2022 IEEE International Ultrasonics Symposium (IUS)最新文献

Segmentation of 2D cardiac ultrasound with deep learning: simpler models for a simple task 基于深度学习的二维心脏超声分割:简单任务的简单模型

2022 IEEE International Ultrasonics Symposium (IUS) Pub Date : 2022-10-10 DOI: 10.1109/IUS54386.2022.9957618

Artem Chernyshov, Andreas Østvik, E. Smistad, L. Løvstakken

{"title":"Segmentation of 2D cardiac ultrasound with deep learning: simpler models for a simple task","authors":"Artem Chernyshov, Andreas Østvik, E. Smistad, L. Løvstakken","doi":"10.1109/IUS54386.2022.9957618","DOIUrl":"https://doi.org/10.1109/IUS54386.2022.9957618","url":null,"abstract":"Low-complexity convolutional neural networks have been shown to be sufficient for segmentation of cardiac US images in A2C and A4C views. The performance of 24 varying-complexity implementations of U-Net and DeepLabV3+ (popular segmentation architectures) has been tested on cardiac US data (CAMUS data set) and street view data (Cityscapes data set). The inference speed of the models has also been measured before and after post-training optimization. The models systematically differed in their structural components: the number of layers and convolutional filters as well as the receptive field size. All models trained to maximize the Dice Coefficient. The Dice Coefficient was consistently high (0.86-0.90) on CA-MUS data and low (0.48-0.67) on Cityscapes data for all models. Each ten-fold reduction in the number of model parameters tended to reduce the score by ≈0.01 on CAMUS and by 0.03-0.05 on Cityscapes. Likewise, low-parameter models, especially the ones based on U-Net, had yielded predictions with higher (worse) Hausdorff Distance values. Increasing the receptive field size of the models partially mitigated this effect. Without post-training optimization, the inference speed mostly varied with the number of layers in the networks. The least complex U-Net model was 83% faster than the most complex one; for the DeepLab models the difference was 53%. With post-training optimization, any reduction in the number of parameters led to increased speed: up to more than 700% for both architecture types.","PeriodicalId":272387,"journal":{"name":"2022 IEEE International Ultrasonics Symposium (IUS)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115377264","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Reconstructing human cerebral vasculature in 3D with high frame rate, freehand 2D Doppler ultrasound using optical tracking 利用光学跟踪技术进行高帧率、徒手二维多普勒超声三维重建人体脑血管系统

2022 IEEE International Ultrasonics Symposium (IUS) Pub Date : 2022-10-10 DOI: 10.1109/IUS54386.2022.9958165

Luuk Verhoef, S. Soloukey, F. Mastik, B. Generowicz, A. Vincent, E. Bos, J. Schouten, C. Dirven, C. D. De Zeeuw, S. Koekkoek, S. Klein, P. Kruizinga

引用次数: 0

Row-Multiplexed 1,024 Element Large Aperture Array for Electronic Scanning in Elevation 用于高程电子扫描的行复用1024元大孔径阵列

