Automatic Frame Selection Using MLP Neural Network in Ultrasound Elastography

Zayed, Abdelrahman; Rivaz, Hassan

doi:10.1007/978-3-030-27272-2_41

Cited by 5 publications

(6 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, ALTRUIST is a fast strain imaging technique where the runtime can be further accelerated by optimizing its implementation on a GPU. Finally, an appropriate motion pattern between the RF frames can be ensured by concatenating ALTRUIST with a CNN‐based automatic frame selection 80 technique. Featuring these consequential advancements, ALTRUIST and its extensions can be stepping stones to the vast clinical adoption of ultrasound elastography.…”

Section: Discussionmentioning

confidence: 99%

Alternating direction method of multipliers for displacement estimation in ultrasound strain elastography

Ashikuzzaman,

Peng,

Jiang

et al. 2023

Medical Physics

Self Cite

View full text Add to dashboard Cite

BackgroundUltrasound strain imaging, which delineates mechanical properties to detect tissue abnormalities, involves estimating the time delay between two radio‐frequency (RF) frames collected before and after tissue deformation. The existing regularized optimization‐based time‐delay estimation (TDE) techniques suffer from at least one of the following drawbacks: (1) The regularizer is not aligned with the tissue deformation physics due to taking only the first‐order displacement derivative into account; (2) The L2‐norm of the displacement derivatives, which oversmooths the estimated time‐delay, is utilized as the regularizer; (3) The modulus function defined mathematically should be approximated by a smooth function to facilitate the optimization of L1‐norm.PurposeOur purpose is to develop a novel TDE technique that resolves the aforementioned shortcomings of the existing algorithms.MethodsHerein, we propose employing the alternating direction method of multipliers (ADMM) for optimizing a novel cost function consisting of L2‐norm data fidelity term and L1‐norm first‐ and second‐order spatial continuity terms. ADMM empowers the proposed algorithm to use different techniques for optimizing different parts of the cost function and obtain high‐contrast strain images with smooth backgrounds and sharp boundaries. We name our technique ADMM for totaL variaTion RegUlarIzation in ultrasound STrain imaging (ALTRUIST). ALTRUIST's efficacy is quantified using absolute error (AE), Structural SIMilarity (SSIM), signal‐to‐noise ratio (SNR), contrast‐to‐noise ratio (CNR), and strain ratio (SR) with respect to GLUE, OVERWIND, and L1‐SOUL, three recently published energy‐based techniques, and UMEN‐Net, a state‐of‐the‐art deep learning‐based algorithm. Analysis of variance (ANOVA)‐led multiple comparison tests and paired t‐tests at 5% overall significance level were conducted to assess the statistical significance of our findings. The Bonferroni correction was taken into account in all statistical tests. Two simulated layer phantoms, three simulated resolution phantoms, one hard‐inclusion simulated phantom, one multi‐inclusion simulated phantom, one experimental breast phantom, and three in vivo liver cancer datasets have been used for validation experiments. We have published the ALTRUIST code at http://code.sonography.ai.ResultsALTRUIST substantially outperforms the four state‐of‐the‐art benchmarks in all validation experiments, both qualitatively and quantitatively. ALTRUIST yields up to , , and SNR improvements and , , and CNR improvements over L1‐SOUL, its closest competitor, for simulated, phantom, and in vivo liver cancer datasets, respectively, where the asterisk (*) indicates statistical significance. In addition, ANOVA‐led multiple comparison tests and paired t‐tests indicate that ALTRUIST generally achieves statistically significant improvements over GLUE, UMEN‐Net, OVERWIND, and L1‐SOUL in terms of AE, SSIM map, SNR, and CNR.ConclusionsA novel ultrasonic displacement tracking algorithm named ALTRUIST has been developed. The principal novelty of ALTRUIST is incorporating ADMM for optimizing an L1‐norm regularization‐based cost function. ALTRUIST exhibits promising performance in simulation, phantom, and in vivo experiments.

