Tag: medical imaging

How Vendors Sell AI

Posted on by Brian Casey

Better patient care is the main selling point used by AI vendors when marketing neuroimaging algorithms, followed closely by time savings. Farther down the list of benefits are lower costs and increased revenue for providers. 

So says a new analysis in JACR that takes a close look at how FDA-cleared neuroimaging AI algorithms are marketed by vendors. It also includes several warning signs for both AI developers and clinicians.

AI is the most exciting technology to arrive in healthcare in decades, but questions percolate on whether AI developers are overhyping the technology. In the new analysis, researchers focused on marketing claims made for 59 AI neuroimaging algorithms cleared by the FDA from 2008 to 2022. Researchers analyzed FDA summaries and vendor websites, finding:

  • For 69% of algorithms, vendors highlighted an improvement in quality of patient care, while time savings for clinicians were touted for 44%. Only 16% of algorithms were promoted as lowering costs, while just 11% were positioned as increasing revenue
  • 50% of cleared neuroimaging algorithms were related to detection or quantification of stroke; of these, 41% were for intracranial hemorrhage, 31% for stroke brain perfusion, and 24% for detection of large vessel occlusion 
  • 41% of the algorithms were intended for use with non-contrast CT scans, 36% with MRI, 15% with CT perfusion, 14% with CT angiography, and the rest with MR perfusion and PET
  • 90% of the algorithms studied were cleared in the last five years, and 42% since last year

The researchers further noted two caveats in AI marketing: 

  • There is a lack of publicly available data to support vendor claims about the value of their algorithms. Better transparency is needed to create trust and clinician engagement.
  • The single-use-case nature of many AI algorithms raises questions about their economic viability. Many different algorithms would have to be implemented at a facility to ensure “a reasonable breadth of triage” for critical findings, and the financial burden of such integration is unclear.

The Takeaway

The new study offers intriguing insights into how AI algorithms are marketed by vendors, and how these efforts could be perceived by clinicians. The researchers note that financial pressure on AI developers may cause them to make “unintentional exaggerated claims” to recoup the cost of development; it is incumbent upon vendors to scrutinize their marketing activities to avoid overhyping AI technology.

Grading AI Report Quality

Posted on by Brian Casey

One of the most exciting new use cases for medical AI is in generating radiology reports. But how can you tell whether the quality of a report generated by an AI algorithm is comparable to that of a radiologist?

In a new study in Patterns, researchers propose a technical framework for automatically grading the output of AI-generated radiology reports, with the ultimate goal of producing AI-generated reports that are indistinguishable from those of radiologists. 

Most radiology AI applications so far have focused on developing algorithms to identify individual pathologies on imaging exams. 

  • While this is useful, helping radiologists streamline the production of their main output – the radiology report – could have a far greater impact on their productivity and efficiency. 

But existing tools for measuring the quality of AI-generated narrative reports are limited and don’t match up well with radiologists’ evaluations. 

  • To improve that situation, the researchers applied several existing automated metrics for analyzing report quality and compared them to the scores of radiologists, seeking to better understand AI’s weaknesses. 

Not surprisingly, the automated metrics fell short in several ways, including false prediction of findings, omitting findings, and incorrectly locating and predicting the severity of findings. 

  • These shortcomings point out the need for better scoring systems for gauging AI performance. 

The researchers therefore proposed a new metric for grading AI-generated report quality, called RadGraph F1, and a new methodology, RadCliQ, to predict how well an AI report would measure up to radiologist scrutiny. 

  • RadGraph F1 and RadCliQ could be used in future research on AI-generated radiology reports, and to that end the researchers have made the code for both metrics available as open source.

Ultimately, the researchers see the construction of generalist medical AI models that could perform multiple complex tasks, such as conversing with radiologists and physicians about medical images. 

  • Another use case could be applications that are able to explain imaging findings to patients in everyday language. 

The Takeaway

It’s a complex and detailed paper, but the new study is important because it outlines the metrics that can be used to teach machines how to generate better radiology reports. Given the imperative to improve radiologist productivity in the face of rising imaging volume and workforce shortages, this could be one more step on the quest for the Holy Grail of AI in radiology.

