RadTwitter/X personality Dr. Longissimus, who asked ChatGPT to write a CT abdomen-pelvis report using Gen Z lingo.

Data has become an invaluable part of medical imaging and can provide insight into healthcare trends, train AI algorithms, and more. But not all data is created equal, and data standardization has become a real issue. Learn more about tools for standardizing your data in this Imaging Wire Show interview with Beth Santori of Enlitic.

Imaging Wire Sponsors

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

Artificial Intelligence

More Work Ahead for Chest X-Ray AI?

In another blow to radiology AI, the UK’s national technology assessment agency issued an equivocal report on AI for chest X-ray, stating that more research is needed before the technology can enter routine clinical use.

The report came from the National Institute for Health and Care Excellence (NICE), which assesses new health technologies that have the potential to address unmet NHS needs. 

The NHS sees AI as a potential solution to its challenge of meeting rising demand for imaging services, a dynamic that’s leading to long wait times for exams. 

• The NHS has taken several steps to spur AI adoption, such as the launch of the AI Diagnostic Fund to pay for chest X-ray pilot projects and the piloting of a national platform for AI deployment. 

But at least some corners of the UK health establishment have concerns about whether AI for chest X-ray is ready for prime time. 

• The NICE report states that – despite the unmet need for quicker chest X-ray reporting – there is insufficient evidence to support the technology, and as such it’s not possible to assess its clinical and cost benefits. And it said there is “no evidence” on the accuracy of AI-assisted clinician review compared to clinicians working alone.

As such, the use of AI for chest X-ray in the NHS should be limited to research, with the following additional recommendations …

• Centers already using AI software to review chest X-rays may continue to do so, but only as part of an evaluation framework and alongside clinician review
• Purchase of chest X-ray AI software should be made through corporate, research, or non-core NHS funding
• More research is needed on AI’s impact on a number of outcomes, such as CT referrals, healthcare costs and resource use, review and reporting time, and diagnostic accuracy when used alongside clinician review

The NICE report listed 14 commercially available chest X-ray algorithms that need more research, and it recommended prospective studies to address gaps in evidence. AI developers will be responsible for performing these studies.

The Takeaway

Taken with last week’s disappointing news on AI for radiology, the NICE report is a wakeup call for what had been one of the most promising clinical use cases for AI. The NHS had been seen as a leader in spearheading clinical adoption of AI; for chest X-ray, clinicians in the UK may have to wait just a bit longer.

AI Applications in Neuroradiology

What are the most common AI applications in neuroradiology? This downloadable e-book from Bayer and Calantic Digital Solutions reviews the most common AI applications for brain imaging and the evidence behind them.

A New Era for fMRI

Reducing acoustic noise from MRI scanners is particularly important in rapid functional MRI exams of the brain. In this article, learn what GE HealthCare is doing with Looping Star, a novel noise reduction method for whole-brain fMRI scanning.

The Wire

• ChatGPT Update Astounds: If you thought ChatGPT was cool, you “haven’t peeped anything yet, fam.” The algorithm’s developer OpenAI last week released an updated version that (for paying customers, at least) enables ChatGPT to access the Internet and incorporate current information into its generative AI output (ChatGPT previously was limited to information accessed before September 2021). Technology enthusiasts flocked to test the new version, and RadTwitter/X blew up over a radiology report penned in Gen Z lingo.

• Breast Screening Age in Canada: In a new survey, 89% of Canadians polled believed routine breast screening should begin before age 50. Currently, guidelines from the Canadian Task Force for Preventive Health Care recommend screening every 2-3 years for women aged 50-74. But momentum may be shifting to an earlier starting age, especially as the USPSTF changed its recommended starting age to 40. Sponsors of the survey, Breast Cancer Canada, also launched a new registry to collect experiences of people with breast cancer.  

• No Age Limit to Screening? Meanwhile south of the border, a poll of US residents found that most believe that life expectancy shouldn’t be used to stop screening tests for older people. University of Michigan researchers found that 62% of people aged 50-80 said national guidelines should not be based on how long a person has left to live, and 70% said they don’t think it’s a problem if some older adults get screening tests when guidelines don’t recommend them. 

