IEEE transactions on ultrasonics, ferroelectrics, and frequency control最新文献

筛选
英文 中文
Super-Resolution Ultrasound: From Data Acquisition and Motion Correction to Localization, Tracking, and Evaluation.
IF 3 2区 工程技术
IEEE transactions on ultrasonics, ferroelectrics, and frequency control Pub Date : 2025-02-25 DOI: 10.1109/TUFFC.2025.3543322
Stefanie Dencks, Matthew Lowerison, Joseph Hansen-Shearer, YiRang Shin, Georg Schmitz, Pengfei Song, Meng-Xing Tang
{"title":"Super-Resolution Ultrasound: From Data Acquisition and Motion Correction to Localization, Tracking, and Evaluation.","authors":"Stefanie Dencks, Matthew Lowerison, Joseph Hansen-Shearer, YiRang Shin, Georg Schmitz, Pengfei Song, Meng-Xing Tang","doi":"10.1109/TUFFC.2025.3543322","DOIUrl":"https://doi.org/10.1109/TUFFC.2025.3543322","url":null,"abstract":"<p><p>Super-resolution ultrasound (SRUS) imaging through localizing and tracking microbubbles, also known as ultrasound localization microscopy (ULM), has achieved unprecedented resolution in deep tissue in vivo. In this review we will focus on the key technical steps of ULM, including data acquisition and tissue clutter removal, motion correction, localization, tracking, and final image visualization, as well as offering the authors' perspectives of the techniques. In each of the technical steps, we review what has been done and the state of the art, describe the key factors and parameters that influence each step, existing issues, and considerations when choosing the parameters. Finally, methods for evaluation of ULM image quality with or without ground truth are also reviewed.</p>","PeriodicalId":13322,"journal":{"name":"IEEE transactions on ultrasonics, ferroelectrics, and frequency control","volume":"PP ","pages":""},"PeriodicalIF":3.0,"publicationDate":"2025-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143541854","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Tissue Clutter Filtering Methods in Ultrasound Localization Microscopy Based on Complex-valued Networks and Knowledge Distillation.
IF 3 2区 工程技术
IEEE transactions on ultrasonics, ferroelectrics, and frequency control Pub Date : 2025-02-24 DOI: 10.1109/TUFFC.2025.3544692
Wenzhao Han, Wenjun Zhou, Lijie Huang, Jianwen Luo, Bo Peng
{"title":"Tissue Clutter Filtering Methods in Ultrasound Localization Microscopy Based on Complex-valued Networks and Knowledge Distillation.","authors":"Wenzhao Han, Wenjun Zhou, Lijie Huang, Jianwen Luo, Bo Peng","doi":"10.1109/TUFFC.2025.3544692","DOIUrl":"https://doi.org/10.1109/TUFFC.2025.3544692","url":null,"abstract":"<p><p>Ultrasound Localization Microscopy (ULM) is a blood flow imaging technique that utilizes micron-sized microbubbles (MBs) as contrast agents to achieve high-resolution microvessel reconstruction through precise localization and tracking of MBs. The accuracy of MB localization is critical for producing high-quality images, which makes tissue clutter filtering an essential step in ULM. Recent advances in deep learning have led to innovative methods for tissue clutter filtering, particularly those based on 3D convolution, which effectively capture the spatiotemporal features of MBs. These methods significantly improve upon traditional approaches by addressing issues such as lengthy inference time and limited flexibility. However, many deep learning techniques primarily focus on B-mode images and demonstrate lower efficiency. To overcome these limitations, this study proposes knowledge distillation for tissue clutter filtering to enhance filtering efficiency while maintaining performance. This study first develops a lightweight 2D complex-valued CNN (CL-UNet) as the teacher model, utilizing I/Q signal input. Subsequently, a 2D real-valued CNN (UNet-T) is developed as the student model, which uses envelope data as input. Feature-based knowledge distillation is applied to transfer knowledge from the teacher model to the student model (Guided UNet-T). All models are trained on simulated data and fine-tuned on in vivo data. The experimental results show that CL-UNet (I/Q, ours) demonstrates better filtering performance compared to the B-mode image-based approach on both simulated and in vivo data. Guided UNet-T outperforms both Singular Value Decomposition (SVD) and Random SVD (RSVD) in terms of both performance and speed, offering the best balance between filtering efficiency and effectiveness.</p>","PeriodicalId":13322,"journal":{"name":"IEEE transactions on ultrasonics, ferroelectrics, and frequency control","volume":"PP ","pages":""},"PeriodicalIF":3.0,"publicationDate":"2025-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143541858","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Study on Loss mechanisms in SAW Resonators Using 42-LT Thin Plate by Full-3D FEM with Hierarchical Cascading Technique.
