Amazon Alexa could have a job in a radiology office soon – and not as the office DJ responsible for background music.

RAD-Assistant, an Amazon Alexa skill, developed by researchers at the University of Pittsburgh Medical Center, can take direction from radiologists and accurately return follow-up guidelines for pulmonary nodules and ovarian cysts, making it a strong candidate to be a point-of-care clinical decision support tool.

The research team made their results available in the 

Society of Imaging Informatics in Medicine 2020

“This free, voice-enabled assistant is capable of relieving radiologists from constant reference of guidelines via web-browser on PACS workstations with expensive screen real-estate,” they said. “We demonstrate the Alexa service is capable of understanding the medical lexicon with accurate recommendations based on pre-programmed user intents.”

According to the research team, RAD-Assistant is comprised of a voice user interface (VUI) that listens for pre-defined user “utterances” to decipher the user’s intent. Visual menus and re-prompts can supplement audio queues. To confirm the basis for the recommendation, the VUI reads back the submitted information.

To determine the skill’s efficacy, the team had two native English speakers verbalize their requests to receive ovarian cyst and pulmonary nodule recommendations to three devices: Echo Spot, Samsung phone, and iPhone. Overall, 143 of 154 (92.9 percent) of requests were successfully completed, and all completed intents resulted in correct Society of Radiologist in Ultrasound or Fleischner Society recommendations. Broken down by subgroup, the ovarian cyst group had 73 of 77 (94.8 percent) successful attempts, and the pulmonary nodule group had 70 of 77 (90.9 percent) success.

The investigators did note two obstacles for RAD-Assistant. Currently, the Alexa platform is not HIPAA-compliant, and further validation with additional accents, dialects, and languages is necessary. However, they noted, expanding to other published algorithms, such as TI-RADS and LI-RADS is a possibility.

Articles

Amazon Alexa skill RAD-Assistant successfully retrieves pulmonary nodule and ovarian cyst clinical follow-up guidelines.


Alexa: Get My Follow-Up Guidelines

The push to improve care delivery throughout radiology has had a multi-pronged approach for many years. One of the fundamental components is effective patient engagement – and, in today’s environment, technology has become a powerful tool in improving these interactions.

Across the board, technology is being used to augment patient knowledge, skills, and interest in participating in his or her healthcare. Not only does it enhance communication with patients, making them feel more empowered, but it can also increase patient satisfaction rates.

 spoke with Alexander Towbin, M.D., associate chief of clinical operations and informatics and chair of radiology informatics at Cincinnati Children’s Hospital Medical Center about his presentation on this topic at the 

 Virtual Meeting. Towbin shared his insights and his facility’s experience with the role of technology in patient engagement, as well as some best practices.

Videos

Alexander Towbin, M.D., from Cincinnati Children’s Hospital Medical Center shares his thoughts during SIIM 2020.

Best Practices: Technology and Patient Engagement

The combined use of a nevus identification algorithm and 3D total body imaging may help to reduce clinical subjectivity and improve estimations of melanoma risk, according to findings presented at 

As a major risk factor for melanoma, assessment of nevi on the skin is an important part of the dermatological exam, though the manual counting process uses up an extensive amount of resources. Often, nevi identification and counting is left up to the patient, which can introduce a large margin of error in clinical evaluations.

To combat this, researchers led by Brigid D. Betz-Stablein, PhD, sought to develop an automated nevus identification algorithm using 3D body imagery produced by the VECTRA WB360 imaging system, which allows for total body photography.

Dermatologists were used to identify nevi with diameters of at least 2mm on VECTRA 3-D avatars created from members of the general population; the labeled nevi were used to train a neural network-based artificial intelligence algorithm, which was then tested an additional 10, random avatars not included in the training set. Ultimately, results from the algorithm were compared with the in-clinic assessment as well as consensus of on-screen nevi counts from 3 additional experts.

