Tag: radiology

Taking Ultrasound Beyond Breast Density

Posted on by Brian Casey

When should breast ultrasound be used as part of mammography screening? It’s often used in cases of dense breast tissue, but other factors should also come into play, say researchers in a new study in Cancer. 

Conventional X-ray mammography has difficulties when used for screening women with dense breast tissue, so supplemental modalities like ultrasound and MRI are called into play. But focusing too much on breast density alone could mean that many women who are at high risk of breast cancer don’t get the additional imaging they need.

To study this issue, researchers analyzed the risk of mammography screening failures (defined as interval invasive cancer or advanced cancer) in ~825k screening mammograms in ~377k women, and more than ~38k screening ultrasound studies in ~29k women. All exams were acquired from 2014 to 2020 at 32 healthcare facilities across the US.

Researchers then compared the mammography failure rate in women who got ultrasound and mammography to those who got mammography alone. Their findings included: 

  • Ultrasound was appropriately targeted at women with heterogeneously or extremely dense breasts, with 95.3% getting scans
  • However, based on their complete risk factor profile, women with dense breasts who got ultrasound had only a modestly higher risk of interval breast cancer compared to women who only got mammography (23.7% vs. 18.5%) 
  • More than half of women undergoing ultrasound screening had low or average risk of an interval breast cancer based on their risk factor profile, despite having dense breasts
  • The risk of advanced cancer was very close between the two groups (32.0% vs. 30.5%), suggesting that a large fraction of women at risk of advanced cancer are getting only mammography screening with no supplemental imaging

The Takeaway 

On the positive side, ultrasound is being widely used in women with dense breast tissue, indicating success in identifying these women and getting them the supplemental imaging they need. But the high rate of advanced cancer in women who only received mammography indicates that consideration of other risk factors – such as family history of breast cancer and body mass index – is necessary beyond just breast tissue density to identify women in need of supplemental imaging. 

Mayo’s AI Model

Posted on by Brian Casey

SAN DIEGO – What’s behind the slow clinical adoption of artificial intelligence? That question permeated the discussion at this week’s AIMed Global Summit, an up-and-coming conference dedicated to AI in healthcare.

Running June 4-7, this week’s meeting saw hundreds of healthcare professionals gather in San Diego. Radiology figured prominently as the medical specialty with a lion’s share of the over 500 FDA-cleared AI algorithms available for clinical use.

But being available for use and actually being used are two different things. A common refrain at AIMed 2023 was slow clinical uptake of AI, a problem widely attributed to difficulties in deploying and implementing the technology. One speaker noted that less than 5% of practices are using AI today.

One way to spur AI adoption is the platform approach, in which AI apps are vetted by a single entity for inclusion in a marketplace from which clinicians can pick and choose what they want. 

The platform approach is gaining steam in radiology, but Mayo Clinic is rolling the platform concept out across its entire healthcare enterprise. First launched in 2019, Mayo Clinic Platform aims to help clinicians enjoy the benefits of AI without the implementation headache, according to Halim Abbas, senior director of AI at Mayo, who discussed Mayo’s progress on the platform at AIMed. 

The Mayo Clinic Platform has several main features:

  • Each medical specialty maintains its own internal AI R&D team with access to its own AI applications 
  • At the same time, Mayo operates a centralized AI operation that provides tools and services accessible across departments, such as data de-identification and harmonization, augmented data curation, and validation benchmarks
  • Clinical data is made available outside the -ologies, but the data is anonymized and secured, an approach Mayo calls “data behind glass”

Mayo Clinic Platform gives different -ologies some ownership of AI, but centralizes key functions and services to improve AI efficiency and smooth implementation. 

The Takeaway 

Mayo Clinic Platform offers an intriguing model for AI deployment. By removing AI’s implementation pain points, Mayo hopes to ramp up clinical utilization, and Mayo has the organizational heft and technical expertise to make it work (see below for news on Mayo’s new generative AI deal with Google Cloud). 

But can Mayo’s AI model be duplicated at smaller health systems and community providers that don’t have its IT resources? Maybe we’ll find out at AIMed 2024.

