Tag: radiology

Doubling Lung Screening Rates with Patient Outreach

Posted on by Brian Casey

Low CT lung cancer screening rates have disappointed medical imaging professionals and public health advocates alike since the test received USPSTF recommendation over 10 years ago. But a new study shows how one health system doubled its lung cancer screening rates – to levels approaching those of more established cancer screening exams. 

USPSTF recommended low-dose CT lung cancer screening in 2013, but 10 years later patient screening rates languished in the mid-teens, compared to rates of around 75% for breast and cervical cancer and above 72% for colorectal cancer. 

  • That means many lung cancer patients are showing up with late-stage disease, when it’s more difficult to cure. Perhaps as a result, lung cancer is expected to cause almost 125k deaths in the U.S. in 2025.

Breaking that cycle was the goal of researchers at the University of Rochester Medical Center in New York, who wrote about their experiences in a study published in NEJM Catalyst. 

  • They wanted to boost lung cancer screening adherence across their network of 42 locations in western New York. 

So how did they do it? Success came through a combination of IT innovation and old-fashioned legwork in patient outreach. Clinicians…

  • Provided evidence on lung cancer screening to primary care providers.
  • Updated their EHR software to identify patients eligible for lung screening based on the daily schedule to provide screening prompts during patient visits.
  • Created dashboards to guide outreach to patients due or overdue for screening exams.
  • Developed an extensive follow-up program with patient navigators to facilitate recall for annual exams.
  • Created a centralized pulmonary team to provide referrals for smoking cessation, conduct shared decision making for screening exams, and manage pulmonary nodules.

The program produced immediate results. In an analysis comparing screening rates in March 2022 to June 2025, researchers found…

  • Lung screening rates doubled (from 33% to 72%).
  • On-time completion of annual LDCT screening exceeded 94%.
  • 78% of lung cancer cases in 2023 and 2024 were diagnosed at an early stage.
  • There were no statistically significant differences in screening rates by patient race.

The Takeaway
The new results match up with recent findings – such as those presented at WCLC 2025 in September – underscoring the importance of reaching out to potential lung cancer screening candidates to bring them into the fold. Despite CT lung screening’s halting history, these studies show that it can be done.

AI First Drafts: A New Dawn for Radiology Reporting

Posted on by Partner Content

For radiologists – the medical detectives who find clues in our medical images – the daily grind can feel like a “death by a thousand cuts.” Much of their time is spent not on diagnosis, but on tedious reporting. 

Now, a new generation of artificial intelligence is stepping in to serve as a high-tech scribe, automating the drudgery.

  • This AI tackles reporting, the most time-consuming part of radiologists’ workflow.

AI-enabled radiology reporting makes transcribing data from technologist worksheets a thing of the past, using Optical Character Recognition (OCR) to decipher everything, even what looks like “chicken scratch handwriting.” Then…

  • A large language model (LLM) applies clinical context to ensure it understands the meaning.
  • It intelligently injects that data into the correct sections of the radiologist’s personal report template.
  • Finally, it performs its own “inference,” like calculating a TI-RADS score and dropping it right into the impression.

Modern AI also learns from a radiologist’s actions, providing a hands-free way to build a report, with features such as…

Smart Measurements: When a lesion is measured, the AI recognizes the location and automatically adds the data and comparisons to prior scans into the report.

Automated Prior Population: Instead of struggling with speech-to-text, the AI notices when a prior study is opened for comparison and automatically populates that exam’s date.

Streamlined Expert Findings: A radiologist can simply state positive findings, and the AI acts as both writer and editor. 

AI-enabled radiology reporting weaves dictated phrases into complete sentences, generates an impression based on clinical guidelines like BI-RADS, and serves as a vigilant proofreader, flagging errors like laterality mistakes or semantic impossibilities. 

As AI technology matures, the software itself is becoming easier to build. The true differentiator is the team behind it. 

  • For radiologists evaluating these new reporting tools, it’s critical to look for teams that are “AI native” – built from the ground up with AI at their core. 

Companies founded on these principles, such as New Lantern, are pioneering these all-in-one radiology reporting solutions, treating the challenge not as a problem to be fixed with another widget, but as an opportunity to build one complete, intelligent platform. 

