Month: December 2023

Top 10 Radiology Stories of 2023

Posted on by Brian Casey

What were the top 10 radiology stories of 2023 in The Imaging Wire? From worklist cherry-picking to a wearable breast ultrasound scanner – and with lots of AI in between – this year’s top 10 list demonstrates the fascinating new developments going on every day in medical imaging.

1. The Perils of Worklist Cherry-Picking

If you’re a radiologist, chances are at some point in your career you’ve cherry-picked the worklist. But picking easy, high-RVU imaging studies to read before your colleagues isn’t just rude – it’s bad for patients and bad for healthcare. That’s according to a study in Journal of Operations Management that analyzed radiology cherry-picking in the context of operational workflow and efficiency. 

2. Tipping Point for Breast AI? 

Have we reached a tipping point when it comes to AI for breast screening? A study in Radiology demonstrated the value of AI for interpreting screening mammograms. 

3. Autonomous AI for Medical Imaging is Here. Should We Embrace It? 

What is autonomous artificial intelligence, and is radiology ready for this new technology? In this paper, we explored one of the most exciting autonomous AI applications, ChestLink from Oxipit. 

4. Undermining the Argument for NPPs

If you think you’ve been seeing more non-physician practitioners (NPPs) reading medical imaging exams, you’re not alone. A study in Current Problems in Diagnostic Radiology found that the rate of NPP interpretations went up almost 27% over four years. 

5. Reimbursement Drives AI Adoption

It’s no secret that insurance reimbursement drives adoption of new medical technology. But an analysis in NEJM AI showed exactly how reimbursement is affecting the diffusion into clinical practice of perhaps the newest medical technology – artificial intelligence. 

6. Radiation and Cancer Risk

New research on the cancer risk of low-dose ionizing radiation could have disturbing implications for those who are exposed to radiation on the job – including medical professionals. In a study in BMJ, researchers found that nuclear workers exposed to occupational levels of radiation had a cancer mortality risk that was higher than previously estimated.

7. Cardiac Imaging in 2040

What will cardiac imaging look like in 2040? It will be more automated and preventive, and CT will continue to play a major – and growing – role. That’s according to an April 11 article in Radiology in which Dr. David Bluemke and Dr. João Lima looked into the future and offered a top 10 list of major developments in cardiovascular imaging in 2040.

8. When AI Goes Wrong

What impact do incorrect AI results have on radiologist performance? That question was the focus of a study in European Radiology in which radiologists who received incorrect AI results were more likely to make wrong decisions on patient follow-up – even though they would have been correct without AI’s help.

9. The 35 Best Radiology Newsletters, Blogs, and Websites to Follow

We dedicated March 6th’s top story to the people and publications that we rely on to find the most interesting medical imaging stories. Assuming that you already subscribe to The Imaging Wire, these are the 35 other newsletters, websites, blogs, and accounts to follow if you want to know what’s happening in radiology.

10. Breast Ultrasound Gets Wearable

Wearable devices are all the rage in personal fitness – could wearable breast ultrasound be next? MIT researchers have developed a patch-sized wearable breast ultrasound device that’s small enough to be incorporated into a bra for early cancer detection. They described their work in a paper in Science Advances.

The Takeaway

The Imaging Wire’s list of top 10 articles for 2023 shows that, while artificial intelligence featured prominently during the year, there was much more to radiology than just AI. We hope you enjoyed reading our content this year as much as we enjoyed bringing it to you.

Lunit’s Deal for Volpara and AI Consolidation

Posted on by Brian Casey

Is the long-awaited consolidation of the healthcare AI sector gaining steam? In a deal valued at close to $200M, South Korean AI developer Lunit announced a bid to acquire Volpara Health, a developer of software for calculating breast density and cancer risk. 

At first glance, the alliance seems to be a match made in heaven. Lunit is a well-regarded AI developer that has seen impressive results in clinical trials of its Insight family of algorithms for indications ranging from mammography to chest imaging. 

  • Most recently, Lunit received FDA clearance for its Insight DBT software, marking its entry into the US breast screening market, and it also raised $150M in a public stock offering. 

Volpara has a long pedigree as a developer of breast imaging software, although it has shied away from image analysis applications to instead focus on breast center operations and risk assessment, in particular by calculating breast density. 

