1
|
Beuret S, Heriard-Dubreuil B, Martiartu NK, Jaeger M, Thiran JP. Windowed Radon Transform for Robust Speed-of-Sound Imaging With Pulse-Echo Ultrasound. IEEE TRANSACTIONS ON MEDICAL IMAGING 2024; 43:1579-1593. [PMID: 38109237 DOI: 10.1109/tmi.2023.3343918] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 12/20/2023]
Abstract
In recent years, methods estimating the spatial distribution of tissue speed of sound with pulse-echo ultrasound are gaining considerable traction. They can address limitations of B-mode imaging, for instance in diagnosing fatty liver diseases. Current state-of-the-art methods relate the tissue speed of sound to local echo shifts computed between images that are beamformed using restricted transmit and receive apertures. However, the aperture limitation affects the robustness of phase-shift estimations and, consequently, the accuracy of reconstructed speed-of-sound maps. Here, we propose a method based on the Radon transform of image patches able to estimate local phase shifts from full-aperture images. We validate our technique on simulated, phantom and in-vivo data acquired on a liver and compare it with a state-of-the-art method. We show that the proposed method enhances the stability to changes of beamforming speed of sound and to a reduction of the number of insonifications. In particular, the deployment of pulse-echo speed-of-sound estimation methods onto portable ultrasound devices can be eased by the reduction of the number of insonifications allowed by the proposed method.
Collapse
|
2
|
Long X, Tian C. Spatial and channel attention-based conditional Wasserstein GAN for direct and rapid image reconstruction in ultrasound computed tomography. Biomed Eng Lett 2024; 14:57-68. [PMID: 38186951 PMCID: PMC10770017 DOI: 10.1007/s13534-023-00310-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/15/2023] [Revised: 07/28/2023] [Accepted: 08/01/2023] [Indexed: 01/09/2024] Open
Abstract
Ultrasound computed tomography (USCT) is an emerging technology that offers a noninvasive and radiation-free imaging approach with high sensitivity, making it promising for the early detection and diagnosis of breast cancer. The speed-of-sound (SOS) parameter plays a crucial role in distinguishing between benign masses and breast cancer. However, traditional SOS reconstruction methods face challenges in achieving a balance between resolution and computational efficiency, which hinders their clinical applications due to high computational complexity and long reconstruction times. In this paper, we propose a novel and efficient approach for direct SOS image reconstruction based on an improved conditional generative adversarial network. The generator directly reconstructs SOS images from time-of-flight information, eliminating the need for intermediate steps. Residual spatial-channel attention blocks are integrated into the generator to adaptively determine the relevance of arrival time from the transducer pair corresponding to each pixel in the SOS image. An ablation study verified the effectiveness of this module. Qualitative and quantitative evaluation results on breast phantom datasets demonstrate that this method is capable of rapidly reconstructing high-quality SOS images, achieving better generation results and image quality. Therefore, we believe that the proposed algorithm represents a new direction in the research area of USCT SOS reconstruction.
Collapse
Affiliation(s)
- Xiaoyun Long
- College of Engineering Science, University of Science and Technology of China, Hefei, 230026 Anhui China
- Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, 230088 Anhui China
| | - Chao Tian
- College of Engineering Science, University of Science and Technology of China, Hefei, 230026 Anhui China
- Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, 230088 Anhui China
| |
Collapse
|
3
|
Long X, Chen J, Liu W, Tian C. Deep Learning Ultrasound Computed Tomography Under Sparse Sampling. IEEE TRANSACTIONS ON ULTRASONICS, FERROELECTRICS, AND FREQUENCY CONTROL 2023; 70:1084-1100. [PMID: 37523276 DOI: 10.1109/tuffc.2023.3299954] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 08/02/2023]
Abstract
Ultrasound computed tomography (USCT) is a fast-emerging imaging modality that is expected to help detect and characterize breast tumors by quantifying the distribution of the speed of sound (SOS) and acoustic attenuation in breast tissue. High-quality quantitative SOS reconstruction in USCT requires a large number of transducers, which incurs high system costs and slow computation. In contrast, sparsely distributed arrays are low-cost and fast but significantly degrade image quality. Thus, we propose a framework to achieve high-quality SOS reconstruction under sparse sampling based on a convolutional neural network (SRSS-Net) with faster computation. We first apply the bent-ray algorithm to sparsely sampled data and then apply the SRSS-Net to efficiently improve the image quality. Experimental results on synthetic and real datasets demonstrate that the proposed SRSS-Net provides reconstructions that are superior to those of state-of-the-art methods in terms of artifact suppression, structural preservation, quantitative restoration, and computational speed. As demonstrated in our experiments, the fine-tuning training strategy is suggested when applying SRSS-Net to real-world circumstances. The imaging and computational performance of SRSS-Net on the inhomogeneous breast phantom further demonstrates that SRSS-Net has great potential in real-time breast cancer detection.
