Tag: radiologists

AI Detects Interval Cancer on Mammograms

Posted on by Brian Casey

In yet another demonstration of AI’s potential to improve mammography screening, a new study in Radiology shows that Lunit’s Insight MMG algorithm detected nearly a quarter of interval cancers missed by radiologists on regular breast screening exams. 

Breast screening is one of healthcare’s most challenging cancer screening exams, and for decades has been under attack by skeptics who question its life-saving benefit relative to “harms” like false-positive biopsies.  

  • But AI has the potential to change the cost-benefit equation by detecting a higher percentage of early-stage cancers and improving breast cancer survival rates. 

Indeed, 2024 has been a watershed year for mammography AI. 

U.K. researchers used Insight MMG (also used in the BreastScreen Norway trial) to analyze 2.1k screening mammograms, of which 25% were interval cancers (cancers occurring between screening rounds) and the rest normal. 

  • The AI algorithm generates risk scores from 0-100, with higher scores indicating likelihood of malignancy, and this study was set at a 96% specificity threshold, equivalent to the average 4% recall rate in the U.K. national breast screening program.

In analyzing the results, researchers found … 

  • AI flagged 24% of the interval cancers and correctly localized 77%.
  • AI localized a higher proportion of node-positive than node-negative cancers (24% vs. 16%).
  • Invasive tumors had higher median risk scores than noninvasive (62 vs. 33), with median scores of 26 for normal mammograms.

Researchers also tested AI at a lower specificity threshold of 90%. 

  • AI detected more interval cancers at this level, but in real-world practice this would bump up recall rates.  

It’s also worth noting that Insight MMG is designed for the analysis of 2D digital mammography, which is more common in Europe than DBT. 

  • For the U.S., Lunit is emphasizing its recently cleared Insight DBT algorithm, which may perform differently.  

The Takeaway

As with the MASAI and BreastScreen Norway results, the new study points to an exciting role for AI in making mammography screening more accurate with less drain on radiologist resources. But as with those studies, the new results must be interpreted against Europe’s double-reading paradigm, which differs from the single-reading protocol used in the U.S. 

When Follow-Up Falls Short for Lung Nodules

Posted on by Brian Casey

Making sure suspicious imaging findings are followed up appropriately is a key element in providing quality patient care. But a new study found that some suspicious findings aren’t being adequately tracked, especially when it comes to lung nodules. 

Lung nodules are commonly detected on chest CT exams, and are often found incidentally, when patients are being examined for other reasons. 

  • While most smaller nodules don’t represent a threat to patients, it’s important to work up the ones that could be clinically significant. 

In the new paper, Japanese researchers studied 10.5k initial chest CT reports at their institution from 2020 to 2023. 

  • They developed a natural language processing algorithm that analyzed free-text reports to see which ones recommended follow-up. 

They determined that 1.5k reports (14%) recommended additional imaging with exams like chest CT or PET/CT; they then calculated whether these follow-up exams were conducted within 400 days of the initial exam. Further analysis indicated … 

  • For 36% of exams (543) researchers could not confirm that follow-up imaging had taken place.
  • In a random sample of 42 of these patients, 40.5% (17) were not followed up appropriately. 
  • For these cases, either no imaging was documented or no reason was given for the lack of follow-up.

The researchers clarified that they found no evidence of false negatives (missed cancers), as that wasn’t a goal of their study. 

The Takeaway

The new findings indicate both the challenge and opportunity of follow-up management. While radiology must do better in tracking patients with suspicious findings, the study shows that software-based solutions could help, especially those that are automated to scan radiology reports and alert radiologists to cases that need their attention.

Should Patients Get Their Radiology Reports?

Posted on by Brian Casey

It’s one of radiology’s great dilemmas – should patients get their own radiology reports? A new review article in JACR examines this question in more detail, documenting shifting attitudes toward data sharing among radiologists, referring physicians, and patients themselves.

In reality, the question of whether patients should get their own reports has been settled by the 2022 implementation of federal information blocking rules that prevent providers from withholding patient data. 

  • But open questions remain, such as the best mechanisms for delivering data to patients and how to ensure they aren’t confused or alarmed by radiology findings.

To that end, researchers conducted a systematic review of studies from 2007 to 2023 on patient access to radiology reports, eventually identifying 33 publications that revealed …

  • 70% of studies found patients expressing positive preference toward accessing their radiology reports, a trend consistent over the entire study period.
  • 42% of studies documented patient difficulties in understanding medical terminology.
  • 33% highlighted concerns about patient anxiety and emotional impact.
  • Physician opinions on report sharing shifted from 2010 to 2022, from initial dissatisfaction to a gradual appreciation of its benefits.
  • Most studies focused on patient opinions rather than those of referring physicians and radiologists, whose opinions were found in only 18% and 9% of studies, respectively.

