Pub Date : 2024-07-15DOI: 10.1109/TUFFC.2024.3428917
Pooja Dubey;Shreya Nigam;Dicky Silitonga;Nico F. Declercq
Diffraction gratings, with their periodically ordered structures, have been critical components in acoustics, optics, and spectroscopy for over a century. The classical grating equation describes the emergence of diffraction phenomena by gratings, considering the groove periodicity and the characteristics of the incident wave. These gratings find extensive applications in communication, spectroscopy, architectural acoustics, and underwater research, and they are foundational to pioneering investigations in phononic crystals and meta-materials. While much attention has been given to understanding the diffraction behavior of linear acoustics concerning gratings, the literature lacks research regarding the influence of high-amplitude ultrasonic waves, which introduce observable nonlinear effects. This experimental enquiry presents a pioneering methodology for isolating higher harmonics from these nonlinear phenomena. We have developed a spatial filtering apparatus with a single-frequency transducer and a specially designed grating profile, enabling precise frequency selection or rejection.
{"title":"Unveiling the Potential of Diffraction Gratings for Precision Separation of Higher Harmonics in Nonlinear Acoustics","authors":"Pooja Dubey;Shreya Nigam;Dicky Silitonga;Nico F. Declercq","doi":"10.1109/TUFFC.2024.3428917","DOIUrl":"10.1109/TUFFC.2024.3428917","url":null,"abstract":"Diffraction gratings, with their periodically ordered structures, have been critical components in acoustics, optics, and spectroscopy for over a century. The classical grating equation describes the emergence of diffraction phenomena by gratings, considering the groove periodicity and the characteristics of the incident wave. These gratings find extensive applications in communication, spectroscopy, architectural acoustics, and underwater research, and they are foundational to pioneering investigations in phononic crystals and meta-materials. While much attention has been given to understanding the diffraction behavior of linear acoustics concerning gratings, the literature lacks research regarding the influence of high-amplitude ultrasonic waves, which introduce observable nonlinear effects. This experimental enquiry presents a pioneering methodology for isolating higher harmonics from these nonlinear phenomena. We have developed a spatial filtering apparatus with a single-frequency transducer and a specially designed grating profile, enabling precise frequency selection or rejection.","PeriodicalId":13322,"journal":{"name":"IEEE transactions on ultrasonics, ferroelectrics, and frequency control","volume":"71 9","pages":"1152-1161"},"PeriodicalIF":3.0,"publicationDate":"2024-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141619903","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}
Pub Date : 2024-07-09DOI: 10.1109/TUFFC.2024.3417640
{"title":"IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control Publication Information","authors":"","doi":"10.1109/TUFFC.2024.3417640","DOIUrl":"https://doi.org/10.1109/TUFFC.2024.3417640","url":null,"abstract":"","PeriodicalId":13322,"journal":{"name":"IEEE transactions on ultrasonics, ferroelectrics, and frequency control","volume":"71 7","pages":"C2-C2"},"PeriodicalIF":3.0,"publicationDate":"2024-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10591484","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141583536","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}
Pub Date : 2024-07-09DOI: 10.1109/TUFFC.2024.3404105
Xiaoning Jiang;Alessandro Stuart Savoia;Chih-Chung Huang
Wearable healthcare devices are expected to greatly improve the quality of human life by providing continuous health monitoring, remedying weakened or lost body or organ functions, and sometimes enabling superhuman capabilities. Enabled by recent advancements in soft matter, nanotechnology, integrated circuits, portable power technology, and artificial intelligence (AI), and inspired by the demands of healthcare applications, wearable ultrasound research has gained unprecedented momentum and is expected to play an increasingly important role in continuous healthcare sensing, imaging, therapy, drug delivery applications, and so on.
