Ross J et al, writing in Clinical Radiology on their proposal to create a program to track postmarket AI performance.

Imaging Wire Sponsors

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

Uncategorized

A New Breast Imaging Option?

When it comes to mammography screening for women with dense breast tissue, radiologists have long looked for alternatives to established modalities like MRI and ultrasound. In a paper in Radiology: Imaging Cancer, researchers put a new twist on an older technology, positron emission mammography (PEM). 

Molecular imaging technologies like PEM have been investigated for years as potential adjuncts to conventional mammography due to the challenges X-ray imaging has with dense breast tissue. 

• These technologies have carried different names – PEM, breast-specific gamma imaging, molecular breast imaging – but in the end all have fallen short due to the higher radiation dose they deliver compared to mammography. 

But Canadian startup Radialis has developed a new version of PEM with its Radialis PET Imager that drastically cuts radiation dose by targeting specific organs, enabling clinicians to use far lower doses of radiopharmaceuticals. The company received clearance for the system in 2022. 

• Radialis touts its system as having high spatial resolution and a small field of view thanks to digital detectors with thousands of silicon sensors that can be placed next to the target organ; this makes it well-suited for imaging specific organs like the breast.

In the new paper, Canadian researchers tested the Radialis system as an adjunct to X-ray mammography in a pilot study of 25 women recently diagnosed with breast cancer. 

• They wanted to see if PEM performed as well as breast MRI, but with fewer false positives and a radiation dose closer to screening mammography.  

Women underwent PEM at three FDG dose levels – 37, 74, or 185 MBq (for comparison, standard whole-body PET uses 370 MBq, a level that translates to a radiation exposure of 6.2-7.1 mSv). Researchers found …

• PEM had sensitivity of 87% across all FDG dose levels (MRI was 100%)
  • The sample size was too small to detect statistically significant differences in sensitivity between dose levels
• PEM had specificity of 95%
• PEM detected 96% of known index malignant lesions (24 of 25), with the one miss occurring in a patient at the 37MBq level
• PEM’s radiation dose ranged from 0.62-1.42 mSv, versus 0.44 mSv for a two-view screening digital mammogram

The Takeaway

The findings show that PEM with the Radialis system is a feasible adjunctive breast imaging modality at a radiation dose that’s mostly acceptable relative to X-ray-based mammography. But (as always) additional studies with larger patient populations are needed.

Best in KLAS PACS

Intelerad’s InSight PACS has been named Best in KLAS for UK and Ireland PACS by KLAS Research. Learn more about the solution that’s been adopted by over 250 healthcare providers across the UK and Ireland.

Visit TeraRecon at ECR 2024

Discover how TeraRecon’s solutions can deliver clinical decision support across your enterprise and explore the latest updates to their industry-leading advanced visualization software at ECR 2024. Schedule a meeting today.

The Wire

• AI Postmarket Evaluation: The number of AI algorithms gaining regulatory approval is skyrocketing, but there’s still a need to track AI safety and how well models work in the real world. That’s the message of a new article in Clinical Radiology by members of the UK’s Royal College of Radiologists AI committee that recommends the creation of an AI postmarket surveillance and evaluation system. It could be modeled on systems already in place for pharmaceutical and surgical devices, and could leverage existing programs like the UK’s PERFORMS system for mammography quality assurance. 

• AI Safety Consortium Forms: In the same vein, the US government last week formed the AI Safety Institute, a new body in the National Institutes of Standards and Technology dedicated to advancing safe and trustworthy AI. The group includes over 200 companies and organizations, but interestingly no radiology AI developers are on the list (although a number of universities are). Healthcare AI safety was also the focus of a February 8 House of Representatives hearing, with speakers including Peter Shen of Siemens Healthineers and Ziad Obermeyer, MD, of UC Berkeley. 

• Viz.ai Clearance for ICH Algorithm: AI developer Viz.ai has received 510(k) clearance for Viz ICH Plus, an AI algorithm for detecting intracerebral hemorrhage on non-contrast brain CT scans. The model automates the process of identifying, labeling, and quantifying the volume of segmentable brain structures on CT images; Viz AI notes that ICH accounts for up to 15% of all strokes and has high rates of morbidity and mortality. In related news, Viz AI touted six studies on its algorithms presented at the International Stroke Conference last week. 

