Category: CT Scanners

AI Detects Incidental PE

Posted on by Brian Casey

In one of the most famous quotes about radiology and artificial intelligence, Curtis Langlotz, MD, PhD, once said that AI will not replace radiologists, but radiologists with AI will replace those without it. A new study in AJR illustrates his point, showing that radiologists using a commercially available AI algorithm had higher rates of detecting incidental pulmonary embolism on CT scans. 

AI is being applied to many clinical use cases in radiology, but one of the more promising is for detecting and triaging emergent conditions that might have escaped the radiologist’s attention on initial interpretations.

  • Pulmonary embolism is one such condition. PE can be life-threatening and occurs in 1.3-2.6% of routine contrast-enhanced CT exams, but radiologist miss rates range from 10-75% depending on patient population.

AI can help by automatically analyzing CT scans and alerting radiologists to PEs when they can be treated quickly; the FDA has authorized several algorithms for this clinical use. 

  • In the new paper, researchers conducted a prospective real-world study of Aidoc’s BriefCase for iPE Triage at the University of Alabama at Birmingham. 

Researchers tracked rates of PE detection in 4.3k patients before and after AI implementation in 2021, finding … 

  • Radiologists saw their sensitivity for PE detection go up after AI implementation (80% vs. 96%) 
  • Specificity was unchanged (99.1% vs. 99.9%, p=0.58)
  • The PE incidence rate went up (1.4% vs. 1.6%)
  • There was no statistically significant difference in report turnaround time before and after AI (65 vs. 78 minutes, p=0.26)

The study echoes findings from 2023, when researchers from UT Southwestern also used the Aidoc algorithm for PE detection, in that case finding that AI cut times for report turnaround and patient waits. 

The Takeaway

While studies showing AI’s value to radiologists are commonplace, many of them are performed under controlled conditions that don’t translate to the real world. The current study is significant because it shows that with AI, radiologists can achieve near-perfect detection of a potentially life-threatening condition without a negative impact on workflow.

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.

AI of Cardiac CT Predicts Risk

Posted on by Brian Casey

In a landmark study of 40k patients from the UK published in The Lancet, an AI-derived score that analyzed coronary arterial inflammation on coronary CT angiography scans was effective in predicting future cardiac risk in people regardless of whether they had obstructive coronary artery disease.

CCTA’s power for predicting heart problems has been demonstrated in multiple studies, and it’s now considered a first-line test for individuals with chest pain. 

  • But the situation is trickier in those without obstructive disease – prompting researchers to ask whether CCTA’s ability to visualize subtle changes in cardiac structure and function could be leveraged – such as with AI – to deliver even more prognostic power. 

The Oxford Risk Factors And Noninvasive imaging (ORFAN) study in the UK is addressing that question by conducting CCTA scans in 40k patients as part of routine clinical care at eight hospitals. 

  • Researchers analyzed outcomes in the entire ORFAN population of 40k patients, then followed a subset of 3.4k higher-risk patients for 7.7 years to study the value of a perivascular fat attenuation index (FAI) score. 

FAI scores measure heart inflammation in coronary arteries and are calculated using Caristo Diagnostics’ CaRi-Heart AI software.

  • The scores are combined with other traditional risk factors to create an AI-Risk classification that predicts the likelihood of an adverse event.  

Researchers found that … 

  • Across the entire 40k cohort, patients without obstructive CAD accounted for 64% of cardiac deaths and 66% of MACE – twice as many as those with obstructive CAD
  • In the smaller higher-risk cohort, patients with an elevated FAI score in all three coronary arteries had a higher risk of cardiac mortality (HR=29.8) or MACE (HR=12.6)
  • Elevated FAI scores in any coronary artery also predicted cardiac mortality
  • AI-Risk scores were associated with cardiac mortality (HR=6.75) and MACE (HR=4.68) when comparing very-high-risk versus low- or medium-risk patients 

The first data point is worth noting, as it illustrates the need to improve risk stratification and management in people without obstructive CAD.

The Takeaway
The ORFAN results are an exciting development for cardiac CT AI (in addition to being a major coup for Caristo, which raised $16.3M last year to commercialize CaRi-Heart globally). Measurements of coronary inflammation could give clinicians another tool – in addition to plaque measurements and calcium scoring – to predict cardiac events.

Lung Screening Narrows Disparities

Posted on by Brian Casey

New research confirms that not only does low-dose CT screening reduce lung cancer mortality, it can also narrow health disparities. Researchers found that screening’s beneficial impact was greater at lower socioeconomic levels in a new study published in Lancet Regional Health – Europe.