Collapse
|
4
|
Ali R, Brevett T, Zhuang L, Bendjador H, Podkowa AS, Hsieh SS, Simson W, Sanabria SJ, Herickhoff CD, Dahl JJ. Aberration correction in diagnostic ultrasound: A review of the prior field and current directions. Z Med Phys 2023; 33:267-291. [PMID: 36849295 PMCID: PMC10517407 DOI: 10.1016/j.zemedi.2023.01.003] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/07/2022] [Revised: 12/17/2022] [Accepted: 01/09/2023] [Indexed: 02/27/2023]
Abstract
Medical ultrasound images are reconstructed with simplifying assumptions on wave propagation, with one of the most prominent assumptions being that the imaging medium is composed of a constant sound speed. When the assumption of a constant sound speed are violated, which is true in most in vivoor clinical imaging scenarios, distortion of the transmitted and received ultrasound wavefronts appear and degrade the image quality. This distortion is known as aberration, and the techniques used to correct for the distortion are known as aberration correction techniques. Several models have been proposed to understand and correct for aberration. In this review paper, aberration and aberration correction are explored from the early models and correction techniques, including the near-field phase screen model and its associated correction techniques such as nearest-neighbor cross-correlation, to more recent models and correction techniques that incorporate spatially varying aberration and diffractive effects, such as models and techniques that rely on the estimation of the sound speed distribution in the imaging medium. In addition to historical models, future directions of ultrasound aberration correction are proposed.
Collapse
Affiliation(s)
- Rehman Ali
- Department of Imaging Sciences, University of Rochester Medical Center, Rochester, NY, USA
| | - Thurston Brevett
- Department of Electrical Engineering, Stanford University, Stanford, CA, USA
| | - Louise Zhuang
- Department of Electrical Engineering, Stanford University, Stanford, CA, USA
| | - Hanna Bendjador
- Department of Radiology, Stanford University School of Medicine, Stanford, CA, USA
| | - Anthony S Podkowa
- Department of Radiology, Stanford University School of Medicine, Stanford, CA, USA
| | - Scott S Hsieh
- Department of Radiology, Mayo Clinic, Rochester, MN, USA
| | - Walter Simson
- Department of Radiology, Stanford University School of Medicine, Stanford, CA, USA
| | - Sergio J Sanabria
- Department of Radiology, Stanford University School of Medicine, Stanford, CA, USA; University of Deusto/ Ikerbasque Basque Foundation for Science, Bilbao, Spain
| | - Carl D Herickhoff
- Department of Biomedical Engineering, University of Memphis, TN, USA
| | - Jeremy J Dahl
- Department of Radiology, Stanford University School of Medicine, Stanford, CA, USA.
