Tag: radiology

Opportunistic Calcium Scoring Shifts to Abdomen

Posted on by Brian Casey

Most of the recent research on calcium scoring has focused on calcium in the coronary arteries and its link to cardiovascular disease. But a new study in American Heart Journal used abdominal CT scans with AI analysis for opportunistic measurement of abdominal aortic calcium to predict cardiac events – possibly earlier than CAC scores.

CT-derived CAC scores have become a powerful tool for predicting cardiovascular disease, helping physicians determine when to begin preventive therapy with treatments like statins.

  • CAC scores can be generated from dedicated cardiac CT scans, or even lung screening exams as part of a two-for-one test. 

Abdominal CT represents another promising area for calculating calcium. 

  • Previous research has found that atherosclerosis in the abdominal aorta may occur before its development in the coronary arteries, creating the opportunity to detect calcium earlier. 

Researchers from NYU Langone did just that in the new study, performing abdominal and cardiac CT scans in 3.6k patients and using an AI algorithm they developed in partnership with Visage Imaging to calculate AAC. They found that over an average three-year follow-up period … 

  • AI analysis of AAC severity was positively associated with CAC.
  • AAC could be used to rule out the presence of CAC relative to two versions of the PREVENT score (AUC=0.701 and 0.7802). 
  • The presence of AAC was associated with a higher adjusted risk of major adverse cardiovascular events (HR=2.18).
  • A doubling of the AAC score was linked to 11% higher risk of MACE.

The Takeaway

The new results are an exciting demonstration of opportunistic screening’s value, especially given the volume of abdominal CT scans performed annually. AI analysis of routinely acquired abdominal CT could give radiologists a tool for detecting heart disease risk even earlier than what’s possible with CAC scoring.

MRI Recon Gets Real with AI-Driven Protocols

Posted on by Brian Casey

AI-based data reconstruction for MRI scans took a step forward this week with studies showing how to generate 3T-like images from ultralow-field scanners, and improve scanner efficiency by cutting energy consumption.

MRI is radiology’s premier modality, but MRI scanners are cumbersome to install and expensive to operate. 

  • Ultralow-field scanners could help but some believe they lack the image quality for some clinical applications. 

Enter AI-based image reconstruction. Deep learning protocols are being developed for a wide range of imaging modalities, from PET to CT to MRI. 

  • These algorithms take images acquired with lower-quality input data – be it less CT radiation dose or lower MRI field strength – and upscale them to resemble full-fidelity images.

This trend is illustrated by research published this week in Radiology in which researchers tested a generative adversarial network algorithm called LowGAN for reconstructing data acquired on Hyperfine’s Swoop 0.064T portable ultralow-field MRI scanner.

  • Their goal was to enable Swoop to generate images resembling those acquired on a 3T system. 

After training LowGAN on paired 3T and 0.064T images, they tested the algorithm in 50 patients with multiple sclerosis and further validated it with a separate 13-patient cohort. They then judged LowGAN against several measures of MR image quality, finding that it …

  • Showed the biggest improvement on synthetic FLAIR and T1 images.
  • Improved conspicuity of white matter lesions, without introducing false lesions.
  • Increased consistency of cortical and subcortical volume measurements with 3T images.
  • But was unable to reveal brain lesions that were missed in the original low-field scans. 

AI-based data reconstruction also has environmental implications. Medical imaging is a major contributor to greenhouse gas emissions, and anyone who’s managed an MRI operation knows how much energy these massive scanners consume. 

  • A second paper published this week in Radiology described how MRI acceleration – scans acquired at a faster speed and then reconstructed for better image quality – reduced energy use, lowering carbon emissions while boosting imaging capacity. 

Researchers tried three techniques for speeding MRI acquisition – parallel acceleration, simultaneous multi-slice, and a deep learning algorithm. 

  • All three reduced energy consumption 21% to 65% and increased daily capacity by one to seven scanning slots, with deep learning showing the biggest effect.

The Takeaway

The new papers demonstrate an exciting future in which less powerful data acquisition technologies can be upscaled with AI to produce images that more closely resemble state-of-the-art scanning. The benefits will be enjoyed by both patients and the planet.