{"title":"Wearable Ultrasound Devices, Materials, and Applications","authors":"Xiaoning Jiang;Alessandro Stuart Savoia;Chih-Chung Huang","doi":"10.1109/TUFFC.2024.3404105","DOIUrl":"https://doi.org/10.1109/TUFFC.2024.3404105","url":null,"abstract":"Wearable healthcare devices are expected to greatly improve the quality of human life by providing continuous health monitoring, remedying weakened or lost body or organ functions, and sometimes enabling superhuman capabilities. Enabled by recent advancements in soft matter, nanotechnology, integrated circuits, portable power technology, and artificial intelligence (AI), and inspired by the demands of healthcare applications, wearable ultrasound research has gained unprecedented momentum and is expected to play an increasingly important role in continuous healthcare sensing, imaging, therapy, drug delivery applications, and so on.","PeriodicalId":13322,"journal":{"name":"IEEE transactions on ultrasonics, ferroelectrics, and frequency control","volume":"71 7","pages":"709-712"},"PeriodicalIF":3.0,"publicationDate":"2024-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10591485","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141583534","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}
Color Doppler echocardiography enables visualization of blood flow within the heart. However, the limited frame rate impedes the quantitative assessment of blood velocity throughout the cardiac cycle, thereby compromising a comprehensive analysis of ventricular filling. Concurrently, deep learning is demonstrating promising outcomes in postprocessing of echocardiographic data for various applications. This work explores the use of deep learning models for intracardiac Doppler velocity estimation from a reduced number of filtered I/Q signals. We used a supervised learning approach by simulating patient-based cardiac color Doppler acquisitions and proposed data augmentation strategies to enlarge the training dataset. We implemented architectures based on convolutional neural networks (CNNs). In particular, we focused on comparing the U-Net model and the recent ConvNeXt model, alongside assessing real-valued versus complex-valued representations. We found that both models outperformed the state-of-the-art autocorrelator method, effectively mitigating aliasing and noise. We did not observe significant differences between the use of real and complex data. Finally, we validated the models on in vitro and in vivo experiments. All models produced quantitatively comparable results to the baseline and were more robust to noise. ConvNeXt emerged as the sole model to achieve high-quality results on in vivo aliased samples. These results demonstrate the interest of supervised deep learning methods for Doppler velocity estimation from a reduced number of acquisitions.
{"title":"Boosting Cardiac Color Doppler Frame Rates With Deep Learning","authors":"Julia Puig;Denis Friboulet;Hang Jung Ling;François Varray;Michael Mougharbel;Jonathan Porée;Jean Provost;Damien Garcia;Fabien Millioz","doi":"10.1109/TUFFC.2024.3424549","DOIUrl":"10.1109/TUFFC.2024.3424549","url":null,"abstract":"Color Doppler echocardiography enables visualization of blood flow within the heart. However, the limited frame rate impedes the quantitative assessment of blood velocity throughout the cardiac cycle, thereby compromising a comprehensive analysis of ventricular filling. Concurrently, deep learning is demonstrating promising outcomes in postprocessing of echocardiographic data for various applications. This work explores the use of deep learning models for intracardiac Doppler velocity estimation from a reduced number of filtered I/Q signals. We used a supervised learning approach by simulating patient-based cardiac color Doppler acquisitions and proposed data augmentation strategies to enlarge the training dataset. We implemented architectures based on convolutional neural networks (CNNs). In particular, we focused on comparing the U-Net model and the recent ConvNeXt model, alongside assessing real-valued versus complex-valued representations. We found that both models outperformed the state-of-the-art autocorrelator method, effectively mitigating aliasing and noise. We did not observe significant differences between the use of real and complex data. Finally, we validated the models on in vitro and in vivo experiments. All models produced quantitatively comparable results to the baseline and were more robust to noise. ConvNeXt emerged as the sole model to achieve high-quality results on in vivo aliased samples. These results demonstrate the interest of supervised deep learning methods for Doppler velocity estimation from a reduced number of acquisitions.","PeriodicalId":13322,"journal":{"name":"IEEE transactions on ultrasonics, ferroelectrics, and frequency control","volume":"71 11","pages":"1540-1551"},"PeriodicalIF":3.0,"publicationDate":"2024-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141558628","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}
Ultrasound localization microscopy (ULM), an emerging medical imaging technique, effectively resolves the classical tradeoff between resolution and penetration inherent in traditional ultrasound imaging, opening up new avenues for noninvasive observation of the microvascular system. However, traditional microbubble tracking methods encounter various practical challenges. These methods typically entail multiple processing stages, including intricate steps such as pairwise correlation and trajectory optimization, rendering real-time applications unfeasible. Furthermore, existing deep learning-based tracking techniques neglect the temporal aspects of microbubble motion, leading to ineffective modeling of their dynamic behavior. To address these limitations, this study introduces a novel approach called the gated recurrent unit-based multitasking temporal neural network (GRU-MT). GRU-MT is designed to simultaneously handle microbubble trajectory tracking and trajectory optimization tasks. In addition, we enhance the nonlinear motion model initially proposed by Piepenbrock et al. to better encapsulate the nonlinear motion characteristics of microbubbles, thereby improving trajectory tracking accuracy. In this study, we perform a series of experiments involving network layer replacements to systematically evaluate the performance of various temporal neural networks, including recurrent neural network (RNN), long short-term memory network (LSTM), GRU, Transformer, and its bidirectional counterparts, on the microbubble trajectory tracking task. Concurrently, the proposed method undergoes qualitative and quantitative comparisons with traditional microbubble tracking techniques. The experimental results demonstrate that GRU-MT exhibits superior nonlinear modeling capabilities and robustness, both in simulation and in vivo dataset. In addition, it achieves reduced trajectory tracking errors in shorter time intervals, underscoring its potential for efficient microbubble trajectory tracking. The model code is open-sourced at https://github.com/zyt-Lib/GRU-MT .