• ScreenPoint Touts Transpara Trials: At last week’s EUSOBI conference in Spain, ScreenPoint Medical highlighted recent research based on the use of its Transpara breast AI technology. The company pointed to landmark studies such as the MASAI trial in which Transpara reduced mammography workload by 44%, a US study that paired AI with volumetric breast density calculations, a breast screening study from Norway, and a Danish study using Transpara to analyze breast texture patterns to predict cancer risk. Transpara is being used in place of a second reader in three European countries.

• UK Breast Recalls Rose during Pandemic: The UK’s national breast screening program may have seen higher sensitivity but more unnecessary recalls during the COVID-19 pandemic. In European Radiology, researchers said that for imagers taking a test set of mammography cases, sensitivity was higher during 2020 compared to 2015-2022 (95% vs. range of 85-92%), but specificity fell compared to every other year except 2019 (78.9% vs. range of 78.8-86.2%). Researchers said the data indicate breast screeners were “over recalling” cases, apparently because fewer women were being screened.

• Cancer Diagnoses Drop: Meanwhile, a new report from the American Cancer Society confirms previous research showing a sharp drop in new diagnoses of six major cancers in early 2020, when the COVID-19 pandemic began. And the drop was greatest for cancers typically diagnosed via screening, such as female breast (-9%), lung (-15%), and colorectal cancer (-16%). The decline in diagnoses correlated with reports of lower screening rates during the pandemic, although excess all-cause mortality from COVID could account for part of the decline.

• RP Gets Victory vs. UnitedHealthcare: Score one for Radiology Partners (RP) in its litigation with UnitedHealthcare over radiology billing. UnitedHealthcare sued RP charging that it billed for imaging services that weren’t performed, but RP last week won a motion to compel arbitration in the case, with a judge saying the insurer’s complaints were “substantively identical” to an existing arbitration already underway between the companies. UnitedHealthcare recently lost a $91.3M arbitration ruling in a billing dispute with Envision Healthcare; will history repeat?

• FDA Clears Qure Chest X-Ray AI: The FDA has cleared qXR-CTR, Qure.ai’s application for measuring cardiothoracic ratio (CTR) from chest X-ray exams. The algorithm identifies risk of heart failure by providing an indicator of cardiomegaly from plain-film images. It measures CTR automatically by calculating the ratio of the maximum transverse diameter of the heart to the minimum inner traverse diameter of the thoracic cavity. The application becomes Qure’s 12th FDA-cleared algorithm, joining algorithms for applications such as triaging pneumothorax and pleural effusion.

• Reading Room Coordinators: Reading room coordinators hired to reduce interruptions during off-hours had a measurable impact on radiologist efficiency. In a new study in JACR, University of Iowa researchers describe how they hired coordinators as full-time staff for overnight and weekend positions to facilitate radiology resident workflow. In a dataset of 64.4k exams, turnaround time fell for both emergency and inpatient exams (-7 minutes) and the percentage of emergency studies signed within 30 minutes rose (66% vs. 58%). Should a coordinator be your department’s next hire?

• Siemens Lands MRI Clearance: Siemens Healthineers received FDA 510(k) clearance for Magnetom Viato.Mobile, a new 1.5T MRI scanner designed for mobile use. Viato.Mobile sports a 70cm bore and can be installed in a trailer for easy transportation to offsite locations. Siemens migrated technology from its fixed MRI scanners to Viato.Mobile, including its BioMatrix Technology for adapting to different patient anatomies and Deep Resolve AI-powered image reconstruction. Siemens debuted Viato.Mobile at RSNA 2022. 

• Sirona Picks Partners: Hot on the heels of last week’s teaser announcement of its November 13 platform launch, Sirona Medical announced a slate of founding partners. The firms are using its Amplify SDK open developer system for clinical radiology to embed their applications into Sirona’s RadOS platform, which unifies radiology image viewing and reporting. Sirona customers will have one-click access to AI algorithms developed by Koios Medical and RevealDX, as well as access to applications Sirona gained through its acquisition of Nines in 2022. 

• United Imaging’s Manhattan Milestone: A new imaging center has opened in Manhattan’s Upper East Side featuring equipment from United Imaging. AMRIC is operating with MRI, CT, and molecular imaging scanners that represent the 20,000th, 20,001st, and 20,002nd systems shipped worldwide from the company. The scanners were delivered from United Imaging’s North American headquarters in Houston and are the first of their kind installed in Manhattan. 