  • Thus, combining Lunit’s concentration in image analysis with Volpara’s focus on operations and risk assessment enables the combined company to offer a wider breadth of products to breast centers.

Lunit will also be able to take advantage of the marketing and sales structure that Volpara has built in the US mammography sector (97% of Volpara’s sales come from the US, where it has an installed base of 2k sites). Volpara expects 2024 sales of $30M and is cash-flow positive.

The question is whether the acquisition is a sign of things to come in the AI market. 

  • As commercial AI sales have been slow to develop, AI firms have largely funded their operations through venture capital firms – which are notoriously impatient in their quest for returns.

In fact, observers at the recent RSNA 2023 meeting noted that there were very few new start-up entrants into the AI space, and many AI vendors had smaller booths. 

  • And previous research has documented a slowdown in VC funding for AI developers that is prompting start-up firms to seek partners to provide more comprehensive offerings while also focusing on developing a road to profitability. 

The Takeaway

It’s not clear yet whether the Lunit/Volpara deal is a one-off combination or the start of a renewed consolidation trend in healthcare AI. Regardless of what happens, this alliance unites two of the stronger players in the field and has exciting potential for the years to come. 

How to Improve CT Lung Cancer Screening

Posted on by Brian Casey

As the US grapples with low CT lung cancer screening rates, researchers and clinicians around the world are pressing ahead with ways to make the exam more effective – especially in countries with high smoking rates. Two new studies published this week show the progress that’s being made.

In Brazil, researchers in JAMA Network Open found that using broader criteria to determine who should get CT lung screening not only expanded the eligible population, but it also reduced racial disparities in screening’s effectiveness. 

Researchers compared three strategies for determining screening eligibility: two based on 2013 and 2021 USPSTF criteria, and one in which all ever-smokers ages 50-80 were screened, finding: 

  • Screening all ever-smokers generated the largest possible screening population (27.3M people) compared to USPSTF criteria for 2013 (5.1M) and 2021 (8.4M)
  • Number of life-years gained if lung cancer is averted due to screening was highest with all-screening (23 vs. 19 & 21)
  • But the all-screening strategy also had the highest number needed to screen to prevent one lung cancer death (472 vs 177 & 242)
  • The USPSTF 2021 criteria reduced (but did not eliminate) racial disparities; the USPSTF 2013 criteria produced the greatest disparity 

The authors said the results showed that CT lung cancer screening in Brazil could identify 57% of preventable lung cancer deaths if 22% of ever-smokers are screened. Their study should help the country decide which screening strategy to adopt. 

In a second paper in the same journal, researchers from China described how they performed CT lung cancer screening via opportunistic screening, offering low-dose CT scans to patients visiting their doctor for other reasons, such as a routine checkup or a health problem other than a pulmonary issue. Among 5.2k patients, researchers found that people who got opportunistic LDCT screening had:

  • 49% lower risk of lung cancer death by hazard ratio
  • 46% lower risk of all-cause mortality
  • 43% received their lung cancer diagnosis through opportunistic screening

The Takeaway

This week’s studies continue the positive progress toward CT lung cancer screening that’s being made around the world. Both offer different strategies for making screening even more effective, and add to the growing weight of evidence in favor of population-based lung screening.

AI Powers Opportunistic Screening

Posted on by Brian Casey

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. 

AI’s Impact on Breast Screening

Posted on by Brian Casey

One of the most exciting radiology use cases for AI is in breast screening. At last week’s RSNA 2023 show, a paper highlighted the technology’s potential for helping breast imagers focus on cases more likely to have cancer.

Looking for cancers on screening mammography has been compared to finding a needle in a haystack, and as such it’s considered to be one of the areas where AI can best help. 

  • One of the earliest use cases was in identifying suspicious breast lesions during radiologist interpretation (remember computer-aided detection?), but more recently researchers have focused on using AI as a triage tool, by identifying cases most likely to be normal that could be removed from the radiologist’s urgent worklist. Studies have found that 30-40% of breast screening cases could be read by AI alone or triaged to a low-suspicion list.

But what impact would AI-based breast screening triage have on radiologist metrics such as recall rate? 

  • To answer this question, researchers from NYU Langone Health prospectively tested their homegrown AI algorithm for analyzing DBT screening cases.