show abstract

Section: Discussionmentioning

confidence: 99%

Alternating direction method of multipliers for displacement estimation in ultrasound strain elastography

Ashikuzzaman,

Peng,

Jiang

et al. 2023

Medical Physics

Self Cite

View full text Add to dashboard Cite

show abstract

“…3) PCA-GLUE, which relies on DP to compute the initial displacement map, is robust to potential DP failures. This work is an extension of our recent work [39], [40], with the following major changes. First, we replace the multi-layer perceptron (MLP) classifier with a more robust one that can generalize better to unseen data.…”

mentioning

confidence: 92%

“…First, we replace the multi-layer perceptron (MLP) classifier with a more robust one that can generalize better to unseen data. Second, we used automatically annotated images for training the classifier, compared to manual annotation that we previously used in [40]. Third, testing is now substantially more rigorous and is performed on 5 different datasets from simulation, phantom and in vivo data.…”

mentioning

confidence: 99%

“…Third, testing is now substantially more rigorous and is performed on 5 different datasets from simulation, phantom and in vivo data. And last, the criteria for measuring the performance of the classifier used in this paper are the accuracy and F1-measure instead of using the signal to Noise Ratio (SNR) and Contrast to Noise Ratio (CNR) in [40]. Our code is available at https://code.sonography.ai and at https://github.com/AbdelrahmanZayed…”

mentioning

confidence: 99%

See 1 more Smart Citation

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

Zayed

Rivaz

2021

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

Self Cite

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

“…An implicit strain reconstruction technique based on convolutional neural network has been proposed in [43], [44]. In addition, a neural network-based technique for the automatic selection of the suitable frames for ultrasonic strain estimation has been introduced in [45]. Another technique [46] has retrained three existing networks named FlowNet 2.0 [42], PWC-Net [47], and LiteFlow-Net [48] with simulation datasets and tested the performance on real datasets.…”

Section: Introductionmentioning

confidence: 99%

Incorporating Gradient Similarity for Robust Time Delay Estimation in Ultrasound Elastography

Ashikuzzaman¹,

Hall²,

Rivaz³

2022

Preprint

Self Cite

View full text Add to dashboard Cite

Energy-based ultrasound elastography techniques minimize a regularized cost function consisting of data and continuity terms to obtain local displacement estimates based on the local time-delay estimation (TDE) between radio-frequency (RF) frames. The data term associated with the existing techniques takes only the amplitude similarity into account and hence is not sufficiently robust to the outlier samples present in the RF frames under consideration. This drawback creates noticeable artifacts in the strain image. To resolve this issue, we propose to formulate the data function as a linear combination of the amplitude and gradient similarity constraints. We estimate the adaptive weight concerning each similarity term following an iterative scheme. Finally, we optimize the non-linear cost function in an efficient manner to convert the problem to a sparse system of linear equations which are solved for millions of variables. We call our technique rGLUE: robust data term in GLobal Ultrasound Elastography. rGLUE has been validated using simulation, phantom, in vivo liver, and breast datasets. In all of our experiments, rGLUE substantially outperforms the recent elastography methods both visually and quantitatively. For simulated, phantom, and in vivo datasets, respectively, rGLUE achieves 107%, 18%, and 23% improvements of signalto-noise ratio (SNR) and 61%, 19%, and 25% improvements of contrast-to-noise ratio (CNR) over GLUE, a recently-published elastography algorithm.

show abstract

Automatic Frame Selection Using MLP Neural Network in Ultrasound Elastography

Cited by 5 publications

References 22 publications

Alternating direction method of multipliers for displacement estimation in ultrasound strain elastography

Alternating direction method of multipliers for displacement estimation in ultrasound strain elastography

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

Incorporating Gradient Similarity for Robust Time Delay Estimation in Ultrasound Elastography

Contact Info

Product

Resources

About