AI-guided echo helps novice nurses perform ultrasound

 By Emily Hayes, AuntMinnie.com contributing writer

February 19, 2021

Nurses with no training in ultrasound were able to acquire diagnostic-quality echocardiography images thanks to the guidance of an artificial intelligence (AI)-based software application, according to a study published February 18 in JAMA Cardiology.

In the prospective study of 240 patients at academic medical centers, nurses were able to acquire images of high quality using a commercially available software application (Caption Guidance, Caption Health) installed on a portable ultrasound system. Images were judged to be of diagnostic quality on four key endpoints: quality for ventricular size, assessment of left ventricular size and function, right ventricular size and function, and presence of pericardial effusion.

"The ability to provide echocardiography outside the traditional laboratory setting is largely limited by a lack of trained sonographers and cardiologists to acquire and interpret images," Northwestern University cardiologist Dr. James D. Thomas and colleagues noted in their report about the data. "Using this AI-based technology, individuals with no previous training may be able to obtain diagnostic echocardiographic clips of several key cardiac parameters."

The study was conducted for regulatory purposes with the U.S. Food and Drug Administration (FDA). It exceeded the requirements for accuracy and the software was cleared in February 2020 through the agency's de novo pathway for novel products.

Each nurse performed 30 scans with using the guidance software installed on a portable ultrasound scanner (uSmart 3200t Plus, Terason). The mean acquisition time was 30 minutes. Ten standard transthoracic echocardiography views were obtained for each patient.

Separately, scans were conducted by sonographers on the same ultrasound unit but without the AI guidance software. Then the diagnostic quality of the scans was independently evaluated by a panel of five expert echocardiographers.

Still images of standard transthoracic echocardiographic views acquired by a nurse using the deep-learning algorithm were judged to be of diagnostic quality. Image courtesy of Caption Health.

Per the FDA, the software needed to demonstrate diagnostic quality enabling diagnosis in at least 80% of patients on four key outcome measures. The nurses' scans were of diagnostic quality in from 92.5% to 98.8% of patients (see table), with no significant difference compared with scans by sonographers.

"Our study met all FDA-prespecified primary end points, with consistent results across [body mass index] categories and cardiac pathology, including potential distractors, such as pacemakers and prosthetic valves, with little difference between the nurse and sonographer scans," Smith and colleagues wrote.

AI-guided echocardiography, performance by nurses on four key outcome measures
Endpoint	Percent, diagnostic quality
Left ventricular size	98.8%
Global left ventricular function	98.8%
Right ventricular size	92.5%
Nontrivial pericardial effusion	98.8%

Performance of nurses was also on par with sonographers on a range of secondary endpoints. However, performance of sonographers was better than nurses when it came to determining the size of the inferior vena cava (91.5% diagnostic quality compared with 57.4%) and this is a "clear target for further algorithm development," the authors wrote.

The authors also acknowledged that limitations of the study included a relatively small number of patients and nurses and the lack of recruitment from intensive care units and emergency departments.

Smith and colleagues believe the results complement prior research, which has largely focused on the application of AI in medical imaging following the acquisition of images, as opposed to use in guiding image acquisition.

"Improvements in ultrasonography and computer hardware have led to the downsizing and cost reduction of ultrasonography machines, with handheld devices commercially available including standalone transducers interfacing with smart phones," they noted. "The [deep learning] algorithm developed in this study is relatively compact (approximately 1.5 GB) and trained on images from multiple vendors, and it therefore could be ported to work on multiple platforms."

CHÚC MỪNG NĂM MỚI

 

USPSTF advises against carotid artery stenosis screening

 By Kate Madden Yee, AuntMinnie.com staff writer

February 2, 2021 -- The U.S. Preventive Services Task Force (USPSTF) is advising against screening for asymptomatic carotid artery stenosis in the general adult population in a final recommendation statementpublished February 2 in JAMA.

