Nikhil Suresh of Hermit Technology, in a snark-filled rant on the down side of generative AI.

Imaging Wire Sponsors

AGFA HealthCare  •  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

AI Detects Incidental PE

In one of the most famous quotes about radiology and artificial intelligence, Curtis Langlotz, MD, PhD, once said that AI will not replace radiologists, but radiologists with AI will replace those without it. A new study in AJR illustrates his point, showing that radiologists using a commercially available AI algorithm had higher rates of detecting incidental pulmonary embolism on CT scans. 

AI is being applied to many clinical use cases in radiology, but one of the more promising is for detecting and triaging emergent conditions that might have escaped the radiologist’s attention on initial interpretations.

• Pulmonary embolism is one such condition. PE can be life-threatening and occurs in 1.3-2.6% of routine contrast-enhanced CT exams, but radiologist miss rates range from 10-75% depending on patient population.

AI can help by automatically analyzing CT scans and alerting radiologists to PEs when they can be treated quickly; the FDA has authorized several algorithms for this clinical use. 

• In the new paper, researchers conducted a prospective real-world study of Aidoc’s BriefCase for iPE Triage at the University of Alabama at Birmingham. 

Researchers tracked rates of PE detection in 4.3k patients before and after AI implementation in 2021, finding … 

• Radiologists saw their sensitivity for PE detection go up after AI implementation (80% vs. 96%) 
• Specificity was unchanged (99.1% vs. 99.9%, p=0.58)
• The PE incidence rate went up (1.4% vs. 1.6%)
• There was no statistically significant difference in report turnaround time before and after AI (65 vs. 78 minutes, p=0.26)

The study echoes findings from 2023, when researchers from UT Southwestern also used the Aidoc algorithm for PE detection, in that case finding that AI cut times for report turnaround and patient waits. 

The Takeaway

While studies showing AI’s value to radiologists are commonplace, many of them are performed under controlled conditions that don’t translate to the real world. The current study is significant because it shows that with AI, radiologists can achieve near-perfect detection of a potentially life-threatening condition without a negative impact on workflow.

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.

AI for Incidental Osteoporosis Findings

Looking to learn more about how AI is used for incidental osteoporosis findings? Watch this on-demand webinar from Blackford in which clinical leaders discuss the benefits of preventive care and share their real-life experiences.

Looking to Improve Patient Satisfaction and Avoid Care Delays?

Join PocketHealth at SIIM as they speak with industry leaders about overcoming challenges with patient-centric solutions on June 28. CE credits available. Don’t miss it!

The Wire

• Open-Source PACS AI Platform: A group of Canadian researchers is developing an open-source PACS-AI platform that’s designed to make it easier to deploy and use AI algorithms clinically. They describe their approach in a new paper in Canadian Journal of Cardiology, detailing their belief that an academia-led open-source effort would have advantages over single-vendor single-algorithm commercial approaches. Their PACS-AI platform works as an interface between existing PACS and AI models, and has been deployed for research use at several Canadian and US hospitals.

• Early Ovary Removal Linked to Brain Changes: Women who had their ovaries removed before age 40 had brain changes visible on MRI scans. In a paper in Alzheimer’s & Dementia, researchers used 3T MRI to analyze brain structure of 1k women; the 22 women under 40 who underwent premenopausal bilateral oophorectomy had worse white matter integrity in multiple brain regions later in life. Researchers theorized that early ovary removal results in a loss of estrogen and testosterone, which could put women at higher risk for neurodegenerative diseases like Alzheimer’s.  

• Calculating Equity in Cancer Care: Reducing healthcare disparities has become a major goal for clinicians and public policy advocates alike. A new tool called the Cancer Equity Compass from the Harvey L. Neiman Health Policy Institute can help by revealing county-level overlap between cancer disparities and social determinants of health. The tool displays the relationship between metrics like screening, prevalence, and mortality rates and social determinants such as education, income, minority rates, and pollution; it focuses on the four most common cancers: breast, prostate, colorectal, and lung. 

