Liane Philpotts, MD, in an editorial in Radiology on the PERFORMS study. 

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

What are some of the major innovations happening now in the medical image acquisition chain? In the latest edition of The Imaging Wire Show, we talked to Josh Gurewitz and Ajit Shankaranarayanan of Subtle Medical about new developments in image acquisition and enhancement.

Breast Imaging

Tipping Point for Breast AI?

Have we reached a tipping point when it comes to AI for breast screening? This week another study was published – this one in Radiology – demonstrating the value of AI for interpreting screening mammograms. 

Of all the medical imaging exams, breast screening probably could use the most help. Reading mammograms has been compared to looking for a needle in a haystack, with radiologists reviewing thousands of images before finding a single cancer. 

AI could help in multiple ways, either at the radiologist’s side during interpretation or by reviewing mammograms in advance, triaging the ones most likely to be normal while reserving suspicious exams for closer attention by radiologists (indeed, that was the approach used in the MASAI study in Sweden in August).

In the new study, UK researchers in the PERFORMS trial compared the performance of Lunit’s INSIGHT MMG AI algorithm to that of 552 radiologists in 240 test mammogram cases, finding that …

• AI was comparable to radiologists for sensitivity (91% vs. 90%, P=0.26) and specificity (77% vs. 76%, P=0.85). 
• There was no statistically significant difference in AUC (0.93 vs. 0.88, P=0.15)
• AI and radiologists were comparable or no different with other metrics

Like the MASAI trial, the PERFORMS results show that AI could play an important role in breast screening. To that end, a new paper in European Journal of Radiology proposes a roadmap for implementing mammography AI as part of single-reader breast screening programs, offering suggestions on prospective clinical trials that should take place to prove breast AI is ready for widespread use in the NHS – and beyond. 

The Takeaway

It certainly does seem that AI for breast screening has reached a tipping point. Taken together, PERFORMS and MASAI show that mammography AI works well enough that “the days of double reading are numbered,” at least where it is practiced in Europe, as noted in an editorial by Liane Philpotts, MD. 

While double-reading isn’t practiced in the US, the PERFORMS protocol could be used to supplement non-specialized radiologists who don’t see that many mammograms, Philpotts notes. Either way, AI looks poised to make a major impact in breast screening on both sides of the Atlantic.

Creating a Modern Imaging Network in Costa Rica

SOIN Soluciones Integrales of Costa Rica turned to enterprise imaging solutions from Merge by Merative when it wanted to modernize the imaging environments of 50 hospitals across the country. Download this PDF white paper to find out how they did it.

The Challenges of Poor Medical Imaging Data

Healthcare organizations around the world are working with poor-quality data – and 80% don’t trust their own data. Learn about the challenges of poor data and how Enlitic’s solutions can help in this article.

The Wire

• Medicare Spending Flattens: Over the past decade, Medicare spending per beneficiary has flattened, in spite of predictions that it would continue growing. An analysis by the New York Times found that spending in 2011 was $13,159 per beneficiary, and in 2023 stood at $12,459 – representing savings of almost $4T compared to projections. The story offered several reasons for the trend, from Obamacare to budget cuts to the impact of cholesterol-lowering drugs and blood pressure medication. The question is, will the trend continue?

• More Work for Less Pay: Meanwhile, radiologists are working harder than they did 18 years ago while getting paid less. A new analysis in JACR found that radiologist reimbursement per Medicare beneficiary declined 25% from 2005 to 2021 after adjustment for inflation, while RVUs per radiologist went up 13.1%. The study laid the blame on Medicare’s budget-neutrality requirement, which means increases for one medical service are offset by reductions for others. Given the radiologist shortage, the situation could create imaging access problems for Medicare patients. 

• FDA to Modernize 510(k) Rules: The FDA said it is planning to modernize its 510(k) program, the regulatory path that most medical imaging devices and software go through to get to market. The agency issued draft guidances in three areas: 1) selecting a predicate device for 510(k) submissions, 2) using clinical data in applications, and 3) evidentiary expectations for 510(k) implant devices. The FDA also noted that starting October 1, all 510(k) submissions must be submitted electronically with its eSTAR process.

• AI Predicts Missed Care: What if there was an AI algorithm that could predict which patients were mostly likely to miss a healthcare episode like a doctor’s appointment, lab test, or screening exam? GE HealthCare and Mass General Brigham have developed just such a tool as part of a collaboration they started in 2017. Their missed care opportunity (MCO) solution had accuracy rates up to 96% in preliminary tests; it is part of the schedule predictions dashboard in GE’s Radiology Operations Module.  

• Cancer Diagnoses Drop in Canada: An analysis in JAMA Network Open of cancer diagnoses in Manitoba, Canada during the COVID-19 pandemic revealed a 23% drop in overall cancer incidence. The declines varied by cancer type, with the biggest reductions in melanoma (65%), head and neck (50%), rectal (47%), breast (46%), and colon (35%). While diagnoses for some cancers rebounded, the province still had a 5% diagnosis deficit in December 2021. The new numbers are a bit higher than the 15% drop in US cancer diagnoses found in a recent analysis. 

• Global Surge in Under-50 Cancer: There’s been a 77% surge in new cases of cancer in people under age 50 from 1990 to 2019, with breast cancer leading the way. A new analysis in BMJ Oncology shows that while cancer remains more common in older people, new cases are rising for under 50s for breast, windpipe, lung, stomach and bowel cancer. The study blames diet, alcohol consumption, and tobacco use as factors driving the growth; physical inactivity, obesity, and high blood sugar don’t help either.