The Takeaway 

The evolution in AI-enabled radiology reporting isn’t about replacing radiologists; it’s a tool to augment their skills. Radiologists who harness AI to create reports faster will significantly outpace those who do not, allowing them to return their full focus to the art of diagnosis.

Uneven Access to Brain MRI

Posted on by Brian Casey

Patients from disadvantaged neighborhoods or those traveling farther for brain MRI scans presented in worse clinical condition than patients with better access. That’s according to a new JACR study that reopens the debate over disparities in healthcare access. 

The past several years have seen numerous studies published that document disparities in healthcare access and their impact on clinical outcomes.

Many previous studies have also concentrated on access to care in rural areas, in which long distances make it harder for patients to travel to medical centers.

  • In the current study, researchers led by authors from Emory University flipped the script to examine care access in the Atlanta metropolitan area in an effort to quantify how distance and socioeconomic status might impact patient care. 

They examined the demographic backgrounds of 4.8k patients who got brain MRI scans over a one-year period starting in March 2019, calculating factors like distance from home to imaging facility and socioeconomic status based on the area deprivation index. 

  • They then correlated these data to patient illness severity – also known as acuity – when they presented for their scans, using a three-point scale ranging from normal (level 1) to findings requiring a change in patient management (level 3).

Based on the data, researchers found…

  • Patients in neighborhoods with lower socioeconomic status had 34% higher odds of level 2 acuity versus level 1 for inpatient scans and 27% higher for emergency scans. 
  • Patients living twice the distance from an imaging facility had 6.5% higher odds of level 2 acuity compared to level 1, and 15% higher for level 3.
  • Other factors affecting acuity level included age, race, and insurance status.
  • Medicaid recipients in particular were sicker, with 68% higher odds of acuity level 2 and 81% higher odds of acuity level 3 compared to those with commercial insurance. 

The findings track with other studies that have linked chronic health conditions with brain pathologies, such as the connection between diabetes and stroke. 

The Takeaway

The new findings offer additional details on how patient demographics affect both their health status and their access to care, in particular for advanced imaging scans like brain MRI. Follow-up studies could examine whether a similar phenomenon occurs with CT, which is the workhorse modality for emergency imaging. 

Reducing CT Radiation Dose System-Wide

Posted on by Brian Casey

CT radiation dose has been one of the top radiology headlines this year due to the publication of several studies linking radiation to cancer risk. But new research offers hope that CT radiation dose can be reduced, even across large healthcare systems. 

CT’s link to cancer risk has been controversial, but most established models connect low-level radiation to cancer formation.

There are lots of great technologies for reducing CT radiation dose, from photon-counting CT to adjusting scanner parameters like mA and kVp, while image reconstruction algorithms can upscale noisy low-dose images to look like higher-quality exams.

  • But the problem has always been getting these technologies into the hands of clinicians – and then making sure they use them, especially across large multi-center health systems, where dose can vary even within the same network.  

Taking a crack at the problem were cardiologists from Lee Health Heart Institute in Fort Myers, Florida, in a new paper in JACC: Case Reports. 

  • They specifically looked at radiation dose for coronary CT angiography exams, determining that based on the literature an optimal radiation dose for CCTA should be ≤ 4 mSv – lower than the system’s 6.2 mSv median dose. 

So they implemented several strategies for reducing CCTA dose…

  • Standardizing scanning protocols that emphasized prospective ECG gating, reduced field of view, BMI-tailored tube voltage (kVp), and elimination of redundant imaging phases.
  • Setting parameters for single-source CT at 100 kVp for patients with BMI <30 and 120 kVp for BMI ≥30, with prospective scanning for 60-80% of the cardiac cycle.
  • Using similar kVp settings for dual-source CT scanners, but implementing systolic imaging between 250-450 milliseconds.

How well did it work? After reviewing the program, researchers found…

  • System-wide radiation dose fell 23% (4.8 vs. 6.2 mSv).
  • Diagnostic quality improved as measured by the acceptance rate for FFR-CT exams (93% vs. 91%). 
  • Dose consistency was achieved across locations despite differences in scanner models and practices.