{"title":"Efficient Microbubble Trajectory Tracking in Ultrasound Localization Microscopy Using a Gated Recurrent Unit-Based Multitasking Temporal Neural Network","authors":"Yuting Zhang;Wenjun Zhou;Lijie Huang;Yongjie Shao;Anguo Luo;Jianwen Luo;Bo Peng","doi":"10.1109/TUFFC.2024.3424955","DOIUrl":"10.1109/TUFFC.2024.3424955","url":null,"abstract":"Ultrasound localization microscopy (ULM), an emerging medical imaging technique, effectively resolves the classical tradeoff between resolution and penetration inherent in traditional ultrasound imaging, opening up new avenues for noninvasive observation of the microvascular system. However, traditional microbubble tracking methods encounter various practical challenges. These methods typically entail multiple processing stages, including intricate steps such as pairwise correlation and trajectory optimization, rendering real-time applications unfeasible. Furthermore, existing deep learning-based tracking techniques neglect the temporal aspects of microbubble motion, leading to ineffective modeling of their dynamic behavior. To address these limitations, this study introduces a novel approach called the gated recurrent unit-based multitasking temporal neural network (GRU-MT). GRU-MT is designed to simultaneously handle microbubble trajectory tracking and trajectory optimization tasks. In addition, we enhance the nonlinear motion model initially proposed by Piepenbrock et al. to better encapsulate the nonlinear motion characteristics of microbubbles, thereby improving trajectory tracking accuracy. In this study, we perform a series of experiments involving network layer replacements to systematically evaluate the performance of various temporal neural networks, including recurrent neural network (RNN), long short-term memory network (LSTM), GRU, Transformer, and its bidirectional counterparts, on the microbubble trajectory tracking task. Concurrently, the proposed method undergoes qualitative and quantitative comparisons with traditional microbubble tracking techniques. The experimental results demonstrate that GRU-MT exhibits superior nonlinear modeling capabilities and robustness, both in simulation and in vivo dataset. In addition, it achieves reduced trajectory tracking errors in shorter time intervals, underscoring its potential for efficient microbubble trajectory tracking. The model code is open-sourced at \u0000<uri>https://github.com/zyt-Lib/GRU-MT</uri>\u0000.","PeriodicalId":13322,"journal":{"name":"IEEE transactions on ultrasonics, ferroelectrics, and frequency control","volume":"71 12: Breaking the Resolution Barrier in Ultrasound","pages":"1714-1734"},"PeriodicalIF":3.0,"publicationDate":"2024-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141558629","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}
Pub Date : 2024-06-27DOI: 10.1109/TUFFC.2024.3420158
Luca De Marchi
Key requirements to boost the applicability of ultrasonic systems for in situ, real-time operations are low hardware complexity and low power consumption. These features are not available in present-day systems due to the fact that US inspections are typically achieved through phased arrays featuring a large number of individually controlled piezoelectric transducers and generating huge quantities of data. To minimize the energy and computational requirements, novel devices that feature enhanced functionalities beyond the mere conversion (i.e., metatransducers) can be conceived. This article reviews the potential of recent research breakthroughs in the transducer technology, which allow them to efficiently perform tasks, such as focusing, energy harvesting, beamforming, data communication, or mode filtering, and discusses the challenges for the widespread adoption of these solutions.