As we mentioned in our last issue, CT lung cancer screening is gaining momentum globally; at the same time, researchers have documented greater mortality and morbidity for a variety of diseases among racial minorities and at lower socioeconomic levels.

  • This difference can be especially profound when it comes to lung disease, given higher smoking rates among some minority groups and economically disadvantaged populations.

In the original UK Lung Cancer Screening Trial (UKLS) in 2021, researchers found that a single CT screening round produced a 16% lung cancer mortality reduction. 

  • The new study is a secondary analysis of UKLS to investigate whether CT lung screening’s impact differed by socioeconomic status, which is important given that smoking occurs in England at higher rates in the most deprived neighborhoods compared to wealthier ones (24% vs. 6.8%).

UKLS researchers compared lung cancer mortality rates in 4k individuals in different groups classified by a widely used socioeconomic barometer. They found that … 

  • CT lung screening had the same lung cancer mortality benefit in both low and high socioeconomic groups (-19% vs. -20%)
  • But there was a bigger reduction in death from COPD in lower socioeconomic groups (-34% vs. +4%)
  • And fewer deaths from other lung diseases (-32% vs. +10%)
  • While cardiovascular mortality was also lower (-30% vs. -13%)
  • All-cause mortality was lower in lower socioeconomic groups – a benefit not seen at higher levels

Lung screening’s reduction in all-cause mortality is particularly intriguing, as this is an accomplishment that has eluded most other cancer screening tests – a point that has been repeatedly hammered home by screening skeptics.

The Takeaway

The new findings highlight how – to a greater degree than other major cancer screening tests – CT lung screening has the potential to address ongoing racial and socioeconomic healthcare disparities. It’s yet another reason to press for broader adoption of lung screening.

CT Lung Screening Shows Progress at ATS 2024

Posted on by Brian Casey

Making CT lung cancer screening more effective has been a hot topic at the American Thoracic Society meeting, which convened this weekend in San Diego. Presentations at ATS 2024 have ranged from improving screening compliance rates to eliminating racial disparities in screening attendance.

After years of fits and starts, low-dose CT lung cancer screening appears to be finally making progress. 

  • While the US still struggles with overly restrictive screening criteria and convoluted reimbursement rules, the rest of the world – including Australia, Germany, and Taiwan – is moving ahead with population-based screening programs designed to counter the tobacco epidemic’s deadly scourge.

At ATS 2024, investigators are presenting research to ensure that the benefits of CT lung cancer screening are delivered to those who need it, with the following highlights …

  • Researchers at the University of Minnesota saw a 7.2% completion rate for screening-specific low-dose CT among 91k eligible individuals – an indication of “overall poor uptake of screening” 
  • To improve uptake, another group implemented a centralized nurse coordinator for lung screening, resulting in a 23-day reduction in time from initial consultation to report delivery as well as better adherence to eligibility criteria
  • Patients who self-identify as Black are more likely to miss a scheduled CT screening appointment (OR=2.05), while Hispanic patients also have high miss rates (OR=1.92) as do those with limited English proficiency (OR=1.72). The numbers highlight the need for patient conversations to boost completion rates
  • Incidence rates of lung and bronchus cancer dropped from 2007-2019 compared to 1999-2006, underscoring the importance of smoking cessation and supporting current USPSTF age criteria for lung screening
  • Pulmonary physicians significantly overestimated their patients’ lung screening completion rates, with almost half thinking the rate was higher than 60% when it was actually 17%. Researchers suggested interventions for improving completion rates

The Takeaway

The fact that ATS 2024 has seen so many presentations on CT lung cancer screening – the vast majority presented by US authors – indicates that low screening rates haven’t discouraged American researchers and clinicians. The presentations underscore the progress being made toward making the benefits of lung screening available to Americans who would benefit from it.

Slashing CT Radiation Dose

Posted on by Brian Casey

Cutting CT radiation dose should be the goal of every medical imaging facility. A new paper in European Radiology offers a promising technique that slashed CT dose to one-tenth of conventional CT – and just twice that of a standard chest X-ray.

CT’s wide availability, excellent image quality, and relatively low cost make it an invaluable modality for many clinical applications.

  • CT proved particularly useful during the COVID-19 pandemic for diagnosing lung pathology caused by the virus, and it continues to be used to track cases of long COVID.

But patient monitoring can involve multiple CT scans, leading to cumulative radiation exposure that can be concerning, especially for younger people.

  • Researchers in Austria wanted to see if they could use commercially available tools to produce ultra-low-dose CT scans, and then assess how they compared to conventional CT for tracking patients with long COVID.

