Perry Pickhardt, MD, in an RSNA 2023 presentation on the potential of opportunistic screening.

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  •  Subtle Medical  •  United Imaging  •  Us2.ai  •  Visage Imaging

Artificial Intelligence

AI Powers Opportunistic Screening

The growing power of AI is opening up new possibilities for opportunistic screening – the detection of pathology using data acquired for other clinical indications. The potential of CT-based opportunistic screening – and AI’s role in its growth – was explored in a session at RSNA 2023.

What’s so interesting about opportunistic screening with CT? 

• As one of imaging’s most widely used modalities, CT scans are already being acquired for many clinical indications, collecting body composition data on muscle, fat, and bone that can be biomarkers for hidden pathology. 

What’s more, AI-based tools are replacing many of the onerous manual measurement tasks that previously required radiologist involvement. There are four primary biomarkers for opportunistic screening, which are typically related to several major pathologies, said Perry Pickhardt, MD, of the University of Wisconsin-Madison, who led off the RSNA session:

• Skeletal muscle density (sarcopenia)
• Hard calcified plaque, either coronary or aortic (cardiovascular risk)
• Visceral fat (cardiovascular risk)
• Bone mineral density (osteoporosis and fractures) 

But what about the economics of opportunistic screening? 

• A recent study in Abdominal Radiology found that in a hypothetical cohort of 55-year-old men and women, AI-assisted opportunistic screening for cardiovascular disease, osteoporosis, and sarcopenia was more cost-effective compared to both “no-treatment” and “statins for all” strategies – even assuming a $250/scan charge for use of AI.

But there are barriers to opportunistic screening, despite its potential. In a follow-up talk, Arun Krishnaraj, MD, of UVA Health in Virginia said he believes fully automated AI algorithms are needed to avoid putting the burden on radiologists. 

And the regulatory environment for AI tools is complex and must be navigated, said Bernardo Bizzo, MD, PhD, of Mass General Brigham.

Ready to take the plunge? The steps for setting up a screening program using AI were described in another talk by John Garrett, PhD, Pickhardt’s colleague at UW-Madison. This includes: 

• Normalizing your data for AI tools
• Identifying the anatomical landmarks you want to focus on
• Automatically segmenting areas of interest
• Making the biomarker measurements
• Plugging your data into AI models to predict outcomes and risk-stratify patients

The Takeaway

Opportunistic screening has the potential to flip the script in the debate over radiology utilization, making imaging exams more cost-effective while detecting additional pathology and paving the way to more personalized medicine. With AI’s help, radiologists have the opportunity to place themselves at the center of modern healthcare. 

Solutions for Radiology’s Workflow Challenges

Radiology faces numerous challenges to more efficient workflow, from the siloed nature of healthcare enterprises to mundane tasks that are ripe for automation. In this Imaging Wire Show, we talked to Matthew Lungren, MD, and Calum Cunningham of Nuance Communications.

Allina Turns to the Cloud for Better Patient Care

Allina Health needed to replace its on-premises PACS to better serve patients. Learn how Allina turned to Amazon Web Services (AWS) and Visage Imaging for a cloud-based implementation of the Visage 7 enterprise imaging platform.

The Wire

• ACR’s AI Transparency Checkmarks: The ACR’s Data Science Institute has added a feature to its AI Central database that adds green checkmarks to algorithms that have met the group’s standards for transparency. AI’s perceived lack of transparency has been an argument against the technology, so the new program should give AI buyers more information on how algorithms were created and tested. At first glance, however, most of the algorithms in the database haven’t yet been certified as transparent. 

• 4DMedical to Buy Imbio: Lung imaging developer 4DMedical has signed a deal to buy Imbio, a developer of AI solutions for chronic lung and cardiothoracic diseases. The companies see a fit between 4DMedical’s XV Technology for lung perfusion and Imbio’s quantitative imaging analysis technology, which transforms chest CT scans into visual maps of a patient’s lungs. The acquisition is a major step forward for 4DMedical as it ramps up commercialization of XV; the company recently got FDA clearance for a CT-based version of the software. 

• RadNet Doubles Down on DeepHealth: At RSNA 2023, RadNet offered new details on its AI strategy, branding its portfolio of AI solutions as DeepHealth. RadNet also rebranded many of the algorithms it has recently acquired, including Saige Prostate (formerly Quantib Prostate), Saige Lung (formerly Aidence Veye Lung Nodules), and Saige Brain (formerly Quantib ND). Anchoring the family is DeepHealth OS, a cloud-native workflow engine. Separately, RadNet said it launched a pilot of its MammogramNow AI interpretation service at a Delaware Walmart Supercenter that’s offering breast screening.