When AI Goes Wrong

Posted on by Brian Casey

What impact do incorrect AI results have on radiologist performance? That question was the focus of a new study in European Radiology in which radiologists who received incorrect AI results were more likely to make wrong decisions on patient follow-up – even though they would have been correct without AI’s help.

The accuracy of AI has become a major concern as deep learning models like ChatGPT become more powerful and come closer to routine use. There’s even a term – the “hallucination effect” – for when AI models veer off script to produce text that sounds plausible but in fact is incorrect.

While AI hallucinations may not be an issue in healthcare – yet – there is still concern about the impact that AI algorithms are having on clinicians, both in terms of diagnostic performance and workflow. 

To see what happens when AI goes wrong, researchers from Brown University sent 90 chest radiographs with “sham” AI results to six radiologists, with 50% of the studies positive for lung cancer. They employed different strategies for AI use, ranging from keeping the AI recommendations in the patient’s record to deleting them after the interpretation was made. Findings included:

  • When AI falsely called a true-pathology case “normal,” radiologists’ false-negative rates rose compared to when they didn’t use AI (20.7-33.0% depending on AI use strategy vs. 2.7%)
  • AI calling a negative case “abnormal” boosted radiologists’ false-positive rates compared to without AI (80.5-86.0% vs. 51.4%)
  • Not surprisingly, when AI calls were correct, radiologists were more accurate with AI than without, with increases in both true-positive rates (94.7-97.8% vs. 88.3%) and true-negative rates (89.7-90.7% vs. 77.3%)

Fortunately, the researchers offered suggestions on how to mitigate the impact of incorrect AI. Radiologists had fewer false negatives when AI provided a box around the region of suspicion, a phenomenon the researchers said could be related to AI helping radiologists focus. 

Also, radiologists’ false positives were higher when AI results were retained in the patient record versus when they were deleted. Researchers said this was evidence that radiologists were less likely to disagree with AI if there was a record of the disagreement occurring. 

The Takeaway 
As AI becomes more widespread clinically, studies like this will become increasingly important in shaping how the technology is used in the real world, and add to previous research on AI’s impact. Awareness that AI is imperfect – and strategies that take that awareness into account – will become key to any AI implementation.

When TIA Imaging Is Incomplete

Posted on by Brian Casey

A new study in AJR calculates the cost to patients when imaging evaluation is incomplete, finding that people with transient ischemic attack (TIA) who didn’t get full imaging workups were 30% more likely to have a new stroke diagnosis within the next 90 days.

Some 240,000 people experience TIA annually in the US. While TIAs typically last only a few minutes and don’t cause lasting neurological damage, they can be a warning sign of future neurological events to come.

Medical imaging – typically CT and MRI – are key in the neurological workup of TIA patients, and TIA can be treated with antithrombotic therapy, which reduces the likelihood of a stroke 90 days later. Therefore, guidelines call for prompt neuroimaging of the brain and neck in TIA patients, typically within 48 hours, with MRI the primary and CT the secondary options.

But what happens if TIA patients don’t get complete imaging as part of their workup? To answer this question, researchers from Colorado and California analyzed a database of 111,417 people seen at 4,253 hospitals who presented to the ED with TIA symptoms from 2016 to 2017. 

They tracked which patients received complete neurovascular imaging within 48 hours as part of their workup, then followed how many received a primary diagnosis of stroke within 90 days of the initial TIA encounter. Findings included:

  • 62.7% of patients received brain imaging and complete neurovascular imaging (both head and neck) within 48 hours
  • 37.3% received brain imaging but incomplete neurovascular imaging 
  • There was a higher rate of stroke at 90 days in TIA patients with incomplete imaging workup (7.0% vs. 4.4%)
  • Patients with incomplete neurovascular imaging also had a greater chance of stroke at 90 days (OR=1.3)

The Takeaway 

While the benefits of neuroimaging for stroke have been demonstrated in the literature, imaging’s value for TIA has been less certain – until now. The AJR study shows that neuroimaging is just as vital for TIA workup, and it supports guidelines calling for cross-sectional imaging of the head and neck within 48 hours of TIA.