Breast Ultrasound Gets Wearable

Posted on by Brian Casey

Wearable devices are all the rage in personal fitness – could wearable breast ultrasound be next? MIT researchers have developed a patch-sized wearable breast ultrasound device that’s small enough to be incorporated into a bra for early cancer detection. They described their work in a new paper in Science Advances.

This isn’t the first use of wearable ultrasound. In fact, earlier this year UCSD researchers revealed their work on a wearable cardiac ultrasound device that obtains real-time data on cardiac function. 

The MIT team’s concept expands the idea into cancer detection. They took advantage of previous work on conformable piezoelectric ultrasound transducer materials to develop cUSBr-Patch, a one-dimensional phased-array probe integrated into a honeycomb-shaped patch that can be inserted into a soft fabric bra. 

The array covers the entire breast surface and can acquire images from multiple angles and views using 64 elements at a 7MHz frequency. The honeycomb design means that the array can be rotated and moved into different imaging positions, and the bra can even be reversed to acquire images from the other breast. 

The researchers tested cUSBr-Patch on phantoms and a human subject, and compared it to a conventional ultrasound scanner. They found that cUSBr-Patch:

  • Had a field of view up to 100mm wide and an imaging depth up to 80mm
  • Achieved resolution comparable to conventional ultrasound
  • Detected cysts as small as 30mm in the human volunteer, a 71-year-old woman with a history of breast cysts
  • The same cysts were detected with the array in different positions, an important capability for long-term monitoring

The MIT researchers believe that wearable breast ultrasound could detect early-stage breast cancer, in cases such as high-risk people in between routine screening mammograms. 

The researchers ultimately hope to develop a version of the device that’s about the size of a smartphone (right now the array has to be hooked up to a conventional ultrasound scanner to view images). They also want to investigate the use of AI to analyze images.

The Takeaway

It’s still early days for wearable breast ultrasound, but the new results are an exciting development that hints of future advances to come. Wearable breast ultrasound could even have an advantage over other wearable use cases like cardiac monitoring, as it doesn’t require continuous imaging during the user’s activities. Stay tuned.

Does ‘Automation Neglect’ Limit AI’s Impact?

Posted on by Brian Casey

Radiologists ignored AI suggestions in a new study because of “automation neglect,” a phenomenon in which humans are less likely to trust algorithmic recommendations. The findings raise questions about whether AI really should be used as a collaborative tool by radiologists. 

How radiologists use AI predictions has become a growing area of research as AI moves into the clinical realm. Most use cases see radiologists employing AI in a collaborative role as a decision-making aid when reviewing cases. 

But is that really the best way to use AI? In a paper published by the National Bureau of Economic Research, researchers from Harvard Medical School and MIT explored the effectiveness of radiologist performance when assisted by AI, in particular its impact on diagnostic quality.

They ran an experiment in which they manipulated radiologist access to predictions from the CheXpert AI algorithm for 324 chest X-ray cases, and then analyzed the results. They also assessed radiologist performance with and without clinical context. The 180 radiologists participating in the study were recruited from US teleradiology firms, as well as from a health network in Vietnam. 

It was expected that AI would boost radiologist performance, but instead accuracy remained unchanged:

  • AI predictions were more accurate than two-thirds of the radiologists
  • Yet, AI assistance failed to improve the radiologists’ diagnostic accuracy, as readers underweighted AI findings by 30% compared to their own assessments
  • Radiologists took 4% longer to interpret cases when either AI or clinical context were added
  • Adding clinical context to cases had a bigger impact on radiologist performance than adding AI interpretations

The findings show automation neglect can be a “major barrier” to human-AI collaboration. Interestingly, the new article seems to run counter to a previous study finding that radiologists who received incorrect AI results were more likely to follow the algorithm’s suggestions – against their own judgment. 

The Takeaway

The authors themselves admit the new findings are “puzzling,” but they do have intriguing ramifications. In particular, the researchers suggest that there may be limitations to the collaborative model in which humans and AI work together to analyze cases. Instead, it may be more effective to assign AI exclusively to certain studies, while radiologists work without AI assistance on other cases.