The recommendation is consistent with the task force's 2014 statement, which graded carotid artery stenosis screening a D. The reason for the low grade is that the harms of carotid artery screening outweigh the benefits, according to USPSTF member Dr. Michael Barry of Massachusetts General Hospital in Boston.

"The Task Force wants to help prevent people from having a stroke, but screening for coronary artery stenosis is not an effective way to do so," he said in a USPSTF statement. "Unfortunately, screening for coronary artery stenosis in adults without symptoms does more harm than good, and we continue to recommend against it."

Carotid artery stenosis affects extracranial carotid arteries, and asymptomatic carotid artery stenosis refers to stenosis in persons without a history of ischemic stroke, transient ischemic attack, or other neurologic symptoms referable to the carotid arteries, the task force wrote in the JAMA article. Screening for the disease is accomplished through a variety of imaging modalities, including carotid duplex ultrasonography, MRI angiography, and CT angiography.

But these screening exams just aren't effective, according to the task force.

"The USPSTF found no externally validated risk stratification tools that could reliably distinguish between asymptomatic persons who have clinically important carotid artery stenosis and persons who do not, or the risk of stroke related to carotid artery stenosis," it wrote.

In an editorial also published in JAMA on February 2, Dr. Larry Goldstein, a neurologist at the University of Kentucky in Lexington, lauded the USPSTF's position.

"The estimated population-attributable risk for stroke related to asymptomatic carotid artery stenosis is approximately 0.7%, a risk considerably lower than for other stroke risk factors such as hypertension, atrial fibrillation, cigarette smoking, and hyperlipidemia," Goldstein wrote. "There remains no validated risk stratification tool for identifying a subpopulation of adults with a prevalence of asymptomatic carotid artery stenosis with a higher population-attributable risk that would lead to a benefit of intervention beyond risk factor management.'

Others pushed back, suggesting that the task force did not include evidence of the benefits of screening in its evaluation process -- or consideration of risk factors that occur in almost a third of U.S. adults, such as high blood pressure, hyperlipidemia, diabetes, smoking, limited physical activity, and poor diet.

"Without a true randomized clinical trial to directly answer the question, there is a lack of consensus and clarity on the role of carotid ultrasonographic screening for prevention of stroke in individuals who are asymptomatic," wrote Dr. Rebecca Smith-Bindman of the University of California, San Francisco in a JAMA Network Open editorial. "Nearly all of the specialty societies actually agree with the USPSTF and recommend against screening with carotid ultrasonography. However, these strong statements against screenings are all followed by the list of exceptions of individuals who, based on risk factors or characteristics, should in fact be screened."

Philips debuts ultrasound tools for AAA

By AuntMinnie.com staff writers

January 27, 2021 -- Philips Healthcare parent Royal Philips has introduced 3D ultrasound-based technology to monitor abdominal aortic aneurysms (AAAs)

The company's AAA model is designed to assist clinicians by providing key measurements, including the partial volume and centerline of aneurysms.

The AAA model has received the CE Mark in Europe, and the U.S. Food and Drug Administration has cleared it for sale in the U.S. The model is making its debut at the virtual Leipzig Interventional Course (LINC), which is currently underway.

The AAA model provides measurements including the maximum anterior-to-posterior diameter and partial volume of the aneurysm, while also indicating the centerline. Image courtesy of Philips Healthcare

Seno gets FDA nod for breast optoacoustic ultrasound

By AuntMinnie.com staff writers

January 19, 2021 -- Optoacoustic imaging firm Seno Medical Instruments has garnered U.S. Food and Drug Administration (FDA) premarket approval (PMA) for its Imagio breast imaging optoacoustic ultrasound system.

Designed to help providers characterize and differentiate breast masses in real-time, Imagio combines laser optics and grayscale ultrasound to provide fused functional and anatomical breast imaging, according to the vendor. These optoacoustic images provide a blood map in and around breast masses, while the ultrasound technology yields a traditional anatomic image, Seno said. The company believes that Imagio could help to reduce the number of unnecessary diagnostic breast biopsies.

