Continuous Artery Monitoring Using a Flexible and Wearable Single-Element Ultrasonic Sensor

Steinberg, Shane; Huang, Andy C.; Ono, Yuu; Rajan, Sreeraman

doi:10.1109/mim.2022.9693453

Cited by 12 publications

(4 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Such a system could be paired with portable ultrasound hardware to permit non-traditional users of ultrasound (e.g., paramedics, respiratory therapists, and military personnel) to assess for a life-threatening PTX virtually anywhere. With the maturation of wearable ultrasound devices [ 47 , 48 ], eventual automated and real-time monitoring of PTXs at the bedside is also conceivable.…”

Section: Discussionmentioning

confidence: 99%

Improving the Generalizability and Performance of an Ultrasound Deep Learning Model Using Limited Multicenter Data for Lung Sliding Artifact Identification

Wu,

Smith,

VanBerlo

et al. 2024

Diagnostics

View full text Add to dashboard Cite

Deep learning (DL) models for medical image classification frequently struggle to generalize to data from outside institutions. Additional clinical data are also rarely collected to comprehensively assess and understand model performance amongst subgroups. Following the development of a single-center model to identify the lung sliding artifact on lung ultrasound (LUS), we pursued a validation strategy using external LUS data. As annotated LUS data are relatively scarce—compared to other medical imaging data—we adopted a novel technique to optimize the use of limited external data to improve model generalizability. Externally acquired LUS data from three tertiary care centers, totaling 641 clips from 238 patients, were used to assess the baseline generalizability of our lung sliding model. We then employed our novel Threshold-Aware Accumulative Fine-Tuning (TAAFT) method to fine-tune the baseline model and determine the minimum amount of data required to achieve predefined performance goals. A subgroup analysis was also performed and Grad-CAM++ explanations were examined. The final model was fine-tuned on one-third of the external dataset to achieve 0.917 sensitivity, 0.817 specificity, and 0.920 area under the receiver operator characteristic curve (AUC) on the external validation dataset, exceeding our predefined performance goals. Subgroup analyses identified LUS characteristics that most greatly challenged the model’s performance. Grad-CAM++ saliency maps highlighted clinically relevant regions on M-mode images. We report a multicenter study that exploits limited available external data to improve the generalizability and performance of our lung sliding model while identifying poorly performing subgroups to inform future iterative improvements. This approach may contribute to efficiencies for DL researchers working with smaller quantities of external validation data.

show abstract

Section: Discussionmentioning

confidence: 99%

Improving the Generalizability and Performance of an Ultrasound Deep Learning Model Using Limited Multicenter Data for Lung Sliding Artifact Identification

Wu,

Smith,

VanBerlo

et al. 2024

Diagnostics

View full text Add to dashboard Cite

show abstract

“…To date, the majority of the reported wearable US devices support A-mode, M-mode, and B-mode imaging [8], [18], [69], [81], [106], [111], [122], [123]. Blood flow imaging (e.g., color flow and color power imaging), tissue Doppler, and strain elastography have also been recently demonstrated [106] [111].…”

Section: Imaging Modes and Beamformingmentioning

confidence: 99%

Clinical, Safety, and Engineering Perspectives on Wearable Ultrasound Technology: A Review

Song,

Andre,

Chitnis

et al. 2024

IEEE Trans. Ultrason., Ferroelect., Freq. Contr.

View full text Add to dashboard Cite

Wearable ultrasound has the potential to become a disruptive technology enabling new applications not only in traditional clinical settings, but also in settings where ultrasound is not currently used. Understanding the basic engineering principles and limitations of wearable ultrasound is critical for clinicians, scientists, and engineers to advance potential applications and translate the technology from bench to bedside. Wearable ultrasound devices, especially monitoring devices, have the potential to apply acoustic energy to the body for far longer durations than conventional diagnostic ultrasound systems. Thus, bioeffects associated with prolonged acoustic exposure as well as skin health need to be carefully considered for wearable ultrasound devices. This paper reviews emerging clinical applications, safety considerations, and future engineering and clinical research directions for wearable ultrasound technology.

show abstract

“…Most ultrasonic sensors were made of PVDF film with silver paint electrodes and polyimide (PI) films with silicone glue for electrical insulation, sensor protection, and water resistance. [ 113d,194 ] Despite the fabrication and monitoring of several ultrasound sensors for diverse organs, including muscle thickness, [ 195 ] skeletal muscle, [ 188 ] diabetic foot care, [ 113d ] artery monitoring, [ 196 ] and finger printing. [ 113a ] This particular design exhibited three significant flaws: i) the PI film and silicone adhesive caused internal ultrasound reflections that made it hard to find desired ultrasonic signals near the sensor, ii) the sensor was sensitive to electronic noise because it did not have a way to block out electromagnetic radiation, and iii) the polymers are not suitable to serve as transmitters because of their low electromechanical coupling coefficients, low dielectric constants, and high dielectric losses.…”

Section: Advanced Designs and Technologies For Conformable Ultrasound...mentioning

confidence: 99%

An Emerging Era: Conformable Ultrasound Electronics

Zhang,

Du,

Kim

et al. 2023

Advanced Materials

View full text Add to dashboard Cite

Conformable electronics are regarded as the next generation of personal healthcare monitoring and remote diagnosis devices. In recent years, piezoelectric based conformable ultrasound electronics (cUSE) have been intensively studied due to their unique capabilities, including no‐radiative monitoring, soft tissue imaging, deep signal decoding, wireless power transfer, portability, and compatibility. This review provides a comprehensive understanding of cUSE for use in biomedical and healthcare monitoring systems and a summary of their recent advancements. Following an introduction to the fundamentals of piezoelectrics and ultrasound transducers, the critical parameters for transducer design are discussed. Next, five types of cUSE with their advantages and limitations are highlighted, and the fabrication of cUSE using advanced technologies is discussed. In addition, the working function, acoustic performance, and accomplishments in various applications are thoroughly summarized. We note that application considerations must be given to the tradeoffs between material selection, manufacturing processes, acoustic performance, mechanical integrity, and the entire integrated system. Finally, we highlight current challenges and directions for the development of cUSE, and provide research flow as the roadmap for future research. In conclusion, these advances in the fields of piezoelectric materials, ultrasound transducers, and conformable electronics spark an emerging era of biomedicine and personal healthcare.This article is protected by copyright. All rights reserved

show abstract

Continuous Artery Monitoring Using a Flexible and Wearable Single-Element Ultrasonic Sensor

Cited by 12 publications

References 15 publications

Improving the Generalizability and Performance of an Ultrasound Deep Learning Model Using Limited Multicenter Data for Lung Sliding Artifact Identification

Improving the Generalizability and Performance of an Ultrasound Deep Learning Model Using Limited Multicenter Data for Lung Sliding Artifact Identification

Clinical, Safety, and Engineering Perspectives on Wearable Ultrasound Technology: A Review

An Emerging Era: Conformable Ultrasound Electronics

Contact Info

Product

Resources

About