2022 IEEE International Ultrasonics Symposium (IUS) Pub Date : 2022-10-10 DOI: 10.1109/IUS54386.2022.9958124

R. Wodnicki, Hanna Bendjador, Haochen Kang, J. Foiret, C. Notard, Qifa Zhou, K. Ferrara

{"title":"Row-Multiplexed 1,024 Element Large Aperture Array for Electronic Scanning in Elevation","authors":"R. Wodnicki, Hanna Bendjador, Haochen Kang, J. Foiret, C. Notard, Qifa Zhou, K. Ferrara","doi":"10.1109/IUS54386.2022.9958124","DOIUrl":"https://doi.org/10.1109/IUS54386.2022.9958124","url":null,"abstract":"We have been developing highly-integrated and modular large aperture multi-row 1.75D linear arrays interfaced to a configurable ultrasound system (Verasonics Vantage 32LE) using custom ASIC multiplexing electronics with the goal to improve detection of liver cancer deep in the body. The array consists of multiple rows which are capable of multiplexing an aperture in elevation for realization of synthetic focusing and imaging in both azimuthal and elevational planes. The large array addresses 1,024 acoustic elements $(boldsymbol{42} mathbf{mm} times boldsymbol{16} mathbf{mm}$ aperture with $boldsymbol{650}mu mathbf{m} mathbf{azi}. times boldsymbol{1000 mu} mathbf{m}$ elev. element pitch) with 64 elements in azimuth and 16 rows in elevation. Each of the columns are interfaced directly to a single respective imaging system channel. Rows are selected using commands sent to a local FPGA which controls the ASICs during imaging. Beamforming for individual rows in azimuth is accomplished by the configurable imaging system using plane wave imaging in azimuth and either SRA or STRA synthetic aperture imaging performed to create images in the elevation dimension. Imaging in elevation was performed at Fc $boldsymbol{=2.5}$ MHz and achieved 1.3 mm and 0.8 mm resolution at a depth of 20 mm for SRA and STRA modes respectively. We are currently integrating the probe acoustic array and electronics into a handheld form factor for future use in human imaging.","PeriodicalId":272387,"journal":{"name":"2022 IEEE International Ultrasonics Symposium (IUS)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117143865","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Ultra-Low-Voltage High-Efficiency CMUTs with Piston-Structured Plates for Fill Level Sensing 具有活塞结构板的超低电压高效CMUTs用于填充液位传感

2022 IEEE International Ultrasonics Symposium (IUS) Pub Date : 2022-10-10 DOI: 10.1109/IUS54386.2022.9957501

Fabian Merbeler, Sonja Wismath, M. Haubold, Christian Bretthauer, M. Kupnik

{"title":"Ultra-Low-Voltage High-Efficiency CMUTs with Piston-Structured Plates for Fill Level Sensing","authors":"Fabian Merbeler, Sonja Wismath, M. Haubold, Christian Bretthauer, M. Kupnik","doi":"10.1109/IUS54386.2022.9957501","DOIUrl":"https://doi.org/10.1109/IUS54386.2022.9957501","url":null,"abstract":"Capacitive micromachined ultrasonic transducers (CMUTs) provide manifold advantages over ultrasound transducers based on piezo-electric materials. However, a limited output pressure and a high voltage requirement are still drawbacks to address. We present a CMUT design with small geometrical measures for plate thickness, gap and insulation layer, in order to ensure low-voltage operation < 10 V. Three designs allow studying the bare piston effects for identical plate diameter. The piston-like deflection intends to overcome low output pressures. Moreover, we present an acoustic coupling approach to demonstrate through-wall fill level sensing through a conductive material. Displacement measurements in air via vibrometer are utilized to validate FEM simulations for the designs. The pull-in voltage is determined for the operational point for acoustic characterization in immersion as well as fill level sensing application. The piston design reveals an emitted surface sound pressure of 0.5 MPa and a transmit sensitivity of 24.8 kPa/V - an improvement over the bare plate design by a factor of 11.2 in sound pressure as well as 3.35 for transmit sensitivity, for a 100-ns-pulse with 80% of the pull-in voltage. With acoustic impedance matching via a silicone film stacked with epoxy material, we can improve the transmission into aluminum from 20% to 35%. By that, fill level measurements for 2.3 mm of water up to 610 mm through 4-mm-thick aluminum are demonstrated. The capabilities of an advanced CMUT design for applications other than medical imaging are shown, opening the field for diverse industrial and consumer applications of CMUTs.","PeriodicalId":272387,"journal":{"name":"2022 IEEE International Ultrasonics Symposium (IUS)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117266010","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Accurate Location of Key Features in Ultrasonic-based Spot Weld Inspection 超声点焊检测关键特征的精确定位