The Takeaway

The new study on CCTA radiation dose shows that dose can be reduced system-wide while maintaining – and even improving – diagnostic image quality. Is it a problem that the research was led by cardiologists and not radiologists? Not if you’re a patient. 

Perils of Missed Mammography

Posted on by Brian Casey

Yet another study is illustrating the perils of missing mammography screening. New research in JAMA Network Open found that women diagnosed with breast cancer who missed their previous screening exam had signs of delayed diagnosis and worse clinical outcomes. 

Mammography screening is generally credited – along with improved treatments – with a steady decline in breast cancer death rates since the start of population-based breast screening.

  • But most studies on mammography’s effectiveness tend to compare women who participated regularly in screening with those who never did. 

That’s not really a realistic comparison these days, as mammography’s relatively high compliance rate means that most women are getting screened at least some of the time.

  • But what happens if women miss a screening exam? In a BMJ study published last month, researchers found that women who missed their first screening exam had a 40% higher risk of breast cancer death.

In the current study, researchers took a slightly different tack, looking at 8.6k women in Sweden whose breast cancer was detected on screening exams starting in 2015. 

  • In all, 17% of women missed the screening exam immediately before their cancer diagnosis. 

Compared to women who attended all screening rounds, those who missed their previous exam had higher adjusted odds ratio for…

  • Larger tumors ≥ 20 mm (AOR = 1.55).
  • Lymph node involvement (AOR = 1.28).
  • Distant metastasis (AOR = 4.64).
  • Worse breast cancer-specific survival (AOR = 1.33).
  • Lower 20-year breast cancer-specific survival (86% vs. 89%). 

What’s more, the program’s cancer detection rate per 1k screenings was sharply higher in the second screening round for women who missed the first round (7.35 vs. 5.59). 

  • This is most likely a sign that cancers that could have been detected in the first round instead were detected in the second round – another sign of delayed diagnosis.

Women who had missed their previous screening tended to be younger, unemployed, unmarried, and born outside of Sweden, and also had lower income. 

  • Women with these characteristics could be targeted for more intensive outreach, such as shorter invitation intervals or outreach after a missed appointment. 

The Takeaway

The new study once again highlights the importance of regular mammography screening in detecting breast cancer. Even one missed exam can have serious clinical consequences – highlighting the importance of identifying and contacting women who might be more prone to missed appointments.

Emergency CT Use Booms

Posted on by Brian Casey

Increased use of CT drove a boom in medical imaging utilization in the emergency department setting over the past 10 years. That’s according to a new study in Radiology that comes amid increased scrutiny over the long-term health effects of CT radiation. 

CT is tailor-made for evaluating patients in the emergency setting. It’s fast, relatively inexpensive, and provides high-quality images that can deliver a diagnosis quickly.

  • For these reasons, emergency departments have been quick to install workhorse CT scanners running at all hours in the hope that faster diagnoses will lead to better patient outcomes. 

But there are also downsides to the growth in CT utilization. It can put strains on radiology departments to read all the new scans – a particular challenge in an era of workforce shortages.

  • Concerns about the link between CT radiation dose and cancer also persist. Two controversial studies were published this year on the subject, one linking CT to future cancers across the U.S. population and the other specifically to pediatric blood cancer. 

The new study offers a useful benchmark for tracking CT’s growth in the ED. Researchers chronicled changes in U.S. emergency imaging use in Medicare from 2013 to 2023, finding that per 100 Medicare beneficiaries…

  • CT use grew 96% (37 vs. 19 encounters).
  • While ultrasound only grew 20% (2.8 vs. 2.3 encounters).
  • And radiography use remained flat at 37 encounters in both years.

In addition, the number of overall ED encounters actually declined 16% (55 vs. 65 encounters), showing that imaging’s growth was due to more imaging per ED encounter rather than overall increased ED visits by beneficiaries. 

  • On a per-encounter basis, CT use grew 134% over the study period compared to 43% for ultrasound and 19% for radiography. 

Researchers believe that the difference in modality growth rates could be due to the use of CT to accelerate patient turnover in the ED.