{"title":"The Blossoming of Ultrasonic Metatransducers","authors":"Luca De Marchi","doi":"10.1109/TUFFC.2024.3420158","DOIUrl":"10.1109/TUFFC.2024.3420158","url":null,"abstract":"Key requirements to boost the applicability of ultrasonic systems for in situ, real-time operations are low hardware complexity and low power consumption. These features are not available in present-day systems due to the fact that US inspections are typically achieved through phased arrays featuring a large number of individually controlled piezoelectric transducers and generating huge quantities of data. To minimize the energy and computational requirements, novel devices that feature enhanced functionalities beyond the mere conversion (i.e., metatransducers) can be conceived. This article reviews the potential of recent research breakthroughs in the transducer technology, which allow them to efficiently perform tasks, such as focusing, energy harvesting, beamforming, data communication, or mode filtering, and discusses the challenges for the widespread adoption of these solutions.","PeriodicalId":13322,"journal":{"name":"IEEE transactions on ultrasonics, ferroelectrics, and frequency control","volume":"71 9","pages":"1097-1105"},"PeriodicalIF":3.0,"publicationDate":"2024-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10574853","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141467647","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}
Pub Date : 2024-06-24DOI: 10.1109/TUFFC.2024.3418708
Stephan Strassle Rojas;Alexander Samady;Saeyoung Kim;Brooks D. Lindsey
Coronary artery disease (CAD) is one of the leading causes of death globally. Currently, diagnosis and intervention in CAD are typically performed via minimally invasive cardiac catheterization procedures. Using current diagnostic technology, such as angiography and fractional flow reserve (FFR), interventional cardiologists must decide which patients require intervention and which can be deferred; 10% of patients with stable CAD are incorrectly deferred using current diagnostic best practices. By developing a forward-viewing intravascular ultrasound (FV-IVUS) 2-D array capable of simultaneously evaluating morphology, hemodynamics, and plaque composition, physicians would be better able to stratify risk of major adverse cardiac events in patients with intermediate stenosis. For this application, a forward-viewing, 16-MHz 2-D array transducer was designed and fabricated. A 2-mm-diameter aperture consisting of 140 elements, with element dimensions of $98times 98times 70~mu $ m ( ${w}times {h}times {t}$ ) and a nominal interelement spacing of $120~mu $ m, was designed for this application based on simulations. The acoustic stack for this array was developed with a designed center frequency of 16 MHz. A novel via-less interconnect was developed to enable electrical connections to fan-out from a 140-element 2-D array with 120- $mu $ m interelement spacing. The fabricated array transducer had 96/140 functioning elements operating at a center frequency of 16 MHz with a −6-dB fractional bandwidth of 62% $pm ~7$ %. Single-element SNR was $23~pm ~3$ dB, and the measured electrical crosstalk was $- 33~pm ~3$ dB. In imaging experiments, the measured lateral resolution was 0.231 mm and the measured axial resolution was 0.244 mm at a depth of 5 mm. Finally, the transducer was used to perform 3-D B-mode imaging of a 3-mm-diameter spring and 3-D B-mode and power Doppler imaging of a tissue-mimicking phantom.
