Do We Need Pre-Processing for Deep Learning Based Ultrasound Shear Wave Elastography?

Introduction. The shear wave ultrasound elastography is a recently developed ultrasound-based method in the clinical practice, which allows the qualitative visual and quantitative measurements of tissue stiffness. In the 2010 this technology of the shear wave was called Shear Wave Elastograhpy. Due to the front of the shear waves the qualitative and quantitative assessment of the tissue stiffness is possible. Objective is to examine the efficacy of the shear wave ultrasound elastography in the evaluation of the prevalence of the oncological disease in patients with the prostate cancer and to compare the obtained results with the routine method X-ray diagnostics. Materials and methods. From the april 2015 in the I.M. Sechenov First Moscow State Medical University Urology Clinic there were conducted 314 shear wave ultrasound elastography examinations of the prostate. The ultrasound system Aixplorer® by SuperSonic Imagine was used. This system provides information provided by B-mode and shear wave ultrasound elastography mode. The transrectal echograms were made in 6 dimensions, so called Q-boxes (3 demensions in the every lobe on the segments from the base to the apex, according to the biopsy zone). The unit of measurement was the mean value in the kilopaskals (kPa). All the patients were randomized into 3 groups. There were 146 men with the possible prostate cancer in the first group (prospective study), 120 men with the certain diagnosis of the prostate cancer in the second group (retrospective study) and 48 healthy men in the third group (control study). In all the patients of the first and the second groups the routine complete examination, including the prostate specific antigen (PSA) level examination, digital rectal examination (DRE), doppler transrectal ultrasonography (TRUS), histoscanning and ultrasound shear wave elastography (SWE), was conducted. In the 229 patients of the first and the second groups the prostatectomy with the morphological verification of postoperative material was made. In the 63 patients of the first and the second groups the contrast-enhanced magnetic resonance imaging (MRI) of the pelvic organs was made. In the health men’s group, besides the ultrasound shear wave elastography, only the routine diagnosis methods of the prostate cancer (PSA level, TRUS and DRE) were used. Results. According to the results of our study, the threshold values for the normal prostate tissue stiffness due to the ultrasound shear wave elastography were from 0 to 23 kPa, for the hyperplastic prostate – from 23.4 to 50 kPa, for the prostate cancer – from 50.5 kPa. The data analysis of the 212 patients with the verified prostate cancer showed the increase of the mean degree of tissue stiffness due to the clinical stage and tumor differentiation (Gleason scale total score). All the patients were divided into the subgroups with the certain correlation values. In patients with the Gleason scale total score < 7, the mean degree of tissue stiffness was 72 kPa (n = 63). In 57 patients with the Gleason scale total score 7, the mean degree of tissue stiffness was 69 kPa. In 48 patients with the Gleason scale total score from 8 to 10, the tissue stiffness was averagely 119 kPa. The locally advanced stage Т3–4 was determined in 44 examined patients. The tissue stiffness value correlated with the tumor differentiation rate: the index variations were from 120 to 295 kPa. On the results of this method analysis, its resistance was 90,8 % and specificity was 94,6 %. According to the comparative assessment with the other examination technics, the informative value of the ultrasound shear wave elastography is far above the DRE, the doppler TRUS and the histoscanning, but is lower than the contrast-enhanced magnetic resonance imaging. Conclusion. In view of the above, the ultrasound shear wave elastography is a very informative method of the prostate cancer detection and it has a high rate of the agreement of the results with the contrast-enhanced magnetic resonance imaging and is more specific than the histoscanning.

There is a paucity of available literature describing the frequency of technical success of liver two-dimensional (2-D) ultrasound (US) shear wave elastography (SWE) in children and young adults. To determine the frequency of technical success of liver 2-D ultrasound (US) SWE in children and young adults based on the interquartile range (IQR)/median of 10 shear wave speed (SWS) measurements. Clinical 2-D US SWE exams performed between February 2016 and March 2018 were retrospectively identified. Patient age and gender, median/mean liver stiffness (10 SWS measurements), IQR/median, abdominal wall thickness, body mass index (BMI) and serum alanine aminotransferase (ALT) were documented. The number of technically inadequate exams was calculated using three methods: 1) IQR/median >0.3, 2) IQR/median >95th percentile for our study population and 3) statistical outlier identification using the Tukey method. The effect of age, gender, median SWS, abdominal wall thickness, BMI, US transducer and ALT on measurement variability (IQR/median) was assessed using multivariable linear regression. During the study period, 573 exams were performed. Mean age was 12.6±7.1years; 274 (47.8%) exams were in male patients. Average median liver stiffness was 1.75±0.47m/s. Based on Methods 1, 2 and 3, 29/573 (5.1%), 28/573 (4.9%, IQR/median cutoff value=0.303) and 30/573 (5.2%) exams were technically inadequate. Predictors of IQR/median included age (P=0.03), abdominal wall thickness (P=0.003), median SWS (P<0.0001) and transducer (P<0.0001). Approximately 95% of liver 2-D US SWE exams are technically successful based on IQR/median in children and young adults.