• GE’s Augmented Reality Play: GE HealthCare’s augmented reality collaboration with MediView XR is bearing fruit. The companies announced the first installation and clinical use of OmnifyXR Interventional Suite, an AR-based interventional radiology suite that combines a holographic heads-up display that streams live medical images and 3D models during procedures. The milestone installation was at North Star Vascular and Interventional in Minneapolis, Minnesota; GE and MediView began collaborating in late 2022. 

• GPT-4 Creates Better Structured Reports: The GPT-4 version of the ChatGPT large language model created better structured reports than GPT-3 in a new paper in Radiology. Researchers tested both versions for creating synoptic reports – or reports based on structured templates – from original free-text radiology reports in 180 cases of pancreatic ductal adenocarcinoma. GPT-4 performed better for recall (99.6% vs. 95.7%), precision (99.7% vs. 97.7%), and F1 (a combination of precision and recall), (0.997 vs. 0.967). AI expert Woojin Kim, MD, breaks down the paper’s significance in a LinkedIn post.    

• RADPAIR Signs NewVue as Partner: Two relatively recent arrivals on the radiology scene – RADPAIR and NewVue – are partnering. RADPAIR will be integrating its AI reporting capabilities into NewVue’s workflow orchestrator, giving radiologists a new solution for interacting with worklists, managing clinical information, dictating reports, and tracking productivity. RADPAIR recently signed a deal with Radiopaedia, while NewVue has been busy inking relationships with Electromek Diagnostic Systems and  InsiteOne.

• InsiteOne Reports New Installs: Speaking of InsiteOne, the company is building off momentum from its acquisition of BRIT Systems by cementing deals to install RIS/PACS at six new customer sites in the first half of 2024. The deals cover locations ranging from imaging centers to teleradiology practices to hospitals, which the company believes shows the broad appeal of BRIT’s solutions. Separately, InsiteOne debuted PACS Guardian, a cloud-based offering designed to counter cybersecurity threats by mirroring an existing PACS while including disaster recovery features. 

• PET vs. SPECT for Thyroid Disease: PET/CT with an F18-choline (FCH) radiotracer could replace SPECT/CT with 99mTc-sestamibi (MIBI) as a first-line imaging tool for preoperative localization of parathyroid adenomas in patients with primary hyperparathyroidism. In a paper in JAMA Otolaryngology–Head & Neck Surgery, French researchers compared the two techniques in 57 patients, finding that FCH-PET/CT had higher sensitivity than MIBI-SPECT/CT (82% vs. 63%); the findings could lay the groundwork for broader use of FCH-PET/CT, despite its higher cost. 

• Gen X Cancer Rates Jump: Incidence of invasive cancer has jumped among members of Generation X – at higher rates than any other generation since 1908. A new analysis in JAMA Network Open found that Gen X cancer incidence was higher than Baby Boomers for most cancers with the exception of lung cancer in both men and women, cervical cancer in women, and liver and gallbladder cancer in men. The authors said the results were surprising given the decline in tobacco smoking and success of screening; obesity, sedentary lifestyles, and carcinogenic exposure could account for the growth.

• Esaote Launches US Scanner at SIRM: At the SIRM 2024 Italian radiology congress last week, Esaote launched MyLab E80, a new cart-based ultrasound scanner designed for more complex clinical cases. The scanner includes AI-based automation features and workflow management, and Esaote migrated its Augmented Insight functions from MyLab X90 to the new system, giving users the option of either a conventional or touchscreen control panel. E80 completes Esaote’s renewal of its ultrasound scanner line, with recently launched systems MyLab X90, MyLab A70, and MyLab A50. 

• LucidHealth to Roll Out Rad AI: LucidHealth will be rolling out Rad AI’s Omni Impressions software at its radiology practices under a deal between the firms. The deployment began at a LucidHealth radiology practice in Wisconsin, and will continue with three additional practices in the state, as well as at sites in Connecticut, Florida, Iowa, and Nevada. LucidHealth’s teleradiology service will also use the solution, which automatically generates the “impressions” sections of radiology reports using findings dictated by radiologists.