{"title":"High-Frequency, 2-mm-Diameter Forward-Viewing 2-D Array for 3-D Intracoronary Blood Flow Imaging","authors":"Stephan Strassle Rojas;Alexander Samady;Saeyoung Kim;Brooks D. Lindsey","doi":"10.1109/TUFFC.2024.3418708","DOIUrl":"10.1109/TUFFC.2024.3418708","url":null,"abstract":"Coronary artery disease (CAD) is one of the leading causes of death globally. Currently, diagnosis and intervention in CAD are typically performed via minimally invasive cardiac catheterization procedures. Using current diagnostic technology, such as angiography and fractional flow reserve (FFR), interventional cardiologists must decide which patients require intervention and which can be deferred; 10% of patients with stable CAD are incorrectly deferred using current diagnostic best practices. By developing a forward-viewing intravascular ultrasound (FV-IVUS) 2-D array capable of simultaneously evaluating morphology, hemodynamics, and plaque composition, physicians would be better able to stratify risk of major adverse cardiac events in patients with intermediate stenosis. For this application, a forward-viewing, 16-MHz 2-D array transducer was designed and fabricated. A 2-mm-diameter aperture consisting of 140 elements, with element dimensions of \u0000<inline-formula> <tex-math>$98times 98times 70~mu $ </tex-math></inline-formula>\u0000m (\u0000<inline-formula> <tex-math>${w}times {h}times {t}$ </tex-math></inline-formula>\u0000) and a nominal interelement spacing of \u0000<inline-formula> <tex-math>$120~mu $ </tex-math></inline-formula>\u0000m, was designed for this application based on simulations. The acoustic stack for this array was developed with a designed center frequency of 16 MHz. A novel via-less interconnect was developed to enable electrical connections to fan-out from a 140-element 2-D array with 120-\u0000<inline-formula> <tex-math>$mu $ </tex-math></inline-formula>\u0000m interelement spacing. The fabricated array transducer had 96/140 functioning elements operating at a center frequency of 16 MHz with a −6-dB fractional bandwidth of 62% \u0000<inline-formula> <tex-math>$pm ~7$ </tex-math></inline-formula>\u0000%. Single-element SNR was \u0000<inline-formula> <tex-math>$23~pm ~3$ </tex-math></inline-formula>\u0000 dB, and the measured electrical crosstalk was \u0000<inline-formula> <tex-math>$- 33~pm ~3$ </tex-math></inline-formula>\u0000 dB. In imaging experiments, the measured lateral resolution was 0.231 mm and the measured axial resolution was 0.244 mm at a depth of 5 mm. Finally, the transducer was used to perform 3-D B-mode imaging of a 3-mm-diameter spring and 3-D B-mode and power Doppler imaging of a tissue-mimicking phantom.","PeriodicalId":13322,"journal":{"name":"IEEE transactions on ultrasonics, ferroelectrics, and frequency control","volume":"71 8","pages":"1051-1061"},"PeriodicalIF":3.0,"publicationDate":"2024-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141446031","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}
Ultrasound elastography images, which enable quantitative visualization of tissue stiffness, can be reconstructed by solving an inverse problem. Classical model-based methods are usually formulated in terms of constrained optimization problems. To stabilize the elasticity reconstructions, regularization techniques, such as Tikhonov method, are used with the cost of promoting smoothness and blurriness in the reconstructed images. Thus, incorporating a suitable regularizer is essential for reducing the elasticity reconstruction artifacts, while finding the most suitable one is challenging. In this work, we present a new statistical representation of the physical imaging model, which incorporates effective signal-dependent colored noise modeling. Moreover, we develop a learning-based integrated statistical framework, which combines a physical model with learning-based priors. We use a dataset of simulated phantoms with various elasticity distributions and geometric patterns to train a denoising regularizer as the learning-based prior. We use fixed-point approaches and variants of gradient descent for solving the integrated optimization task following learning-based plug-and-play (PnP) prior and regularization by denoising (RED) paradigms. Finally, we evaluate the performance of the proposed approaches in terms of relative mean square error (RMSE) with nearly 20% improvement for both piecewise smooth simulated phantoms and experimental phantoms compared with the classical model-based methods and 12% improvement for both spatially varying breast-mimicking simulated phantoms and an experimental breast phantom, demonstrating the potential clinical relevance of our work. Moreover, the qualitative comparisons of reconstructed images demonstrate the robust performance of the proposed methods even for complex elasticity structures that might be encountered in clinical settings.