Overall, the algorithm showed a sensitivity and specificity of 79% and 91%, respectively, and an overall accuracy of 90% in its ability to identify nevi of at least 2mm in diameter. Kappa increased from 0.56 to 0.72 for nevi larger than 5mm. Notably, the algorithm was unable to consistently differentiate between nevi and seborrheic keratoses, resulting in significant differences in nevi counts in individuals with a large number of seborrheic keratoses. Still, there was good agreement observed between the clinician evaluations and the algorithm assessments when broken down by nevus density (few, <20; some, 20-50; many, >50). Perhaps most important was the observed high heterogeneity between the relative risk of melanoma dependent on extent of partial or total body counts.

While the algorithm could be improved by incorporating seborrheic keratoses images in the training set, overall the AI nevus assessment has potential to have a positive impact on clinical assessment of nevi and evaluation of melanoma risk, conserving clinician time and costs.

The automated algorithm can help save both time and money and minimize clinical subjectivity. 

AI-Driven Nevus Identification May Help Better Quantify Melanoma Risk

In an increasingly digital industry, security has become an ever-present concern. Given the volume of imaging data each facility maintains, it is incumbent for providers and practice administrators to take proactive, protective steps, according to industry experts.

During the Society of Imaging Informatics in Medicine 2020 virtual meeting, Tom Kern, CIIP, senior imaging informatics analyst at Children’s Hospital Colorado, shared his insights on the importance of maintaining proper security and how facilities and practices can maximize it for their imaging informatics.

“We have a really long tail on modalities throughout the industry that we’re still actively using for patient care,” he said, highlighting one of the main security problems that radiology faces. “There are a fair number of machines out there that are still running on old operating systems that, except for a random patch here and there, have had no significant upgrades.”

Without a current operating system that allows for proper protection, he cautioned, facilities are left vulnerable to viruses and hacking. Bad actors are frequently aware of these weaknesses and will actively exploit them. And, once they are inside a facility’s network, he said, they have access to anything on that network as long as it can be reached via IP, potentially becoming a persistent threat.

There are several things facilities can do, though, to protect themselves, Kern said.

 Identify who is responsible for all maintenance and security patches. In some cases, large vendors will automatically push updates to a system, alleviating the need for any action. But, smaller vendors frequently leave actual update installation to the client.

“Knowing who’s responsible for patching and who’s responsible for the care and feeding of your modalities is important,” he said.

 Keep devices that contain personal health information segmented and separated from a standard desktop PC, iPad, or other similar devices. Kern also advised not having them directly connected to the internet unless it is absolutely necessary.

 Partner with an info-security team, as well as network administrators outside of imaging, he said.

“Imaging informatics professionals are really good at a lot of things, but we can’t really be good at everything,” he explained. “Engage those resources outside of imaging to make sure your network is set up properly, make sure that you’re doing patching properly, and have a schedule set up.”

 Limit the targets that are allowed to communicate with each modality. With these firewalls in place, systems must conduct a security review process for any new target, potentially identifying ones that present risks.

Ultimately, Kern said, it is imperative that facilities know exactly what is on their network. With a solid level of familiarity, it will be easier to catch security threats.

“If you have a CT scanner that’s talking to an IP in Southeast Asia or Western Europe, and you don’t have clients in those locations, it’s worth investigating,” he advised. “Be curious – not only about what you have but what your systems are talking to, as well.”

Go-to steps from a senior imaging informatics analyst during SIIM 2020 to bolster security efforts.

Maximizing Imaging Informatics Security

Imaging findings from several modalities have revealed an emerging disease in children who either have COVID-19 infection or who have been exposed to the virus, according to a new case series.

Known as Multisystem Inflammatory Syndrome in Children (MIS-C), this condition is characterized by airway inflammation, rapid development of pulmonary edema, coronary artery aneurysms, and extensive intra-abdominal inflammatory changes. A team of investigators from Evelina London Children’s Hospital in London assessed these findings in children admitted to the hospital and published their findings in the June 25 

“Our hospital saw an unprecedented cluster of children presenting with MIS-C, a new hyperinflammatory syndrome in children related to the current COVID-19 pandemic – the recognition of which led to a national alert,” said lead study author Shema Hameed, M.B.B.S., consultant pediatric radiologist at Evelina London Children’s Hospital. “Our intention is to bring these findings to the attention of the wider radiological community.”