2022 IEEE International Ultrasonics Symposium (IUS) Pub Date : 2022-10-10 DOI: 10.1109/IUS54386.2022.9958162

A. Baradarani, A. Denisov, R. Maev

{"title":"Accurate Location of Key Features in Ultrasonic-based Spot Weld Inspection","authors":"A. Baradarani, A. Denisov, R. Maev","doi":"10.1109/IUS54386.2022.9958162","DOIUrl":"https://doi.org/10.1109/IUS54386.2022.9958162","url":null,"abstract":"Ultrasonic-based non-destructive spot weld inspection techniques heavily rely on advanced signal processing al-gorithms developed for this particular application. RSWA-F1® [1] and RSWA-F2® [2] are two portable ultrasonic devices from Tessoni® designed and manufactured for the use in automotive industry to evaluate the quality of resistance spot welds. Both the RSWA-F1® and RSWA-F2® employ the multi-channel matrix transducer technology to collect and analyze data from the surface and internal structures of the weld. The original signal processing algorithm used in the first generation of the RSWA was based on detecting the amplitude of internal reflection between welded metal plates. The second generation on the other hand incorporated the secondary echo detection analysis because the amplitudes of internal reflections were often small compared to noise. In this paper, we briefly introduce a new technique that a further developed version of it may be used in the third generation of the RSWAs to extract accurate location of key features more efficiently. High degree of accuracy is obtained for the correct location of the key characteristics, e.g., the delay line, surface pulse, first echo, backwall and potential defects inside the weld nugget.","PeriodicalId":272387,"journal":{"name":"2022 IEEE International Ultrasonics Symposium (IUS)","volume":"EM-32 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121004373","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Changes in quantitative ultrasound imaging as the predictor of response to neoadjuvant chemotherapy in patients with breast cancer 定量超声成像变化作为乳腺癌患者对新辅助化疗反应的预测因子

2022 IEEE International Ultrasonics Symposium (IUS) Pub Date : 2022-10-10 DOI: 10.1109/IUS54386.2022.9957940

H. Piotrzkowska-Wróblewska, K. Dobruch-Sobczak, M. Gumowska, J. Litniewski

引用次数: 1

Contactless Positioning of Objects on Acoustically Reflective Surfaces by Means of Ultrasonic Forces 利用超声力对声反射表面上物体的非接触定位

2022 IEEE International Ultrasonics Symposium (IUS) Pub Date : 2022-10-10 DOI: 10.1109/IUS54386.2022.9957627

Marc Röthlisberger, Timo Wilhelm, M. Schuck, J. Kolar

引用次数: 0

A Lithium Niobate MEMS-coupled Matching Network for BFSK Modulated Signal Amplification in Spectrum Monitoring Applications 用于频谱监测中BFSK调制信号放大的铌酸锂mems耦合匹配网络

2022 IEEE International Ultrasonics Symposium (IUS) Pub Date : 2022-10-10 DOI: 10.1109/IUS54386.2022.9958508

L. Colombo, E. Guerrero, Nicolas Casilli, Gabriel Giribaldi, Bernard Herrera-Soukup, P. de Paco, M. Rinaldi

引用次数: 0

Characterization of Nonlinear Elasticity of the Carotid Artery Using Pulse Wave Imaging: a Feasibility Study in Hypertensive and Carotid Artery Disease Patients in Vivo 用脉冲波成像表征颈动脉非线性弹性:高血压和颈动脉疾病患者体内可行性研究

2022 IEEE International Ultrasonics Symposium (IUS) Pub Date : 2022-10-10 DOI: 10.1109/IUS54386.2022.9957838

Parth Gami, Paul Kemper, Grigorios M. Karageorgos, Timothy R. Swingle, Rachel Webber, E. Konofagou