Patients Want Mammo AI, But Mostly As Backup

Posted on by Brian Casey

Patients support the idea of having AI review their screening mammograms – under certain conditions. That’s according to a new study in Radiology: Imaging Cancer that could have implications for breast imagers seeking to integrate AI into their practices.

Mammography screening has been identified as one of the most promising use cases for AI, but clinical adoption has been sluggish for reasons that range from low reimbursement to concerns about data privacy, security, algorithm bias, and transparency. 

  • Vendors and providers are working on solving many of the problems impeding greater AI use, but patient preference is an often overlooked factor – even as some providers are beginning to offer AI review services for which patients pay out of pocket.

To gain more insight into what patients want, researchers from the University of Texas Southwestern Medical Center surveyed 518 women who got screening mammography over eight months in 2023, finding …

  • 71% preferred that AI be used as a second reader along with a radiologist.
  • Only 4.4% accepted standalone AI interpretation of their images.
  • 74% wanted patient consent before AI review.
  • If AI found an abnormality, 89% wanted a radiologist to review their case, versus 51% who wanted AI to review abnormal findings by radiologists.
  • If AI missed a finding, 58% believed “everyone” should be accountable, while 15% said they would hold the AI manufacturer accountable. 

Patient preference for use of AI in collaboration with radiologists tracks with other recent research. 

  • Patients seem to want humans to retain oversight of AI, and seem to value trust, empathy, and accountability in healthcare – values associated with providers, not machines. 

The findings should also be good news for imaging services companies offering out-of-pocket AI review services. 

The Takeaway

The new findings should be encouraging not only for breast imagers and AI developers, but also for the imaging services companies that are banking on patients to shell out their own money for AI review. As insurance reimbursement for AI languishes, this may be the only way to move mammography AI forward in the short term.

CT Cancer Risk Study Raises Questions

Posted on by Brian Casey

The radiology world was turned on its head this week with the publication of a new paper in JAMA Internal Medicine on CT radiation risk. Researchers estimated that all the CT scans performed in the U.S. in a single year would cause more than 100k cancers over the lives of the patients who got them. 

Radiation risk has always been the Achilles heel of CT, radiology’s workhorse modality for advanced imaging. 

  • But CT is plagued by dose variation and a lack of reporting on exactly how much dose patients are getting – especially when it exceeds guidelines.

In the new study, researchers led by radiation safety expert Rebecca Smith-Bindman, MD, of UCSF used existing estimates of low-level radiation risk to calculate how many cancers would result from the 93M CT scans performed in the U.S. in 2023, finding …

  • CT radiation dose would cause 103k future cancers over the lifetimes of the patients.
  • At the current rate, “CT-associated cancer” would account for 5% of all cancers – about the same number caused by alcohol. 
  • The study’s projection of CT-linked cancers is 3X-4X higher than previous estimates, mostly due to the growth in CT utilization. 

The paper generated pushback from sources including the ACR and AAPM, who questioned whether it really reveals any new information about the risks of CT radiation. 

  • They reiterated the medical value of CT scans, noting that the research was based on statistical models and that there are no published studies directly linking CT scans to cancer.

Another thing the paper doesn’t touch on are the dramatic reductions in CT radiation dose that have occurred in recent years. 

  • CT protocol optimization and AI-based data reconstruction – as well as technologies like photon-counting CT – have enabled imaging professionals to reduce doses to levels previously thought impossible, such as under 1 mSv for a routine chest exam. 

To help providers manage dose, CMS this year launched new dose reporting quality measures, CMS1074v2, designed to reward radiology practices for tracking and reporting radiation dose. 

  • Smith-Bindman is a co-founder of Alara Imaging, which provides software to help radiology providers comply with the new CMS measures. ACR also offers a variety of dose optimization and monitoring tools.

The Takeaway

So what to make of the new study? On the one hand, the sensational headlines it generated could scare many patients away from getting medically necessary CT scans. On the other, any attention toward radiation dose reduction and appropriate imaging is a good thing, and if it spurs new efforts toward more judicious and consistent use of CT at lower radiation levels, so much the better. 

High-Risk Breast Clinics: A Smart Move for Imaging Providers

Posted on by Partner Content

High-risk breast cancer clinics are no longer just a good idea – they’re becoming a strategic imperative. These programs, focused on identifying and managing women at elevated risk for breast cancer, are proving their value clinically and financially.