Imagio also comes with SenoGram, an artificial intelligence (AI)-based decision-support tool for aiding radiologists in interpreting the new images and helping them in transitioning from ultrasound alone to optoacoustic ultrasound imaging, the firm said.

Ultrasound shows lymph node changes after COVID-19 vaccine

By Theresa Pablos, AuntMinnie staff writer

January 22, 2021 -- Breast ultrasound was used to demonstrate signs of lymph node enlargement in four cases of patients who received the COVID-19 vaccine. Radiologists from NewYork-Presbyterian published the case studies on January 18 in Clinical Imaging.

The case studies involve women in their 40s and 50s who presented to the radiology department for breast imaging within two weeks of receiving a Pfizer-BioNTech or Moderna COVID-19 vaccine. Breast ultrasound showed the women had at least one enlarged lymph node. In all cases, the authors recommended follow-up imaging at a later time.

"With widespread rollout of the COVID-19 vaccine, it is prudent for radiologists to consider vaccine-induced hyperplastic adenopathy as an etiology of unilateral axillary adenopathy seen on breast imaging," wrote the authors, led by Dr. Nishi Mehta, a radiology fellow at NewYork-Presbyterian/Weill Cornell Medical Center.

Axillary adenopathy can be a sign of breast cancer. But it can also result from a number of benign causes, including local infection, inflammation, or trauma in the breast, thoracic wall, or nearby arm.

Vaccines are one reported benign cause of one-sided axillary adenopathy, and the symptom has been documented after vaccination for smallpox, bacillus Calmette-Guerin (tuberculosis), and anthrax. It appears more often in vaccines that evoke a very strong immune response.

As reported in the study, axillary adenopathy can occur after vaccination with the Pfizer-BioNTech and Moderna COVID-19 vaccines. The U.S. Centers for Disease Control and Prevention (CDC) lists axillary adenopathy as one of the most frequently reported adverse reactions to the Moderna COVID-19 vaccine. The CDC also noted more adenopathy cases occurred in patients who received the Pfizer-BioNTech vaccine than a placebo.

Ultrasound images of a 59-year-old patient who found a palpable lump nine days after receiving the first dose of the Pfizer-BioNTech vaccine in her left arm. (a) Gray-scale and (b) color Doppler images of an enlarged left axillary lymph node. (c) Normal right axillary lymph node. All images courtesy of Dr. Nishi Mehta / Clinical Imaging.

This appeared to be the case for four women who presented for breast imaging at NewYork-Presbyterian. The patients had no preexisting conditions and were all frontline workers who qualified for the first round of Moderna or Pfizer-BioNTech vaccines.

In one case, a 59-year-old woman with no personal history of breast cancer came to the department after finding a palpable lump near her left armpit. Her mammogram was unremarkable, but targeted sonography showed her left axillary lymph node had uniform cortical thickening of 0.7 cm in an area corresponding to the patient's concern.

When asked about her history, the patient said she had recently received the Pfizer-BioNTech COVID-19 vaccine and noticed the lump nine days after receiving her first vaccine dose.

Ultrasound images of a 42-year-old patient who presented for sonographic follow-up of probably benign bilateral breast masses. The patient had received the first dose of the Moderna vaccine in her left arm 13 days prior to imaging. (a) Gray-scale and (b) color Doppler images of an enlarged left axillary lymph node. (c) Unremarkable right axilla.

The authors reported similar findings in two women who presented for routine breast ultrasound screening, as well as one woman who underwent ultrasound follow-up of probably benign bilateral breast masses. All three of these women had diffuse cortical thickening in at least one axillary lymph node within 13 days of receiving a first or second vaccine dose.