Ultrasound shear wave elastography for measuring intracompartmental pressure of compartment syndrome using a turkey hind limb model

Objective:We compare the repeatability and accuracy of ultrasound shear wave elastography (USE) and transient optical coherence elastography (OCE).Methods:Elastic wave speed in gelatin phantoms and chicken breast was measured with USE and OCE and compared with uniaxial mechanical compression testing. Intra- and Inter-repeatability were analyzed using Bland-Altman plots and intraclass correlation coefficients (ICC).Results:OCE and USE differed from uniaxial testing by a mean absolute percent error of 8.92% and 16.9%, respectively, across eight phantoms of varying stiffness. Upper and lower limits of agreement for intrasample repeatability for USE and OCE were ±0.075 m/s and −0.14 m/s and 0.13 m/s, respectively. OCE and USE both had ICCs of 0.9991. In chicken breast, ICC for USE was 0.9385 and for OCE was 0.9924.Conclusion:OCE and USE can detect small speed changes and give comparable measurements. These measurements correspond well with uniaxial testing.

Ultrasound Shear Wave Elastography: A Novel Method to Evaluate Bladder Pressure

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. 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 imagemaps. 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 60kPa. A total of 185570 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 . 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 9.9dB 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 livertissue. 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 noisydata.

Objectives: To determine the prognostic significance of tissue stiffness measurement using transrectal ultrasound shear wave elastography in predicting biochemical recurrence following radical prostatectomy for clinically localized prostate cancer.Patients and Methods: Eligible male patients with clinically localized prostate cancer and extraperitoneal laparoscopic radical prostatectomy between November 2013 and August 2017 were retrospectively selected. Information of potential biochemical recurrence predictors, including imaging (ultrasound shear wave elastography and magnetic resonance imaging), clinicopathological characteristics, and preoperative prostate specific antigen (PSA) levels were obtained. Recurrence-free survival (Kaplan–Meier curve) and a multivariate model were constructed using Cox regression analysis to evaluate the impact of shear wave elastography as a prognostic marker for biochemical recurrence.Results: Patients experienced biochemical recurrence in an average of 26.3 ± 16.3 months during their follow-up. A cutoff of 144.85 kPa for tissue stiffness measurement was estimated for recurrence status at follow-up with a sensitivity of 74.4% and a specificity of 61.7%, respectively (p < 0.05). In univariate analysis, shear wave elastography performed well in all preoperative factors compared to biopsy Gleason Score, PSA and magnetic resonance imaging; in multivariate analysis with postoperative pathological factors, shear wave elastography was statistically significant in predicting postoperative biochemical recurrence, which improved the C-index of predictive nomogram significantly (0.74 vs. 0.70, p < 0.05).Conclusions: The study revealed that quantitative ultrasound shear wave elastography-measured tissue stiffness was a significant imaging marker that enhanced the predictive ability with other clinical and histopathological factors in prognosticating postoperative biochemical recurrence following radical prostatectomy for clinically localized prostate cancer.

Ultrasound shear wave elastography is an objective tool to evaluate the stiffness of human tissues. Patients with sialolithiasis could be treated by interventional sialendoscopy with a high success rate. Sialolithiasis could be extracted, and the diseased gland could be preserved and evaluated after treatment. Whether ultrasound shear wave elastography could be used for objective outcome measurement and short-term follow-up of the parenchyma of gland in patients with sialolithiasis remains unclear. This retrospective self-controlled study was conducted. Patients with sialolithiasis treated by interventional sialendoscopy and followed by high-resolution ultrasound shear wave elastography were selected between January and September 2017. Seventeen patients with sialolithiasis (mean age: 39.63 ± 12.49 years), including 10 women and 7 men, were enrolled. Fifteen patients had sialolithiasis in the submandibular gland and two in the parotid gland. The preoperative value of shear wave velocity was significantly higher in the diseased gland than in the contralateral normal gland (p < .001; 95% confidence interval [CI], 0.3915-0.6046). After successful treatment by interventional sialendoscopy surgery, the shear wave velocity of the diseased gland decreased significantly (p=0.001; 95% CI, -0.38792 to -0.20474). However, there was a significant difference between the diseased and contralateral normal glands (p=0.001; 95% CI, 0.0423-0.2895) after 1.55 months of surgery. Ultrasound shear wave elastography could be an adjuvant tool to distinguish sialolithiasis-affected diseased glands from contralateral normal glands and assess the short-term treatment outcome objectively. The changing trend of shear wave velocity could help monitor the healing process of the parenchyma in the diseased gland after treatment. 4.