{"title":"Integrating Learning-Based Priors With Physics-Based Models in Ultrasound Elasticity Reconstruction","authors":"Narges Mohammadi;Soumya Goswami;Irteza Enan Kabir;Siladitya Khan;Fan Feng;Steve McAleavey;Marvin M. Doyley;Mujdat Cetin","doi":"10.1109/TUFFC.2024.3417905","DOIUrl":"10.1109/TUFFC.2024.3417905","url":null,"abstract":"Ultrasound elastography images, which enable quantitative visualization of tissue stiffness, can be reconstructed by solving an inverse problem. Classical model-based methods are usually formulated in terms of constrained optimization problems. To stabilize the elasticity reconstructions, regularization techniques, such as Tikhonov method, are used with the cost of promoting smoothness and blurriness in the reconstructed images. Thus, incorporating a suitable regularizer is essential for reducing the elasticity reconstruction artifacts, while finding the most suitable one is challenging. In this work, we present a new statistical representation of the physical imaging model, which incorporates effective signal-dependent colored noise modeling. Moreover, we develop a learning-based integrated statistical framework, which combines a physical model with learning-based priors. We use a dataset of simulated phantoms with various elasticity distributions and geometric patterns to train a denoising regularizer as the learning-based prior. We use fixed-point approaches and variants of gradient descent for solving the integrated optimization task following learning-based plug-and-play (PnP) prior and regularization by denoising (RED) paradigms. Finally, we evaluate the performance of the proposed approaches in terms of relative mean square error (RMSE) with nearly 20% improvement for both piecewise smooth simulated phantoms and experimental phantoms compared with the classical model-based methods and 12% improvement for both spatially varying breast-mimicking simulated phantoms and an experimental breast phantom, demonstrating the potential clinical relevance of our work. Moreover, the qualitative comparisons of reconstructed images demonstrate the robust performance of the proposed methods even for complex elasticity structures that might be encountered in clinical settings.","PeriodicalId":13322,"journal":{"name":"IEEE transactions on ultrasonics, ferroelectrics, and frequency control","volume":"71 11","pages":"1406-1419"},"PeriodicalIF":3.0,"publicationDate":"2024-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141446032","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}
Left ventricle (LV) segmentation of 2-D echocardiography images is an essential step in the analysis of cardiac morphology and function and—more generally—diagnosis of cardiovascular diseases (CVD). Several deep learning (DL) algorithms have recently been proposed for the automatic segmentation of the LV, showing significant performance improvement over the traditional segmentation algorithms. However, unlike the traditional methods, prior information about the segmentation problem, e.g., anatomical shape information, is not usually incorporated for training the DL algorithms. This can degrade the generalization performance of the DL models on unseen images if their characteristics are somewhat different from those of the training images, e.g., low-quality testing images. In this study, a new shape-constrained deep convolutional neural network (CNN)—called B-spline explicit active surface (BEAS)-Net—is introduced for automatic LV segmentation. The BEAS-Net learns how to associate the image features, encoded by its convolutional layers, with anatomical shape-prior information derived by the BEAS algorithm to generate physiologically meaningful segmentation contours when dealing with artifactual or low-quality images. The performance of the proposed network was evaluated using three different in vivo datasets and was compared with a deep segmentation algorithm based on the U-Net model. Both the networks yielded comparable results when tested on images of acceptable quality, but the BEAS-Net outperformed the benchmark DL model on artifactual and low-quality images.
{"title":"BEAS-Net: A Shape-Prior-Based Deep Convolutional Neural Network for Robust Left Ventricular Segmentation in 2-D Echocardiography","authors":"Somayeh Akbari;Mahdi Tabassian;João Pedrosa;Sandro Queirós;Konstantina Papangelopoulou;Jan D’Hooge","doi":"10.1109/TUFFC.2024.3418030","DOIUrl":"10.1109/TUFFC.2024.3418030","url":null,"abstract":"Left ventricle (LV) segmentation of 2-D echocardiography images is an essential step in the analysis of cardiac morphology and function and—more generally—diagnosis of cardiovascular diseases (CVD). Several deep learning (DL) algorithms have recently been proposed for the automatic segmentation of the LV, showing significant performance improvement over the traditional segmentation algorithms. However, unlike the traditional methods, prior information about the segmentation problem, e.g., anatomical shape information, is not usually incorporated for training the DL algorithms. This can degrade the generalization performance of the DL models on unseen images if their characteristics are somewhat different from those of the training images, e.g., low-quality testing images. In this study, a new shape-constrained deep convolutional neural network (CNN)—called B-spline explicit active surface (BEAS)-Net—is introduced for automatic LV segmentation. The BEAS-Net learns how to associate the image features, encoded