For imaging providers, they present an opportunity both to improve care and grow service lines in a value-based care environment, while also differentiating themselves in increasingly competitive markets. A recently published white paper offers a full explanation of the benefits of high-risk breast clinics.

Treating late-stage breast cancer is extremely costly – $76,000+ in the final year of life alone – and it represents a major portion of oncology spend nationwide. 

  • By identifying high-risk patients early and offering enhanced surveillance with breast MRI, clinics can diagnose more cancers at early stages, when treatment is more effective and less expensive. 

Studies show MRI screening in BRCA1 carriers is cost-effective at ~$50,900 per QALY. 

  • This makes it a smart investment from both a patient and payor perspective.

Historically, preventive programs were considered cost centers. Not so with high-risk breast clinics. 

  • Once a patient is flagged as high risk, the care pathway includes reimbursable   genetic counseling and testing, supplemental imaging (MRI or contrast-enhanced mammography), biopsies, chemoprevention, and even risk-reducing surgeries. Each step creates downstream revenue for imaging centers and affiliated specialists – all while improving patient care.

Integration is key. Embedding risk assessment tools like Tyrer-Cuzick or AI-based models (e.g. Mirai) into the high-risk clinic’s imaging workflow enables automatic triage. 

  • Patients with ≥20% lifetime risk can be directly referred to the high-risk clinic. Some models now use short-term risk from imaging data alone to identify the top 5-10% women most likely to develop cancer within five years – significantly outperforming traditional tools in clinical studies.

Successful clinics rely on multidisciplinary teams. Advanced-practice providers manage most visits. Genetic counselors – in person or via telehealth – manage testing results and family history. Patient navigators coordinate follow-ups and authorizations. 

  • This team-based approach keeps physician time focused and costs under control, ensuring the clinic operates efficiently and sustainably.

The Takeaway

For imaging providers, high-risk breast clinics offer a powerful blend of patient impact and business growth. They reduce expensive late-stage cancers, drive high-value imaging, and create long-term patient relationships. In an era of value-based care, they’re not just a clinical upgrade – they’re a strategic advantage. Forward-thinking imaging leaders are recognizing this model as essential to the future of preventive breast care.

Getting Paid for AI – Will It Get Easier?

Posted on by Brian Casey

Reimbursement is one of the major stumbling blocks holding back wider clinical adoption of artificial intelligence. But new legislation was introduced into the U.S. Congress last week that could ease AI’s reimbursement path. 

For AI developers, getting an algorithm approved is just the first step toward commercial acceptance. 

  • Perhaps even more important than FDA clearance is Medicare reimbursement, as healthcare providers are reluctant to use a product they won’t get paid for. 

Reimbursement drives clinical AI adoption, as evidenced by a 2023 analysis listing the top algorithms by CPT claims submitted (HeartFlow Analysis topped the list). 

  • But CMS uses a patchwork system governing reimbursement, from temporary codes like New Technology Add-On Payment codes that expire after 2-3 years to G-codes for procedures that don’t have CPT codes, on up to the holy grail of medical reimbursement: Category I codes. 

The new legislation – S.1399 or the Health Tech Investment Act – would simplify the situation by setting up a dedicated Medicare coverage pathway for AI-enabled medical devices approved by the FDA (called “algorithm-based healthcare services”), as follows … 

  • All FDA-approved products would be assigned a Category III New Technology Ambulatory Payment Classification in the HOPPS program.
  • NTAPC codes would last for five years to enable collection of cost data before a permanent payment code is assigned. 
  • Payment classifications will be based on the cost of service as estimated by the manufacturer. 

The bill at present has co-sponsors from both political parties, Sen. Mike Rounds (R-SD) and Sen. Martin Heinrich (D-NM). 

  • The legislation has also drawn support from industry heavyweights like GE HealthCare and Siemens Healthineers, as well as industry groups like AdvaMed and others.

The Takeaway

The new bill sounds like a great idea, but it’s easy to be skeptical about its prospects in today’s highly charged political environment – especially when even bipartisan compromises like the 2025 Medicare fix got scuttled. Still, S.1399’s introduction at least shows that the highest levels of the U.S. government are cognizant of the need to improve clinical AI reimbursement.