IF 3 2区 工程技术
IEEE transactions on ultrasonics, ferroelectrics, and frequency control Pub Date : 2025-02-19 DOI: 10.1109/TUFFC.2025.3543541
Yiming Liu, Yiwen He, Zijiang Yang, Fangyi Li, Jingfu Bao, Ken-Ya Hashimoto
{"title":"Study on Loss mechanisms in SAW Resonators Using 42-LT Thin Plate by Full-3D FEM with Hierarchical Cascading Technique.","authors":"Yiming Liu, Yiwen He, Zijiang Yang, Fangyi Li, Jingfu Bao, Ken-Ya Hashimoto","doi":"10.1109/TUFFC.2025.3543541","DOIUrl":"https://doi.org/10.1109/TUFFC.2025.3543541","url":null,"abstract":"<p><p>This paper describes study of loss mechanisms in an incredible high performance surface acoustic wave (I.H.P. SAW) resonator on the 42°YX-LiTaO<sub>3</sub>/SiO<sub>2</sub>/Si structure. The full three-dimensional (3D) finite element method (FEM) is applied with the assistance of the hierarchical cascading technique. Excellent agreement is obtained between calculation and measurement not only for the effective electromechanical coupling factor k<sub>eff</sub><sup>2</sup> but also the Bode Q without inclusion of empirical loss mechanisms. Behavior of calculated Bode Q is mostly governed by the number of IDT finger pairs N<sub>I</sub> and aperture length W. SAW field distribution is derived from the FEM result. Oblique SAW leakage is observed in the busbar region of reflectors and becomes negligible when N<sub>I</sub> is large. From this, it is concluded that the Bode Q reduction discussed here is mainly occurred by the oblique SAW leakage caused by the in-plane diffraction. Finally, the mBVD model is applied for quantitative characterization. It is shown that the in-plane SAW diffraction can be modelled well by the mBVD model and gives significant impact only to the anti-resonance Q. Surprisingly its loss is dominant even when N<sub>I</sub>=100.</p>","PeriodicalId":13322,"journal":{"name":"IEEE transactions on ultrasonics, ferroelectrics, and frequency control","volume":"PP ","pages":""},"PeriodicalIF":3.0,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143556750","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
xDDx: a Numerical Toolbox for Ultrasound Transducer Characterization and Design with Acoustic Holography.
