Dictionary Representations for Electrode Displacement Elastography

Pohlman, Robert M.; Varghese, Tomy

doi:10.1109/tuffc.2018.2874181

Cited by 10 publications

(6 citation statements)

References 73 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…PCA-GLUE was inspired by the success of [30] in natural images. Similar work by Pohlman and Varghese [31] has shown promising results on displacement estimation using dictionary representations.…”

mentioning

confidence: 55%

Fast Strain Estimation and Frame Selection in Ultrasound Elastography Using Machine Learning

Zayed

Rivaz

2021

IEEE Trans. Ultrason., Ferroelect., Freq. Contr.

View full text Add to dashboard Cite

Ultrasound Elastography aims to determine the mechanical properties of the tissue by monitoring tissue deformation due to internal or external forces. Tissue deformations are estimated from ultrasound radio frequency (RF) signals and are often referred to as time delay estimation (TDE). Given two RF frames I 1 and I 2 , we can compute a displacement image which shows the change in the position of each sample in I 1 to a new position in I 2 . Two important challenges in TDE include high computational complexity and the difficulty in choosing suitable RF frames. Selecting suitable frames is of high importance because many pairs of RF frames either do not have acceptable deformation for extracting informative strain images or are decorrelated and deformation cannot be reliably estimated. Herein, we introduce a method that learns 12 displacement modes in quasi-static elastography by performing Principal Component Analysis (PCA) on displacement fields of a large training database. In the inference stage, we use dynamic programming (DP) to compute an initial displacement estimate of around 1% of the samples, and then decompose this sparse displacement into a linear combination of the 12 displacement modes. Our method assumes that the displacement of the whole image could also be described by this linear combination of principal components. We then use the GLobal Ultrasound Elastography (GLUE) method to fine-tune the result yielding the exact displacement image. Our method, which we call PCA-GLUE, is more than 10 times faster than DP in calculating the initial displacement map while giving the same result. This is due to converting the problem of estimating millions of variables in DP into a much simpler problem of only 12 unknown weights of the principal components. Our second contribution in this paper is determining the suitability of the frame pair I 1 and I 2 for strain estimation, which we achieve by using the weight vector that we calculated for PCA-GLUE as an input to a multilayer perceptron (MLP) classifier. We validate PCA-GLUE using simulation, phantom, and in vivo data. Our classifier takes only 1.5 ms during the testing phase and has an F1-measure of more than 92% when tested on 1,430 instances collected from both phantom and in vivo datasets.

show abstract

mentioning

confidence: 55%

Fast Strain Estimation and Frame Selection in Ultrasound Elastography Using Machine Learning

Zayed

Rivaz

2021

IEEE Trans. Ultrason., Ferroelect., Freq. Contr.

View full text Add to dashboard Cite

show abstract

“…Many sequential publications have shown successes of EDE in simulation, phantom, ex vivo, and in vivo data (Bharat and Varghese 2006;Bharat et al 2008;Jiang et al 2010;Rubert et al 2010;DeWall et al 2012;Peng et al 2016;Yang et al 2016) as well as high correlation between elastography strain tensor images and histopathology (Rubert et al 2010). Further improvements to displacement estimation used for estimating tissue properties in EDE have greatly improved visualization of liver masses and ablated regions presented in (Pohlman et al 2019b) and with the addition of machine learning in (Pohlman and Varghese 2018), yet low success rates and varying ablated region sizes hinder clinical utilization.…”

Section: Introductionmentioning

confidence: 99%

Physiological Motion Reduction Using Lagrangian Tracking for Electrode Displacement Elastography

Pohlman

Varghese

2020

Ultrasound in Medicine & Biology

Self Cite

View full text Add to dashboard Cite

Minimally invasive treatments such as microwave ablation (MWA), have been growing in popularity for extending liver cancer survival rates in patients, when surgery is not an option. As a nonionizing, real-time alternative to contrast-enhanced computed tomography (CECT), electrode displacement elastography (EDE) has shown promise as an imaging modality for MWA. Despite imaging efficacy, motion artifacts present due to physiological motion result in unintended speckle pattern variance thereby inhibiting consistent and accurate ablated region visualization. To combat these unavoidable motion artifacts, a Lagrangian deformation tracking (LDT) approach based on freehand EDE was developed to track tissue movement and better define tissue properties. For validating LDT efficacy, a spherical inclusion phantom as well as 7 in vivo data sets were processed, and strain tensor images compared to identical time sampled images estimated using a traditional Eulerian approach. In vivo results demonstrate greater consistency among visualized LDT strain tensor images, with segmented ablated regions showing standard deviation reductions of up to 98% when compared to Eulerian strain tensor images. Additionally, Lagrangian strain tensor images provided Dice coefficient improvements up to 25% and success rates improved from approximately 50% to nearly 100% for ablated region visualization.

show abstract

“…We then estimate any kind of compression as some weighted summation of these principal components. A recent work shows promising results of displacement estimation by learning a global dictionary of deformations in electrode displacement elastography [10].…”

Section: Introductionmentioning

confidence: 99%

Fast Approximate Time-Delay Estimation in Ultrasound Elastography Using Principal Component Analysis

Zayed

Rivaz

2019

2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

View full text Add to dashboard Cite

Time delay estimation (TDE) is a critical and challenging step in all ultrasound elastography methods. A growing number of TDE techniques require an approximate but robust and fast method to initialize solving for TDE. Herein, we present a fast method for calculating an approximate TDE between two radio frequency (RF) frames of ultrasound. Although this approximate TDE can be useful for several algorithms, we focus on GLobal Ultrasound Elastography (GLUE), which currently relies on Dynamic Programming (DP) to provide this approximate TDE. We exploit Principal Component Analysis (PCA) to find the general modes of deformation in quasistatic elastography, and therefore call our method PCA-GLUE. PCA-GLUE is a data-driven approach that learns a set of TDE principal components from a training database in real experiments. In the test phase, TDE is approximated as a weighted sum of these principal components. Our algorithm robustly estimates the weights from sparse feature matches, then passes the resulting displacement field to GLUE as initial estimates to perform a more accurate displacement estimation. PCA-GLUE is more than ten times faster than DP in estimation of the initial displacement field and yields similar results.

show abstract

Dictionary Representations for Electrode Displacement Elastography

Cited by 10 publications

References 73 publications

Fast Strain Estimation and Frame Selection in Ultrasound Elastography Using Machine Learning

Fast Strain Estimation and Frame Selection in Ultrasound Elastography Using Machine Learning

Physiological Motion Reduction Using Lagrangian Tracking for Electrode Displacement Elastography

Fast Approximate Time-Delay Estimation in Ultrasound Elastography Using Principal Component Analysis

Contact Info

Product

Resources

About