  • Meanwhile, ultrasound use may have grown more modestly due to the proliferation of point-of-care handheld scanners among non-radiologists.

The Takeaway

The new findings underscore the conundrum behind emergency CT – it’s an incredibly powerful technology that nevertheless requires restraint in order to be used judiciously. Let’s hope emergency physicians take note.

Does BMI Affect AI Accuracy?

Posted on by Brian Casey

High body mass index is known to create problems for various medical imaging modalities, from CT to ultrasound. Could it also affect the accuracy of artificial intelligence algorithms? Researchers asked this question as it pertains to lung nodule detection in a new study in European Journal of Radiology. 

X-ray photons attenuate as they pass through body tissue, which can decrease image quality and produce more noise.

  • This is particularly a challenge for CT exams that don’t use a lot of radiation, like low-dose CT lung screening. 

At the same time, AI algorithms are being developed to make LDCT screening more efficient, such as by identifying and classifying lung nodules.

  • But if high BMI makes CT images noisier, will that affect AI’s performance? Researchers from the Netherlands tested the idea in 352 patients who got LDCT screening as part of the Lifelines study.

Researchers compared patients at both the high end of the BMI spectrum (mean 39.8) and low end (mean 18.7). 

  • Lung nodule detection by both Siemens Healthineers’ AI-Rad Companion Chest CT algorithm and a human radiologist was performed and compared. 

Across the study population, researchers found…

  • There was no statistically significant difference in AI’s sensitivity between high and low BMI groups (0.75 vs. 0.80, p = 0.37). 
  • Nor was there any difference in the human radiologist’s sensitivity (0.76 vs. 0.84, p = 0.17).
  • AI had fewer false positives per scan in the high BMI group than low BMI (0.30 vs. 0.55), a difference that was statistically significant (p = 0.05). 
  • While the difference in false positives with the human radiologist was not statistically significant (0.05 vs. 0.16, p = 0.09).

The study authors attributed AI’s lower performance to more noise in the high BMI scans.

  • They recommended that AI developers include people with both high and low BMI in datasets used for training algorithms.

The Takeaway

The results offer some comfort that patient BMI probably doesn’t have a huge effect on AI performance for nodule detection in lung screening, but it suggests a possible effect that might have achieved statistical significance with a larger sample size. More study in the area is definitely needed given the rising importance of AI for CT lung cancer screening. 

Missing Breast Screening Boosts Death Risk

Posted on by Brian Casey

Missing a first breast cancer screening exam can be hazardous to your health. A new study in BMJ found that women who missed their first mammography screening had a 40% higher long-term risk of breast cancer death. 

Mammography screening has been shown to prevent breast cancer deaths by detecting cancer earlier, when it can be treated more effectively.

  • But breast screening adherence rates still aren’t as high as they should be, leaving women’s health advocates to wonder what they can do to spur better compliance.

In the new study, researchers investigated whether mammography compliance itself could be an early warning sign that women might not be taking screening seriously enough.

  • They analyzed data on 433k women invited to the Swedish Mammography Screening Programme from 1991 to 2020 and correlated clinical outcomes over 25 years with whether or not patients completed their first screening exam (32% didn’t).

Compared to women who missed their first mammography appointment, women who followed through with their exam…

  • Had a 40% lower risk of dying from breast cancer. 
  • Had lower breast cancer mortality rates per 1k women (7 vs. 9.9). 
  • Got nearly twice as many breast screenings over the study period (8.7 vs. 4.8 screenings).
  • Had similar breast cancer incidence rates (7.8% vs. 7.6%), a sign that non-participation delayed detection rather than increased incidence. 

What’s more, women who missed their first appointment were 32% more likely to have invasive cancer and had higher odds ratios for stage III and stage IV disease (OR = 1.53 and 3.61, respectively). 

Researchers concluded that women who missed their first mammography appointment were also more likely to miss future ones – putting them at higher risk of breast cancer death.

  • But a missed initial appointment also could serve as a warning to women’s health centers that these patients deserve extra attention, through tools as simple as more provider outreach or automatically scheduled second appointments. 