Initially, she said, the children’s symptoms, including fever, headaches, abdominal pain, rash, and conjunctivitis, potentially pointed to a diagnosis of Kawasaki disease, a condition that causes blood vessel wall inflammation, Kawasaki-disease shock syndrome, or toxic-shock syndrome. However, the symptoms were atypical and more severe.

To determine what was actually going on, the researchers performed a retrospective review of clinical, laboratory, and imaging findings, including ultrasound, CT, and X-ray studies, on the first 35 children under age 17 who were admitted to the pediatric hospital and who met the MIS-C case definition. The group, admitted between April 14, 2020, and May 9, 2020, included 27 boys and eight girls with an average age of 11.

Upon analysis of the medical data, the investigators identified several common symptoms. The most frequently occurring was fever, present in 94 percent of children. In addition, gastrointestinal symptoms, including abdominal pain, vomiting and diarrhea were seen in 86 percent of children, rash was present in 37 percent, and conjunctivitis developed in 26 percent. Of the group, 60 percent were in shock.

In many cases, children required substantial medical intervention. According to the team, 69 percent of patients had a clinical status severe enough to warrant management in the pediatric intensive care unit. Twenty percent of those children needed mechanical ventilation, and 57 percent required inotropic support. Due to severe myocardial dysfunction, two children needed extracorporeal membrane oxygenation, and lab tests revealed that all children had abnormal white blood cell counts.

Overall, the investigators identified a pattern of imaging findings that indicated post-COVID-19 MIS-C. Based on chest X-ray, chest CT, and abdominal ultrasound, they pinpointed airway inflammation, rapidly progressive pulmonary edema, coronary artery aneurysm, and extensive abdominal inflammatory changes within the right iliac fossa.

For modality-specific results, the investigators found:

All 35 children underwent this study based on fever, sepsis, or multi-system inflammation features. Of the group, 19 X-rays were abnormal with the most common finding being bronchial wall thickening.

Conducted in three children, the most common findings were basal consolidation and collapsed lung with pleural effusions.

Five children underwent these studies, and findings included inflammatory changes within the right iliac fossa with mesenteric fat stranding, lymphadenopathy, and bowel wall thickening, along with free fluid identified in the pelvis.

 Echocardiogram findings revealed cardiac dysfunction, including deteriorating myocardial function, myocarditis, pancarditis, pericardial effusions, and coronary artery aneurysms, in 18 children. Thirty patients underwent cardiac CT with six showing coronary artery aneurysms.

Investigators acknowledged that their study population was small, limiting the ability to make their findings generalizable. Consequently, they outlined the need for further investigations. But, these results are still valuable in adding knowledge to the understanding of how COVID-19 affects children.

“With these detailed findings and our postulated mechanisms for them, we hope to raise the awareness of this emerging condition among a radiology readership,” they said.

Multisystem Inflammatory Syndrome in Children appearing in pediatric patients with COVID-19 infection and exposure. 

Imaging Reveals Emerging Post-COVID Disease in Children

When it comes to the risk of developing Alzheimer’s disease, PET and MRI imaging results from a new study have revealed that women have four strikes against them.

In a research article published in the June 24 

 journal, investigators from Weill Cornell Medicine in New York, determined that women score worse than men on every measure used to assess their risk of having Alzheimer’s biomarkers.

“Our findings suggest that middle-aged women may be more at risk for the disease, perhaps because of lower levels of the hormone estrogen during and after menopause,” said lead study author Lisa Mosconi, Ph.D., director of the Weill Cornell Women’s Brain Initiative. “While all sex hormones are likely involved, our findings suggest that declines in estrogen are involved in the Alzheimer’s biomarker abnormalities in women we observed. The pattern of gray matter loss in particular shows anatomical overlap with the brain estrogen network.”