CT Flexes Muscles in Heart

Posted on by Brian Casey

CT continues to flex its muscles as a tool for predicting heart disease risk, in large measure due to its prowess for coronary artery calcium scoring. In JAMA, a new paper found CT-derived CAC scores to be more effective in predicting coronary heart disease than genetic scores when added to traditional risk scoring. 

Traditional risk scoring – based on factors such as cholesterol levels, blood pressure, and smoking status – has done a good job of directing cholesterol-lowering statin therapy to people at risk of future cardiac events. But these scores still provide an imprecise estimate of coronary heart disease risk. 

Two relatively new tools for improving CHD risk prediction are CAC scoring from CT scans and polygenic risk factors, based on genetic variants that could predispose people toward heart disease. But the impact of either of these tools (or both together) when added to traditional risk scoring hasn’t been investigated. 

To answer this question, researchers analyzed the impact of both types of scoring on participants in the Multi-Ethnic Study of Atherosclerosis (1,991 people) and the Rotterdam Study (1,217 people). CHD risk was predicted based on both CAC and PRS and then compared to actual CHD events over the long term. 

They also tracked how accurate both tools were in reclassifying people into different risk categories (higher than 7.5% risk calls for statins). Findings included: 

  • Both CAC scores and PRS were effective in predicting 10-year risk of CHD in the MESA dataset (HR=2.60 for CAC score, HR=1.43 for PRS). Scores were slightly lower but similar in the Rotterdam Study
  • The C statistic was higher for CAC scoring than PRS (0.76 vs. 0.69; 0.7 indicates a “good” model and 0.8 a “strong” model) 
  • The improved accuracy in reclassifying patient risk was statistically significant when CAC was added to traditional factors (half of study participants moved into the high-risk group), but not when PRS was added  

The Takeaway 

This study adds to the growing body of evidence supporting cardiac CT as a prognostic tool for heart disease, and reinforces CT’s prowess in the heart. The findings also support the growing chorus in favor of using CT as a screening tool in cases of intermediate or uncertain risk for future heart disease.

AI Investment Shift

Posted on by Brian Casey

VC investment in the AI medical imaging sector has shifted notably in the last couple years, says a new report from UK market intelligence firm Signify Research. The report offers a fascinating look at an industry where almost $5B has been raised since 2015. 

VC investment in the AI medical imaging sector has shifted in the last couple years, with money moving to later-stage companies.

Total Funding Value Drops – Both investors and AI independent software vendors (ISVs) have noticed reduced funding activity, and that’s reflected in the Signify numbers. VC funding of imaging AI firms fell 32% in 2022, to $750.4M, down from a peak of $1.1B in 2021.

Deal Volume Declines – The number of deals getting done has also fallen, to 42 deals in 2022, off 30% compared to 60 in 2021. In imaging AI’s peak year, 2020, 95 funding deals were completed. 

VC Appetite Remains Strong – Despite the declines, VCs still have a strong appetite for radiology AI, but funding has shifted from smaller early-stage deals to larger, late-stage investments. 

HeartFlow Deal Tips Scales – The average deal size has spiked this year to date, to $27.6M, compared to $17.9M in 2022, $18M in 2021, and $7.9M in 2020. Much of the higher 2023 number is driven by HeartFlow’s huge $215M funding round in April; Signify analyst Sanjay Parekh, PhD, told The Imaging Wire he expects the average deal value to fall to $18M by year’s end.

The Rich Get Richer – Much of the funding has concentrated in a dozen or so AI companies that have raised over $100M. Big winners include HeartFlow (over $650M), and Cleerly, Shukun Technology, and Viz.ai (over $250M). Signify’s $100M club is rounded out by Aidoc, Cathworks, Keya Medical, Deepwise Shenrui, Imagen Technologies, Perspectum, Lunit, and Annalise.ai.

US and China Dominate – On a regional basis, VC funding is going to companies in the US (almost $2B) and China ($1.1B). Following them are Israel ($513M), the UK ($310M), and South Korea ($255M).  

The Takeaway 

Signify’s report shows the continuation of trends seen in previous years that point to a maturing market for medical imaging AI. As with any such market, winners and losers are emerging, and VCs are clearly being selective about choosing which horses to put their money on.

