Automated Field of Interest Determination for Quantitative Ultrasound Analyses of Cervical Tissues: Toward Real-time Clinical Translation in Spontaneous Preterm Birth Risk Assessment.

OBJECTIVE: Quantitative ultrasound (QUS) analysis of the human cervix is valuable for predicting spontaneous preterm birth risk. However, this approach currently requires an offline processing step wherein a medically trained analyst manually draws a free-hand field of interest (Manual FOI) for QUS computation. This offline step hinders the clinical adoption of QUS. To address this challenge, we developed a method to determine automatically the cervical FOI (Auto FOI). This study's objective is to evaluate the agreement between QUS results obtained from the Auto and Manual FOIs and assess the feasibility of using the Auto FOI to replace the Manual FOI for cervical QUS computation. METHODS: The auto FOI method was developed and evaluated using cervical ultrasound data from 527 pregnant women, using Manual FOIs as the reference. A deep learning model was developed using the cervical B-mode image as the input to determine automatically the FOI. RESULTS: Quantitative comparison between the Auto and Manual FOIs yielded a high pixel accuracy of 97% and a Dice coefficient of 87%. Further, the Auto FOI yielded QUS biomarker values that were highly correlated with those obtained from the Manual FOIs. For example, the Pearson correlation coefficient was 0.87 between attenuation coefficient values obtained using Auto and Manual FOIs. Further, Bland-Altman analyses showed negligible bias between QUS biomarker values computed using the Auto and Manual FOIs. CONCLUSION: The results support the feasibility of using Auto FOIs to replace Manual FOIs in QUS computation, an important step toward the clinical adoption of QUS technology.

Trajectory of Postpartum Cervical Remodeling in Women Delivering Full-Term and Spontaneous Preterm: Sensitivity to Quantitative Ultrasound Biomarkers.

OBJECTIVE: Women with a history of spontaneous preterm birth (sPTB) face an increased risk of recurrence. Yet, the factors contributing to the increased risk are unknown, hampering the development of targeted interventions. Noninvasive quantitative ultrasound (QUS) has been validated in the characterization of cervical tissue and has the potential to provide information about postpartum cervical remodeling. The objective of this study was to determine the postpartum cervical remodeling trajectories of women over 12 mo post-delivery and to determine whether there were differences between women who delivered full-term and spontaneous preterm that were sensitive to QUS biomarkers. METHODS: Data were collected prospectively from 55 women: 41 who delivered full-term and 14 who delivered spontaneously preterm at 6 wk, 3, 6, 9 and 12 mo (±2 wk) postpartum. Data from QUS biomarkers: Attenuation Coefficient; Backscatter Coefficient; Shear Wave Speed; and Lizzi-Feleppa Slope, Intercept and Midband were analyzed from the acquired radiofrequency data using a Siemens S2000 ultrasound system with a transvaginal MC 9-4 MHz probe. The biomarkers were analyzed using descriptive statistics and linear mixed-effects models. RESULTS: QUS biomarkers, Backscatter Coefficient and Lizzi-Feleppa Intercept showed significant differences during the year after delivery between women who had a full-term birth and sPTB (p < 0.05), suggesting that there are differences in the cervical remodeling trajectories between the two groups. All QUS biomarkers demonstrated significant variations between the full-term birth and sPTB groups over time (p < 0.05), indicating ongoing cervical remodeling for both groups during the 12-mo postpartum period. CONCLUSION: QUS biomarkers identified cervical microstructure differences and trajectories in the year after delivery between women who delivered full-term and spontaneous preterm.

Evaluation of Scatterer Parameters From Ultrasound Scattering Models Taking Into Account Scattering From Nuclei and Cells of Cell-Pellet Biophantoms and Ex Vivo Tumors.

The Quantitative Ultrasound backscatter coefficient provides the capability to evaluate tissue microstructure parameters. Tissue-based scatterer parameters are extracted using ultrasound scattering models. It is challenging to correlate ultrasound scatterer parameters of tissue structures from optical-measured histology, possibly because of inappropriate scattering models or the presence of multiple scatterers. The objective of this study is to pursue the quantification of pertinent scatterer parameters with scattering models that consider ultrasound scattering from nuclei and cells. The concentric sphere model (CSM) and the structure factor model adapted for two types of scatterers (SFM2) are evaluated for cell-pellet biophantoms and ex vivo tumors of four cell lines: 4T1, JC, LMTK, and MAT. The structure factor model (SFM) was used for comparison. CSM and SFM2 provided scatterer parameters closer to histology (lower relative errors) for nucleus and cell radii and volume fractions than SFM but were not always accompanied by lower dispersion of the scatterer distribution (lower coefficient of variation). CSM and SFM2 quantified cell and nucleus radius and volume fraction parameters with lower relative error compared to SFM. For tumors, CSM provided better results than SFM2.