| |
Collapse
|
5
|
Rau R, Schweizer D, Vishnevskiy V, Goksel O. Speed-of-sound imaging using diverging waves. Int J Comput Assist Radiol Surg 2021; 16:1201-1211. [PMID: 34160749 PMCID: PMC8260432 DOI: 10.1007/s11548-021-02426-w] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/15/2021] [Accepted: 05/28/2021] [Indexed: 10/29/2022]
Abstract
PURPOSE Due to its safe, low-cost, portable, and real-time nature, ultrasound is a prominent imaging method in computer-assisted interventions. However, typical B-mode ultrasound images have limited contrast and tissue differentiation capability for several clinical applications. METHODS Recent introduction of imaging speed-of-sound (SoS) in soft tissues using conventional ultrasound systems and transducers has great potential in clinical translation providing additional imaging contrast, e.g., in intervention planning, navigation, and guidance applications. However, current pulse-echo SoS imaging methods relying on plane wave (PW) sequences are highly prone to aberration effects, therefore suboptimal in image quality. In this paper we propose using diverging waves (DW) for SoS imaging and study this comparatively to PW. RESULTS We demonstrate wavefront aberration and its effects on the key step of displacement tracking in the SoS reconstruction pipeline, comparatively between PW and DW on a synthetic example. We then present the parameterization sensitivity of both approaches on a set of simulated phantoms. Analyzing SoS imaging performance comparatively indicates that using DW instead of PW, the reconstruction accuracy improves by over 20% in root-mean-square-error (RMSE) and by 42% in contrast-to-noise ratio (CNR). We then demonstrate SoS reconstructions with actual US acquisitions of a breast phantom. With our proposed DW, CNR for a high contrast tumor-representative inclusion is improved by 42%, while for a low contrast cyst-representative inclusion a 2.8-fold improvement is achieved. CONCLUSION SoS imaging, so far only studied using a plane wave transmission scheme, can be made more reliable and accurate using DW. The high imaging contrast of DW-based SoS imaging will thus facilitate the clinical translation of the method and utilization in computer-assisted interventions such as ultrasound-guided biopsies, where B-Mode contrast is often to low to detect potential lesions.
Collapse
Affiliation(s)
- Richard Rau
- Computer-assisted Applications in Medicine group, ETH Zurich, Zurich, Switzerland
| | - Dieter Schweizer
- Computer-assisted Applications in Medicine group, ETH Zurich, Zurich, Switzerland
| | - Valery Vishnevskiy
- Computer-assisted Applications in Medicine group, ETH Zurich, Zurich, Switzerland
| | - Orcun Goksel
- Computer-assisted Applications in Medicine group, ETH Zurich, Zurich, Switzerland
| |
Collapse
|
6
|
|
7
|
Bernhardt M, Vishnevskiy V, Rau R, Goksel O. Training Variational Networks With Multidomain Simulations: Speed-of-Sound Image Reconstruction. IEEE TRANSACTIONS ON ULTRASONICS, FERROELECTRICS, AND FREQUENCY CONTROL 2020; 67:2584-2594. [PMID: 32746211 DOI: 10.1109/tuffc.2020.3010186] [Citation(s) in RCA: 7] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/11/2023]
Abstract
Speed-of-sound (SoS) has been shown as a potential biomarker for breast cancer imaging, successfully differentiating malignant tumors from benign ones. SoS images can be reconstructed from time-of-flight measurements from ultrasound images acquired using conventional handheld ultrasound transducers. Variational networks (VNs) have recently been shown to be a potential learning-based approach for optimizing inverse problems in image reconstruction. Despite earlier promising results, these methods, however, do not generalize well from simulated to acquired data, due to the domain shift. In this work, we present for the first time a VN solution for a pulse-echo SoS image reconstruction problem using diverging waves with conventional transducers and single-sided tissue access. This is made possible by incorporating simulations with varying complexity into training. We use loop unrolling of gradient descent with momentum, with an exponentially weighted loss of outputs at each unrolled iteration in order to regularize the training. We learn norms as activation functions regularized to have smooth forms for robustness to input distribution variations. We evaluate reconstruction quality on the ray-based and full-wave simulations as well as on the tissue-mimicking phantom data, in comparison with a classical iterative [limited-memory Broyden-Fletcher-Goldfarb-Shanno (L-BFGS)] optimization of this image reconstruction problem. We show that the proposed regularization techniques combined with multisource domain training yield substantial improvements in the domain adaptation capabilities of VN, reducing the median root mean squared error (RMSE) by 54% on a wave-based simulation data set compared to the baseline VN. We also show that on data acquired from a tissue-mimicking breast phantom, the proposed VN provides improved reconstruction in 12 ms.
