terra.X, the latest version of the 7T platform.

• Imagion Expands Siemens MRI Deal: In other MRI contrast news, Australian contrast developer Imagion Biosystems has signed an expansion of its collaboration with Siemens Healthineers for Imagion’s MagSense HER2 agent. The agent is dedicated for imaging lymph nodes of breast cancer patients, and Siemens has provided support to Imagion for phase I clinical studies, with multisite phase II trials on the near horizon. The new deal extends the collaboration between the companies for two years and expands it to the US.  

• Volpara Nabs Microsoft Award: Density software developer Volpara Health has received the Healthcare & Life Sciences 2023 Microsoft Partner of the Year Award. The award recognizes Microsoft partners that have “developed and delivered outstanding Microsoft-based applications, services, and devices” over the past year, with honorees chosen from over 4,200 submitted nominations. Microsoft experts worked with Volpara to develop software for detecting breast arterial calcification (BAC), a possible sign of heart disease, on mammography and tomosynthesis images. 

• Affidea Expands in Portugal: European imaging services provider Affidea is expanding in Portugal with the acquisition of two imaging centers. The company has purchased Clínica Radiologia de Albufeira and Clínica do Coração do Alentejo, entering the Algarve region of southwestern Portugal. Affidea last year began working with AI platform developer Incepto on the rollout of AI applications across Affidea centers in Portugal. 

• Neko Raises $65M: Swedish whole-body scanning firm Neko Health raised $65M in a Series A funding round that the company will use to fast-track its concept of preventive care across Europe and the US. The firm was cofounded by Spotify CEO Daniel Ek, and it plans to offer a 10-minute scan that will cost about $270. 

Imaging AI’s Next Wave

We may be entering a third wave of imaging AI’s rapid evolution, one that brings a shift from narrow point solutions to comprehensive multi-finding AI systems. Hear this discussion with Annalise.ai Chief Medical Officer Rick Abramson, MD, exploring how this transition could take place, how radiologist and VC perspectives on AI are changing, and how AI might continue to evolve in the future.

The Complete Guide to Radiology AI

Radiology is leading healthcare’s AI revolution, and yet many people in radiology are just starting to build their understanding of AI. That’s why Bayer published its truly Complete Guide to Artificial Intelligence in Radiology, detailing how AI can address radiology’s challenges, AI’s core use cases, and AI’s path towards adoption.

The Resource Wire

• Imaging AI is evolving fast, but radiology leaders’ expectations for their AI technologies might be evolving even faster. In this Imaging Wire Show with Dr. Charlene Liew of SingHealth and Dr. Nina Kottler of Radiology Partners, we explore radiology leaders’ current and future expectations for AI, and the central role platforms play in their AI roadmaps.

• How is PocketHealth empowering patients with image-sharing technology that gives them fast and easy access to their medical information? Find out in this BackTable Innovation Podcast interview with the company’s co-founder and CEO, Rishi Nayyar.

• Every 34 seconds, a patient dies of cardiovascular disease. Find out how you can better manage cardiovascular image data and improve patient care with syngo Dynamics from Siemens Healthineers.

• Radiology follows a structured workflow to ensure accurate and timely imaging. But where does efficiency break down between referral and diagnosis, and how can you prevent this from happening? Find out in this Enlitic white paper.

• What’s the latest news from United Imaging Healthcare? Driven by a focus on R&D, United has increased its brand influence and market share worldwide. Get the details in the company’s first annual report since going public. 

• Over 9 out of 10 people who should be screened for lung cancer aren’t, and nearly 50% of lung cancer cases are caught in the advanced stages. But lung cancer screening has been challenging. Riverain has assembled this resource page for anyone interested in starting or improving their lung screening program.

• What tools are available to help radiologists work remotely? In this case study, teleradiology provider 4ways Healthcare of the UK describes how they used Merative’s Merge PACS 8.0 platform to improve their service to clients while supporting remote radiologists.

• Medical providers and health systems are looking to ditch the disc and modernize their patients’ journey. Learn how Clearpath helps them reduce the cost of retrieving and fulfilling patient requests for imaging and medical records.

• Trying to decide between public and private cloud for medical image management? Watch this brief Change Healthcare animation detailing the operational benefits of public cloud hosting for imaging.

• How can radiology practices use innovative training and education techniques to grow and overcome the ongoing shortage of radiologists? Find out in this Imaging Wire Show interview with Daniel Arnold and Deanna Heier of Medality.

• Mount Sinai Hospital is using AI echo technology from Us2.ai and Core Sound Imaging to expand access to heart health in a pilot program that will allow more New York hospitals to benefit from AI tools and workflow improvements. 

• Us2.ai just published what might be the most comprehensive paper we’ve seen on AI echo, detailing the benefits of AI-automated echocardiography, the global need for more scalable and flexible CVD assessments, and how its technology is fit for the future. 

• AI delivers value to a wide range of healthcare stakeholders, but its primary value to health systems originates from its ability to automate tasks, democratize care, and deliver hard and soft ROI. See how these factors impact health systems’ bottom line in this Arterys report.

• Join the conversation in this webinar recording and hear from PACS administrator Griff R. Van Dusen of Memorial Health System how Nuance PowerScribe One’s next-generation reporting experience helps streamline workflow and improve report quality so radiologists can get more done in less time. 

• CloudPACS has finally arrived. Learn more about the benefits that cloud-based PACS can have for your radiology practice and how Visage Imaging’s Visage 7 was built from the ground up to ensure maximum performance, security, and scale. 

• Check out this Blackford Analysis video detailing how its AI platform streamlines AI adoption and workflows, allowing radiology teams to achieve AI’s clinical benefits without operational sacrifices.