SUSHI: Sparsity-Based Ultrasound Super-Resolution Hemodynamic Imaging

Bar‐Zion, Avinoam; Solomon, Oren; Tremblay-Darveau, Charles; Adam, Dan; Eldar, Yonina C.

doi:10.1109/tuffc.2018.2873380

Cited by 99 publications

(101 citation statements)

References 42 publications

Supporting

Mentioning

100

Contrasting

Unclassified

Order By: Relevance

“…LSPARCOM takes after the general framework of SPARCOM, but replaces the need for explicit prior knowledge of the PSF, used in SPARCOM to calculate the measurement matrix, with learned filters. The mathematical justification for this replacement arises from replacing the original input to SPARCOM (v), which uses the information regarding the PSF to choose and weight elements of the covariance matrix R y , with a hard-choice of only the diagonal elements, yielding the variance matrix of the input movie, similar to the approach used in second-order SOFI with auto-cumulants and SUSHI [5,30]. While in second-order auto-cumulant SOFI this leads to the final estimation of the super-resolved image, requiring no knowledge or estimation of the PSF, in SUSHI this image is the starting point to a sparse coding procedure.…”

Section: Conclusion and Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Learned SPARCOM: Unfolded Deep Super-Resolution Microscopy

Dardikman-Yoffe

Eldar

2020

Preprint

Self Cite

View full text Add to dashboard Cite

The use of photo-activated fluorescent molecules to create long sequences of low emitter-density diffraction-limited images enables high-precision emitter localization. However, this is achieved at the cost of lengthy imaging times, limiting temporal resolution. In recent years, a variety of approaches have been suggested to reduce imaging times, ranging from classical optimization and statistical algorithms to deep learning methods. Classical methods often rely on prior knowledge of the optical system and require heuristic adjustment of parameters or do not lead to good enough performance. Deep learning methods proposed to date tend to suffer from poor generalization ability outside the specific distribution they were trained on, and require learning of many parameters. They also tend to lead to black-box solutions that are hard to interpret. In this paper, we suggest combining a recent high-performing classical method, SPARCOM, with model-based deep learning, using the algorithm unfolding approach which relies on an iterative algorithm to design a compact neural network considering domain knowledge. We show that the resulting network, Learned SPARCOM (LSPARCOM), requires far fewer layers and parameters, and can be trained on a single field of view. Nonetheless it yields comparable or superior results to those obtained by SPARCOM with no heuristic parameter determination or explicit knowledge of the point spread function, and is able to generalize better than standard deep learning techniques. It even allows producing a high-quality reconstruction from as few as 25 frames. This is due to a significantly smaller network, which also contributes to fast performance -5× improvement in execution time relative to SPARCOM, and a full order of magnitudes improvement relative to a leading competing deep learning method (Deep-STORM) when implemented serially. Our results show that we can obtain super-resolution imaging from a small number of high emitter density frames without knowledge of the optical system and across different test sets. Thus, we believe LSPARCOM will find broad use in single molecule localization microscopy of biological structures, and pave the way to interpretable, efficient live-cell imaging in a broad range of settings.

show abstract

Section: Conclusion and Discussionmentioning

confidence: 99%

“…Seeking for a formulation which does not mandate prior knowledge of the PSF, a similar optimization problem to that given in (8) can be obtained by posing a sparse recovery problem on the variance image directly [30]. This can be done by applying the variance operator Var[·] on (2)…”

Section: Algorithm 2 Lsaprcom At Inference Timementioning

confidence: 99%

Learned SPARCOM: Unfolded Deep Super-Resolution Microscopy

Dardikman-Yoffe

Eldar

2020

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Recent developments also leverage the microbubbles used in CEUS to yield super-resolution imaging [30], [31], [32], [33]. Ultrasound localization microscopy (ULM) is a particularly popular approach to achieve this [8].…”

Section: Advanced Applicationsmentioning

confidence: 99%

“…As such, long acquisitions of tens of minutes are required, even with uULM [94]. To boost the achieved coverage in a given timespan, methods that enable the use of higher concentrations can be leveraged [32], [33], [95], [96], [97].…”

Section: A Ultrasound Localization Microscopymentioning

confidence: 99%

“…To that end, a multiple-measurement vector model [98] and its structure in a transformed domain can be considered, e.g. by assuming that a temporal stack of frames x is sparse in the temporal correlation domain [32], [33]. Considering the temporal dimension, sparse recovery may be improved by exploiting the motion of microbubbles, allowing the application of a prior on the spatial microbubble distribution through Kalman tracking [99].…”

Section: B Exploiting Signal Structurementioning

confidence: 99%

See 1 more Smart Citation

Deep Learning in Ultrasound Imaging

2020

Self Cite

View full text Add to dashboard Cite

Deep learning is taking an ever more prominent role in medical imaging. This paper discusses applications of this powerful approach in ultrasound imaging systems along with domain-specific opportunities and challenges.ABSTRACT | We consider deep learning strategies in ultrasound systems, from the front-end to advanced applications. Our goal is to provide the reader with a broad understanding of the possible impact of deep learning methodologies on many aspects of ultrasound imaging. In particular, we discuss methods that lie at the interface of signal acquisition and machine learning, exploiting both data structure (e.g. sparsity in some domain) and data dimensionality (big data) already at the raw radio-frequency channel stage.As some examples, we outline efficient and effective deep learning solutions for adaptive beamforming and adaptive spectral Doppler through artificial agents, learn compressive encodings for color Doppler, and provide a framework for structured signal recovery by learning fast approximations of iterative minimization problems, with applications to clutter suppression and super-resolution ultrasound. These emerging technologies may have considerable impact on ultrasound imaging, showing promise across key components in the receive processing chain.

show abstract