Collapse
|
8
|
|
9
|
Walheim J, Dillinger H, Kozerke S. Multipoint 5D flow cardiovascular magnetic resonance - accelerated cardiac- and respiratory-motion resolved mapping of mean and turbulent velocities. J Cardiovasc Magn Reson 2019; 21:42. [PMID: 31331353 PMCID: PMC6647085 DOI: 10.1186/s12968-019-0549-0] [Citation(s) in RCA: 38] [Impact Index Per Article: 7.6] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/21/2018] [Accepted: 06/05/2019] [Indexed: 01/24/2023] Open
Abstract
BACKGROUND Volumetric quantification of mean and fluctuating velocity components of transient and turbulent flows promises a comprehensive characterization of valvular and aortic flow characteristics. Data acquisition using standard navigator-gated 4D Flow cardiovascular magnetic resonance (CMR) is time-consuming and actual scan times depend on the breathing pattern of the subject, limiting the applicability of the method in a clinical setting. We sought to develop a 5D Flow CMR framework which combines undersampled data acquisition including multipoint velocity encoding with low-rank image reconstruction to provide cardiac- and respiratory-motion resolved assessment of velocity maps and turbulent kinetic energy in fixed scan times. METHODS Data acquisition and data-driven motion state detection was performed using an undersampled Cartesian tiny Golden angle approach. Locally low-rank (LLR) reconstruction was implemented to exploit correlations among heart phases and respiratory motion states. To ensure accurate quantification of mean and turbulent velocities, a multipoint encoding scheme with two velocity encodings per direction was incorporated. Velocity-vector fields and turbulent kinetic energy (TKE) were obtained using a Bayesian approach maximizing the posterior probability given the measured data. The scan time of 5D Flow CMR was set to 4 min. 5D Flow CMR with acceleration factors of 19 .0 ± 0.21 (mean ± std) and velocity encodings (VENC) of 0.5 m/s and 1.5 m/s per axis was compared to navigator-gated 2x SENSE accelerated 4D Flow CMR with VENC = 1.5 m/s in 9 subjects. Peak velocities and peak flow were compared and magnitude images, velocity and TKE maps were assessed. RESULTS While net scan time of 5D Flow CMR was 4 min independent of individual breathing patterns, the scan times of the standard 4D Flow CMR protocol varied depending on the actual navigator gating efficiency and were 17.8 ± 3.9 min on average. Velocity vector fields derived from 5D Flow CMR in the end-expiratory state agreed well with data obtained from the navigated 4D protocol (normalized root-mean-square error 8.9 ± 2.1%). On average, peak velocities assessed with 5D Flow CMR were higher than for the 4D protocol (3.1 ± 4.4%). CONCLUSIONS Respiratory-motion resolved multipoint 5D Flow CMR allows mapping of mean and turbulent velocities in the aorta in 4 min.
Collapse
Affiliation(s)
- Jonas Walheim
- Institute for Biomedical Engineering, University and ETH Zurich, Gloriastrasse 35 8092, Zurich, Switzerland
| | - Hannes Dillinger
- Institute for Biomedical Engineering, University and ETH Zurich, Gloriastrasse 35 8092, Zurich, Switzerland
| | - Sebastian Kozerke
- Institute for Biomedical Engineering, University and ETH Zurich, Gloriastrasse 35 8092, Zurich, Switzerland
| |
Collapse
|
10
|
Deep Variational Networks with Exponential Weighting for Learning Computed Tomography. LECTURE NOTES IN COMPUTER SCIENCE 2019. [DOI: 10.1007/978-3-030-32226-7_35] [Citation(s) in RCA: 10] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/24/2023]
|