AI Automates Liver Fat Detection

Posted on by Brian Casey

An automated AI algorithm that analyzes CT scans for signs of hepatic steatosis could make it possible to perform opportunistic screening for liver disease. In a study in AJR, researchers described their tool and the optimal CT parameters it needs for highest accuracy. 

Hepatic steatosis (fatty liver) is a common condition that can represent non-alcoholic fatty liver disease (NAFLD), also known as metabolic dysfunction-associated steatotic liver disease (MASLD). Imaging is the only noninvasive tool for detecting steatosis and quantifying liver fat, with CT having an advantage due to its widespread availability. 

Furthermore, abdominal CT data acquired for other clinical indications could be analyzed for signs of fatty liver – the classic definition of opportunistic screening. Patients could then be moved into treatment or intervention.

But who would read all those CT scans? Not who, but what – an AI algorithm trained to identify hepatic steatosis. To that end, researchers from the US, UK, and Israel tested an algorithm from Nanox AI that was trained to detect moderate hepatic steatosis on either non-contrast or post-contrast CT images. (Nanox AI was formed when Israeli X-ray vendor Nanox bought AI developer Zebra Medical Vision in 2021.)

The group’s study population included 2,777 patients with portal venous phase CT images acquired for different indications. AI was used to analyze the scans, and researchers noted the algorithm’s performance for detecting moderate steatosis under a variety of circumstances, such as liver attenuation in Hounsfield units (HU). 

  • The AI algorithm’s performance was higher for post-contrast liver attenuation than post-contrast liver-spleen attenuation difference (AUC=0.938 vs. 0.832)
  • Post-contrast liver attenuation at <80 HU had sensitivity for moderate steatosis of 77.8% and specificity of 93.2%
  • High specificity could be key to opportunistic screening as it enables clinicians to rule out individuals who don’t have disease without requiring diagnostic work-up that might lead to false positives

The authors point out that opportunistic screening would make abdominal CT scans more cost-effective by using them to identify additional pathology at minimal additional cost to the healthcare system. 

The Takeaway

This study represents another step forward in showing how AI can make opportunistic screening a reality. AI algorithms can comb through CT scans acquired for a variety of reasons, identifying at-risk individuals and alerting radiologists that additional work-up is needed. The only question is what’s needed to put opportunistic screening into clinical practice. 

CMS May Shake Up PET Payments

Posted on by Brian Casey

In a major victory for PET advocates, CMS this week said it was opening a review of its reimbursement policy on PET scans for Alzheimer’s disease. The review could lead to more generous Medicare and Medicaid payments for PET to detect amyloid buildup in the brain, long known as a link to the debilitating – and inevitably fatal – disease. 

Medicare’s current policy on PET for Alzheimer’s has been in place since 2013 and is based on its coverage with evidence (CED) framework; it restricts reimbursement to a single scan per lifetime for patients who must be participating in clinical trials. The CED policy reflects not only CMS’ cautious approach to new technology, but also the fact that for years there have been no effective treatments for Alzheimer’s disease. 

That’s all changed within the last year. A new class of drugs that target amyloid buildup in the brain has begun to receive FDA approval, the most recent being Leqembi from Esai/Biogen in January 2023. And this week, Eli Lilly reported positive results for its amyloid-targeting treatment donanemab (see below), with approval expected by the end of 2023. 

The new drugs have changed the game when it comes to diagnosis and treatment of Alzheimer’s disease: 

  • PET can now be used to identify eligible patients and monitor their treatment
  • Thanks to PET, patients won’t continue to be given expensive drugs after amyloid buildup has been eliminated
  • Expanded PET reimbursement could boost the use of PET diagnostic tracers for identifying amyloid buildup 

CMS is taking comments on its proposal through August 16. If the agency eliminates the CED policy in favor of a national coverage decision, then decisions on PET reimbursement will be made by local Medicare Administrative Contractors (MACs). 