The Perils of Worklist Cherry-Picking

Posted on by Brian Casey

If you’re a radiologist, chances are at some point in your career you’ve cherry-picked the worklist. But picking easy, high-RVU imaging studies to read before your colleagues isn’t just rude – it’s bad for patients and bad for healthcare.

That’s according to a new study in Journal of Operations Management that analyzes radiology cherry-picking in the context of operational workflow and efficiency. 

Based on previous research, researchers hypothesized that radiologists who are free to pick from an open worklist would choose the easier studies with the highest compensation – the classic definition of cherry-picking.

To test their theory, they analyzed a dataset of 2.2M studies acquired at 62 hospitals from 2014 to 2017 that were read by 115 different radiologists. They developed a statistical metric called “bang for the buck,” or BFB, to classify the value of an imaging study in terms of interpretation time relative to RVU level. 

They then assessed the impact of BFB on turnaround time (TAT) for different types of imaging exams based on priority, classified as Stat, Expedited, and Routine. Findings included:

  • High-priority Stat studies were reported quickly regardless of BFB, indicating little cherry-picking impact
  • For Routine studies, those with higher BFB had much lower reductions in turnaround — a sign of cherry-picking
  • Adding one high-BFB Routine study to a radiologist’s worklist resulted in a much longer increase in TAT for Expedited exams compared to low-BFB studies (increase of 17.7 minutes vs. 2 minutes)
  • The above delays could result in longer patient lengths of stay that translate to $2.1M-$4.2M in extra costs across the 62 hospitals in the study. 

The findings suggest that radiologists in the study prioritized high-BFB Routine studies over Expedited exams – undermining the exam prioritization system and impacting care for priority cases.

Fortunately, the researchers offer suggestions for countering the cherry-picking effect, such as through intelligent scheduling or even hiding certain studies – like high-BFB Routine exams – from radiologists when there are Expedited studies that need to be read. 

The Takeaway 

The study concludes that radiology’s standard workflow of an open worklist that any radiologist can access can become an “imbalanced compensation scheme” that can lead to poorer service for high-priority tasks. On the positive side, the solutions proposed by the researchers seem tailor-made for IT-based interventions, especially ones that are rooted in AI. 

Medical Malpractice Crisis

Posted on by Brian Casey

Is a new crisis looming in medical malpractice insurance? An AMA analysis finds that medical liability premiums are skyrocketing again – and radiologists may be among the physicians most affected due to their higher exposure to malpractice suits.

The proportion of medical liability premiums that increased year-to-year for OB/GYN, general surgery, and internal medicine doctors (radiologists weren’t surveyed) doubled from 2018 to 2019 (13.7% to 26.5%), and went up 30% year-to-year from 2020 to 2022. The last time rates rose this fast was during the medical liability crisis of the early 2000s, according to the AMA paper.

Insurers are raising premiums due to deteriorating underwriting results, lower loss reserve margins, and lower returns on investment, per the report. These trends are echoed in a new analysis of the medical malpractice segment by credit agency AM Best, which describes a “difficult environment” for medical liability insurers. The medical professional liability segment has seen eight straight years of underwriting losses.

Why should radiologists care? Well, radiologists are more likely to have experienced medical liability claims during their career than most other physicians. Another AMA survey of over 6k doctors found: 

  • Radiologists were more likely to say they had been sued in their career than all physician types (40.2% vs. 32.1%)
  • More radiologists have experienced a lawsuit in the past year than all physicians (4.2% vs. 2.0%)
  • The only other medical specialists more likely to be sued than radiologists were surgeons (48.9%) and emergency medicine physicians (46.8%) 

The first AMA report closes by saying that a medical liability insurance “hard” market – a market characterized by rapid price increases – already exists in a number of states, and is “slowly spreading” across the rest of the US. 

Further, there is “striking” geographic variation in premiums. OB/GYNs in Los Angeles County, California see average manual premiums of $49,804 a year, while those in Miami-Dade County, Florida are staring at a $226,224 liability insurance bill.

The Takeaway 

The AMA said the growing medical malpractice crisis could have multiple ramifications. Physicians in states with difficult liability environments could relocate or even drop some clinical services that raise their risk. Will the worsening environment draw the attention of state and federal regulators? Only time will tell. 