The Takeaway

The new findings offer – yet again – more support for the effectiveness of population-based breast screening in reducing breast cancer deaths. What’s novel is that they show that non-participation is an early warning sign that could activate a slate of more aggressive outreach measures to bring these women in. 

Could States Take Over AI Regulation from the FDA?

Posted on by Brian Casey

Could states take over AI regulation from the FDA as a possible solution to the growing workforce shortage in radiology? It may seem like a wild idea at first, but it’s a question proposed in a special edition of Academic Radiology focusing on radiology and the law. 

Healthcare’s workforce shortage is no secret, and in radiology it’s manifested itself with tight supplies of both radiologists and radiologic technologists. 

  • AI has been touted as a potential solution to lighten the workload, such as by triaging images mostly likely to be normal from requiring immediate radiologist review. 

And autonomous AI – algorithms that operate without human oversight – are already nibbling at radiology’s fringes, with at least one company claiming its solution can produce full radiology reports without human intervention.

  • But the FDA is notoriously conservative when it comes to authorizing new technologies, and AI is no exception. So what’s to stop a state facing a severe radiologist shortage from adopting autonomous AI on its own to help out? 

The new article reviews the legal landscape behind both constitutional and state law, finding examples in which some states have successfully defied federal regulation – such as by legalizing marijuana use – if the issue has broad public support. 

But the authors eventually answer their own question in the negative, stating that it’s not likely states will usurp the FDA’s role regulating AI because…

  • The U.S. Constitution’s Supremacy and Commerce clauses ensure federal law will always supersede state law.
  • If AI made an error, malpractice regulation would be murky given a lack of legal precedent at the state level. 
  • Teleradiologists could opt out of providing care to a state if AI regulations were too burdensome – which could exacerbate the workforce crisis. 

The Takeaway

Ultimately, it’s not likely states will take over AI regulation from the FDA, even if the healthcare workforce shortage worsens significantly. But the Academic Radiology article is an interesting thought experiment that – in an environment in which U.S. healthcare policies have already been turned upside down – may not be so unthinkable after all. 

AI Spots Lung Nodules

Posted on by Brian Casey

A new study in Radiology on an AI algorithm for analyzing lung nodules on CT lung cancer screening exams shows that radiologists may be able to have their cake and eat it too: better identification of malignant nodules with lower false-positive rates. 

The rising utilization of low-dose CT screening is great news for clinicians (and eligible patients), but managing suspicious nodules remains a major challenge, as false-positive findings expose patients to unnecessary biopsies and costs.

  • False-positive rates have come down somewhat from the high rates seen in the big lung cancer screening clinical trials like NLST and NELSON, but there is still room for improvement.

Dutch researchers applied AI to the problem, developing a deep learning algorithm trained on 16.1k NLST nodules that produces a score from 0% to 100% based on a nodule’s likelihood of malignancy. 

  • They then tested the algorithm with baseline screening rounds of 4.1k patients from three datasets drawn from different lung cancer screening trials: NELSON, DLSCT in Denmark, and MILD in Italy.

The algorithm’s performance was compared to the Pan-Canadian Early Detection of Lung Cancer model, a widely used clinical guideline that uses patient characteristics like age and family history and nodule characteristics size and location to estimate risk.

Compared to PanCan, the deep learning algorithm…

  • Reduced false-positive findings sharply by classifying more benign cases as low risk (68% vs. 47%) when set at 100% sensitivity for cancers diagnosed within one year.
  • For all nodules, achieved comparable AUCs at one year (0.98 vs. 0.98), two years (0.96 vs. 0.94), and throughout screening (0.94 vs. 0.93).
  • For indeterminate nodules 5-15 mm, significantly outperformed PanCan at one year (0.95 vs. 0.91), two years (0.94 vs. 0.88), and throughout screening (0.91 vs. 0.86).

The model’s performance for indeterminate nodules is particularly intriguing, as these are challenging to manage due to their small size and can lead to unnecessary follow-up procedures.

The Takeaway

Using AI to differentiate malignant from benign nodules promises to make CT lung cancer screening more accurate and easier to perform than manual nodule classification methods – and should add to the exam’s growing momentum.

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

Like the website? You'll love the newsletter

Completely free. Every Monday and Thursday