• Tempus Partners with AstraZeneca: Tempus Labs is partnering with pharmaceutical giant AstraZeneca on the use of AI to guide clinical care of lung cancer patients. AstraZeneca will use Tempus’ Pixel AI software to analyze imaging data to identify and study lung nodules. This will be correlated with clinical data to identify the nodules that should be worked up. The deal complements other alliances AstraZeneca has made in the identification and treatment of lung diseases. 

• RadTwitter Royalty: What are the top 10 radiology accounts on X, the social media platform formerly known as Twitter? A sub-analysis of a recent study in JACR offers interesting insights. That study ordered the top 100 accounts alphabetically to focus on their demographic and academic characteristics, but the new analysis lists the top 10 in order based on Right Relevance, which generates scores using a topic-specific pagerank-like algorithm for a social network. Top accounts are @drgmcginty, @RichDuszak, @DrIanWeissman, @vilavaite, @amykotsenas, @amykpatel, @cekahn, @WendeNGibbs, @DeanMeltzer, and @RogueRad. 

• AI Discussion Dominated ECR 2023: In a related vein, a new analysis of social media posts at ECR 2023 found that topics related to AI made up nearly half of the discussion. In European Radiology, Gennaro D’Anna, MD, found that 46% of LinkedIn posts and 48% of tweets were about AI and machine learning; workflow optimization was next. D’Anna noted that ECR 2023’s top influencers were journalists and industry attendees; he urged radiologists to step up and be more present on social media.

• Riverain Adds Strategic Radiology: Riverain Technologies has signed an agreement with national radiology coalition Strategic Radiology that will give its members access to Riverain’s ClearRead AI solutions for analyzing thoracic CTs and X-rays. The relationship follows on Riverain’s recent deal to provide ClearRead to the Dayton VA Medical Center for detecting lung cancer on CT scans.

• Viz.ai Licenses UCSF Algorithms: Viz.ai has signed an agreement with UCSF to license three AI algorithms for automated detection of cardiovascular disease. The algorithms address three cardiac conditions based on analysis of ECG data: 1) cardiac amyloidosis, 2) pulmonary hypertension, 3) supraventricular tachycardia. Once they get regulatory clearance, the algorithms will become part of Viz.ai’s expanding family of cardiac AI offerings in its Cardio Suite.

• HeartFlow’s FFRCT’s National Impact: Two-year results from the NHS’ nationwide implementation of HeartFlow’s FFRCT Analysis solution revealed significant improvements in patient outcomes and clinical efficiency. The deliciously named FISH&CHIPS study of 90k UK patients showed that FFRCT adoption led to statistically significant reductions in cardiovascular and all-cause mortality (-14% & -8%). Those mortality improvements complement solid efficiency gains, driven by reductions in invasive cardiac angiography and additional noninvasive heart testing following CCTA, and an increase in PCI procedures (-5% & -14% & +8%).

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. 

How Valley View Integrated PocketHealth with PowerShare

Valley View Hospital in Colorado wanted to share images and records with patients while continuing to use its existing PowerShare implementation for providers. Find out how PocketHealth helped them do it in this article.

Building a Mobile Lung Cancer CT Screening Program

The number of patients eligible for low-dose CT lung cancer screening has expanded, and so has the need to reach at-risk patients closer to where they live. That’s why Siemens Healthineers’ Mobile Lung Screening Solution combines the quality, ease of use, and flexibility needed to create a program that meets the real-life needs of your community.

The Resource Wire

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

• What is Clear Visual Intelligence (CVI) from Riverain Technologies? CVI uses deep learning to remove interfering normal structures within the chest like bones, vessels, and machine noise to help you focus on actionable data. Learn more and book a demo today.

• Us2.ai has 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. 

• 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.

• What’s happening at the intersection of AI and precision medicine? In this Imaging Wire Show, we talked to Chiranjiv Singh, general manager at Arterys, a Tempus Labs company, about their vision for building a 360° view of the patient.

• With burnout and staffing shortages on the rise, and the increasing volume of imaging, radiology teams are searching for solutions. This interactive guide from Nuance can help you create an environment where radiologists thrive by building a powerful imaging strategy with AI-driven, real-time intelligence.

• 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. 

• See how cloud-native imaging avoids traditional software’s resource utilization constraints and eliminates unexpected disruptions in this Change Healthcare animation.

• More than 80% of health systems are reporting shortages in their radiology departments. Learn the countermeasures you can take to reduce burnout in this ITN Online article by Intelerad President Morris Panner. 

• In today’s hyper-competitive radiologist job market, radiologist recruiting and retention is more important than ever. Learn from industry experts and practice leaders in this on-demand Medality webinar as they reveal how to overcome hiring challenges, keep your team engaged, and provide opportunities for growth.

• Subtle Medical has been named to CB Insights’ 2023 list of top 100 AI companies worldwide. The laureates were picked from a pool of nearly 9k companies, and were chosen based on a variety of criteria developed by CB Insights.

• Concussions and mild traumatic brain injury (mTBI) can be hard to identify on conventional imaging, even with 3T MRI. Find out how GE HealthCare’s MAGNUS gradient platform is changing the game in TBI imaging to see the unseen.

• 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.

• 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. 

• 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.