• AI Helps Residents Spot PE: Avicenna.AI’s CINA-PE AI algorithm helped radiology residents detect pulmonary embolism on CT pulmonary angiography exams. In a paper in European Journal of Radiology, researchers found that residents reading CTPA exams of patients with suspected PE (n=196) saw their sensitivity go up using AI (93% vs. 82%); concordance between residents also improved when using AI as measured by kappa (0.88 vs. 0.77). Researchers noted that residents are often the initial interpreters of PE studies after-hours, and AI could improve their accuracy. 

• GE to Supply MedQuest: GE HealthCare has signed a three-year deal to supply medical imaging technology to outpatient imaging center operator MedQuest Associates (over 50 imaging centers in 8 US states), with a focus on workflow improvement. The agreement includes digital technologies like GE’s AIR Recon DL MRI reconstruction solution and AIR Touch workflow offering for MRI coil selection, as well as Imaging Protocol Manager, Smart Subscription, and Imaging 360 operations management software. 

• Free-Breathing MRI for Heart Disease: French researchers used a deep learning reconstruction algorithm to create cine cardiac MRI sequences acquired during free-breathing scans of patients with suspected ischemic heart disease. In a study of 26 patients in AJR, researchers describe how the DL-ESPIRiT neural network enabled the acquisition of high-quality cine images to assess left ventricular ejection fraction in less time than standard protocols (0.6 vs. 2.4 minutes). The protocol could be useful for cardiac MRI evaluation of patients unable to repeatedly hold their breath.

• Lower CCTA Radiation Dose: Thanks to AI reconstruction, wide 16cm detectors, and a fast 0.25-second gantry rotation time, researchers from China conducted coronary CT angiography scans of patients with irregular heart rhythms at the same radiation dose as those with regular heart rhythms. In a paper in Heliyon, they described scanning 427 patients who got prospective CCTA with ECG triggering on United Imaging Healthcare’s uCT960+ CT scanner. There was no statistically significant difference in radiation dose between patients (2.7 vs. 2.9 mSv,  p=0.61); image quality was similar. 

• Premier Radiology Buys NationalRad: It’s been a busy time for teleradiology services provider Premier Radiology Services. The company last week acquired NationalRad, a Florida-based subspecialty teleradiology company, in a deal that expands Premier’s service offering, especially in MSK and neuroradiology MRI. Just prior to that, Premier signed an extension through 2030 to its contract with occupational medicine provider Concentra, giving Premier continued access to Concentra’s 540 medical centers across the US.  

• MRI Scan Hesitancy: Older Asian Americans are less likely than their White peers to participate in research involving MRI scans, and this hesitancy could affect the quality of future dementia research. In a study in Alzheimer’s & Dementia: Translational Research & Clinical Interventions, researchers surveyed 246 people over 65, finding that South Asians and East Asians had lower desire to learn of MRI results for both serious findings and benign conditions. Older Asians were also less likely to believe that healthy people should participate in research studies. 

• Rao Joins CARPL Board: Radiology thought leader Vijay Rao, MD, has joined the advisory board of AI platform CARPL.ai. Rao is professor of radiology and senior vice president of enterprise imaging at Jefferson Health, and was president of RSNA 2018. In the research field, she is perhaps best known for her work in radiology economics. 

• IBA to Buy Dosimetry Firm Radcal: Belgian radiation oncology firm Ion Beam Applications has signed a deal to acquire Radcal, a California-based provider of X-ray measurement products such as dosimeters. Radcal generates $6M in revenues, and IBA expects the deal to support its continued growth in the dosimetry and quality assurance market, especially in the US.

• 3M on Track with Healthcare Spinoff: 3M is on track to spin off its healthcare unit into a new company called Solventum in the first half of 2024, the company confirmed during its recent Q4 investor call. The Medical Solutions Division reported revenue growth in the low single digits, while revenue for 3M’s other business units continued a downward trend. 3M’s M*Modal front-end speech recognition solution was a KLAS Research awardee last week.

MRI Access and the Cost of Inpatient Stays

Longer inpatient stays due to delayed MRI access are a long-standing and costly issue for hospital systems. Find out how STAGE from SpinTech MRI can reduce your MRI backlog and inpatient stays by shortening brain scan times by 30%.