A major problem identified by the researchers is that radiology reports have medical terminology that isn’t easily understood by patients – this can lead to confusion and anxiety.

  • Communicating findings in plain language could be one solution, but the researchers said little progress has been made due to “resistance from radiologists and entrenched reporting practices.” 

Although it wasn’t mentioned by the study authors, generative AI offers one possible solution by using natural language processing algorithms to create patient-friendly versions of clinical reports.

The Takeaway

Once patients get access to their own reports, it’s impossible to put that genie back in the bottle. Rather than debating whether patients should get radiology reports, the question now should be how radiologists can ensure their reports will be understood without confusion by their ultimate customer – patients.

Unpacking 2025 Medicare Changes

Posted on by Brian Casey

Here we go again. CMS has once again proposed cuts in Medicare and Medicaid reimbursement, and the healthcare community is once again rallying to try to stave them off. 

CMS last month released its proposed reimbursement changes for 2025, and there were a few victories for radiology. 

  • CMS finally agreed to pay for CT colonography, and also agreed to unbundle payments for PET radiotracers from the PET scan itself.

But CMS also proposed changes in the Medicare Physician Fee Schedule (MPFS) conversion factor that continue the slow drip of reimbursement reduction for physicians.

  • The agency said the proposal would result in no change for radiology, but a deeper dive reveals that’s not the case. 

For example, the analysts at revenue cycle management firm Healthcare Administrative Partners have reviewed the MPFS changes, calculating that if Congressional adjustments are factored in, the outlook is quite different…

  • Interventional radiology will see a -5.8% reduction in the imaging center global fee and a -1.8% drop in the hospital professional fee, for a combined decline of -4.8%
  • The numbers for radiology and nuclear medicine are -3.8% for imaging centers and -1.8% for hospitals, for combined declines of -2.8%

It may seem like -2.8% isn’t a huge cut, but it continues years of steady declines in Medicare reimbursement (HAP notes that the Medicare physician fee schedule has dropped -10% in the last 10 years).

  • And as anyone in healthcare knows, the costs that healthcare practices face have only gone up over that period.  

There’s always the chance that Congress will come to the rescue, as it did when it passed the Consolidated Appropriations Act of 2024 – indeed, professional medical groups led by the AMA published a letter last week urging lawmakers to reform CMS’ rate-setting system in several ways …

  • Enact an annual payment update tied to inflation
  • Eliminate the requirement that changes in payments be budget-neutral
  • Overhaul the Merit-based Incentive Payment System (MIPS)
  • Make modifications to Alternative Payment Models

The Takeaway

The annual ritual in which CMS proposes sharp cuts in Medicare reimbursement only to have Congress lift them at the last minute is a sort of public policy kabuki dance in which the outcome is practically preordained. Medicare reform is badly needed to end this cycle and put physicians on firmer footing so they can focus on what’s important: caring for patients.

Radiologist Shortage Looms

Posted on by Brian Casey

A new report from healthcare staffing firm Medicus Healthcare Solutions paints a gloomy picture of the demographic crush facing radiology as the US population ages and imaging volumes rise, but the number of radiologists remains static. 

Radiology’s demographic dilemma isn’t new to anyone in the field. Radiologists are having to work harder to meet growing demand for imaging by an aging population, while reimbursement falls.

  • Meanwhile, efforts to grow the number of radiologists are hamstrung by the country’s physician training system, which requires a literal act of Congress in order to expand the number of residency slots. 

The new Medicus report mostly draws on established data sources, but it provides insight into the supply and demand challenges facing radiology, presented in an attractive graphical format. Salient points include …

  • There are about 37.7k diagnostic radiologists in the US, with job growth of 4% annually through 2032
  • Since 2020 there have been only 22 new diagnostic radiology residency PGY-1 positions added
  • From 2010 to 2020, the number of diagnostic radiology trainees grew 2.5%, while the number of US adults over 65 rose 34%
  • By 2030, all baby boomers will be aged 65 and older – and will require more medical care
  • The gap between radiology supply and demand is expected to grow through 2034 (see above chart)

What’s more, the vast majority of radiologists reaching retirement age are generalists, while the field’s recent focus on subspecialization means many younger radiologists aren’t comfortable reading scans outside their focus. 

The Medicus report isn’t all doom and gloom. It does offer some possible solutions to the staffing shortage, including teleradiology, AI, and increased use of locums tenens radiologist services (which Medicus provides). 

The Takeaway

The Medicus report provides a snapshot of a medical specialty that – like many others – is facing a demographic crunch between rising demand and fixed supply. Hopefully, technologies like AI will enable radiologists to do more with less in the years to come.

Top 6 Radiology Trends of 2024’s First Half

Posted on by Brian Casey

You can put the first half of 2024 in the books … and it was full of major developments for radiology. What follows are the top six trends in medical imaging – one for each month of the first half.