• Let the ERAS Games Begin: It has nothing to do with Taylor Swift, but the opening of the Electronic Residency Application Service (ERAS) was still a big deal, marking the official start of the medical residency application process. If you noticed a flood of fresh-faced young medical students in your Twitter/X feed announcing their residency intentions, you’re not alone. Ironically, at least one high-profile radiology training program is not reviewing head shots with residency applications this year to reduce bias in the resident selection process.

Generative AI Tackles Medical Imaging

Generative AI has emerged as a powerful resource for a variety of tasks. Intelerad President Morris Panner surveys the medical imaging use cases for generative AI in this article in Healthcare IT Today.

How AI Tools Enable Fast, Low-Dose Imaging

New AI-based reconstruction tools are making it possible to perform imaging exams that are faster and at lower radiation dose. Learn from the experts how it’s done in this webinar recording hosted by Subtle Medical and Incepto.

AI-Assisted Triage of Chest X-Ray Improves Efficiency

Using AI to triage chest X-ray cases can improve the efficiency of radiologists. Find out how AI worked to augment clinical workflow and produce productivity benefits in this article from Annalise.ai.

The Resource Wire

• Interest is growing in collecting patient-reported outcome measures (PROMs) in healthcare, but how can your hospital implement a PROM collection system? Learn how to get started in this white paper from PocketHealth.  

• The ESC has updated its heart failure guidelines, for the first time including a guideline-directed medical therapy for heart failure with preserved ejection fraction (HFpEF). Learn how echo AI can find these cases earlier in this video from Us2.ai. 

• Healthcare providers can’t feel confident in the impact they make for their patients without feeling their IT environments are resilient and reliable. This eBook from Merge by Merative  breaks down 3 essential ingredients of a resilient imaging IT environment: hybrid cloud, reliable uptime, and zero-trust security. 

• 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.

• Change Healthcare’s cloud-native, zero-footprint Stratus Imaging PACS is live in clinical use. See how Stratus Imaging PACS is helping radiology practices improve productivity and patient care, while eliminating the cost and resource constraints of on-premise systems.

• United Imaging is developing modern medical imaging technology for better patient outcomes. CEO Jeffrey Bundy, PhD, explains the company’s unique philosophy in this interview with Healthcare Tech Outlook. 

• Get to know Clearpath and its novel approach to empowering patients by giving them digital access to their images and medical records in this video interview from SIIM 2023. 

• See how Thomas Jefferson University relied on CARPL.ai to accelerate its AI validation and clinical adoption in this presentation by informatics and AI leader, Dr. Paras Lakhani.

• Early adopters of photon-counting CT are impacting patient care by performing scans that were previously impossible. Check out this Siemens Healthineers resource of peer-reviewed papers showing the immense potential of photon-counting CT.

• AI automates what radiologists can’t stand, surfaces what radiologists can’t see, and identifies what radiologists can’t miss. But only if it’s implemented in the way radiologists work. See how Nuance helps radiologists achieve these results through a single, streamlined, end-to-end AI experience.

• In a new research study in Clinical Imaging, see how Visage Imaging’s PACS-integrated Visage Breast Density application had high accuracy and agreement with radiologist assessments for classifying mammography exams into BI-RADS categories.

• How are the worlds of health technology and business intersecting? In this episode of The Radiology Report, Intelerad Medical Systems President Morris Panner sits down with Medality CEO Daniel Arnold to explore his career and discuss the evolution of the industry.

• This Blackford Analysis video details how imaging AI can improve radiology efficiency and patient care, and discusses the key role that AI assessments and curation plays in achieving these improvements.

• See why radiologist Dr. Eleanna Saloura called Tempus Radiology’s Lung AI solution “a fast and reliable second opinion” for chest CT lung nodule analysis and tracking, allowing “more accurate diagnostic and treatment decisions.”

• Data standardization has emerged as a key issue for both clinical and research aspects of medical imaging. Learn about its pivotal role in healthcare in this Enlitic webinar on October 25 featuring radiologist Cheryl Petersilge, MD, founder and CEO of Vidagos.