Multi-frame elastography using a handheld force-controlled ultrasound probe

Kuzmin, Andrey; Zakrzewski, A; Anthony, Brian W.; Lempitsky, Victor

doi:10.1109/tuffc.2015.007133

Cited by 20 publications

(9 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…From the acquired image sequences, we compute the gradient of the displacement distribution, which forms the approximate tissue strain map. Given the known, controlled contact force at the body surface, the inverse elastography problem can be solved iteratively to determine tissue elasticity as a function of location 12 . We have applied this approach to simultaneously calculating the elastic properties of tissue and the pressure of an enclosed artery, and have established feasibility in simulations and in a realistic phantom set-up 13 .…”

Section: Bp Estimation From An Expanded Model Of Compression Elasticitymentioning

confidence: 99%

Enhanced ultrasound for advanced diagnostics, ultrasound tomography for volume limb imaging and prosthetic fitting

Anthony

2016

SPIE Proceedings

Self Cite

View full text Add to dashboard Cite

Ultrasound imaging methods hold the potential to deliver low-cost, high-resolution, operator-independent and nonionizing imaging systems -such systems couple appropriate algorithms with imaging devices and techniques. The increasing demands on general practitioners motivate us to develop more usable and productive diagnostic imaging equipment. Ultrasound, specifically freehand ultrasound, is a low cost and safe medical imaging technique. It doesn't expose a patient to ionizing radiation. Its safety and versatility make it very well suited for the increasing demands on general practitioners, or for providing improved medical care in rural regions or the developing world. However it typically suffers from sonographer variability; we will discuss techniques to address user variability.We also discuss our work to combine cylindrical scanning systems with state of the art inversion algorithms to deliver ultrasound systems for imaging and quantifying limbs in 3-D in vivo. Such systems have the potential to track the progression of limb health at a low cost and without radiation exposure, as well as, improve prosthetic socket fitting. Current methods of prosthetic socket fabrication remain subjective and ineffective at creating an interface to the human body that is both comfortable and functional. Though there has been recent success using methods like magnetic resonance imaging and biomechanical modeling, a low-cost, streamlined, and quantitative process for prosthetic cup design and fabrication has not been fully demonstrated. Medical ultrasonography may inform the design process of prosthetic sockets in a more objective manner. This keynote talk presents the results of progress in this area.

show abstract

Section: Bp Estimation From An Expanded Model Of Compression Elasticitymentioning

confidence: 99%

Enhanced ultrasound for advanced diagnostics, ultrasound tomography for volume limb imaging and prosthetic fitting

Anthony

2016

SPIE Proceedings

Self Cite

View full text Add to dashboard Cite

show abstract

“…the change of speckle appearance due to out-of-plane motion. A different strategy, which can be referred to as optimisation-based methods, involves minimising a cost function that combines image similarity and displacement regularity (Pellot-Barakat et al 2004 , Kuzmin et al 2015 , Hashemi and Rivaz 2017 ). These methods assume the displacement throughout the tissue to be smooth and, therefore, justify the use of a regularisation parameter that penalises the correlation function to prevent displacement discontinuity.…”

Section: Introductionmentioning

confidence: 99%

An unsupervised learning approach to ultrasound strain elastography with spatio-temporal consistency

Delaunay

Vercauteren

2021

Phys. Med. Biol.

View full text Add to dashboard Cite

Quasi-static ultrasound elastography (USE) is an imaging modality that measures deformation (i.e. strain) of tissue in response to an applied mechanical force. In USE, the strain modulus is traditionally obtained by deriving the displacement field estimated between a pair of radio-frequency data. In this work we propose a recurrent network architecture with convolutional long-short-term memory decoder blocks to improve displacement estimation and spatio-temporal continuity between time series ultrasound frames. The network is trained in an unsupervised way, by optimising a similarity metric between the reference and compressed image. Our training loss is also composed of a regularisation term that preserves displacement continuity by directly optimising the strain smoothness, and a temporal continuity term that enforces consistency between successive strain predictions. In addition, we propose an open-access in vivo database for quasi-static USE, which consists of radio-frequency data sequences captured on the arm of a human volunteer. Our results from numerical simulation and in vivo data suggest that our recurrent neural network can account for larger deformations, as compared with two other feed-forward neural networks. In all experiments, our recurrent network outperformed the state-of-the-art for both learning-based and optimisation-based methods, in terms of elastographic signal-to-noise ratio, strain consistency, and image similarity. Finally, our open-source code provides a 3D-slicer visualisation module that can be used to process ultrasound RF frames in real-time, at a rate of up to 20 frames per second, using a standard GPU.

show abstract

“…The displacement estimation, also known as time-delay estimation, has been historically performed by maximizing a correlation function between local frame windows, either in the time or phase domain [18,20,2,22,1]. More recently, different approaches have added a regularization parameter to account for displacement discontinuity and improve displacement estimates [15,6]. Although these methods demonstrated the ability to make an accurate displacement estimation, current techniques are sensitive to noise and global decorrelation, i.e.…”

Section: Introductionmentioning

confidence: 99%

An Unsupervised Approach to Ultrasound Elastography with End-to-end Strain Regularisation

Delaunay,

Hu,

Vercauteren

2020

Preprint

View full text Add to dashboard Cite

Quasi-static ultrasound elastography (USE) is an imaging modality that consists of determining a measure of deformation (i.e. strain) of soft tissue in response to an applied mechanical force. The strain is generally determined by estimating the displacement between successive ultrasound frames acquired before and after applying manual compression. The computational efficiency and accuracy of the displacement prediction, also known as time-delay estimation, are key challenges for real-time USE applications. In this paper, we present a novel deeplearning method for efficient time-delay estimation between ultrasound radio-frequency (RF) data. The proposed method consists of a convolutional neural network (CNN) that predicts a displacement field between a pair of pre-and post-compression ultrasound RF frames. The network is trained in an unsupervised way, by optimizing a similarity metric between the reference and compressed image. We also introduce a new regularization term that preserves displacement continuity by directly optimizing the strain smoothness. We validated the performance of our method by using both ultrasound simulation and in vivo data on healthy volunteers. We also compared the performance of our method with a state-of-the-art method called OVERWIND [17]. Average contrast-tonoise ratio (CNR) and signal-to-noise ratio (SNR) of our method in 30 simulation and 3 in vivo image pairs are 7.70 and 6.95, 7 and 0.31, respectively. Our results suggest that our approach can effectively predict accurate strain images. The unsupervised aspect of our approach represents a great potential for the use of deep learning application for the analysis of clinical ultrasound data.

show abstract

Multi-frame elastography using a handheld force-controlled ultrasound probe

Cited by 20 publications

References 30 publications

Enhanced ultrasound for advanced diagnostics, ultrasound tomography for volume limb imaging and prosthetic fitting

Enhanced ultrasound for advanced diagnostics, ultrasound tomography for volume limb imaging and prosthetic fitting

An unsupervised learning approach to ultrasound strain elastography with spatio-temporal consistency

An Unsupervised Approach to Ultrasound Elastography with End-to-end Strain Regularisation

Contact Info

Product

Resources

About