• Economics of Mobile Stroke Units: A paper at RSNA 2023 addressed the economics of mobile stroke units (MSUs) – ambulances outfitted with mobile CT scanners. German researchers found that an MSU program should have a coverage area of at least 400k inhabitants. MSUs had an acceptable incremental cost-effectiveness ratio ($37,348 per QALY), and providing stroke coverage for 16 hours a day/7 days a week was more economical than 24/7 coverage in terms of cost per ischemic stroke case ($5,667 vs. $8,285). 

• NVIDIA Launches AI Cloud Service: GPU developer NVIDIA launched a new cloud-based version of MONAI, its open-source framework for developing radiology AI algorithms. Developers can now access MONAI APIs via the cloud, which NVIDIA believes will make it easier for them to integrate AI into their medical imaging software. The MONAI cloud API is already integrated into Flywheel’s research and data AI platform. NVIDIA developed MONAI in collaboration with King’s College London. 

• AI Recon Speeds MRI Scan Times: Using an AI-based MRI data reconstruction protocol improved productivity by 57%. At RSNA 2023, researchers from Argentina discussed their use of GE HealthCare’s AIR Recon DL algorithm for reconstructing 3T MRI data. Used mostly for knee, spine, and brain MRI scans, they found it cut scan times (5.7 vs. 10.3 minutes), and the center saw an overall 58% reduction in scanning time required, which creates the potential for a 35% increase in monthly billing. 

• Annalise Launches AI-Powered Reporting: Annalise expanded its AI offerings at RSNA 2023 by introducing Annalise Reporting, which creates draft radiology reports that are integrated into reporting workflow. The solution uses AI models to codify findings into a set of structured interpretations. In other news, Annalise partnered with Mass General Brigham to deploy its Annalise Triage product across the MGB system; they will also work on joint AI development. Finally, Annalise inked a distribution partnership with Avreo and signed a new customer for Annalise Triage, Raleigh Radiology. 

• Deepc Lands AI Partner: Deepc has added AI algorithms from Huiying Medical Technology (HY Medical) of China to its deepcOS platform. HY Medical is contributing the following algorithms: DR AI-assisted Bone Fracture Detection for X-ray extremity analysis, DR AI-assisted Pulmonary TB Diagnosis for detecting pulmonary tuberculosis on CT scans, and CT AI-assisted Lung Nodule Detection for analyzing lung CT scans. Deepc has been expanding its AI portfolio of late, such as with Qure.ai, and also inked a deal with Hyland Software.  

• Health Systems Eye PACS Replacement: A new report from KLAS finds that some 20% of US health systems are planning to replace their PACS networks – and more would do so if they had the chance. The report analyzes 90 recent PACS purchases in the two years up to September 2023, finding that health system consolidation and the need to replace aging technology are driving interest. Sectra is the market leader in both considerations and selections, while Visage Imaging is gaining momentum at large health systems. 

• Aidoc to Invest $30M on Foundation Models: Aidoc plans to invest $30M to develop a clinical AI foundation model to speed up training and development of AI algorithms. Foundation models like large language models accept multiple types of data besides language as input; Aidoc is developing a foundation model that will address a broad spectrum of medical conditions and that supports the faster development of precise AI algorithms. The foundation model would complement Aidoc’s aiOS platform and AI point solutions.

• Breast AI Spots High-Risk Women: European researchers used iCAD’s ProFound AI Risk software to identify women at risk of later-stage breast cancer, finding it worked well across three different countries with different types of screening programs. In The Lancet Regional Health – Europe, researchers used ProFound AI Risk to predict two-year risk of breast cancer from 8.5k mammograms in Italy, Spain, and Germany; those classified as high risk had nearly 7X the cancer rate versus those at general risk (risk ratio=6.7). 

• iCAD Partners with CancerIQ: In other iCAD news, the company signed a partnership with cancer prevention firm CancerIQ to combine their respective software into a platform designed to enable earlier breast cancer detection. iCAD’s ProFound Density assessment score and ProFound AI Risk short-term risk analysis tool will be combined with CancerIQ’s lifetime risk calculator to give clinicians a clearer picture of an individual’s current and future breast cancer risk.