How AI Can Liberate Radiologists

Attend this talk at SIIM 2024 at 1 pm on June 27 by Allen Hundley of Riverain Technologies to learn how AI can liberate radiologists from repetitive and monotonous elements of their workflow. 

Presenting Unboxing AI

Check out CARPL’s brand-new video series, Unboxing AI, featuring experts discussing AI and its future in radiology. The next episode on June 28 features Melissa Davis, MD, of Yale University – reserve your seat today.

Imaging Workflows that Actually Work

Not a fan of medical image exchange on discs? Then check out Clearpath and find out how it’s removing obstacles to better radiology workflow. Request a demo today.

The Resource Wire

• Transforming Healthcare with Advanced AI: Visit Enlitic at booth #524 at SIIM 2024 to discover how the company’s advanced AI solutions are helping healthcare institutions standardize their data. See you there!

• Ignite Your Imaging AI Strategy: Take your imaging AI strategy to the next level at SIIM 2024 by attending insightful sessions on AI adoption and deployment from Calantic by Bayer, including planning an AI orchestration platform and the benefits of integrating AI in radiology departments. Reserve your spot today.

• Visit Gleamer at SIIM 2024: Be sure to visit Gleamer in booth #530 at SIIM 2024 to learn more about the company’s full range of AI solutions, including BoneView for fracture assessment. Learn more about BoneView today. 

• Collaborative Care in the Age of Innovation: Unlock the future of collaborative care with AGFA HealthCare’s pioneering Enterprise Imaging solution. Request a demo today to learn more at SIIM 2024, or visit them at booth #613.

• Meet Merge at SIIM 2024: Whether you’re a physician, IT administrator, or imaging business leader, meet with Merge by Merative at SIIM 2024 to find out how you can benefit from Merge imaging solutions, and sign up now for a June 28 talk on a modular approach to innovation. 

• Experience the Platform for the Future: Register now for a priority demo at SIIM 2024 of Visage 7, Visage Imaging’s trailblazing platform for the future of enterprise imaging, based on industry standards and multi-cloud support. 

• Echo AI for Heart Failure by Novices: Read this Nature Scientific Reports study to learn about the role of Us2.ai in empowering novices to obtain accurate ultrasound information to diagnose heart failure. AI offered a more sensitive and objective alternative than NT-proBNP to initiate guideline-directed medical therapy in primary care clinics.

• Generative AI’s Transformative Impact on Radiology: Register today for a SIIM #AskIndustry Panel Discussion at 11 am ET on June 28 to hear from Sham Sokka, CTO and COO of DeepHealth, alongside key industry leaders on how the next wave of AI innovation will revolutionize diagnostic accuracy, radiologist efficiency, and patient outcomes.

• The Value of MRI Ownership: Are you wondering whether buying a new MRI scanner is the best use of scarce capital equipment funds? Check out Siemens Healthineers’ interactive ROI calculator to see the value of purchasing the MAGNETOM Free.Max. 

• A Holistic Strategy For Enterprise AI: Finding, vetting, and deploying the right radiology AI solutions can be challenging. In this SIIM 2024 session on June 27 presented by Microsoft + Nuance, learn how industry leaders are laying the foundation for AI while solving today’s real-world workflow challenges.

• Impact You Can See: Visit Intelerad at SIIM 2024 to learn the next chapter of their story: a reimagined and refined brand identity with solutions that can drive impact for your team. Stop by booth #412-414 or schedule your visit today. 

• Treating Local Patients Like Family: Holzer Health System in the rural community of Jackson, Ohio, treats local patients like family, offering the same level of top-quality care that can be found anywhere. Find out how United Imaging’s Software Upgrades for Life program helps them stay current.

• 4 Reasons Why Subscription Is Better: The KLAS-leading Intuition advanced visualization solution from TeraRecon includes all the clinical features you need, plus a growing list of exclusive subscription-only content. Learn more about what’s included. 

• Efficiency, Mentorship, and Subspecialization in Radiology: In this episode of The Radiology Report podcast, Medality Co-Founder and CEO Daniel Arnold talks to Richard Duszak, MD, chair of the department of radiology at the University of Mississippi about efficiency, mentorship, and subspecialization in radiology.