These findings, she said, contradict the widely held belief that women experience Alzheimer’s disease at greater rates because they live longer than men. This is the first study to look at how sex-specific risks can impact Alzheimer’s-related brain changes in midlife. Knowing more about these biomarkers is vital, her team emphasized, because existing evidence shows they can detect Alzheimer’s decades before the onset of clinical symptoms. 

Mosconi’s team used PET and MRI to evaluate and compare the differences between men and women in four areas:

Volumes of both gray and white matter in the brain

Glucose metabolization rate in the brain (an indicator of brain activity)

The investigators enrolled 121 participants -- 85 women and 36 men – with an average age of 52. Participants had no cognitive impairment, and they exhibited similar thinking and memory skills, thyroid function, Alzhiemer’s family history, vascular risk factors, and physical lifestyles.

Each participant underwent PET imaging with carbon-11-labeled Pittsburgh Compound B (PiB) to pinpoint any amyloid-beta plaques in the brain. FDG was used to identify the extent of any neurodegeneration, and structural MRI scans measured each participant’s gray and white brain matter. 

According to the results, women had worse scores than men across all four categories:

30 percent more beta amyloid plaques in their brains

22 percent lower glucose metabolism in the superior frontal gyrus, medial frontal gyrus, and inferior parietal lobule,

11 percent less average gray matter volume – 0.73 cm

11 percent less average white matter volume– 0.74 cm

Despite these lower scores, Mosconi’s team found women, including post- and perimenopausal women, did not demonstrate any reduced levels of cognitive performance compared to the male study participants. This result, they posited, suggests that biomarkers are more sensitive and can more accurately detect Alzheimer’s risk in individuals not showing symptoms than cognitive tests.

Mosconi pointed out that these results are applicable to healthy, middle-aged adults who do not have severe cerebrovascular or cardiovascular disease. More studies are needed to determine whether these results can be generalized.

Women score worse than men in four key brain health areas associated with Alzheimer’s biomarkers. 

PET, MRI Identify What Increases Women’s Likelihood of Alzheimer’s

One of the most widespread impacts of the COVID-19 pandemic has been the delayed study. For many patients, their screening or diagnostic studies have been put on hold for the foreseeable future. But, the postponement is more than a simple delay – it is a compounding factor that is starting to make an already existing problem worse.

It is no secret in the industry that patients who fail to arrive for follow-up care are a pervasive pain point for practices. Add in the delay, the risk, and the fear associated with the pandemic, and it is recipe for an even deeper drop in imaging volume.

Contacting Patients About Abnormal Findings Isn’t Enough to Prompt Follow-Up

To help practices address this issue – and potentially side-step it – 

 spoke with Sander Kloet, senior director of product management, diagnostics, for Nuance Communications about his session during Society for Imaging Informatics in Medicine 2020 Virtual Meeting. Here, he shares his insights on the frequency of the problem during the pandemic, strategies facilities can use to reduce the impact of failed follow-ups, and proactive tactics practices can implement.

COVID-19 is an additional factor in patients shying away from follow-up exams. Nuance Communication’s Sander Kloet shares his perspectives from SIIM on addressing this issue.

Addressing Failed Patient Follow-Ups During the Pandemic

A daily dashboard that highlights details about number of exams and time-to-report generation can significantly reduce turnaround times in emergency departments where the most rapid, efficient care can be critical, according to new research.

During the Society for Imaging Informatics in Medicine (SIIM) Virtual Meeting 2020, researchers from the Cleveland Clinic presented a post, detailing how a dashboard – and an accompanying daily report – can help emergency medicine radiologists truncate the time it takes them to fully complete the image analysis process by more than 10 percent.

“Faster image interpretation directly impacts the quality of patient care,” they said, “especially in the case of the emergency department, so it is vital that images are interpreted in the most timely and efficient manner.”

Slow turnaround times not only hamstring emergency physicians who need imaging reports to determine best treatment options, but they can also slow down discharge or admission, significantly increasing emergency room wait times.

To fix this problem, the team created a dashboard, called the Turnaround Time Compliance dashboard, to track turnaround times by provider. This tool identified busy times in the department, highlighting opportunities to proactively balance workload, and it also revealed PACS data on the number of available images at any given time, potentially uncovering times when batching studies might inadvertently delay a radiologist's productivity.