IF 3 2区 工程技术
IEEE transactions on ultrasonics, ferroelectrics, and frequency control Pub Date : 2025-02-14 DOI: 10.1109/TUFFC.2025.3542405
Pavel B Rosnitskiy, Oleg A Sapozhnikov, Vera A Khokhlova, Wayne Kreider, Sergey A Tsysar, Gilles P L Thomas, Kaizer Contreras, Tatiana D Khokhlova
{"title":"xDDx: a Numerical Toolbox for Ultrasound Transducer Characterization and Design with Acoustic Holography.","authors":"Pavel B Rosnitskiy, Oleg A Sapozhnikov, Vera A Khokhlova, Wayne Kreider, Sergey A Tsysar, Gilles P L Thomas, Kaizer Contreras, Tatiana D Khokhlova","doi":"10.1109/TUFFC.2025.3542405","DOIUrl":"10.1109/TUFFC.2025.3542405","url":null,"abstract":"<p><p>Transient acoustic holography is a useful technique for characterization of ultrasound transducers. It involves hydrophone measurements of the 2-D distribution of acoustic pressure waveforms in a transverse plane in front of the transducer - a hologram - and subsequent numerical forward or backward projection of the ultrasound field. This approach enables full spatiotemporal reconstruction of the acoustic field, including the vibrational velocity at the transducer surface. This allows identification of transducer defects as well as structural details of the radiated acoustic field such as side lobes and hot spots. However, numerical projections may be time-consuming (1010 - 1011 operations with complex exponents). Moreover, back-projection from the measurement plane to the transducer surface is sensitive to misalignment between the axes of the positioning system and the axes associated with the transducer. This paper presents an open access transducer characterization toolbox for use in MATLAB or Octave on Windows computers (https://github.com/pavrosni/xDDx/releases). The core algorithm is based on the Rayleigh integral implemented in C++ executables for graphics and central processing units (GPUs and CPUs). The toolbox includes an automated procedure for correcting axes misalignments to optimize the visualization of transducer surface vibrations. Beyond using measured holograms, the toolbox can also simulate the fields radiated by user-defined transducers. Measurements from two focused 1.25-MHz 12-element sector transducers (apertures of 87 mm, focal distances of 65 mm and 87 mm) were used with the toolbox for demonstration purposes. Simulation speed tests for different computational devices showed a range of 0.2 s - 3 min for GPUs and 1.6 s - 57 min for CPUs.</p>","PeriodicalId":13322,"journal":{"name":"IEEE transactions on ultrasonics, ferroelectrics, and frequency control","volume":"PP ","pages":""},"PeriodicalIF":3.0,"publicationDate":"2025-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143541895","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Advancing Single-Plane Wave Ultrasound Imaging with Implicit Multi-Angle Acoustic Synthesis via Deep Learning. 通过深度学习,利用隐式多角度声学合成推进单面波超声波成像。
IF 3 2区 工程技术
IEEE transactions on ultrasonics, ferroelectrics, and frequency control Pub Date : 2025-02-13 DOI: 10.1109/TUFFC.2025.3541113
Yijia Liu, Na Jiang, Zhifei Dai, Miaomiao Zhang
{"title":"Advancing Single-Plane Wave Ultrasound Imaging with Implicit Multi-Angle Acoustic Synthesis via Deep Learning.","authors":"Yijia Liu, Na Jiang, Zhifei Dai, Miaomiao Zhang","doi":"10.1109/TUFFC.2025.3541113","DOIUrl":"10.1109/TUFFC.2025.3541113","url":null,"abstract":"<p><p>Plane Wave Imaging (PWI) is pivotal in medical ultrasound, prized for its ultrafast capabilities essential for real-time physiological monitoring. Traditionally, enhancing image quality in PWI has necessitated an increase in the number of plane waves, unfortunately compromising its hallmark high frame rates. To fully leverage the frame rate advantage of PWI, existing deep-learning-based methods often employ single-plane wave (PW) as the sole input for training strategies to replicate multi-PWs compounding results. However, these typically fail to