  • The Rise of AI for Breast Screening – The first half of 2024 saw the publication of studies conducted in Norway and Denmark that underlined the potential role of AI for breast screening, particularly for ruling out exams most likely to be normal. But research conducted within Europe’s paradigm of double-reading workflow for 2D mammograms may not be so relevant in the US, and more studies are needed.
  • Mammography Guideline Controversy – Changes to breast screening guidelines in both the US and Canada were first-half headlines. In the US, the USPSTF made official its proposal to lower to 40 the recommended age to start screening, but many were disappointed it failed to provide stronger guidance on dense breast screening. Things were even worse in Canada, where a federal task force declined to lower the screening age from 50 to 40. Canadian advocates have vowed to fight on at the provincial level. 
  • AI Funding Pullback Continues – The ongoing pullback in venture capital funding for AI developers continues. A study by Signify Research found that not only did VC funding fall 19% in 2023, but it got off to a slow start in 2024 as well. The new environment could be putting more pressure on AI firms to demonstrate ROI to both healthcare providers and investors, while also having broader implications – a major AI conference rescheduled a show that had been on the calendar for May, citing “market conditions.” On the positive side, Tempus AI’s IPO boomed, raising $412M. 
  • Opportunistic Screening Gains Steam – The concept of opportunistic screening – detecting pathology on medical images acquired for other indications – has been around for a while. But it’s only really started to catch on with the development of AI algorithms that can process thousands of images without a radiologist’s involvement. The first half of 2024 saw publication of several exciting studies for indications including detecting osteoporosis, scoring coronary artery calcifications, and predicting major adverse cardiac events. 
  • ChatGPT Frenzy Subsides – The frenzied interest in ChatGPT and other generative AI large language models seen throughout 2023 seemed to subside in the first half of 2024. A quick search of The Imaging Wire archives, for example, finds just four references to ChatGPT in the first six months of 2024 compared to 21 citations at the same point in 2023. LLM developers need to address major issues – from GenAI’s “hallucination effect” to potential misuse of the technology – before LLMs can be used in clinical settings.

The Takeaway

The midpoint of the year is a great time to take stock of radiology’s progress and the issues that have bubbled to the surface over the past six months. In 2024’s back half, look for renewed attention on breast screening as the FDA’s density reporting rules go into effect in September, and keep on the lookout for signs that real-world AI adoption is growing, even as AI developers look for consolidation opportunities.

More Backing for CT Lung Screening

Posted on by Brian Casey

Yet another study is showing support for CT lung cancer screening. In a real-world study in Cancer, researchers tracked screening’s impact on military veterans, finding that it contributed to more early-stage diagnoses as well as lower all-cause mortality. 

It’s no secret that uptake of CT lung screening has been disappointing since the USPSTF in 2013 endorsed the test for high-risk people – mostly those with smoking histories. 

  • Uptake rates have been estimated to be under 10% by some studies, although recent research has shown that targeted interventions can improve that figure.

In the new study, researchers described results from the Veterans Health Administration’s effort to provide low-dose CT lung cancer screening to veterans from 2011 to 2018.

  • The researchers noted that smoking rates are higher among veterans, resulting in lung cancer incidence rates that are 76% higher than the general population. 

Researchers tracked outcomes retrospectively for 2.2k veterans who got screening before a lung cancer diagnosis and compared them to those with lung cancer who weren’t screened, finding that screening led to…

  • Higher rates of stage I diagnosis (52% vs. 27%)
  • Lower rates of stage IV diagnosis (11% vs. 32%)
  • Lower rates of cancer mortality (41% vs. 70%)
  • Lower rates of all-cause mortality (50% vs. 72%)

The sharp reduction in all-cause mortality is particularly striking. 

  • As we’ve discussed in the past, most population-based cancer screening tests have been shown to reduce cancer-specific deaths, but it’s been harder to show a decline in deaths from all causes. 

The study also illustrates the advantage of providing lung screening within a large, integrated healthcare system, where it’s easier to track at-risk individuals and direct them to screening if necessary.

The Takeaway

Of all the positive studies published so far this year on CT lung cancer screening, this one is the most exciting. The findings show that even in an environment of low lung screening uptake, dramatic benefits can be realized with the right approach.

Radiology’s Private-Practice Squeeze

Posted on by Brian Casey

It’s no secret that US radiology’s traditional private-practice model has been slowly fading away, but new numbers published in AJR illustrate the magnitude of the shift. The number of radiologist-affiliated and radiologist-only practices has dropped, even as the total number of US radiologists has gone up. 

Radiology has long prided itself on a cozy business model in which radiologists banded together as owner-operators of small private-practice groups that contracted their services with hospitals. 