During the study, each radiologist received an individualized report at the end of the day, detailing three things: time until report creation, time until preliminary report was made available, and time until report was signed. The reports can also reveal behavioral workflows between radiologists and foster a healthy sense of competition, the investigators said.

According to the team’s analysis, implementing the dashboard reduced turnaround time by approximately 10 percent to 13 percent. But, the system was also beneficial in changing some long-standing behaviors in the department, as well.

That competitive feeling, the team indicated, created a “more focused, streamlined, and timely interpretation of images.” It also limited cherry-picking behavior among the radiologists when selecting which studies to interpret.

While the emergency medicine and radiology providers experienced a positive impact, they said, patients were helped the most.

“Ultimately, these more timely interpretations have had a positive impact on patient care and patient experience,” they explained, “reducing overall time in the emergency room.”

A dashboard to track the total image analysis time, as well as a daily performance report, reduced emergency department turnaround times and improved workflow.

Dashboard Reduces Turnaround Time, Fosters Competition Between Radiologists

Total knee replacement is a significant surgery that potentially anyone with knee osteoarthritis might face. With the advent of a new artificial intelligence (AI) model, providers will have a better idea about which patients are likely to need the procedure.

With more than 14 million Americans living with knee osteoarthritis (OA), and more than 50 percent ultimately needing a total knee replacement, being able to more accurately predict which patients face a trip to the operating room can help providers determine the best treatment strategies.

To help clinicians with this assessment a research team, including imaging and data experts, from New York University designed and tested an AI model with more than 700 participants. Their results, published in the June 23 

indicate that, not only is their model better than current prediction methods, but it could also be used to create disease-modifying therapies designed to prevent (or at least postpone) knee surgery.

“We developed a model to predict OA progression outcomes directly from baseline radiographs,” wrote the team, led by Cem Deniz, Ph.D., assistant professor of radiology at New York University Langone Health. “However, we developed a model to predict OA progression outcomes directly from baseline radiographs with an additional [grading system] prediction task.”

Specifically, the team retrospectively analyzed medical information from 728 individuals – 324 patients with knee osteoarthritis and 324 without the condition who were enrolled in the multi-center, longitudinal Osteoarthritis Initiative. The data evaluated included X-rays and MRI images.

Based on their results – an area under the receiver operating characteristic curve score of 0.87 – the team determined the deep learning model was effective. In fact, it outperformed other system currently used to determine which patients are best suited for total knee replacement, including the Kellgren Lawrence grade and the OA Research Society International atlas.

In an accompanying editorial, Michael L. Richardson, M.D., professor of radiology and orthopedic surgery at the University of Washington in Seattle, noted that while this deep learning model is not the first AI model to predict the likelihood of surgery among patients, its performance is among the highest.

“[This] deep learning model…goes a step further, cuts out the middleman (KL classification) and predicts [total knee replacement] need directly from the patients’ knee radiographs,” he wrote.

Further evaluation is needed with external datasets before this AI model can be used in an actual patient-care setting, but its development could be a huge benefit for patients living with knee OA.

“The availability of an automated system that could accurately predict [total knee replacement] need has important and practical ramifications,” he wrote. “There is, therefore, a great necessity to begin disease-modifying therapies as soon as possible to prevent or delay the need for a [total knee replacement.]”

Deep learning algorithm is more accurate in predicting which patients with knee osteoarthritis might need a total knee replacement. 

AI Model a Step Forward in Predicting Total Knee Replacements

Cardiovascular 4D MRI does a better job of measuring blood flow during exercise than does traditional stress echocardiography, giving providers an improved understanding of dysfunction on the right side of the heart.

In a small study from the University of Wisconsin, researchers analyzed nine healthy adults with 4D flow MRI both during strenuous exercise and at rest. Their results, published in the June 18 

 showed this strategy was both accurate and reliable in quantifying both ascending aorta and main pulmonary artery flow.