capture the intricate information provided by steered waves. In response, we have developed a sophisticated architecture that implicitly integrates multi-angle information by generating and dynamically combining virtual steered plane waves within the network. Employing deep learning techniques, this system creates virtual steered waves from the single primary input view, simulating a limited number of steering angles. These virtual PWs are then expertly merged with actual single PW data through an advanced attention mechanism. Through implicit multi-angle acoustic synthesis, our approach achieves the high-quality output typically associated with extensive multi-angle compounding. Rigorously evaluated on datasets acquired from simulations, experimental phantoms, and in vivo targets, our method has demonstrated superior performance over traditional single-plane wave strategies by providing more stable, reliable, and robust imaging outcomes. It excels in restoring detailed speckle patterns and diagnostic characteristics crucial for in vivo imaging, thereby offering a promising advancement in PWI technology without sacrificing speed. The code of the network is publicly available at https://github.com/yijiaLiu12/Implicit-Plane-Wave-Synthesis.</p>","PeriodicalId":13322,"journal":{"name":"IEEE transactions on ultrasonics, ferroelectrics, and frequency control","volume":"PP ","pages":""},"PeriodicalIF":3.0,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143541881","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control Publication Information
IF 3 2区 工程技术
IEEE transactions on ultrasonics, ferroelectrics, and frequency control Pub Date : 2025-02-11 DOI: 10.1109/TUFFC.2025.3534645
{"title":"IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control Publication Information","authors":"","doi":"10.1109/TUFFC.2025.3534645","DOIUrl":"https://doi.org/10.1109/TUFFC.2025.3534645","url":null,"abstract":"","PeriodicalId":13322,"journal":{"name":"IEEE transactions on ultrasonics, ferroelectrics, and frequency control","volume":"72 2","pages":"C2-C2"},"PeriodicalIF":3.0,"publicationDate":"2025-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10880697","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143388469","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Time-Sharing Acoustic Tweezers for Parallel Manipulation of Multiple Particles
IF 3 2区 工程技术
IEEE transactions on ultrasonics, ferroelectrics, and frequency control Pub Date : 2025-02-10 DOI: 10.1109/TUFFC.2025.3540512
Juan Zhou;Laixin Huang;Min Su;Zhiqiang Zhang;Weibao Qiu;Fei Li;Hairong Zheng
{"title":"Time-Sharing Acoustic Tweezers for Parallel Manipulation of Multiple Particles","authors":"Juan Zhou;Laixin Huang;Min Su;Zhiqiang Zhang;Weibao Qiu;Fei Li;Hairong Zheng","doi":"10.1109/TUFFC.2025.3540512","DOIUrl":"10.1109/TUFFC.2025.3540512","url":null,"abstract":"Holographic acoustic tweezers have various biomedical applications due to their ability to flexibly and rapidly synthesize acoustic fields for manipulating single or multiple particles. Existing multiparticle manipulation techniques are usually realized by precisely designing the incident wave’s phase distribution to synthesize a complex and steady-state acoustic field containing multiple acoustic trapping beams. However, interference effects between multiple beams tend to produce artifacts that trap particles in unwanted positions, limiting accuracy, and the number of manipulated particles. In addition, those techniques can only holistically manipulate multiple particles, namely, lacking parallel working ability. In this study, we proposed a time-sharing acoustic tweezer method to achieve the manipulation of multiple particles by rapidly switching individual trapping beams, minimizing interference artifacts. We applied this method to a 256-element phased-array acoustic tweezer system with designed ultrasonic pulse sequences to synthesize