Ultrasound Shear Wave Elastography for Liver Disease. A Critical Appraisal of the Many Actors on the Stage.

Pancreas shear wave speed might be a biomarker of pancreatic disease in children. This study aimed to measure pancreas shear wave speed by two-dimensional (2-D) ultrasound shear wave elastography (SWE) in a balanced cohort of presumed healthy children. This was a prospective study of 120 children (<18years of age) without a known history of pancreatic disease, who underwent ultrasound 2-D SWE of the pancreas. Five shear wave speed measurements in the pancreas body and/or tail were obtained for each participant using a Canon Aplio i800 system, i8CX1 transducer. The Mann-Whitney U test or Kruskal-Wallis test were used to compare continuous distributions. Spearman's correlation was used to assess univariate relationships between continuous variables. Multivariable regression with stepwise selection was used to evaluate independent predictors of pancreas shear wave speed. The median age for the study population was 5.0years (range: 7days to 17.8years) and 61 (50.8%) of the participants were female. The median depth of shear wave speed measurement was 4.7cm (interquartile range [IQR]: 4.2-5.3). The median pancreas shear wave speed was 1.31m/s (IQR: 1.21-1.40). On multivariable analysis, female biological sex (P=0.051), the number of hours nil per os (P=0.097), the median depth of measurement (P=0.001) and the median liver shear wave speed (P=0.020) were positively associated with pancreas shear wave speed. We report pancreas shear wave speed in a large, balanced cohort of children without a known history of pancreatic disease, providing reference values for normal.

Aim: To evaluate the feasibility of multiple ultrasound markers for the non-invasive characterization of fibrosis, inflammation and steatosis in the liver in pediatric patients. Materials and methods: The quantitative ultrasound measures shear wave elastography (SWE), shear wave dispersion (SWD) and attenuation imaging (ATI) were compared and correlated with percutaneous liver biopsies and corresponding measures in a control cohort. Results: The median age of the 32 patients was 12.1 years (range 0.1–17.9), and that of the 15 controls was 11.8 years (range: 2.6–16.6). Results: There was a significant difference in SWE values between histologic grades of fibrosis (p = 0.003), with a positive correlation according to the grade (r = 0.7; p < 0.0001). Overall, a difference in SWD values between grades of inflammation was found (p = 0.009) but with a lack of correlation (r = 0.1; p = 0.67). Comparing inflammation grades 0–1 (median:13.6 m/s kHz [min; max; 8.4; 17.5]) versus grades 2–3 (16.3 m/s kHz [14.6; 24.2]) showed significant differences between the groups (p = 0.003). In the 30 individuals with a steatosis score of 0, ATI was measured in 23 cases with a median value of 0.56 dB/cm/MHz. Conclusion: Comprehensive ultrasound analysis was feasible to apply in children and has the potential to reflect the various components of liver affection non-invasively. Larger studies are necessary to conclude to what extent these image-based markers can classify the grade of fibrosis, inflammation and steatosis.

