Phidakordor Sahshong, Akash Chandra, Karla P. Mercado-Shekhar, Manish Bhatt
{"title":"Deep denoising approach to improve shear wave phase velocity map reconstruction in ultrasound elastography","authors":"Phidakordor Sahshong, Akash Chandra, Karla P. Mercado-Shekhar, Manish Bhatt","doi":"10.1002/mp.17581","DOIUrl":null,"url":null,"abstract":"<div>\n \n \n <section>\n \n <h3> Background</h3>\n \n <p>Measurement noise often leads to inaccurate shear wave phase velocity estimation in ultrasound shear wave elastography. Filtering techniques are commonly used for denoising the shear wavefields. However, these filters are often not sufficient, especially in fatty tissues where the signal-to-noise ratio (SNR) can be very low.</p>\n </section>\n \n <section>\n \n <h3> Purpose</h3>\n \n <p>The purpose of this study is to develop a deep learning approach for denoising shear wavefields in ultrasound shear wave elastography. This may lead to improved reconstruction of shear wave phase velocity image maps.</p>\n </section>\n \n <section>\n \n <h3> Methods</h3>\n \n <p>The study addresses noise by transforming particle velocity data into a time-frequency representation. A neural network with encoder and decoder convolutional blocks effectively decomposes the input and extracts the signal of interest, improving the SNR in high-noise scenarios. The network is trained on simulated phantoms with elasticity values ranging from 3 to 60 kPa. A total of 1 85 570 samples with 80%–20<span></span><math>\n <semantics>\n <mo>%</mo>\n <annotation>$\\%$</annotation>\n </semantics></math> split were used for training and validation. The approach is tested on experimental phantom and ex-vivo goat liver tissue data. Performance was compared with the traditional filtering methods such as bandpass, median, and wavelet filtering. Kruskal–Wallis one-way analysis of variance was performed to check statistical significance. Multiple comparisons were performed using the Mann–Whitney U test and Holm–Bonferroni adjustment of <span></span><math>\n <semantics>\n <mrow>\n <mi>p</mi>\n <mo>−</mo>\n <mi>values</mi>\n </mrow>\n <annotation>$p-{\\rm values}$</annotation>\n </semantics></math>.</p>\n </section>\n \n <section>\n \n <h3> Results</h3>\n \n <p>The results are evaluated using SNR and the percentage of pixels that can be reconstructed in the phase velocity maps. The SNR levels in experimental data improved from –2 to 9.9 dB levels to 15.6 to 30.3 dB levels. Kruskal–Wallis one-way analysis showed statistical significance (<span></span><math>\n <semantics>\n <mrow>\n <mi>p</mi>\n <mo><</mo>\n <mn>0.05</mn>\n </mrow>\n <annotation>$p<0.05$</annotation>\n </semantics></math>). Multiple comparisons with <i>p</i>-value corrections also showed statistically significant improvement when compared to the bandpass and wavelet filtering scheme (<span></span><math>\n <semantics>\n <mrow>\n <mi>p</mi>\n <mo><</mo>\n <mn>0.05</mn>\n </mrow>\n <annotation>$p<0.05$</annotation>\n </semantics></math>). Smoother phase velocity maps were reconstructed after denoising. The coefficient of variation is less than <span></span><math>\n <semantics>\n <mrow>\n <mn>5</mn>\n <mo>%</mo>\n </mrow>\n <annotation>$5\\%$</annotation>\n </semantics></math> in CIRS phantom and less than <span></span><math>\n <semantics>\n <mrow>\n <mn>18</mn>\n <mo>%</mo>\n </mrow>\n <annotation>$18\\%$</annotation>\n </semantics></math> in ex-vivo goat liver tissue.</p>\n </section>\n \n <section>\n \n <h3> Conclusions</h3>\n \n <p>The proposed approach demonstrates improvement in shear wave phase velocity image map reconstruction and holds promise that deep learning methods can be effectively utilized to extract true shear wave signal from measured noisy data.</p>\n </section>\n </div>","PeriodicalId":18384,"journal":{"name":"Medical physics","volume":"52 3","pages":"1481-1499"},"PeriodicalIF":3.2000,"publicationDate":"2024-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Medical physics","FirstCategoryId":"3","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1002/mp.17581","RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING","Score":null,"Total":0}
引用次数: 0
Abstract
Background
Measurement noise often leads to inaccurate shear wave phase velocity estimation in ultrasound shear wave elastography. Filtering techniques are commonly used for denoising the shear wavefields. However, these filters are often not sufficient, especially in fatty tissues where the signal-to-noise ratio (SNR) can be very low.
Purpose
The purpose of this study is to develop a deep learning approach for denoising shear wavefields in ultrasound shear wave elastography. This may lead to improved reconstruction of shear wave phase velocity image maps.
Methods
The study addresses noise by transforming particle velocity data into a time-frequency representation. A neural network with encoder and decoder convolutional blocks effectively decomposes the input and extracts the signal of interest, improving the SNR in high-noise scenarios. The network is trained on simulated phantoms with elasticity values ranging from 3 to 60 kPa. A total of 1 85 570 samples with 80%–20 split were used for training and validation. The approach is tested on experimental phantom and ex-vivo goat liver tissue data. Performance was compared with the traditional filtering methods such as bandpass, median, and wavelet filtering. Kruskal–Wallis one-way analysis of variance was performed to check statistical significance. Multiple comparisons were performed using the Mann–Whitney U test and Holm–Bonferroni adjustment of .
Results
The results are evaluated using SNR and the percentage of pixels that can be reconstructed in the phase velocity maps. The SNR levels in experimental data improved from –2 to 9.9 dB levels to 15.6 to 30.3 dB levels. Kruskal–Wallis one-way analysis showed statistical significance (). Multiple comparisons with p-value corrections also showed statistically significant improvement when compared to the bandpass and wavelet filtering scheme (). Smoother phase velocity maps were reconstructed after denoising. The coefficient of variation is less than in CIRS phantom and less than in ex-vivo goat liver tissue.
Conclusions
The proposed approach demonstrates improvement in shear wave phase velocity image map reconstruction and holds promise that deep learning methods can be effectively utilized to extract true shear wave signal from measured noisy data.
期刊介绍:
Medical Physics publishes original, high impact physics, imaging science, and engineering research that advances patient diagnosis and therapy through contributions in 1) Basic science developments with high potential for clinical translation 2) Clinical applications of cutting edge engineering and physics innovations 3) Broadly applicable and innovative clinical physics developments
Medical Physics is a journal of global scope and reach. By publishing in Medical Physics your research will reach an international, multidisciplinary audience including practicing medical physicists as well as physics- and engineering based translational scientists. We work closely with authors of promising articles to improve their quality.