As part of the study, the team, led by Jacob Macdonald, Ph.D., performed 4D MRI on nine adults, with an average age of 26, while they worked out on an MRI-compatible stair-stepper, as well as while they were at rest. The data was gathered between March 2016 and July 2017.

The scanning process lasted nine minutes, limiting the number of patients who were able to physically complete the study, but experts in an accompanying 

 noted this work is still valuable in bringing 4D flow MRI into real-world used.

Based on study results, the group determined flow measurements in the ascending aorta and the main pulmonary artery can be reliably captured with “good internal consistency.” And, while the signal-to-noise ratio of mid-exercise scans fell by 16 percent on average, the difference was not significant when compared to the at-rest scans.

According to the editorialists, MRI images show that exercise can blur vessel, ventricular, and arterial boundaries, potentially making flow quantification challenging. Additional studies are necessary, they added, and, this first study testing the feasibility of 4D flow MRI as a hemodynamic monitoring tool for exercise can be used as a model.

Imaging method offers greater understanding into right-sided heart dysfunction.

4D Flow MRI Measurements More Beneficial Than Stress Echocardiography

Interval breast cancers (IBCs) – those that appear during the year between a patient’s screening appointments – could have particular features that make them more aggressive and malignant, a new study has found.

 investigators from Oregon State University revealed the results of their 19-year, nearly 5,500-woman study during which they followed women who received regular screening mammograms. According to their findings, cancers diagnosed within a year of a negative mammogram shared several common traits that point to potential negative outcomes for the patient.

Based on those characteristics, the team said, it is likely that IBCs have unique facets that mean providers should implement alternative screening strategies.

“Interval cancers occurring within one year from a mammogram with negative results may have a unique biology that accounts for aggressive features,” wrote the research team, led by Veronica Irvin, Ph.D., assistant professor of public health and human sciences at Oregon State University. “Women with IBCs diagnosed within one year of negative mammogram results overall were associated with worse survival than women with breast cancers detected by screening.”

To make this determination about IBCs and outcomes, Levin’s team examined mammography, tumor characteristics, and demographic data from patients enrolled in the Women’s Health Initiative (WHI), a longitudinal cohort study of post-menopausal women. Of that group, the team examined data from women, between the ages of 50 and 79, who were enrolled in one of 40 clinical locations between 1993 and 1998. They, then, followed the women for an average of 19 years.

Mammography Screening Produces 41-Percent Drop in Risk of Breast Cancer Death

Investigators divided the study group into two cohorts. One underwent mammography every 2.5 years while the other received yearly scans. The women included in this study, according to the team, had no personal breast cancer history and no suspicious findings on their baseline screening mammogram.

According to the investigators, 3,019 women developed breast cancer during the study – approximately 65 percent of which was diagnosed at screening. The other 35 percent were diagnoses of IBC. And, those IBC cancers were very different from the ones caught on routine screening. They had significantly more lobular histologic characteristics, had a larger tumor size, involved the lymph nodes, and were identified at a later clinical stage.

In addition, the team reported, women who received IBC diagnoses were also more likely to die than those women who had cancer detected at screening. And, adjusting for known breast cancer risk factors, histologic type, waist-to-hip ratio, molecular subtype, lymph node involvement, tumor size, or intervention group did not mitigate that higher mortality risk.

It is important to note, the team said, that they found no significant difference in the tumor traits or patient outcomes for IBCs identified after one year. That result, they said, indicates that IBCs likely have characteristics that set them apart from other forms of breast cancer.

“The unique findings from our study are that IBCs that emerge within one year after negative mammogram results might have distinct tumor characteristics that identify them as at a particularly high risk for metastasis,” the team said.

Consequently, these findings have several clinical implications, they added. Women who have breast cancer symptoms and a negative screening mammogram should be either recalled more frequently or they should have a shorter screening period. In addition, they could also undergo supplemental ultrasound screening or have an MRI. Genomic testing can also play a role in helping providers distinguish between indolent and aggressive breast cancers.

Overall, these results contribute to a greater understanding of breast cancer and how it can be treated more successfully, the team said.