Using Siemens Healthineers’ Somatom Drive third-generation dual-source CT scanner, they adjusted the parameters on the system’s CAREDose automated exposure control and ADMIRE iterative reconstruction to drive down dose as much as possible.

  • Other ultra-low-dose CT settings versus conventional CT included fixed tube voltage (100 kVp vs. 110 kVp), tin filtration (enabled vs. disabled), and CAREDose tube current modulation (enabled – weak vs. enabled – normal). 

They then tested the settings in a group of 153 patients with long COVID seen from 2020 to 2021; both ultra-low-dose and conventional CT scans were compared by radiologists, finding … 

  • Mean entrance-dose radiation levels with ultra-low-dose CT were less than one-tenth those of conventional CT in (0.21 mSv vs. 2.24 mSv); a two-view chest X-ray is 0.1 mSv
  • Image quality was rated 40% lower on a five-point scale (3.0 vs. 5.0)
  • But all ultra-low-dose scans were rated as diagnostic quality
  • Intra-reader agreement between the two techniques was “excellent,” at 93%

The findings led the researchers to conclude that ultra-low-dose CT could be a good option for tracking long COVID, such as in younger patients. 

The Takeaway

The study demonstrates that CT radiation dose can be driven down dramatically through existing commercially available tools. While this study covers just one niche clinical application, such tools could be applied to a wider range of uses, ensuring that the benefits of CT will continue to be made available at lower radiation doses than ever.

Predicting Patient Follow-Up for Imaging Exams

Posted on by Brian Casey

There’s nothing more frustrating than patients who don’t comply with follow-up imaging recommendations. But a new study in JACR not only identifies the factors that can lead to patient non-compliance, it also points the way toward IT tools that could predict who will fall short – and help direct targeted outreach efforts.

The new study focuses specifically on incidental pulmonary nodules, a particularly thorny problem in radiology, especially as CT lung cancer screening ramps up around the world.

  • Prevalence of these nodules can range from 24-51% based on different populations, and while most are benign, a missed nodule could develop into a late-stage lung cancer with poor patient survival. 

Researchers from the University of Pennsylvania wanted to test a set of 13 clinical and socioeconomic factors that could predict lack of follow-up in a group of 1.6k patients who got CT scans from 2016 to 2019. 

  • Next, they evaluated how well these factors worked when fed into several different types of homegrown machine learning models – precursors of a tool that could be implemented clinically – finding …
  • Clinical setting had the strongest association in predicting non-adherence, with patients seen in the inpatient or emergency setting far more likely skip follow-up compared to outpatients (OR=7.3 and 8.6)
  • Patients on Medicaid were more likely to skip follow-up compared to those on Medicare (OR=2)
  • On the other hand, patients with high-risk nodules were less likely to skip follow-up compared to those at low risk (OR=0.25) 
  • Comorbidity was the only one of the 13 factors that was not predictive of follow-up 

The authors hypothesized that the strong association between clinical setting and follow-up was due to the different socio-demographic characteristics of patients typically seen in each environment. 

  • Patients in the outpatient setting often have access to more resources like health insurance, transportation, and health literacy, while those without such resources often have to resort to the emergency department or hospital wards when they become sick enough to require care.

In the next step of the study, the data were fed into four types of machine learning algorithms; all turned in good performance for predicting follow-up adherence, with AUCs ranging from 0.76-0.80. 

The Takeaway

It’s not hard to see the findings from this study ultimately making their way into clinical use as part of some sort of commercial machine-learning algorithm that helps clinicians manage incidental findings. Stay tuned.

AI Powers Two-for-One Screening

Posted on by Brian Casey

In our last issue, we described how effective coronary artery calcium scoring is in predicting future major adverse cardiovascular events. This week, we’re highlighting new research in AJR showing how – thanks to AI – CAC scoring can be performed on CT lung cancer screening exams, giving radiologists a two-for-one screening test.

Using data from one screening exam to also look for other diseases – known as opportunistic screening – has become a hot topic as a way to make screening even more clinically and economically effective. 

In the new study, South Korean researchers leveraged the country’s CT lung cancer screening program to also screen for CAC, a known marker for future cardiac events. 

  • They took two commercially available CAC scoring algorithms – Coreline Soft’s Aview CAC and Siemens Healthineers’ syngo Calcium Scoring – to analyze 1k low-dose CT chest images acquired from 2017-2023 as part of the national lung screening program. 