{"title":"Characterization of Nonlinear Elasticity of the Carotid Artery Using Pulse Wave Imaging: a Feasibility Study in Hypertensive and Carotid Artery Disease Patients in Vivo","authors":"Parth Gami, Paul Kemper, Grigorios M. Karageorgos, Timothy R. Swingle, Rachel Webber, E. Konofagou","doi":"10.1109/IUS54386.2022.9957838","DOIUrl":"https://doi.org/10.1109/IUS54386.2022.9957838","url":null,"abstract":"The vascular walls of the carotid artery, as a result of its elastin and collagen content, possess nonlinear elastic behavior. As an individual ages or develops diseases such as hypertension or carotid artery disease, elastin starts to degrade and fragment, resulting in a stiffer vessel. Early identification of vascular remodeling could provide useful information for the diagnosis and treatment of cardiovascular disease. Using Pulse Wave Imaging (PWI), it is possible to estimate the pulse wave velocity (PWV) at two distinct pressure points in the cardiac cycle, end-diastole (ED) and end-systole (ES). The objective of this preliminary study was to investigate the nonlinear elastic behavior of the carotid artery in patients with hypertension (N=11) (HTN) and subjects with both hypertension and mild carotid artery stenosis (N=11)(<40%) in vivo. No significant difference was found for $PWV_{ED}$ between HTN (5.59 ± 1.42 m/s) and <40% (5.45 ± 2.04 m/s) groups (p=.86). $PWV_{ES}$ was increased in the 40% group (9.92 ± 2.50 m/s) compared to the HTN group (8.68 ± 2.98 m/s) (p=.30). The absolute percent difference between $PWV_{ED}$ and $PWV_{ES}, PWV_{Delta %}$, was higher in the <40% (96.7 ± 66.9 %) subjects compared to HTN (73.0 ± 61.3 %) (p=.39). The increase in $PWV_{ES}$ and $PWV_{Delta %}$ between <40% stenosis and HTN groups may demonstrate changes in the vascular composition and the overall nonlinear mechanical behavior of the carotid artery.","PeriodicalId":272387,"journal":{"name":"2022 IEEE International Ultrasonics Symposium (IUS)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126149287","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Deep Learning-based Virtual Refocusing of Out-of-Plane Images for Ultrasound Computed Tomography 基于深度学习的超声计算机断层扫描面外图像虚拟重聚焦

2022 IEEE International Ultrasonics Symposium (IUS) Pub Date : 2022-10-10 DOI: 10.1109/IUS54386.2022.9957222

Zhaohui Liu, Xinan Zhu, Jiameng Wang, Shanshan Wang, Mingyue Ding, M. Yuchi

{"title":"Deep Learning-based Virtual Refocusing of Out-of-Plane Images for Ultrasound Computed Tomography","authors":"Zhaohui Liu, Xinan Zhu, Jiameng Wang, Shanshan Wang, Mingyue Ding, M. Yuchi","doi":"10.1109/IUS54386.2022.9957222","DOIUrl":"https://doi.org/10.1109/IUS54386.2022.9957222","url":null,"abstract":"Ultrasound computed tomography (USCT) has attracted increasing attention for the potential to quantify the acoustic properties of tissues. The three-dimensional (3D) image can be reconstructed by stacking a group of cross-sectional USCT images with sub-millimeter isotropic spatial resolution. However, the interval of the slice images is set in millimeter-scale with a trade-off of imaging speed and axial resolution, resulting in a loss of axial information and a deviation in volumetric measurements. This paper demonstrates a framework based on a deep neural network to virtually refocus a two-dimensional USCT image onto the user-defined 3D surfaces without relying on any additional axial scanning, increasing the number of slice images by 40 times. In the training stage, an input image is appended with a distance matrix (DM) that represents the distance of the target plane from the plane of input image along the axial direction, each image is refocused to a series of planes ranging from -5mm to 5mm with a step size of 0.25mm, that is, 20 planes above and 20 planes below, thus forming around 16000 image pairs. The residual U-Net learns to refocus an input image appended with a DM to a user-define plane. Once the training is complete, a virtual 3D image stack can be generated when provided with a single image appended with a series of DMs. The proposed framework can virtually refocus a single image to multiple user-define planes represented by different DMs, enabling the USCT 3D imaging with sub-millimeter slice intervals.","PeriodicalId":272387,"journal":{"name":"2022 IEEE International Ultrasonics Symposium (IUS)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125329623","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0