a single focused, twin trap, and vortex beam, enabling the pseudo-parallel manipulation of multiple particles in 3-D space at a beam switching frequency of ≥10 kHz. The experiments on polydimethylsiloxane particles ranging from micrometers to millimeters in diameter demonstrated that up to 96 particles can be successfully trapped and assembled into a 2-D lattice. Different numbers of particles were also patterned into dynamic contours, such as sinusoidal vibration (ten particles) and butterfly flapping (24 particles). In addition, the trapped multiple particles can also be rotated around their respective orbits. The proposed technique improved the number of objects dynamically manipulated in a parallel manner, advancing holographic acoustic tweezers and their applications.","PeriodicalId":13322,"journal":{"name":"IEEE transactions on ultrasonics, ferroelectrics, and frequency control","volume":"72 3","pages":"380-389"},"PeriodicalIF":3.0,"publicationDate":"2025-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143541857","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Remote Super-Resolution Mapping of Wave Fields
IF 3 2区 工程技术
IEEE transactions on ultrasonics, ferroelectrics, and frequency control Pub Date : 2025-02-04 DOI: 10.1109/TUFFC.2025.3538607
Jian-Yu Lu
{"title":"Remote Super-Resolution Mapping of Wave Fields","authors":"Jian-Yu Lu","doi":"10.1109/TUFFC.2025.3538607","DOIUrl":"10.1109/TUFFC.2025.3538607","url":null,"abstract":"Mapping wave field in space has many applications such as optimizing design of radio antennas, improving and developing ultrasound transducers, and planning and monitoring the treatment of tumors using high-intensity focused ultrasound (HIFU). Currently, there are methods that can map wave fields remotely or locally. However, there are limitations to these methods. For example, when mapping the wave fields remotely, the spatial resolution is limited due to a poor diffraction-limited resolution of the receiver, especially when the f-number of the receiver is large. To map the wave fields locally, the receiver is either subject to damage in hazardous environments (corrosive media, high temperature, high wave intensity, and so on) or difficult to be placed inside an object. To address these limitations, in this article, the point spread function (PSF)-modulation super-resolution imaging method was applied to map pulse ultrasound wave fields remotely at a high spatial resolution, overcoming the diffraction limit of a focused receiver. For example, to map a pulse ultrasound field of a full-width-at-half-maximum (FWHM) beamwidth of 1.24 mm at the focal distance of a transmitter, the FWHM beamwidths of the super-resolution mapping of the pulse wave field with a spherical glass modulator of 0.7 mm diameter at two receiver angles (0° and 45°) were about 1.13 and 1.22 mm, respectively, which were close to the theoretical value of 1.24 mm and were much smaller than the diffraction-limited resolution (1.81 mm) of the receiver. Without using the super-resolution method to remotely map the same pulse wave field, the FWHM beamwidth was about 2.06 mm. For comparison, the FWHM beamwidth obtained with a broadband (1–20 MHz) and 0.6-mm-diameter polyvinylidene fluoride (PVDF) needle hydrophone was about 1.41 mm. In addition to the focused pulse ultrasound wave field, a pulse Bessel beam near the transducer surface was mapped remotely with the super-resolution method, which revealed high spatial frequency components of the beam.","PeriodicalId":13322,"journal":{"name":"IEEE transactions on ultrasonics, ferroelectrics, and frequency control","volume":"72 3","pages":"370-379"},"PeriodicalIF":3.0,"publicationDate":"2025-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143541851","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
MM-UKAN++: A Novel Kolmogorov-Arnold Network Based U-shaped Network for Ultrasound Image Segmentation.