“This study adds to a growing body of literature that argues for the development of novel approaches to detect life-threatening cancers currently missed by mammographic screening,” the team wrote.

Breast cancers identified between patient screenings are more aggressive and lethal.

Unique Traits for Interval Breast Cancers Point to Poor Patient Outcomes

One Florida radiology office is relying on technology outside of the scanning room to offer patients greater safety during the COVID-19 pandemic.

Tampa Bay-based Tower Radiology announced its virtual registration system this week that will give patients throughout their service area the power to complete their entire registration process remotely.

“Virtual registration is a big step forward in Tower’s effort to decrease contact with staff, to adhere to social distancing recommendations, and to streamline the completion of necessary paperwork,” office leaders said in a press statement.

The virtual registration process launches once a patient has scheduled his or her appointment. Patients receive a confirmation text and an email with a registration link that will allow them to complete the necessary forms on their phone or computer. They can also take a photo of their ID, as well as exam prescription.

On the day of the appointment, patients receive a reminder text with instructions within 90 minutes of their appointment time. And, after their appointment is complete, it will not be necessary for patients to check out.

Implementing this process offers other benefits alongside increased social distancing and decreased contact with staff, company leaders said. It also truncates lobby wait times and can improve the overall patient experience.

Tower Radiology plans to extend the virtual registration capabilities further in the near future by adding a feature that will let patients schedule their radiology exams online at a time that is most convenient for them.

Tampa Bay-based practice launches text and online registration process for maximum social distancing.


Radiology Office Implements Virtual Registration for Greater Patient Safety

Keep an eye open for magnetic false eyelashes – particularly if you’re sending a patient for an MRI.

These cosmetic attachments are popular, but they frequently go overlooked, according to a recent letter to the editor in the 

Journal of Applied Clinical Medical Physics

 It does not matter if the accessories are clamped to the patient’s natural eyelashes or connected to magnetic eyeliner applied to the eyelid, the chances are high that a patient is going to forget to mention them.

And, that can cause problems, researchers said, potentially putting patients at risk.

“Near the MRI scanner, the eyelashes can rapidly become a moving projectile as close as millimeters from the orbit of the eye and hence become a safety concern,” said a team led by Cihat Eldeniz, Ph.D. an MR physicist with the Mallinckrodt Institute of Radiology in St. Louis. “In addition, even if they do not become a direct hazard to the patient, small ferromagnetic objects that get pulled into the MR system can remain there, or lodge within a receiving coil or accessory, potentially resulting in artifacts that may masquerade as pathology.”

Ferromagnetic Detection System Screens Patients Before MRI

Eldeniz’s team reached this determination after conducting deflection tests with six different eyelash brands with a 3T MR scanner. They did not conduct heating and torque testing as doing so would likely have meant the eyelashes would not have stayed attached to the patient.

According to the study’s results, the team identified deflection angles that measured more than 45 degrees, with heavier lashes exhibiting a more projectile effect. These outcomes confirm that magnetic eyelashes are not safe to wear in the MRI scanner. Specifically, they said, patients should take them off before entering Zone 3, the area before he or she would enter the MRI scanner room.

The team also noted that, even though the study was conducted with a 3T scanner, their results indicated the projectile effect could be significant even at 1.5T. In addition, they advised, any magnetic eyeliner should also be removed prior to entering the MRI scanner room to avoid any potential problems or risks.

Radiologists warn this magnetic cosmetic attachment could pose a risk for patients or compromise image quality.

Keep an Eye Out for Magnetic Eyelashes

The U.S. Food & Drug Administration has granted imaging artificial intelligence company Qure.ai its first 510(k) clearance for its emergency room head CT scan product qER.

This move marks the first time the industry has seen a four-in-one clearance. With the FDA’s decision, 

 can be used to triage radiology scans with intracranial bleeds, mass effect, midline shift, and cranial fractures, covering nearly all critical abnormalities seen on routine head CT scans. Two capabilities – cranial features and midline shift – are exclusive to the Qure.ai project, company official said.