Radiology’s Rising Workload

Posted on by Brian Casey

If you think new imaging IT technologies will reduce radiologist workload in the future, you might want to think again. Researchers who analyzed hundreds of studies on new scientific advances predicted that nearly half of them would increase radiologists’ workload – especially AI. 

Radiologists are desperately in need of help to manage rising imaging volumes during a period of global workforce shortages. 

But how true is that belief? In the new study in European Journal of Radiology, radiologists Thomas Kwee, MD, and Robert Kwee, MD, from the Netherlands analyzed a random sample of 416 articles published in 2024 on imaging applications that could affect future radiologist workloads, finding …

  • 49% of the articles on applications that had the potential to directly impact patient care would increase radiologist workload in the tertiary care academic setting. 
  • Studies on AI-focused applications were 14X more likely to increase workload compared to research that didn’t.
  • Similar numbers were found for non-academic general teaching hospitals.
  • The findings are largely similar to a 2019 study by Kwee et al that used the same methodology.  

Why don’t new imaging applications show more potential to reduce radiologists’ workloads? 

  • The Kwees found that image post-processing and interpretation times have grown for both existing and new applications. 

In the specific case of AI, they cited an example in which a deep learning algorithm was introduced to analyze CT scans to segment and classify features of spontaneous intracerebral hemorrhage and predict hematoma expansion.

  • The model successfully predicted hematoma expansion and automatically segmented lesions, but CT images still had to be post-processed with a separate workflow. This required additional radiologist interpretation time and extended their workload.

The Takeaway

The new study throws cold water on the idea that AI will be able to solve radiology’s workload dilemma. It’s possible that AI will have an impact on radiology that’s similar to that of PACS in the 1990s in making radiologists more productive, but we’ll need new efficiency-oriented changes to achieve that goal.

6 Imaging IT Tools Radiologists Want Now

Posted on by Brian Casey

It’s no secret that radiology faces a variety of challenges, from rising imaging volumes to workforce shortages. But can imaging IT vendors help? A new paper in Academic Radiology suggests they can, and provides a list of the half-dozen imaging IT tools that radiologists say they need most. 

Radiology is already one of the most software-oriented specialties in medicine. 

  • It was an early adopter of digital healthcare through tools like PACS, and is reprising its leadership in the coming AI era with the lion’s share of FDA-approved medical AI applications. 

But that doesn’t mean radiologists have all the IT tools at their disposal that they feel they need. 

  • The new paper is a sort of radiologist wish list, developed after a 2024 meeting between vendors and members of the Association of Academic Radiologists.

Some three dozen key opinion leaders met for breakout discussions on radiology’s unmet IT needs. The discussion was then boiled down into six major areas …

  1. Increased workstation efficiency, with better tools for looking through medical records to find clinical information. 
  2. Better AI tools for radiology reporting, such as auto-generated measurements and findings from prior studies for comparison. 
  3. Better methods for controlling imaging overutilization, such as clinical decision support systems to be used by referring physicians to order exams.
  4. Help from vendors to improve access to high-level radiology services in underserved areas like rural communities, such as through industry-sponsored training positions or improved telemedicine access to patients with follow-up appointments.
  5. Patient engagement tools that promote direct communication between radiologists and patients, including industry-sponsored training modules for radiologists to discuss findings with patients. 
  6. Simpler scheduling systems that allow patients to pick appointment times from their smartphones.

One possible question to ask about the recommendations is whether the needs of academic radiologists truly reflect those of radiologists in general, especially those in private practice.

  • But the items on the wish list appear broad enough that they hit the requirements of a wide range of imaging practitioners. 

The Takeaway

Sure, radiologists face many challenges in today’s healthcare environment. But the fact that radiology is such an IT-centered specialty offers hope that new software tools can help them – and that radiology vendors can lend a hand. 

Who’s Reading Office-Based Medical Images?

Posted on by Brian Casey

Non-radiologist providers are reading almost half of medical images acquired in the office practice setting. A new analysis in AJR raises questions about both the quality of these interpretations as well as whether they are contributing to imaging overutilization. 

