Fast Thresholding of SVD Clutter Filter Using the Spatial Similarity Matrix and a Sum-Table Algorithm

Baranger, Jérôme; Aguet, Julien; Villemain, Olivier

doi:10.1109/tuffc.2023.3289235

Cited by 5 publications

(1 citation statement)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The basic data processing steps of ULM include clutter filtering, localization of the centroids of MBs, and accumulation and reconstruction of multiple-frame MBs to obtain super-resolution ultrasound (SR-US) images of microvessels. Clutter filtering is typically performed using spatiotemporal filtering methods to separate MB signals from tissue signals (Ferrara et al 2000, Mauldin et al 2011, Baranger et al 2018, 2023. The precise positioning of each MB is obtained by a center of mass algorithm or convolution with a two-dimensional point spread function (PSF) (Christensen-Jeffries et al 2015, Ghosh et al 2019).…”

Section: Introductionmentioning

confidence: 99%

Deep learning for fast denoising filtering in ultrasound localization microscopy

Yu,

Luan,

Lei

et al. 2023

Phys. Med. Biol.

View full text Add to dashboard Cite

Objective. Addition of a denoising filter step in ultrasound localization microscopy (ULM) has been shown to effectively reduce the error localizations of microbubbles (MBs) and achieve resolution improvement for super-resolution ultrasound (SR-US) imaging. However, previous image-denoising methods (e.g. block-matching 3D, BM3D) requires long data processing times, making ULM only able to be processed offline. This work introduces a new way to reduce data processing time through deep learning. Approach. In this study, we propose deep learning (DL) denoising based on contrastive semi-supervised network (CS-Net). The neural network is mainly trained with simulated MBs data to extract MB signals from noise. And the performances of CS-Net denoising are evaluated in both in vitro flow phantom experiment and in vivo experiment of New Zealand rabbit tumor. Main results. For in vitro flow phantom experiment, the signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) of single microbubble image are 26.91 dB and 4.01 dB, repectively. For in vivo animal experiment , the SNR and CNR were 12.29 dB and 6.06 dB. In addition, single microvessel of 24 μm and two microvessels separated by 46 μm could be clearly displayed. Most importantly,, the CS-Net denoising speeds for in vitro and in vivo experiments were 0.041 s frame−1 and 0.062 s frame−1, respectively. Significance. DL denoising based on CS-Net can improve the resolution of SR-US as well as reducing denoising time, thereby making further contributions to the clinical real-time imaging of ULM.

show abstract

Section: Introductionmentioning

confidence: 99%

Deep learning for fast denoising filtering in ultrasound localization microscopy

Yu,

Luan,

Lei

et al. 2023

Phys. Med. Biol.

View full text Add to dashboard Cite

show abstract

Adaptive Clutter Filtering for Speckle Decorrelation-Based Blood Flow Measurements

Park,

Park

2024

J. Electr. Eng. Technol.

View full text Add to dashboard Cite

Nonlinear Singular Value Decomposition Beamforming for Ultrasound Imaging of Gas Vesicles

Zhang,

Vert,

Nouhoum

et al. 2024

Preprint

View full text Add to dashboard Cite

Ultrasound imaging holds significant promise for the observation of molecular and cellular phenomena through the utilization of acoustic contrast agents and acoustic reporter genes. Optimizing imaging methodologies for enhanced detection represents an imperative advancement in this field. Most advanced techniques relying on amplitude modulation scheme such as cross amplitude modulation (xAM) and ultrafast amplitude modulation (uAM) combined with Hadamard encoded multiplane wave transmissions have shown efficacy in capturing acoustic signals of gas vesicles (GVs). Nonetheless, uAM sequence requires odd- or even-element transmissions leading to imprecise amplitude modulation emitting scheme, and the complex multiplane wave transmission scheme inherently yields overlong pulse durations. xAM sequence is limited in terms of field of view and imaging depth. To overcome these limitations, we introduce an innovative ultrafast imaging sequence called nonlinear singular value decomposition (SVD) beamforming. Our method demonstrated a contrast imaging sensitivity comparable to the current gold-standard xAM and uAM, while requiring 4.8 times less pulse transmissions. With similar number of transmit pulses, nonlinear SVD beamforming outperforms xAM and uAM in terms of an improvement in signal-to-background ratio of + 4.78 dB and + 8.29 dB respectively. Additionally, our method provides a higher flexibility in terms of the selection of acoustic pressure amplitude compared to the other methods. Furthermore, it shows a significant potential for application in the realm of ultrasound localization microscopy (ULM), where it stands poised to facilitate the more precise extraction of nonlinear signatures originating from contrast agents.

show abstract

Fast Thresholding of SVD Clutter Filter Using the Spatial Similarity Matrix and a Sum-Table Algorithm

Cited by 5 publications

References 28 publications

Deep learning for fast denoising filtering in ultrasound localization microscopy

Deep learning for fast denoising filtering in ultrasound localization microscopy

Adaptive Clutter Filtering for Speckle Decorrelation-Based Blood Flow Measurements

Nonlinear Singular Value Decomposition Beamforming for Ultrasound Imaging of Gas Vesicles

Contact Info

Product

Resources

About