With more than 75 million CT scans performed in the United States annually and more than 10,000 people dying within seven days of emergency room discharge, there is a need in the industry for an AI imaging tool that can help providers prioritize and interpret images, said company leaders.

AI Model Uses MRI To Identify Brain Lesions Causing Mass Effect

“Patient outcomes depend directly on the onset-to-treatment time, especially for brain injuries. Every day, doctors are required to weigh the benefits of a potentially life-saving surgery versus the risks of an intracranial bleed or other complication,” said Pooja Rao, co-founder and head of Qure.ai’s research and development. “The sooner they have in-depth information that helps them make that decision, the better for the patient. This is where qER plays a key role.”

According to company information, because time is critical in dealing with many emergency room situations, such as intracranial hemorrhage, the goal is to continue to shorten the 30-minute turnaround time goal that exists for acutely critical conditions. To help reach that aim, the qER suite plugs directly into the radiology workflow, accelerating critical case prioritization.

510(k) clearance applies to four critical abnormalities; two are exclusive to Qure.ai’s product.

Qure.ai Secures 4-in-1 FDA Clearance for AI-Powered CT Imaging

. I’m senior editor Whitney Palmer. We’re back with you this holiday week to bring you some of the highlights of this week’s radiology news.

This week saw a flurry of news about developments with MRI.

 researchers from Germany used 3T MRI scanners to scan the neocortex, the heavily grooved outer layer of the brain that is integral to language, conscious thought, and other functions, for iron levels. Historically, the neocortex has been difficult to impact because its anatomy prompts distortions, signal decay, and artifacts in MRI scans. However, in this study, investigators were able to show, by comparing patients with Alzheimer’s to healthy participants, that iron levels were higher in the whole cortex for patients with Alzheimer’s, revealing the association between high iron levels in the brain and cognitive deterioration independent of the loss of brain volume. Additionally, the researchers said, their findings point to the possibility of using chelators – iron-reducing drugs – as a potential therapy for Alzheimer’s.

 detailed how an existing MRI technique called T1 mapping could potentially be used to whether children have a particularly aggressive type of cancer – neuroblastoma – and whether the treatment is working at an early stage. Though their current research was conducted in mice, investigators from the Institute of Cancer Research in London said their findings could be applied clinically. In the study, the team used T1 mapping MRI scans to map different tumor cell populations and compared them to maps created with artificial intelligence. They discovered areas with high T1 values corresponded to areas with more aggressive cancer cells, and lower T1 value spots were more benign. They also used T1 mapping to determine the efficacy of two neuroblastoma-targeting drugs, alisertib and vistusertib, and they found that when the drugs succeeded, T1 measures dropped. Their hope, they said, is that this technique can be used to both improve treatment for aggressive cancer and limit the medication side effects children experience by minimizing their exposure to drugs that might not be working.

 a team from the University of Maryland, Baltimore County, detailed a new image analysis method called independent vector analysis for common subspace extraction (IVA-CS) that can be used to categorize fMRI data based solely on brain activity. Clinically, it can help providers treating patients with schizophrenia by grouping patients based on their brain imaging alone. Treatment for schizophrenia is not a one-size-fits-all endeavor, so this data, they said, can be used to just whether a treatment is working, potentially leading to a change in therapy is a patient is seeing no improvement. The investigative team has a plan to researcher this method’s efficacy with addiction and substance abuse in adolescents. 

Across the country, academic medical centers and community hospitals are beginning to see a steep spike in their numbers of COVID-19 patients. Consequently, triaging and managing these patients has become an ever-more critical task as resources and personnel begin to stretch thin. One institution in this position is University of Texas Health in San Antonio. Within the past two weeks, the health system has seen a quadruple increase each in their number of diagnosed COVID-19 cases, the number of patients hospitalized, and the number of patients on ventilators. 

 spoke with Dr. Nilam Soni, director of the Point-of-Care Ultrasound Training Program in the South Texas Veterans Health Care System associated with University of Texas Health, about the role this bedside modality has increasingly played in how they are handling this growing patient volume. Here’s what he shared.

Diagnostic Imaging's Weekly Scan: July 3, 2020