A New Day for Breast Screening

Posted on by Brian Casey

In a breathtaking about-face, the USPSTF said it would reverse 14 years of guidance in breast screening and lower its recommended starting age for routine mammography to 40.

In a proposed guidance, USPSTF said it would recommend screening for women every other year starting at age 40 and continuing through 74. The task force called for research into additional screening with breast ultrasound or MRI for women with dense breasts, and on screening in women older than 75.

The move will reverse a policy USPSTF put in place in 2009, when it withdrew its recommendation that all women start screening at 40, instead advising women in their 40s to consult with their physicians about starting screening. Routine mammography was advised starting at age 50. The move drew widespread condemnation from women’s health advocates, but the USPSTF stuck to the policy even through a 2016 revision.

The task force remained steadfast even as studies showed that the 2009 policy change led to confusion and lower breast screening attendance. The change also gave fuel to anti-mammography extremists who questioned whether any breast screening was a good idea.

That all changes now. In its announcement of the 2023 guidance, USPSTF said it based the new policy on its review of the 2016 update. No new RCTs on breast screening have been conducted for decades (it’s considered unethical to deny screening to women in a control group), so the task force commissioned collaborative modeling studies from CISNET.

USPSTF said the following findings factored into its decision to change the guidance: 

  • Biennial screening from 40-74 would avert 1.3 additional breast cancer deaths per 1,000 women screened compared to biennial screening of women 50-74.
  • The benefits of screening at 40 would be even greater for Black women, at 1.8 deaths averted. 
  • The incidence rate of invasive breast cancer for women 40-49 has increased 2.0% annually from 2015-2019, a higher rate than in previous years. 
  • Biennial screening results in greater incremental life-years gained and mortality reduction per mammogram and better balance of benefits to harms compared to annual screening.

The Takeaway 

As with the FDA’s recent decision to require density reporting nationwide, the USPSTF’s proposal to move the starting age for mammography screening to 40 was long overdue. The question now is how long it will take to repair 14 years of lost momentum and eliminate confusion about breast screening.

Learning Curve in DBT Screening

Posted on by Brian Casey

Digital breast tomosynthesis continues to evolve. First introduced initially as a problem-solving tool in breast imaging, DBT is becoming the workhorse modality for breast screening as well. 

But DBT still requires some adjustment when used for screening. In a study of nearly 15k women in European Radiology, Swedish researchers describe how the false-positive recall rate for DBT cancer screening started higher but then fell over time as radiologists got used to the appearance of lesions on DBT exams.

The Malmö Breast Tomosynthesis Screening Trial was set up to compare one-view DBT to two-view digital mammography for breast screening. Unlike some DBT screening trials, the study did not use synthesized 2D DBT images. DBT images were acquired 2010-2015 with Siemens Healthineers’ Mammomat Inspiration system. 

Findings in the study included: 

  • DBT had a sharply higher false-positive recall rate in year 1 of the study compared to DM (2.6% vs. 0.5%)
  • DBT’s recall rate fell over the five-year course of the study, stabilizing at 1.5% 
  • Recall rates for DM varied between 0.5% and 1% over five years
  • Most of the DBT recalls (37.3%) were for stellate lesions, in which spicules radiate out from a central point or mass. With DM, only 24.0% of recalls were for stellate lesions
  • The number of stellate distortions being recalled with DBT declined over time, a trend the authors attributed to a learning curve in reading DBT images

The authors said that the DBT false-positive recall rate in their study was “in general low” compared to other European trials. They claimed that MBTST is among the first studies to analyze recall rates by lesion appearance, an important point because radiologists may see a different distribution of lesion types on screening DBT compared to what they’re used to with DM.

The Takeaway 

The Malmö Breast Tomosynthesis Screening Trial was one of the first to investigate DBT for breast screening, and previous MBTST research showed that DBT can also reduce interval cancers, which occur between screening rounds. 

The new findings offer further support for DBT breast screening and give hope that whatever shortcomings the technology might have early on in a screening role can be addressed through training and experience. It also confirms recent research indicating that DBT has become the new gold standard for breast screening.

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!