Image quality evaluation of a portable handheld ultrasound machine for the focused assessment with sonography for trauma examination

Baugher, Katherine M.; Euerle, Brian D.; Sommerkamp, Sarah K.; Witting, Michael D.

doi:10.1016/j.ajem.2013.12.034

Cited by 10 publications

(7 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… 3 Although the image quality was not as high as that generated by the cart-based machines used in hospitals and clinics, it was possible to detect chest and abdominal abnormalities. 4 These deviations in image quality have improved due to breakthroughs in imaging technology, paving the way for more mainstream utilization in the prehospital environment. 5 …”

Section: Introductionmentioning

confidence: 99%

A Novel Point-of-care Ultrasound Curriculum for Air Critical Care Personnel

O’Connor

Beth-Urhoy

Allegra

et al. 2023

WestJEM

View full text Add to dashboard Cite

Introduction: Point-of care-ultrasound (POCUS) has become ubiquitous in emergency medicine practice for the management of emergent pathophysiology. There is growing interest in its potential as a diagnostic tool in the prehospital setting. Few studies have examined the feasibility or efficacy of curricula targeted at teaching POCUS to prehospital personnel. Our objective in this study was to investigate a curriculum for the extended focused assessment with sonography in trauma (eFAST) exam in helicopter emergency medical services (HEMS) crews. Methods: This was a pre/post intervention study of HEMS personnel at a tertiary care center. Subjects were administered a pre-intervention written test and an observed structured clinical evaluation (OSCE). Subsequently, they participated in an educational intervention intended to impart proficiency in performing the eFAST. Subjects underwent post-intervention written exams and OSCEs. We analyzed pre- and post-intervention test performance along with the number and quality of practice ultrasound examinations achieved. Results: Sixteen subjects were enrolled (62.5% male, mean age 44.1). After undergoing the intervention, the mean written test score increased 22.1% (t=3.41; P <0.001) and the mean OSCE score increased by 64.5% (t=6.87, P <0.001). All subjects met “passing” criteria for the written test and OSCE on their post-intervention attempt. Subjects accomplished a mean of 21.1 clinically interpretable eFAST sonographs. Most subjects reported the curriculum was useful (90.1%) and that they would incorporate this skill into clinical practice (90.1%). Conclusion: A targeted POCUS curriculum was feasible and effective in establishing clinical proficiency in HEMS crews for performing and interpreting the eFAST exam.

show abstract

Section: Introductionmentioning

confidence: 99%

A Novel Point-of-care Ultrasound Curriculum for Air Critical Care Personnel

O’Connor

Beth-Urhoy

Allegra

et al. 2023

WestJEM

View full text Add to dashboard Cite

show abstract

“…Recent studies have begun to introduce automatic methods of validating the quality of US imaging. 8,9 Deep learning (DL) approaches to US problems have been increasing rapidly in quantity and quality. 10,11 These applications have focused primarily in the areas of classification or computer-aided diagnosis, regression, tissue segmentation, image registration or content retrieval.…”

mentioning

confidence: 99%

Deep Learning for FAST Quality Assessment

Taye

Morrow

Cull

et al. 2022

J of Ultrasound Medicine

View full text Add to dashboard Cite

Objectives To determine the feasibility of using a deep learning (DL) algorithm to assess the quality of focused assessment with sonography in trauma (FAST) exams. Methods Our dataset consists of 441 FAST exams, classified as good‐quality or poor‐quality, with 3161 videos. We first used convolutional neural networks (CNNs), pretrained on the Imagenet dataset and fine‐tuned on the FAST dataset. Second, we trained a CNN autoencoder to compress FAST images, with a 20–1 compression ratio. The compressed codes were input to a two‐layer classifier network. To train the networks, each video was labeled with the quality of the exam, and the frames were labeled with the quality of the video. For inference, a video was classified as poor‐quality if half the frames were classified as poor‐quality by the network, and an exam was classified as poor‐quality if half the videos were classified as poor‐quality. Results The results with the encoder‐classifier networks were much better than the transfer learning results with CNNs. This was primarily because the Imagenet dataset is not a good match for the ultrasound quality assessment problem. The DL models produced video sensitivities and specificities of 99% and 98% on held‐out test sets. Conclusions Using an autoencoder to compress FAST images is a very effective way to obtain features that can be used to predict exam quality. These features are more suitable than those obtained from CNNs pretrained on Imagenet.

show abstract

“…Previous studies comparing conventional PoCUS workstations to earlier generations of handheld ultrasound had shown that handheld ultrasound may have limited image quality compared to conventional cart-based systems. 7,8 However, more recent handheld ultrasound systems ("third generation handheld ultrasound") have improved frequency ranges and use screen resolution that is comparable, if not superior, to many cart-based systems. Resolution is only one parameter that contributes to subjective image quality; other relevant factors include frame rate, image processing/optimization, and screen size.…”

mentioning

confidence: 99%

The future is in your hands – Handheld ultrasound in the emergency department

Thavanathan

Woo

Hall³

2020

CJEM

View full text Add to dashboard Cite

The Canadian Association of Emergency Physicians (CAEP) Emergency Ultrasound Committee recently recommended that a handheld ultrasound is preferred for point-of-care ultrasound (PoCUS) examinations as part of an infection control strategy to minimize the risk of the transmission of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), the virus that causes coronavirus disease (COVID-19). 1 In recent years, handheld ultrasound devices have become smaller and cheaper, with models recently approved for use in Canada that are available for a fraction of the cost of a typical cart-based PoCUS machine. At this price point, they are within reach of not just hospitals purchasing, but also individual physicians. The COVID-19 pandemic has already forced frontline physicians to make many decisions in the absence of high-quality evidence. Before adopting handheld ultrasound systems, a discussion of the potential strengths and weaknesses is warranted. Handheld ultrasound devices (also known as ultraportable or pocket-sized ultrasound) use an ultrasound transducer connected to a smartphone or tablet. These devices are battery powered, weigh only a few hundred grams, and, as the name implies, are small enough to fit in a pocket or a bag. Typically, a handheld ultrasound is operated with one hand operating the probe ("scanning") and the other hand holding and operating the screen on which the images and controls are displayed, using a cloud-based application. Compatibility with operating systems such as iOS or Android varies by device and manufacturer. Archiving images and clips for every performed PoCUS examination is recommended as best practice, 2 and many handheld ultrasound manufacturers facilitate this with products that can integrate with common archiving systems.

show abstract

Image quality evaluation of a portable handheld ultrasound machine for the focused assessment with sonography for trauma examination

Cited by 10 publications

References 6 publications

A Novel Point-of-care Ultrasound Curriculum for Air Critical Care Personnel

A Novel Point-of-care Ultrasound Curriculum for Air Critical Care Personnel

Deep Learning for FAST Quality Assessment

The future is in your hands – Handheld ultrasound in the emergency department

Contact Info

Product

Resources

About