by its convolutional layers, with anatomical shape-prior information derived by the BEAS algorithm to generate physiologically meaningful segmentation contours when dealing with artifactual or low-quality images. The performance of the proposed network was evaluated using three different in vivo datasets and was compared with a deep segmentation algorithm based on the U-Net model. Both the networks yielded comparable results when tested on images of acceptable quality, but the BEAS-Net outperformed the benchmark DL model on artifactual and low-quality images.","PeriodicalId":13322,"journal":{"name":"IEEE transactions on ultrasonics, ferroelectrics, and frequency control","volume":"71 11","pages":"1565-1576"},"PeriodicalIF":3.0,"publicationDate":"2024-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141446030","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}
Pub Date : 2024-06-21DOI: 10.1109/TUFFC.2024.3417818
M. Sait Kilinc;Reza Pakdaman Zangabad;Costas Arvanitis;F. Levent Degertekin
Focused ultrasound (FUS) combined with microbubbles (MBs) has emerged as a promising strategy for transiently opening the blood-brain barrier (BBB) to enhance drug permeability in the brain. Current FUS systems for BBB opening use piezoelectric transducers as transmitters and receivers. While capacitive micromachined ultrasonic transducers (CMUTs) have been suggested as an FUS receiver alternative due to their broad bandwidth, their capabilities as transmitters have not been investigated. This is mainly due to the intrinsic nonlinear behavior of CMUTs, which complicates the detection of MB generated harmonic signals and their low-pressure output at FUS frequencies. Various methods have been proposed to mitigate CMUT nonlinearity; however, these approaches have primarily targeted contrast enhanced ultrasound imaging. In this study, we propose the use of polyphase modulation (PM) technique to isolate MB emissions when CMUTs are employed as transmitters for BBB opening. Our calculations for a human scale FUS system with multiple CMUT transmitters show that 10-kPa peak negative pressure (PNP) at 150-mm focal distance will be sufficient for MB excitation for BBB opening. Experimental findings indicate that this pressure level can be easily generated at 400–800 kHz using a readily available CMUT. Furthermore, more than 50-dB suppression of the fundamental harmonic signal is obtained in free field and transcranial hydrophone measurements by processing receive signals in response to phase-modulated transmit waveforms. In vitro validation of PM is also conducted using Definity MB flowing through a tube phantom. MB-filled tube phantoms show adequate nonlinear signal isolation and SNR for MB harmonic detection. Together our findings indicate that PM can effectively mitigate CMUT harmonic generation, thereby creating new opportunities for wideband transmission and receive operation for BBB opening in clinical and preclinical applications.
{"title":"CMUT as a Transmitter for Microbubble-Assisted Blood-Brain Barrier Opening","authors":"M. Sait Kilinc;Reza Pakdaman Zangabad;Costas Arvanitis;F. Levent Degertekin","doi":"10.1109/TUFFC.2024.3417818","DOIUrl":"10.1109/TUFFC.2024.3417818","url":null,"abstract":"Focused ultrasound (FUS) combined with microbubbles (MBs) has emerged as a promising strategy for transiently opening the blood-brain barrier (BBB) to enhance drug permeability in the brain. Current FUS systems for BBB opening use piezoelectric transducers as transmitters and receivers. While capacitive micromachined ultrasonic transducers (CMUTs) have been suggested as an FUS receiver alternative due to their broad bandwidth, their capabilities as transmitters have not been investigated. This is mainly due to the intrinsic nonlinear behavior of CMUTs, which complicates the detection of MB generated harmonic signals and their low-pressure output at FUS frequencies. Various methods have been proposed to mitigate CMUT nonlinearity; however, these approaches have primarily targeted contrast enhanced ultrasound imaging. In this study, we propose the use of polyphase modulation (PM) technique to isolate MB emissions when CMUTs are employed as transmitters for BBB opening. Our calculations for a human scale FUS system with multiple CMUT transmitters show that 10-kPa peak negative pressure (PNP) at 150-mm focal distance will be sufficient for MB excitation for BBB opening. Experimental findings indicate that this pressure level can be easily generated at 400–800 kHz using a readily available CMUT. Furthermore, more than 50-dB suppression of the fundamental harmonic signal is obtained in free field and transcranial hydrophone measurements by processing receive signals in response to phase-modulated transmit waveforms. In vitro validation of PM is also conducted using Definity MB flowing through a tube phantom. MB-filled tube phantoms show adequate nonlinear signal isolation and SNR for MB harmonic detection. Together our findings indicate that PM can effectively mitigate CMUT harmonic generation, thereby creating new opportunities for wideband transmission and receive operation for BBB opening in clinical and preclinical applications.","PeriodicalId":13322,"journal":{"name":"IEEE transactions on ultrasonics, ferroelectrics, and frequency control","volume":"71 8","pages":"1042-1050"},"PeriodicalIF":3.0,"publicationDate":"2024-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141436732","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：