The algorithm was trained to identify extremely low-risk cases that could be triaged from the worklist while more complex cases where the AI was uncertain were sent to radiologists, who knew in advance the cases they were reading were more complicated. In 11.7k screening mammograms, researchers examined recall rates over two periods, one before AI triage and one after, finding: 

  • The overall recall rate went from 13% before the triage period to 15% after 
  • Recall rates for complex cases went from 17% to 20%
  • Recall rates for extremely low-risk studies went from 6% to 5%
  • There were no statistically significant differences in any of the comparisons
  • No change in median self-reported perceived difficulty of reading from the triage lists compared to non-triage list, regardless of years of experience

In future work, the NYU Langone researchers will continue their study to look at AI’s impact on cancer detection rate, biopsy rate, positive predictive value, and other metrics.

The Takeaway

The NYU Langone study puts a US spin on research like MASAI from Sweden, in which AI was able to reduce radiologists’ breast screening workload by 44%. Given the differences in screening protocols between the US and Europe, it’s important to assess how AI affects workload between the regions.

Further work is needed in this ongoing study, but early results indicate that AI can triage complex cases without having an undue impact on recall rate or self-perceived difficulty in interpreting exams – a surrogate measure for burnout.

RSNA 2023 Video Highlights

Posted on by Brian Casey

That’s a wrap! 

RSNA 2023 just concluded, and by most accounts it was a successful conference. Preliminary figures indicate that attendance was up 11% over 2022. While short of the glory days of RSNA, the numbers indicate that the meeting’s recovery from the COVID-19 pandemic will be slow but steady.

As expected, AI was a dominant theme at McCormick Place, and that’s reflected in our video coverage of the technical exhibit floor. AI busted out of the AI Showcase to permeate both exhibit halls, a sign of the technology’s growing influence on radiology.

We profiled many of the most intriguing companies that were exhibiting at RSNA 2023 – some of them dominant players in the field while others are new entries looking to secure a foothold. 

We hope you enjoy watching our coverage as much as we enjoyed producing it! Check out the links below or visit the Shows page on our website.

AI’s Incremental Revolution

Posted on by Brian Casey

So AI dominated the discussion at last week’s RSNA 2023 meeting. But does that mean it’s finally on the path to widespread clinical use? 

Maybe not so much. For a technology that’s supposed to have a revolutionary impact on medicine, AI is taking a frustratingly long time to arrive. 

Indeed, there was plenty of skepticism about AI in the halls of McCormick Place last week. (For two interesting looks at AI at RSNA 2023, also see Hugh Harvey, MD’s list of takeaways in a post on X/Twitter and Herman Oosterwijk’s post on LinkedIn.) 

But as one executive we talked to pointed out, AI’s advance to routine clinical use in radiology is likely to be more incremental than all at once. 

  • And from that perspective, last week’s RSNA meeting was undoubtedly positive for AI. Scientific sessions were full of talks on practical clinical applications of AI, from breast AI to CT lung screening. 

Researchers also discussed the use of AI apart from image interpretation, with generative AI and large language models taking on tasks from answering patient questions about their reports to helping radiologists with dictation.

It’s fine to be a skeptic (especially when it comes to things you hear at RSNA), but for perspective look at many of the past arguments casting doubt on AI: 

  • AI algorithms don’t have FDA clearance (the FDA authorized 171 algorithms in just the past year)
  • You can’t get paid for using AI clinically (16 algorithms have CPT codes, with more on the way) 
  • There isn’t enough clinical evidence backing the use of AI (tell that to the authors of MASAI, PERFORMS, and a number of other recent studies with positive findings)
  • The AI market is overcrowded with companies and ripe for consolidation (what exciting new growth market isn’t?)

The Takeaway

Sure, it’s taking longer than expected for AI to take hold in radiology. But last week’s conference showed that AI’s incremental revolution is not only advancing but expanding in ways no one expected when IBM Watson was unveiled to an RSNA audience a mere 6-7 years ago. One can only imagine what the field will look like at RSNA 2030.

Looking for more coverage of RSNA 2023? Be sure to check out our videos from the technical exhibit floor, which you can find on our new Shows page.

Get every issue of The Imaging Wire, delivered right to your inbox.

You might also like..

Select All

You're signed up!

It's great to have you as a reader. Check your inbox for a welcome email.

-- The Imaging Wire team

You're all set!