IF 3 2区 工程技术
IEEE transactions on ultrasonics, ferroelectrics, and frequency control Pub Date : 2025-02-04 DOI: 10.1109/TUFFC.2025.3539262
Boheng Zhang, Haorui Huang, Yi Shen, Mingjian Sun
{"title":"MM-UKAN++: A Novel Kolmogorov-Arnold Network Based U-shaped Network for Ultrasound Image Segmentation.","authors":"Boheng Zhang, Haorui Huang, Yi Shen, Mingjian Sun","doi":"10.1109/TUFFC.2025.3539262","DOIUrl":"https://doi.org/10.1109/TUFFC.2025.3539262","url":null,"abstract":"<p><p>Ultrasound (US) imaging is an important and commonly used medical imaging modality. Accurate and fast automatic segmentation of regions of interest (ROI) in US images is essential for enhancing the efficiency of clinical and robot-assisted diagnosis. However, US images suffer from low contrast, fuzzy boundaries, and significant scale variations in ROI. Existing convolutional neural network (CNN)-based and Transformer-based methods struggle with model efficiency and explainability. To address these challenges, we introduce MM-UKAN++, a novel U-shaped network based on Kolmogorov-Arnold Networks (KANs). MM-UKAN++ leverages multi-level KAN layers as the encoder and decoder within the U-network architecture, and incorporates an innovative multi-dimensional attention mechanism to refine skip connections by weighting features from frequency-channel and spatial perspectives. Additionally, the network effectively integrates multi-scale information, fusing outputs from different scale decoders to generate precise segmentation predictions. MM-UKAN++ achieves higher segmentation accuracy with lower computational cost and outperforms other mainstream methods on several open-source datasets for US image segmentation tasks, including achieving 69.42% IoU, 81.30% Dice, and 3.31mm HD in the BUSI dataset with 3.17G Flops and 9.90M Parameters. The excellent performance on our automatic carotid artery US scanning and diagnostic system further proves the speed and accuracy of MM-UKAN++. Besides, the good performance in other medical image segmentation tasks reveals the promising applications of MM-UKAN++. The code is available on GitHub.</p>","PeriodicalId":13322,"journal":{"name":"IEEE transactions on ultrasonics, ferroelectrics, and frequency control","volume":"PP ","pages":""},"PeriodicalIF":3.0,"publicationDate":"2025-02-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143541848","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Waveform-Specific Performance of Deep Learning-Based Super-Resolution for Ultrasound Contrast Imaging.
IF 3 2区 工程技术
IEEE transactions on ultrasonics, ferroelectrics, and frequency control Pub Date : 2025-01-30 DOI: 10.1109/TUFFC.2025.3537298
Rienk Zorgdrager, Nathan Blanken, Jelmer M Wolterink, Michel Versluis, Guillaume Lajoinie
{"title":"Waveform-Specific Performance of Deep Learning-Based Super-Resolution for Ultrasound Contrast Imaging.","authors":"Rienk Zorgdrager, Nathan Blanken, Jelmer M Wolterink, Michel Versluis, Guillaume Lajoinie","doi":"10.1109/TUFFC.2025.3537298","DOIUrl":"https://doi.org/10.1109/TUFFC.2025.3537298","url":null,"abstract":"<p><p>Resolving arterial flows is essential for understanding cardiovascular pathologies, improving diagnosis, and monitoring patient condition. Ultrasound contrast imaging uses microbubbles to enhance the scattering of the blood pool, allowing for real-time visualization of blood flow. Recent developments in vector flow imaging further expand the imaging capabilities of ultrasound by temporally resolving fast arterial flow. The next obstacle to overcome is the lack of spatial resolution. Super-resolved ultrasound images can be obtained by deconvolving radiofrequency (RF) signals before beamforming, breaking the link between resolution and pulse duration. Convolutional neural networks (CNNs) can be trained to locally estimate the deconvolution kernel and consequently super-localize the microbubbles directly within the RF signal. However, microbubble contrast is highly nonlinear, and the potential of CNNs in microbubble localization has not yet been fully exploited. Assessing deep learningbased deconvolution performance for non-trivial imaging pulses is therefore essential for successful translation to a practical setting, where the signal-to-noise ratio is limited, and transmission schemes should comply with safety guidelines. In this study, we train CNNs to deconvolve RF signals and localize the microbubbles driven by harmonic pulses, chirps, or delay-encoded pulse trains. Furthermore, we discuss potential hurdles for in-vitro and in-vivo super-resolution by presenting preliminary experimental results. We find that, whereas the CNNs can accurately localize microbubbles for all pulses, a short imaging pulse offers the best performance in noise-free conditions. However, chirps offer a comparable performance without noise, but are more robust to noise and outperform all other pulses in low-signal-to-noise ratio conditions.</p>","PeriodicalId":13322,"journal":{"name":"IEEE transactions on ultrasonics, ferroelectrics, and frequency control","volume":"PP ","pages":""},"PeriodicalIF":3.0,"publicationDate":"2025-01-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143541894","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信