This week’s news could be a Pyrrhic victory if PET reimbursement levels are set too low. One positive sign is that CMS has said it also plans to review its policy that bundles radiotracer payments together with scan payments, which tends to depress reimbursement.

The Takeaway

The nuclear medicine and molecular imaging community has chafed for years under CMS’ restrictive policies on PET for Alzheimer’s disease, with groups like SNMMI lobbying for the change. This week’s news should have wide-ranging benefits not only for the PET business sector, but also for patients who are facing the scourge of Alzheimer’s disease.

How COVID Crashed CT Scanners in China

Posted on by Brian Casey

In the early days of the COVID-19 pandemic in China, hospitals were performing so many lung scans of infected patients that CT scanners were crashing. That’s according to an article based on an interview with a Wuhan radiologist that provides a chilling first-hand account of radiology’s role in what’s become the biggest public health crisis of the 21st century.

The interview was originally published in 2022 by the Chinese-language investigative website Caixin and was translated and published this month by U.S. Right to Know, a public health advocacy organization. 

In a sign of the information’s sensitivity, the original publication on Caixin’s website has been deleted, but U.S. Right to Know obtained the document from the US State Department under the Freedom of Information Act. 

Radiologists at a Wuhan hospital noticed how COVID cases began doubling every 3-4 days in early January 2020, the article states, with many patients showing signs of ground-glass opacities on CT lung scans – a telltale sign of COVID infection. But Chinese authorities suppressed news about the rapid spread of the virus, and by January 11 the official estimate was that there were only 41 COVID cases in the entire country.

In reality, COVID cases were growing rapidly. CT machines began crashing in the fourth week of January due to overheating, said the radiologist, who estimated the number of cases in Wuhan at 10,000 by January 21. Hospitals were forced to turn infected patients away, and many people were so sick they were unable to climb onto X-ray tables for exams. Other details included: 

  • Chinese regulatory authorities denied that human-to-human transmission of the SARS CoV-2 virus was occurring even as healthcare workers began falling ill
  • Many workers at Chinese hospitals were discouraged from wearing masks in the pandemic’s early days to maintain the charade that human-to-human contact was not possible – and many ended up contracting the virus
  • Radiologists and other physicians lived in fear of retaliation if they spoke up about the virus’ rapid spread

The Takeaway

The article provides a stunning behind-the-scenes look at the early days of a pandemic that would go on to reshape the world in 2020. What’s more, it demonstrates the vital role of radiology as a front-line service that’s key to the early identification and treatment of disease – even in the face of bureaucratic barriers to delivering quality care.

MRI Findings Linked to Psychosis

Posted on by Brian Casey

Over one-quarter of patients presenting with a first episode of psychosis had some kind of abnormality on brain MRI scans, and about 6% of all findings were clinically relevant and required a change in patient management. Writing in JAMA Psychiatry, researchers from the UK and Germany say their study suggests that MRI should be used in the clinical workup of all patients presenting with psychosis. 

Psychosis caused by another medical condition – called secondary psychosis – can have causes that produce brain abnormalities visible on MRI scans. These are findings like white-matter hyperintensities that – while not themselves a form of pathology – are sometimes associated with more serious conditions like cognitive decline. 

MRI scans of people experiencing their first psychotic episode could detect some of these abnormalities before subsequent episodes occur. But at present there is no consensus as to whether MRI should be used in the evaluation of patients presenting with first-episode psychosis. 

In a meta-analysis, researchers wanted to investigate the prevalence of intracranial radiological abnormalities on MRI scans of patients with first-episode psychosis. They reviewed 12 independent studies that covered a total of 1,613 patients. Findings across all the studies included:

  • A prevalence rate of 26.4% for all radiological abnormalities 
  • A prevalence rate of 5.9% for clinically relevant abnormalities 
  • One in 18 patients had a change in management after an MRI scan
  • White-matter hyperintensities were the most common abnormality, with a prevalence of 7.9% for all abnormalities and 0.9% among clinically relevant abnormalities

Given the impact of MRI on patient management, the authors suggested that performing routine scans on people after their first psychotic episode could have both clinical and economic benefits. This could be especially true due to the financial costs of failing to identify a clinically relevant abnormality that could lead to a later episode if not treated.