Monitoring, Benchmarking, Data Privacy, and Ethics in AI

Join Bayer’s Calantic Digital Solutions for a February 28 presentation at ECR 2024 exploring how ethics shape AI’s trajectory, societal impact, and deployment. See Calantic’s entire program and schedule your demo today.

The Evolution of Deep Learning-Based MRI

Learn how deep learning-based MRI reconstruction methods like GE HealthCare’s AIR Recon DL have helped increase spatial resolution while allowing for shorter acquisition times.

The Resource Wire

• Why AI in Radiology is a Game Changer: What are the benefits of AI in radiology? Quite simply, they are game-changing and will drive improved hospital efficiency, according to this article that features Blackford Analysis CEO Ben Panter. 

• A Better Way to Deploy AI: CARPL.ai’s end-to-end modular platform for AI deployment is changing how University Hospitals in Cleveland uses AI to enhance patient care. Hear from UH clinicians and administrators as they share their experiences.

• Give Your Patients the Experience They Want: Empower patients to take control of their healthcare journey by giving them mobile access to their records and images with Clearpath, the world’s first digital fulfillment platform for records and films. Book a demo today. 

• Get a Clear Perspective at ECR 2024: Visit Riverain Technologies at ECR 2024 and get a clear perspective on the company’s ClearRead solutions to help identify lung abnormalities on CT and X-ray. Visit the company’s booth #A1-19 in Expo X1. 

• Experience the Healthcare Revolution: Did you experience the healthcare revolution with United Imaging at RSNA 2023? From the uAIFI Technology Platform to the uDR 380i Pro mobile X-ray system, check out how United Imaging technologies are reshaping healthcare in this video. 

• Change Healthcare’s Secure Cloud: Did you know one-quarter of healthcare organizations have experienced a cyber-attack in the last year? This Change Healthcare animation explains how third party-certified cloud-native enterprise imaging can help secure IT infrastructure that might be exposed with re-platformed imaging systems.

• Medical Imaging Data for Improved Research: The need for high-quality medical imaging data is crucial to drive advancements in diagnostics and treatment. Learn how Enlitic’s ENDEX for data standardization and ENCOG for data anonymization solutions enable researchers to access superior data while optimizing their resources.  

• Best in KLAS for Cardiovascular Imaging: The Merge Cardio and Merge Hemo solutions from Merge by Merative have been named Best in KLAS 2024 for Cardiology and Hemodynamics. Learn more about the solutions that have dominated both KLAS categories since 2007.

• Making Advanced Cardiac CT Accessible Everywhere: How do you bring cardiac CT to high-risk patients in rural areas? Watch this video from Siemens Healthineers to learn insights into setting up a cardiovascular CT program in a rural area – and how to overcome associated challenges.

• A Milestone Study for Cardiac Strain Analysis: Us2.ai’s deep learning algorithm was able to interpret echo AI left ventricular strain images with similar accuracy as conventional measurements. Read all about this milestone study and its implications for patient management in EHJ-Digital Health. 

• Meet Gleamer at ECR 2024: Learn all about Gleamer and its portfolio of AI solutions, including its BoneView algorithm for detecting fractures in adults and children, at the upcoming ECR 2024 conference. Schedule a meeting today. 

• Nuance’s PIN Helps Identifies Emphysema: Emphysema is often underdiagnosed, and this can make treatment more difficult. FirstHealth of the Carolinas was able to improve its diagnosis of emphysema and enhance its CT lung screening service with AI algorithms available through Nuance Precision Imaging Network (PIN).

• A Perfect Balance of Utility and Nirvana: The One Viewer philosophy from Visage Imaging offers end users from across the enterprise the chance to get access to Visage 7’s powerful tools based on their clinical need, with the same #1 rated viewer for multiple workflows. Find out today how it works.

• Delivering the Quadruple Aim Through Image Exchange: Learn how a redesigned enterprise image exchange can enhance patient experiences, improve population health, generate cost savings and increase staff satisfaction in this white paper from PocketHealth.

• Radiology Insights with Ben White, MD: Join Medality founder and CEO Daniel Arnold on The Radiology Report Podcast with Ben White, MD, in a far-ranging discussion on the evolving landscape of medical imaging, including labor shortages and beyond.