Author: Brian Casey

Imaging News from ESC 2024

Posted on by Brian Casey

The European Society of Cardiology annual meeting concluded on September 2 in London, with around 32k clinicians from 171 countries attending some 4.4k presentations. Organizers reported that attendance finally rebounded to pre-COVID numbers. 

While much of ESC 2024 focused on treatments for cardiovascular disease, diagnosis with medical imaging still played a prominent role. 

  • Cardiac CT dominated many ESC sessions, and AI showed it is nearly as hot in cardiology as it is in radiology. 

Major imaging-related ESC presentations included…

  • A track on cardiac CT that underscored CT’s prognostic value:
    • Myocardial revascularization patients who got FFR-CT had lower hazard ratios for MACE and all-cause mortality (HR=0.73 and 0.48).
    • Incidental coronary artery anomalies appeared on 1.45% of CCTA scans for patients with suspected coronary artery disease.
  • AI flexed its muscles in a machine learning track:
    • AI of low-dose CT scans had an AUC of 0.95 for predicting pulmonary congestion, a sign of acute heart failure. 
    • Echocardiography AI identified HFpEF with higher AUC than clinical models (0.75 vs. 0.69).
    • AI of transthoracic echo detected hypertrophic cardiomyopathy with AUC=0.85.

Another ESC hot topic was CT for calculating coronary artery calcium (CAC) scores, a possible predictor of heart disease. Sessions found … 

  • AI-generated volumetry of cardiac chambers based on CAC scans better predicted cardiovascular events than Agatston scores over 15 years of follow-up in an analysis of 5.8k patients from the MESA study. 
  • AI-CAC with CT was comparable to cardiac MRI read by humans for predicting atrial fibrillation (0.802 vs. 0.798) and stroke (0.762 vs. 0.751) over 15 years, which could give an edge to AI-CAC given its automated nature.
  • An AI algorithm enabled opportunistic screening of CAC quantification from non-gated chest CT scans of 631 patients, finding high CAC scores in 13%. Many got statins, while 22 got additional imaging and 2 intervention.
  • AI-generated CAC scores were also highlighted in a Polish study, detecting CAC on contrast CT at a rate comparable to humans on non-contrast CT (77% vs. 79%), possibly eliminating the need for additional non-contrast CT.  

The Takeaway

This week’s ESC 2024 sessions demonstrate the vital role of imaging in diagnosing and treating cardiovascular disease. While radiologists may not control the patients, they can always apply knowledge of advances in other disciplines to their work.

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.

Patients Unclear on Imaging Costs

Posted on by Brian Casey

A new study in Health Policy and Technology shows that patients are surprisingly unclear on how much their imaging exams will cost them. Researchers found that few knew their imaging facilities had price estimator tools and even fewer were aware of their out-of-pocket estimates.

The U.S. government has been trying to make healthcare more transparent and understandable for patients through a variety of new rules it’s implemented in recent years, such as “information blocking” rules that prevent providers from withholding patient data.

  • In 2021, CMS required health systems to notify patients of out-of-pocket expenses and make available tools for estimating prices. 

But how knowledgeable are patients about these initiatives? 

  • Researchers from UC Irvine and the University of Michigan surveyed 423 patients scheduled for CT, PET/CT, or MRI scans in Southern California to find out how much they knew about their out-of-pocket costs. 

Researchers discovered that …

  • Only 11% of patients were aware of their out-of-pocket estimates before getting their scans.
  • Only 17% knew their imaging facilities had price estimator tools.
  • 53% said their illness has been a financial hardship, but only 34% were worried about their out-of-pocket costs for imaging.
  • No patient used the hospital’s estimator tool.
  • Patients were less likely to know their out-of-pocket costs if they had lower income (<$50,000), more financial hardship, and no comorbidities. 

The results show that, two years after out-of-pocket transparency rules went into effect, patients are still unclear on their imaging costs. 

  • This is a major problem due to the high variation in imaging prices that’s been documented in other studies, such as 2023 research that found MRI scans ranging in price from $878 to $3,403.

More outreach could help patients better understand costs. 

  • Such outreach could be made through automated calls or even messages through patient portals prior to their exams.

The Takeaway
The new study – when coupled with recent research on patient reports – shows that radiology still has a ways to go when it comes to keeping patients informed about their imaging exams. Getting patients more involved not only will have economic benefits, but could also help patients participate in their own care.

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.

Two-for-One CT Screening Hits the Road

Posted on by Brian Casey

A new study takes CT screening on the road in rural Appalachia, showing how a mobile van outfitted with a CT scanner can screen at-risk individuals for both lung cancer and cardiovascular disease in one visit. 

Recent studies have demonstrated the effectiveness of CT lung cancer screening not only among the overall population, but particularly among disadvantaged communities with lower healthcare access. 

  • Such limited access is common in rural areas of Appalachia, which also have some of the highest rates of smoking and cardiovascular disease in the U.S.

Researchers from West Virginia University wanted to tackle two challenges at once with LUCAS, a mobile van outfitted with a CT scanner for lung cancer screening. 