Radiologists have jealously guarded their role as the primary interpreters of medical images, but keeping referring physicians away is like holding back the tide – especially when they control the patients.

  • Progress was made in the 1990s with the passage of Stark legislation prohibiting doctors from referring patients to sites where they have a financial interest, but Stark includes an exemption for imaging performed in the doctors’ own offices.

This in-office exemption is a loophole big enough to drive a truck through, and as in-office imaging has grown radiologists have raised questions about:

1. Whether non-radiologist providers have adequate training in image interpretation. 

2. If the economic incentive behind in-office imaging contributes to imaging overutilization. 

So to learn more about who’s reading in-office images, researchers from the ACR’s Harvey L. Neiman Health Policy Institute analyzed 1.6M office-based imaging studies from 2022, discovering … 

  • 44% of office-based medical images are self-interpreted by the provider who ordered them.
  • Self-interpretation rates varied by modality: ultrasound (52%), X-ray (50%), nuclear medicine (40%), MRI (6.1%), and CT (5.3%). 
  • As well as by specialty: orthopedic/sports medicine (76%), cardiology (73%), non-physician providers (31%), primary care (20%), and other specialties (38%). 
  • Larger practices had lower self-interpretation rates, as did practices with a radiologist on-staff.

High image self-interpretation rates could be a patient care issue given that – other than cardiology – non-radiologist physicians don’t usually receive extensive training in image interpretation. 

  • Imaging overutilization could also be occurring as there are no reimbursement restrictions on in-office self-referring physicians, and studies have shown that the Stark laws failed to achieve reductions in self-referred imaging volumes.

The Takeaway

The new study sheds light on one of healthcare’s most persistent problems – in-office physician self-referral. The question is whether it’s a problem that will eventually take care of itself as healthcare consolidation leads to larger medical practices that are more likely to have radiologists on staff. 

CAC Scoring Shines at ACC 2025

Posted on by Brian Casey

The American College of Cardiology’s annual meeting is wrapping up today in Chicago, and new research into coronary artery calcium scoring has been one of cardiac imaging’s top trends at McCormick Place.

CAC scoring has been around for ages as a way to detect and quantify calcium buildup in the coronary arteries based on data from non-contrast CT scans. 

  • But it’s only been in recent years that CAC scoring has come into its own as a tool for predicting risk of mortality and major cardiac events – in some cases years before they happen. 

Clinicians are learning that they can use CT-generated CAC scores to estimate future risk and guide interventions to reduce it, such by prescribing statins or behavior modifications. 

Research presented at ACC 2025 underscored CAC scoring’s potential …

  • In the CLARIFY CAC screening program, researchers found a 6.2% rate of thoracic aneurysm, indicating a need for screening and prevention.
  • CAC scores of 0 were more common in women than men (49% vs. 23%), but there was no statistically significant difference in non-calcified plaque rates between genders.
  • Researchers found moderate accuracy (AUC range=0.60-0.73) for a method of generating CAC scores from 12-lead ECG data rather than non-contrast CT scans.
  • Bunkerhill Health’s I-CAC algorithm was used to generate automated CAC scores for 200 patients. After six months, patients with scores >400 had a 17% rate of cardiac events and 11% all-cause mortality. 
  • A commonly used measure for low-value care based on administrative claims classified too many CAC tests as inappropriate, with a positive predictive value of only 43%.
  • A case study focused on the paradox of a 59-year-old healthy triathlete with a CAC score of 780, possibly due to chronic coronary stress from high-endurance exercise. Invasive testing was deferred in favor of medical therapy due to his low cardiac risk.
  • On the other hand, a literature review of 19.4k people found no statistically significant difference in CAC scores between endurance athletes and healthy controls.
  • Non-calcified plaque in patients with CAC scores of 0 was common (26%) in residents of rural Appalachia, indicating high risk of rupture and suggesting the limitation of relying on CAC scores. 
  • A Sunday debate discussed whether CAC scoring should be added to mammography and colon cancer screening, or reserved as a decision aid. 

The Takeaway

The studies from ACC 2025 show that CAC scoring has a bright future – bright enough that it’s generating heightened interest from cardiology. New CAC scoring tools arriving on the market should improve its predictive value even more. 

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!