AI results were compared to radiologists’ interpretations of CAC presence and severity, finding … 

  • Substantial agreement between both the AI algorithms and the interpreting radiologists for CAC presence and severity (kappa=0.793 & 0.671)
  • The AI algorithms judged CAC to be more prevalent than radiologists (57-60% vs. 53%)
  • AI was more likely to judge CAC severity as mild (35-40% vs. 28%)
  • But less likely to grade it as severe (6.2%-7.3%  vs. 15%)
  • MACE incidence varied by CAC severity: no CAC (1.1-1.3%), mild (3-5%), moderate (2.9-7.9%), and severe (8.6-11%)

The researchers noted that, as with other studies, MACE incidence increased with CAC severity, underlining the importance of coronary calcium evaluation and supporting the use of CT lung screening for CAC detection. 

The Takeaway

Studies like this highlight the exciting role AI can play in making opportunistic screening a reality. With AI at their side, radiologists will be able to play an even more important role in catching disease early, when it can be treated most effectively.

CT First for Chest Pain

Posted on by Brian Casey

CT should be used first to evaluate patients with stable chest pain who are suspected of having a heart attack. That’s the message of a paper being presented this week at the American College of Cardiology Cardiovascular Summit in Washington, DC.

CT is proving itself useful for a variety of applications in cardiac imaging, from predicting heart disease risk through coronary calcium scores to assessing whether people with chest pain need treatment like invasive angiography – or can be sent home and monitored.

  • But cardiac CT often runs up against decades of clinical practice that relies on tools like stress testing or diagnostic invasive coronary angiography for evaluating patients, with the CT-first strategy reserved for a limited number of people, such as those with unestablished coronary artery disease. 

But the new study suggests that the CT-first approach could be used for the vast majority of patients presenting with stable chest pain. 

  • A research team led by senior author Markus Scherer, MD, of Atrium Health-Sanger Heart & Vascular Institute in Charlotte, North Carolina tested the strategy in 786 patients seen from October 2022 to June 2023 who had no prior diagnosis of coronary artery disease and underwent elective invasive angiography to evaluate suspected angina.

The CT-first strategy compared CT angiography with provisional FFRCT testing to traditional evaluation pathways, which included stress echo, stress myocardial perfusion imaging, stress MRI, or no invasive testing before direct referral to angiography. Revascularization rates by strategy were as follows … 

  • 62% for CT-first
  • 50% for stress MRI
  • 40% for stress echo
  • 34% for no prior test
  • 31% for stress MPI

The Takeaway

The results presented this week offer real-world evidence that support recent clinical studies backing broader use of CT for patients with chest pain. Given CT’s advantages in terms of cost and noninvasiveness, the findings raise the question of whether more can be done to get clinicians to adhere to established guidelines calling for a CT-first protocol. 

CT Lung Screening’s Downstream Costs

Posted on by Brian Casey

The growing momentum of CT lung cancer screening was a major radiology news story in 2023. And while things are looking up as 2024 begins, there are still important issues to be sorted out for CT lung screening to achieve the same level of acceptance as other major cancer screening tests. 

A new study called PROSPR in Annals of Internal Medicine highlights some of these challenges. 

  • Researchers found a higher rate of invasive procedures and complications after CT screening compared to the National Lung Screening Trial, the landmark study that showed that low-dose CT screening reduces lung cancer mortality by 20%. 

The PROSPR researchers studied 9.3k individuals who got baseline LDCT lung screening scans from 2014 to 2018 across five US healthcare systems, finding: 

  • Abnormalities on baseline CT scans for 1.5k individuals (16%)
  • Of these, 9.5% were diagnosed with lung cancer within 12 months 
  • A 32% rate of downstream imaging of screened individuals 
  • A 2.8% rate of invasive procedures such as needle biopsy and bronchoscopy 
  • In those who got invasive procedures, rates were higher than NLST for all complications (31% vs. 18%) and for major complications (21% vs. 9.4%)

What gives with the higher complication rates? 

  • One explanation is that the PROSPR population was older and sicker than in NLST, with more individuals 65 and over (52% vs. 27%) and higher rates of current smoking (55% vs. 48%) and COPD (35% vs. 18%). 

Another reason could be that PROSPR’s population was more racially diverse, with fewer Whites than NLST (73% vs. 91%) and with a higher proportion of women (47% vs. 41%) – a sign of healthcare disparities. 

The PROSPR authors acknowledged that their findings could shift the debate over the benefits and harms of CT lung cancer screening in community practice – a debate that has raged in breast screening for decades.

The Takeaway

The PROSPR findings are something of a wake-up call amid the growing enthusiasm worldwide for CT lung cancer screening. It’s no surprise that real-world results will differ from the highly controlled environment of a clinical study like NLST, but lung screening proponents will need to be prepared with a plan for managing downstream findings and a response to screening skeptics who would use results like PROSPR to question whether lung screening should be performed at all.

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!