An official website of the United States government
(Early Access) Effective tissue clutter filtering is critical for non-contrast ultrasound imaging of slow blood flow in small vessels. Independent component analysis (ICA) has been considered by other groups for ultrasound clutter filtering in the past and was shown to be superior to principal component analysis (PCA)-based methods. However, it has not been considered specifically for slow flow applications or revisited since the onset of other slow flow-focused advancements in beamforming and tissue filtering, namely angled plane wave beamforming and full spatiotemporal singular value decomposition (SVD) (i.e., PCA-based) tissue filtering. In this work, we aim to develop a full spatiotemporal ICA-based tissue filtering technique facilitated by plane wave applications and compare it to SVD filtering. We compare ICA and SVD filtering in terms of optimal image quality in simulations and phantoms as well as in terms of optimal correlation to ground truth blood signal in simulations. Additionally, we propose an adaptive blood independent component sorting and selection method. We show that optimal and adaptive ICA can consistently separate blood from tissue better than principal component analysis (PCA)-based methods using simulations and phantoms. Additionally we demonstrate initial in vivo feasibility in ultrasound data of a liver tumor.
more »
« less
A General Framework for Channel Domain SVD Clutter Filtering
Eigen-based clutter filtering of Doppler data has demonstrated greater clutter rejection performance than traditional filtering in a number of studies. However, practical translation of these eigen-based techniques to channel domain filtering applications is limited by their high computational burden. To enable efficient eigen-based filtering of channel data, we propose a domain-adaptive filtering framework. This technique involves using a basis set generated from RF data to filter delayed channel data. Preliminary findings suggest that this technique retains superior clutter rejection performance in comparison to conventional techniques.
more »
« less
- Award ID(s):
- 1750994
- PAR ID:
- 10138674
- Date Published:
- Journal Name:
- 2019 IEEE International Ultrasonics Symposium (IUS)
- Page Range / eLocation ID:
- 2246 to 2248
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
In this article, we exploit the spiked covariance structure of the clutter plus noise covariance matrix for radar signal processing. Using state-of-the-art techniques high dimensional statistics, we propose a nonlinear shrinkage-based rotation invariant spiked covariance ma- trix estimator. We state the convergence of the estimated spiked eigen- values. We use a dataset generated from the high-fidelity, site-specific physics-based radar simulation software RFView to compare the proposed algorithm against the existing rank constrained maximum likelihood (RCML)-expected likelihood (EL) covariance estimationmore » « less
-
The source angle localization problem is studied based on scattering of elastic waves in two dimensions by a phononic array and the exceptional points of its band structure. Exceptional points are complex singularities of a parameterized eigen-spectrum, where two modes coalesce with identical mode shapes. These special points mark the qualitative transitions in the system behavior and have been proposed for sensing applications. The equi-frequency band structures are analyzed with focus on the angle-dependent modal behaviors. At the exceptional points and critical angles, the eigen-modes switch their energy characteristics and symmetry, leading to enhanced sensitivity as the scattering response of the medium is inherently angle-dependent. An artificial neural network is trained with randomly weighted and superposed eigen-modes to achieve deep learning of the angle-dependent dynamics. The trained algorithm can accurately classify the incident angle of an unknown scattering signal, with minimal sidelobe levels and suppressed main lobewidth. The neural network approach shows superior localization performance compared with standard delay-and-sum technique. The proposed application of the phononic array highlights the physical relevance of band topology and eigen-modes to a technological application, adds extra strength to the existing localization methods, and can be easily enhanced with the fast-growing data-driven techniques.more » « less
-
This paper presents clutter detection and mitigation for polarimetric phased array weather radar measurements using machine learning. The following three approaches are analyzed for clutter detection in the cylindrical polarimetric phased array radar measurements, including naive Bayes classifier (NBC), multilayer perceptron (MLP), and convolutional neural network (CNN). Results show that CNN achieves the best performance in clutter detection, followed by MLP and NBC. This is because CNN utilizes spatial information of the input images, which has different features for clutter from that for weather. It is also shown that the combination of physics-based discriminants of power ratio and raw radar measurements is more effective in clutter detection than the direct use of raw radar measurements. In addition, CNN is employed for clutter mitigation and its performance is compared with the traditional speckle filter technique. It is demonstrated that CNN outperforms the speckle filter and incorporation of power ratio in the training process could further improve CNN’s performance in clutter mitigation.more » « less
-
Dynamic spectrum access relies fundamentally on the ability to tune radio transceivers to frequencies that are deemed to be available. Consequently, radio hardware must support tuning over a wide range of frequencies. For the receiver, this precludes the use of fixed frontend filters to reject out-of-band interfering signals. Instead, widely tunable receivers rely on filtering after down-conversion either at IF or baseband. This approach relies on linearity and an ideal mixer to keep the desired signal and interfering signals separated. However, practical receivers exhibit non-linearity, phase noise, and oscillator spurs that cause mixing of the signal of interest and interfering signals. As a result, portions of the interfering signals may appear in the band of the desired signal; this causes interference that cannot be mitigated by filtering. Synthetic diversity mitigates this problem by combining analog and digital processing techniques. In the analog domain, the wide-band RF signal is passed through a passive, lossless multi-port diversity network. Each output from this network is then down-converted and digitized so that multiple versions of the signal are available at digital baseband. As the desired signal and the interfering signals experience different frequency response as they pass through the diversity network, it is possible to employ beam forming methods in digital baseband processing to mitigate the interfering signals while preserving the desired signal. The performance of the proposed synthetic diversity receiver is analyzed and it is shown that excellent interference rejection can be achieved. Rejection performance can be increased even further when the circuit elements in the diversity network can be adapted.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1109/ULTSYM.2019.8925935