The Takeaway 

These findings may break the logjam over whether MRI should be routinely used in the evaluation of patients with first-episode psychosis. The authors note that while many of the abnormalities found on MRI in the studies they reviewed did not require a change in patient management, abnormalities could be harbingers of poorer patient outcomes, even if they don’t eventually lead to a diagnosis of secondary psychosis.

Undermining the Argument for NPPs

Posted on by Brian Casey

If you think you’ve been seeing more non-physician practitioners (NPPs) reading medical imaging exams, you’re not alone. A new study in Current Problems in Diagnostic Radiology found that the rate of NPP interpretations went up almost 27% over four years. 

US radiologists have zealously guarded their position as the primary readers of imaging exams, even as allied health professionals like nurses and physician assistants clamor to extend their scope of practice (SOP) into image interpretation. The struggle often plays out in state legislatures, with each side pushing laws benefiting their positions.

How has this dynamic affected NPP interpretation rates? In the current study, researchers looked at NPP interpretations of 110 million imaging claims from 2016 to 2020. They also examined how NPP rates changed by geographic location, and whether state laws on NPP practice authority affected rates. Findings included:

  • The rate of NPP interpretation for imaging studies went from 2.6% to 3.3% in the study period – growth of 26.9%.
  • Metropolitan areas saw the highest growth rate in NPP interpretation, with growth of 31.3%, compared to micropolitan areas (18.8%), while rates in rural areas did not grow at a statistically significant rate.
  • Rates of NPP interpretation tended to grow more in states with less restrictive versus more restrictive practice-authority laws (45% vs. 16.6%).
  • NPP interpretation was focused on radiography/fluoroscopy (53%), ultrasound (24%), and CT and MRI (21%). 

The findings are particularly interesting because they run counter to one of the main arguments made by NPPs for expanding their scope of practice into imaging: to alleviate workforce shortages in rural areas. Instead, NPPs (like physicians themselves) tend to gravitate to urban areas – where their services may not be as needed. 

The study also raises questions about whether the training that NPPs receive is adequate for a highly subspecialized area like medical imaging, particularly given the study’s findings that advanced imaging like CT and MRI make up one in five exams being read by NPPs. 

The Takeaway    

The findings undermine one of the main arguments in favor of using non-physician practitioners – to address access-to-care issues. The question is whether the study has an impact on the ongoing turf battle between radiologists and NPPs over image interpretation playing out in state legislatures. 

H1 Radiology Recap

Posted on by Brian Casey

That’s a wrap for the first half of 2023. Below are the top stories in radiology for the past 6 months, as well as some tips on what to look for in the second half of the year.

  • Radiology Bounces Back – After several crushing years in the wake of the COVID-19 pandemic, the first half brought welcome news to radiology on several fronts. The 2023 Match wrapped up with diagnostic radiology on top as the most popular medical specialty for medical students over the past 3 years. Radiology was one of the highest-compensated specialties in surveys from Medscape and Doximity, and even vendors got into the act, reporting higher revenue and earnings as supply chain delays cleared up. Will the momentum continue in the second half? 
  • Burnout Looms Large – Even as salaries grow, healthcare is grappling with increased physician burnout. Realization is growing that burnout is a systemic problem – tied to rising healthcare volumes – that defies self-care solutions. Congressional legislation would boost residency slots 5% a year for 7 years, but is even this enough? Alternatively, could IT tools like AI help offload medicine’s more mundane tasks and alleviate workloads? Both questions will be debated in the back half of 2023. 
  • In-Person Shows Are Back – The pandemic took a wrecking ball to the trade show calendar, but things began to return to normal in the first half of 2023. Both ECR and HIMSS held meetings that saw respectable attendance, following up on a successful RSNA 2022. By the time SIIM 2023 rolled around in early June, the pandemic was a distant memory as radiology focused on the value of being together. 

The Takeaway

As the second half of 2023 begins, all eyes will be on ChatGPT and whether a technology that’s mostly a curious novelty now can evolve into a useful clinical tool in the future. 

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!