In all four cases, the authors recommended follow-up imaging with targeted ultrasound. NewYork-Presbyterian is currently recommending clinicians delay follow-up ultrasound imaging until four to 12 weeks after patients receive their second COVID-19 vaccine dose. If the adenopathy still persists at this time, then the authors would recommend biopsy to rule out cancer.

While the report focused on breast imaging, Mehta said breast imagers aren't the only types of radiologists who may come across axillary adenopathy.

"Thoracic imagers will likely see similar findings of unilateral axillary adenopathy and cervical adenopathy on chest imaging studies and should therefore be similarly aware of the diagnosis," she told AuntMinnie.com.

Axillary adenopathy may also be seen on mammography, noted Mehta. Axillary adenopathy after vaccination has also been documented as increased FDG uptake on PET and CT, she added.

"We expect similar findings post COVID-19 vaccination," she said.

POCUS group launches MSK certification

 By AuntMinnie.com staff writers

January 18, 2021 -- The Point-of-Care Ultrasound (POCUS) Certification Academy has launched a new certification program for healthcare providers that use ultrasound in the provision of physical therapy and other disciplines

The academy's POCUS Musculoskeletal (MSK) Certification supports a new measure of proficiency with POCUS that raises the standard of musculoskeletal imaging by testing on best practices of clinical applications.

The certification is designed to support professionals in the fields of physical therapy, physiatry, athletic training, sports medicine, and orthopedics, among others.

Thyroid cancer screening hits the right note

By Theresa Pablos, AuntMinnie staff writer

January 14, 2021

The ultrasound technique works because singing causes the elasticity of surrounding tissues to increase, making it easier for clinicians to pinpoint abnormally stiff areas. Singing during thyroid ultrasonography also has the potential to identify more thyroid tumors while simultaneously putting patients at ease.

"Developing noninvasive methods would reduce the stress of patients during their medical exams," stated lead author Steve Beuve, a doctoral student specializing in medical imaging at University of Tours, in a press release. "Having to sing during a medical exam can perhaps help release some of the nervous tension even more."

The authors called their new technique vocal passive elastography. The method was inspired by passive elastography, which detects changes in elasticity from natural vibrations caused by blood pulsing, heart rhythms, and other natural biological changes.

During vocal passive elastography, a clinician places a linear ultrasound probe at the front of a patient's neck. The patient then sings and maintains the "eee" tone, trying to match their tone to a 150-Hz sound playing from a speaker.

The singing vibrates the patient's trachea, which in turn produces vibrations throughout the thyroid. This allows the clinician to use an ultrafast frame rate to track changes in shear-wave velocity.

"The propagation of shear waves gives us information about mechanical properties of soft tissues," Beuve stated.

For their experiment, the team validated the concept by calculating shear-wave elastography (SWE) measurements as patients sang, then superimposing a map of that data onto B-mode ultrasound images. They created their own algorithm to reconstruct the raw image data and tested their algorithm on two different ultrasound systems.

The vocal passive elastography method succeeded in identifying particle tissue displacement induced by singing on both systems. The values also aligned well with SWE metrics, although the measurements were more similar on the left (thinner) side of the thyroid than on the right (thicker) side.

Left: A volunteer holds a linear ultrasound probe to help prove the feasibility of vocal passive elastography. Right: 2D shear wave speed as calculated by the new technique mapped onto an anatomical brightness mode ultrasound image. Image courtesy of Steve Beuve.

Overall, vocal passive elastography looked like a promising alternative to fine-needle aspiration biopsy, which misses up to 95% of thyroid cancers, according to the authors. It also drastically improved the thyroid signal-to-noise ratio by drowning out natural background noise from nearby organs.

The researchers are already conducting new experiments to further refine the technique, including investigating the benefits of asking patients to match different bandwidths. They are also interested in expanding the use of vocal passive elastography to areas outside of the vocal tract, such as the brain.

"We want to cooperate with physicians to propose protocols to verify the relevance of elasticity as a biomarker of pathogens," Beuve stated