• Classifying Stroke Risk: Clinicians might soon be able to leverage a new universal system for classifying stroke risk. Researchers in JACC detailed the new Plaque-Reporting and Data System (Plaque-RADS) for quantifying stroke risks based on a patient’s ultrasound, CT, and MRI exams. Developed by a panel of experts, Plaque-RADS outlines approaches for imaging and reporting findings of carotid plaque composition and morphology, with score categories ranging from grade 1 (no plaque) to grade 4 (complicated plaque).

• AI Alliance Supports Lung Screening: European radiology software developers Aidence, Incepto, and Thirona have collaborated to develop an AI-powered software package to support CT lung cancer screening and emphysema analysis. The package combines Aidence’s Veye lung nodule analysis software with Thirona’s LungQ clinical suite for lung diseases like emphysema, with the combined application available through Incepto’s AI platform. The companies note that lung cancer screening exams are often also identifying patients with emphysema. Lung screening is gaining momentum in Europe with the publication of new studies on its effectiveness. 

What Exams Are Radiologists Reading?

What kinds of medical imaging exams are radiologists reading today, and how confident do they feel across different subspecialties? Find out in the 2023 Radiology Practice Development Report from Medality.

Echo AI Hits the High Notes in OPERA Study

New results from the OPERA study show how Us2.ai’s echo AI solution improved heart failure screening in the NHS, reducing echo waiting times from 12 months to under 6 weeks. Find out more in this article.

Faster MRI Scans with No Compromise

What if you could speed up your MRI scans with no compromise on image quality? In this video from RSNA 2023, we talked to SpinTech MRI CEO Karen Holzberger and Senior Clinical Sales Executive John Ciliberto about how their STAGE software is making this vision a reality.

The Resource Wire

• Expanding Advanced CT Imaging: How can advanced CT technology like dual-source imaging be made more widely available to hospitals that need it? In this Imaging Wire Show interview, we talked to Olivia Egan of Siemens Healthineers about new dual-source CT technology the company is introducing.

• The Benefits of Breast Imaging AI: Breast imaging AI can help providers reduce their workload and improve patient care. Blackford Analysis offers a wide selection of breast imaging AI apps on its Blackford Platform – find out how they could benefit your organization. 

• 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.

• AI As a Second Reader for Emergency Radiology: Can AI serve as a second reader for emergency radiology exams? Read about how researchers implemented Gleamer’s AI solution for fracture detection in the ER and reported their impressions in a study in Investigative Radiology. 

• Imaging Data Management for PACS and IT: Effective data management policies can help PACS and IT administrators get their jobs done more efficiently. Find out how data standardization practices like good data governance and standardized descriptions can help in this Enlitic white paper.

• 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.

• 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. 

• Solutions to Support Breast Density Reporting: The FDA has ruled that healthcare providers must inform patients of their breast density status. Learn how Intelerad’s solutions can help mammography facilities comply with this new rule well ahead of next year’s deadline. 

• Data-Driven Diagnostics and Treatment: There is growing awareness that greater collaboration to show data can provide clinicians decision support for providing the right treatment to enhance patient care and outcomes. GE HealthCare shares more on how they are looking at cancer care with data-driven diagnostics and treatment.

• The Clinical Value of Soft-Tissue Chest X-Ray: Soft-tissue techniques can improve the visibility and accuracy of chest X-ray.  Learn about two important soft-tissue methods – bone suppression and dual-energy subtraction – in this white paper from Riverain Technologies.

• United Imaging’s RSNA 2023 Highlights: What were the highlights in United Imaging’s booth at RSNA 2023? Watch this video interview with CEO Jeffrey Bundy, PhD, at the conference to learn about the company’s 510(k)-pending 5T MRI scanner, mobile digital radiography system, and more. 

• Enhancing Patient Engagement through Effective Communication: A new downloadable guide from PocketHealth shows how you can create positive patient experiences, eliminate patient anxiety and increase appointment and follow-up adherence.

• To Pay or Not to Pay for AI in Radiology: AI-supported digital applications are expected to transform radiology, but providers need motivation and incentives to adopt them. In this article, authors including executives from Bayer propose a framework to guide payers and AI developers in adoption of radiology AI. 

• Faster PET Scans with SubtlePET: Want to perform PET scans faster, but keep the same image quality? With SubtlePET image enhancement from Subtle Medical, you can conduct PET exams in one-quarter of the original time while preserving image quality. Find out how in this case review. 

• Another Incredible Year at RSNA: As the curtain falls on RSNA 2023, CARPL.ai is reflecting on another extraordinary experience, ranging from CMO Vasanth Venugopal, MD, presenting in the Learning Center theater to live AI-enabled X-ray screening in collaboration with Qure.ai.