  • They noted that CT lung scans can also be used to acquire data on coronary artery calcium (CAC), a known risk factor for cardiovascular disease. 

LUCAS was launched in September 2021, so WVU researchers analyzed data acquired for 526 low-dose CT screenings of high-risk people conducted through December 2022. 

  • They used the CT lung scans to calculate CAC scores based on Agatson criteria, in which a score of 101-400 indicates moderate risk of cardiovascular disease and >400 is classified as high risk; individuals with scores ≥100 should be referred to aspirin or statin therapy. 

They found that LUCAS scans revealed … 

  • Over 54% of patients had coronary calcification on LDCT scans
  • 31% of patients had CAC scores ≥100 
  • 14% had CAC scores ≥400
  • Elevated CAC scores correlated with lung cancer risk based on Lung-RADS scores as well as smoking history based on pack-years
  • Of the patients with CAC scores ≥1 and who weren’t already on statin or aspirin therapy, 6.2% started statins and 3.3% started aspirin

Despite the firm link between CAC scores and lung cancer risk, the researchers expressed disappointment that so few patients started prevention therapy like statins or aspirin after their exams.

  • Indeed, researchers noted that few patients from the study got additional cardiac testing or follow-up referrals for cardiovascular prevention after their screenings. 

The Takeaway

The new study not only confirms recent research showing that opportunistic screening can enhance the value of CT lung cancer scans, but also the role that lung exams can play in reducing healthcare disparities. On the down side, it shows that all the screening in the world won’t make a difference if patients don’t get appropriate follow-up. 

FDA Keeps Pace on AI Approvals

Posted on by Brian Casey

The FDA has updated its list of AI- and machine learning-enabled medical devices that have received regulatory authorization. The list is a closely watched barometer of the health of the AI sector, and the update shows the FDA is keeping a brisk pace of authorizations.

The FDA has maintained double-digit growth of AI authorizations for the last several years, a pace that reflects the growing number of submissions it’s getting from AI developers. 

  • Indeed, data compiled by regulatory expert Bradley Merrill Thompson show how the number of FDA authorizations has been growing rapidly since the dawn of the medical AI era in around 2016 (see also our article on AI safety below). 

The new FDA numbers show that …

  • The FDA has now authorized 950 AI/ML-enabled devices since it began keeping track
  • Device authorizations are up 15% for the first half of 2024 compared to the same period the year before (107 vs. 93)
  • The pace could grow even faster in late 2024 – in 2023, FDA in the second half authorized 126 devices, up 35% over the first half
  • At that pace, the FDA should hit just over 250 total authorizations in 2024 
  • This would represent 14% growth over 220 authorizations in 2023, and compares to growth of 14% in 2022 and 15% in 2021
  • As with past updates, radiology makes up the lion’s share of AI/ML authorizations, but had a 73% share in the first half, down from 80% for all of 2023
  • Siemens Healthineers led in all H1 2024 clearances with 11, bringing its total to 70 (66 for Siemens and four for Varian). GE HealthCare remains the leader with 80 total clearances after adding three in H1 2024 (GE’s total includes companies it has acquired, like Caption Health and MIM Software). There’s a big drop off after GE and Siemens, including Canon Medical (30), Aidoc (24), and Philips (24).

The FDA’s list includes both software-only algorithms as well as hardware devices like scanners that have built-in AI capabilities, such as a mobile X-ray unit that can alert users to emergent conditions. 

  • Indeed, many of the authorizations on the FDA’s list are for updated versions of already-cleared products rather than brand-new solutions – a trend that tends to inflate radiology’s share of approvals.

The Takeaway

The new FDA numbers on AI/ML regulatory authorizations are significant not only for revealing the growth in approvals, but also because the agency appears to be releasing the updates more frequently – perhaps a sign it is practicing what it preaches when it comes to AI openness and transparency. 

Better Prostate MRI with AI

Posted on by Brian Casey

A homegrown AI algorithm was able to detect clinically significant prostate cancer on MRI scans with the same accuracy as experienced radiologists. In a new study in Radiology, researchers say the algorithm could improve radiologists’ ability to detect prostate cancer on MRI, with fewer false positives.

In past issues of The Imaging Wire, we’ve discussed the need to improve on existing tools like PSA tests to make prostate cancer screening more precise with fewer false positives and less need for patient work-up.

  • Adding MRI to prostate screening protocols is a step forward, but MRI is an expensive technology that requires experienced radiologists to interpret.

Could AI help? In the new study, researchers tested a deep learning algorithm developed at the Mayo Clinic to detect clinically significant prostate cancer on multiparametric (mpMRI) scans.

  • In an interesting wrinkle, the Mayo algorithm does not indicate tumor location, so a second algorithm – called Grad-CAM – was employed to localize tumors.