The aim of this study was to evaluate the elasticity and stiffness of the sternocleidomastoid (SCM) muscle in patients with obstructive sleep apnea syndrome (OSAS) using ultrasound shear wave elastography (SWE), and to investigate the potential relationship between SCM muscle stiffness and the severity of OSAS. This study included 72 patients with OSAS diagnosed by polysomnography (PSG) and 35 age- and sex-matched healthy controls who were admitted to the chest diseases outpatient clinic. Following the diagnosis, all participants underwent ultrasound shear wave elastography (SWE) to evaluate the elasticity and stiffness of the sternocleidomastoid (SCM) muscle. SWE measurements were performed in a standardized supine position, with care taken to ensure minimal muscle contraction during imaging. The mean shear wave velocity (SWV) values were recorded for both the right and left SCM muscles. The severity of OSAS was categorized based on apnea-hypopnea index (AHI) scores into mild, moderate, and severe groups. The SWE values were then statistically compared between OSAS subgroups and healthy controls. Correlation analyses were also performed between SCM stiffness (SWV) and AHI values to assess the relationship between muscle stiffness and disease severity. A total of 107 individuals were included in the study: 72 patients with OSAS and 35 healthy controls. The OSAS group showed significantly higher BMI, body fat ratio, neck circumference, and sternocleidomastoid (SCM) muscle stiffness values compared to controls (p < 0.01). Shear wave elastography revealed a significant increase in SCM stiffness with advancing OSAS severity. Spearman's correlation analysis showed that right and left SCM stiffness values were also positively correlated with OSAS severity (r = 0.164 and r = 0.241, respectively; p < 0.001). Ultrasound shear wave elastography revealed increased SCM muscle stiffness in OSAS patients, correlating with disease severity. These findings suggest that SCM muscle biomechanical properties may serve as a supplementary marker in evaluating and monitoring OSAS progression.

The purpose of this study was to compare hepatic stiffness on ultrasound (US) shear wave elastography (SWE) in patients with chronic graft-versus-host disease (GVHD) after allogeneic hematopoietic stem cell transplantation versus patients with no underlying liver disease. We performed a retrospective analysis of 4901 patients who underwent abdominal US examinations with adjunctive liver SWE between August 2014 and December 2016. Each patient was scanned supine with gentle breath holding on LOGIQ E9 (GE Healthcare, Waukesha, WI) or Epiq (Philips Healthcare, Andover, MA) US machines (3-6 MHz). Three to 10 measurements were made intercostally in the right hepatic lobe, following manufacturers' guidelines before release of the 2015 Society of Radiologists in Ultrasound consensus or the 2015 Society of Radiologists in Ultrasound consensus. The median and standard deviation of the shear wave velocity (SWV) were obtained. A 2-sample t test with the Welch approximation was used for statistical analysis. Six patients had documented hepatic chronic GVHD or a high clinical suspicion of liver chronic GVHD. All had normal pretransplant liver function test results and no pretransplant or posttransplant hepatic infection. The control group, obtained from the same database, contained 10 patients with normal liver function test results, no abdominal pain, and no history of liver disease or conditions that may have caused liver stiffness changes. The SWVs in patients with chronic GVHD were double those in the control group (1.96 ± 0.28 versus 0.98 ± 0.27 m/s; P < .0001). Patients with chronic GVHD had substantially higher hepatic parenchymal SWVs than patients without liver disease, indicating increased tissue stiffness. To our knowledge, this phenomenon has not been previously reported in chronic GVHD and suggests potential utility of SWE for diagnosis and monitoring of disease progression and the treatment response in this cohort of patients.

Prospective Assessment of Ultrasound Shear Wave Elastography for Discriminating Biliary Atresia from other Causes of Neonatal Cholestasis

Current shear wave elastography methods primarily focus on 2D imaging. To explore mechanical properties of biological tissues in 3D, a four-dimensional (4D, x, y, z, t) ultrasound shear wave elastography is required. However, 4D ultrasound shear wave elastography is still challenging due to the limitation of the hardware of standard ultrasound acquisition systems. In this study, we introduce a novel method to achieve 4D shear wave elastography, named sequential-based excitation shear wave elastography (SE-SWE). This method can achieve 4D elastography implemented by a 1024-element 2D array with a standard ultrasound 256-channel system. The SE-SWE method employs sequential excitation to generate shear waves, and utilizes a 2D array, dividing it into four sub-sections, to capture shear waves across multiple planes. This process involves sequentially exciting each sub-section to capture shear waves, followed by compounding the acquired data from these subsections. The phantom studies showed strong concordance between the shear wave speeds (SWS) measured by SE-SWE and expected values, confirming the accuracy of this method and potential to differentiate tissues by stiffness. In ex vivo chicken breast experiments, SE-SWE effectively distinguished between orientations relative to muscle fibers, highlighting its ability to capture the anisotropic properties of tissues. The SE-SWE method advances shear wave elastography significantly by using a 2D array divided into four subsections and sequential excitation, achieving high-resolution volumetric imaging at 1.6mm resolution. The SE-SWE method offers a straightforward and effective approach for 3D shear volume imaging of tissue biological properties.