  • This model has had many benefits for radiologists, but it’s begun to fray in the face of competitive threats like teleradiology providers, health system consolidation, and large national radiology groups like Radiology Partners.

Many radiologists have chosen to switch rather than fight, selling out to national groups or taking positions as employees within health systems.

  • Meanwhile, some practices that want to stay independent are finding strength in numbers by joining with other like-minded groups or seeking out multi-specialty medical groups. 

In the new study, researchers from the ACR’s Harvey L. Neiman Health Policy Institute analyzed CMS data from 2014 to 2023, tracking not only changes in the number of US radiologists but also their type of employment, finding …

  • The number of radiologists grew 17%, from 30.7k to 36k
  • But the number of radiologist-affiliated practices fell 15%, from 5.1k to 4.3k
  • The number of radiology-only practices fell 32%
  • The number of small radiology practices fell, with the decline varying by practice size: 1-2 radiologists -19%, 3-9 radiologists -34%, and 10-24 radiologists -25%
  • The number of large practices jumped, with the biggest increase – 349% – at very large practices (over 100 radiologists)
  • The mean number of radiologists per practice shot up 84%, from 9.7 to 17.9

Why the shift? The researchers theorized that much of it was driven by federal policy and reimbursement changes that incentivize consolidation, mostly to spread the risk and cost of compliance with various regulations like ACA and MACRA.

The Takeaway

There’s no question that radiology is changing – the question is what impact the changes will have on how radiologists perceive their work. The old guard may choose to rage against the dying of the light, while younger generations embrace the new model and its benefits for both professional careers and patient care. 

Radiologist Pay Rebounds

Posted on by Brian Casey

Radiologist pay grew 5.6% and radiology moved up one notch on Doximity’s list of highest-paid US medical specialties for 2023. Physician salaries generally rebounded last year after a decline in 2022.

The Doximity survey of 33k doctors found that overall physician pay grew 5.9% last year, a welcome rebound after a decline of 2.4% in 2022. 

  • In other good news, medicine’s gender pay gap narrowed in the new survey, with women making 23% less than men, down from 26% in 2022 and 28% in 2021.

For radiologists, their average annual compensation was $532k, up from $504k a year ago, and radiology jumped ahead of urology on the top 10 list to occupy the ninth spot. 

  • Still, radiology lagged a number of other specialties in terms of salary growth, ranging from hematology (+12.4%) to psychiatry (+7.2%). 

Other findings in the survey include …

  • Some 81% of physicians reported they are overworked, a number that’s actually down from 86% in 2022
  • 88% of respondents said their clinical practice has been affected by the physician shortage
  • 86% of those surveyed said they are concerned about the US healthcare system’s ability to care for its aging population

The Doximity results roughly track recently released salary data from Medscape, which pegged radiologist salaries at $498k in 2023, up 3.1% and ranking sixth on the list of highest-paid specialties. 

The Takeaway

Say what you want about rising workload and burnout in radiology – radiologists are still among the best-compensated physicians in medicine. And the situation in the US is in sharp contrast to Japan, where radiology is one of the lowest-paid specialties (see our article in The Wire section below).

Is Radiology’s AI Edge Fading?

Posted on by Brian Casey

Is radiology’s AI edge fading, at least when it comes to its share of AI-enabled medical devices being granted regulatory authorization by the FDA? The latest year-to-date figures from the agency suggest that radiology’s AI dominance could be declining. 

Radiology was one of the first medical specialties to go digital, and software developers have targeted the field for AI applications like image analysis and data reconstruction.

  • Indeed, FDA data from recent years shows that radiology makes up the vast majority of agency authorizations for AI- and machine learning-enabled medical devices, ranging from 86% in 2020 and 2022 to 79% in 2023. 

But in the new data, radiology devices made up only 73% of authorizations from January-March 2024. Other data points indicate that the FDA …

  • Authorized 151 new devices since August 2023
  • Reclassified as AI/ML-enabled 40 devices that were previously authorized 
  • Authorized a total of 882 devices since it began tracking the field 

      In an interesting wrinkle, many of the devices on the updated list are big-iron scanners that the FDA has decided to classify as AI/ML-enabled devices. 

      • These include CT and MRI scanners from Siemens Healthineers, ultrasound scanners from Philips and Canon Medical Systems, an MRI scanner from United Imaging, and the recently launched Butterfly iQ3 POCUS scanner. 

      The additions could be a sign that imaging OEMs increasingly are baking AI functionality into their products at a basic level, blurring the line between hardware and software. 

      The Takeaway

      It should be no cause for panic that radiology’s share of AI/ML authorizations is declining as other medical specialties catch up to the discipline’s head start. The good news is that the FDA’s latest figures show how AI is becoming an integral part of medicine, in ways that clinicians may not even notice.

      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!