The Mayo algorithm was trained on a population of 5k patients with a cancer prevalence similar to a screening population, then tested in an external test set of 204 patients, finding …

  • No statistically significant difference in performance between the Mayo algorithm and radiologists based on AUC (0.86 vs. 0.84, p=0.68)
  • The highest AUC was with the combination of AI and radiologists (0.89, p<0.001)
  • The Grad-CAM algorithm was accurate in localizing 56 of 58 true-positive exams

An editorial noted that the study employed the Mayo algorithm on multiparametric MRI exams.

  • Prostate cancer imaging is moving from mpMRI toward biparametric MRI (bpMRI) due to its faster scan times and lack of contrast, and if validated on bpMRI, AI’s impact could be even more dramatic.

The Takeaway
The current study illustrates the exciting developments underway to make prostate imaging more accurate and easier to perform. They also support the technology evolution that could one day make prostate cancer screening a more widely accepted test.

Next-Generation Brain PET

Posted on by Brian Casey

A new paper in JNM includes the first human images acquired with a next-generation dedicated brain PET/CT scanner that could create a new standard for neurological research. United Imaging’s NeuroEXPLORER scanner has sensitivity and spatial resolution “an order of magnitude” better than existing technology. 

In addition to its value as a clinical tool, PET has carved out a research role for investigating some of the most fundamental questions about brain function and pathology. 

  • Commercial whole-body scanners can be used for research, but dedicated brain systems like the High Resolution Research Tomograph (HRRT) offer even higher resolution for imaging tiny structures in the brain. 

NeuroEXPLORER was developed by a consortium that includes United Imaging, UC Davis, and Yale University to adapt for dedicated brain imaging the long-axis PET technology found in United’s uEXPLORER total-body PET/CT system. 

  • NeuroEXPLORER was a highlight at the recent SNMMI 2024 conference, and images acquired with the system won the show’s coveted Image of the Year honors.

In the new study, researchers go into more detail about NeuroEXPLORER’s specifications, which include … 

  • An extended axial field of view (FOV) of 49.5cm for higher sensitivity
  • Transverse spatial resolution ranging from 1.64-2.51mm at full-width half-maximum
  • Average time-of-flight resolution of 236 picoseconds
  • NEMA sensitivities of 46.0 and 47.6 kcps/MBq at center and 10cm offset, and absolute sensitivity of 11.8% at the center of the FOV

Such high sensitivity and spatial resolution enables tasks “previously considered difficult or impossible,” like imaging focal tracer uptake of small subcortical regions or low-density binding sites like cortical dopamine receptors. 

  • What’s more, NeuroEXPLORER’s long axial length enables high-quality imaging of the spinal cord and carotid arteries.

Now for the disclaimer: United Imaging notes that NeuroEXPLORER has not been submitted to the FDA for clearance and at present is only for research use; the company’s uEXPLORER scanner does have clearance and is in operation at several commercial sites. 

The Takeaway

Publication in a journal of the first human images from NeuroEXPLORER are an exciting development and underscore the potential of dedicated brain PET to advance research into neurological function and pathology. Whether the scanner develops into a clinical tool remains to be seen.

DBT Detects Earlier Cancers in Swedish Tomo Study

Posted on by Brian Casey

A new analysis of a landmark DBT study from Sweden offers more support for the effectiveness of tomosynthesis mammography screening. Published in Radiology, researchers found that DBT screening seems to detect earlier cancers, most likely before they become more aggressive. 

Most U.S. mammography practices have embraced DBT since its approval in 2011, such that 48% of all certified mammography units are DBT and 90% of all facilities have at least one tomosynthesis unit. 

  • But doubts about DBT have persisted, particularly by mammography skeptics who charge that the technology was adopted without conducting randomized controlled trials to prove its value. 

But apart from RCTs, there have been plenty of observational studies in which DBT showed a benefit, one of them being the Malmö Breast Tomosynthesis Screening Trial of almost 15k women in Sweden.

  • First results from MBTST were published in 2018 and showed that single-view DBT screening had a 34% higher cancer detection rate per 1k women than digital mammography (8.7 vs. 6.5), but with a higher recall rate as well (3.6% vs. 2.5%).

In the new study, researchers wanted to see if DBT’s screening benefits persisted over two subsequent screening rounds with conventional digital mammography. 

  • Their assumption was that the cancer detection rate would be lower in subsequent rounds, and there would be fewer slow-growing, less aggressive cancers – a sign of early cancer detection. 

Their analysis found …

  • The cancer detection rate per 1k women was lower in the first (4.6) and second (5.3) rounds compared to the original MBTST
  • Recall rate was 2.1% – also lower 
  • The odds ratio of cancer detection was lower than MBTST in the first (OR=0.46) and second (OR=0.53) follow-up rounds 
  • Invasive cancers were less prevalent in the first round compared to the second round (66% vs. 83%) 

What do the results mean? The implication is that because DBT detected cancers in the initial screening round, there was lower cancer prevalence and less aggressive cancer in follow-up rounds, an effect that wore off as time went on.

The Takeaway

There may never be a randomized controlled trial of DBT due to the ethical problem of denying a live-saving technology to women in a control group. But studies like the MBTST follow-up are important in adding to the body of evidence showing that DBT actually does work.

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!