Sticky Hard-Sphere Model for Characterizing Tumor Microstructure via Quantitative Ultrasound.

The use of the structure function (SF) to model interscatterer contribution to ultrasonic scattering is a major step to improve the capability and accuracy of quantitative ultrasound (QUS) and tissue characterization. However, existing QUS-based SF models rely on the hard-sphere (HS) model, which is limited in its applicability for complex scatterer distributions in real tissue. This article introduces the sticky HS (SHS) model for QUS and tissue characterization, which considers a very short-range attractive potential that accounts for the adhesive nature of biological cells and yields a new parameter called stickiness. Herein, the analytical SF expression is presented for monodisperse scatterer size and validated using simulations of scatterer distributions with varying degrees of grouping and volume fractions (0.16, 0.32, and 0.40) over the frequency range from 15 to 110 MHz. The SHS model is applied to three mammary tumor types with differing spatial distributions of tumor cells. The histology-derived SF is computed by considering the nuclei as the main sources of scattering. The results show that the SHS model provides more accurate scatterer radius and volume fraction estimates than the HS model when fit to histology-derived SF versus frequency curves. Furthermore, the new stickiness parameter provided by SHS is sensitive to the grouping structure in tumor cell distribution. This stickiness parameter, combined with the radius and volume fraction estimated from the SHS model, enables better differentiation between different tumor types than using the radius and volume fraction obtained from the HS model. This study demonstrates the potential of the SHS model to improve the QUS tissue characterization.

Enhanced identification of women at risk for preterm birth via quantitative ultrasound: a prospective cohort study.

BACKGROUND: Historically, clinicians have relied on medical risk factors and clinical symptoms for preterm birth risk assessment. In nulliparous women, clinicians may rely solely on reported symptoms to assess for the risk of preterm birth. The routine use of ultrasound during pregnancy offers the opportunity to incorporate quantitative ultrasound scanning of the cervix to potentially improve assessment of preterm birth risk. OBJECTIVE: This study aimed to investigate the efficiency of quantitative ultrasound measurements at relatively early stages of pregnancy to enhance identification of women who might be at risk for spontaneous preterm birth. STUDY DESIGN: A prospective cohort study of pregnant women was conducted with volunteer participants receiving care from the University of Illinois Hospital in Chicago, Illinois. Participants received a standard clinical screening followed by 2 research screenings conducted at 20±2 and 24±2 weeks. Quantitative ultrasound scans were performed during research screenings by registered diagnostic medical sonographers using a standard cervical length approach. Quantitative ultrasound features were computed from calibrated raw radiofrequency backscattered signals. Full-term birth outcomes and spontaneous preterm birth outcomes were included in the analysis. Medically indicated preterm births were excluded from the analysis. Using data from each visit, logistic regression with Akaike information criterion feature selection was conducted to derive predictive models for each time frame based on historical clinical and quantitative ultrasound features. Model evaluations included a likelihood ratio test of quantitative ultrasound features, cross-validated receiver operating characteristic curve analysis, sensitivity, and specificity. RESULTS: On the basis of historical clinical features alone, the best predictive model had an estimated receiver operating characteristic area under the curve of 0.56±0.03. By the time frame of Visit 1, a predictive model using both historical clinical and quantitative ultrasound features provided a modest improvement in the area under the curve (0.63±0.03) relative to that of the predictive model using only historical clinical features. By the time frame of Visit 2, the predictive model using historical clinical and quantitative ultrasound features provided significant improvement (likelihood ratio test, P<.01), with an area under the curve of 0.69±0.03. CONCLUSION: Accurate identification of women at risk for spontaneous preterm birth solely through historical clinical features has been proven to be difficult. In this study, a history of preterm birth was the most significant historical clinical predictor of preterm birth risk, but the historical clinical predictive model performance was not statistically significantly better than the no-skill level. According to our study results, including quantitative ultrasound yields a statistically significant improvement in risk prediction as the pregnancy progresses.

Predicting Spontaneous Pre-term Birth Risk Is Improved When Quantitative Ultrasound Data Are Included With Historical Clinical Data.

OBJECTIVE: Predicting women at risk for spontaneous pre-term birth (sPTB) has been medically challenging because of the lack of signs and symptoms of pre-term birth until interventions are too late. We hypothesized that prediction of the sPTB risk level is enhanced when using both historical clinical (HC) data and quantitative ultrasound (QUS) data compared with using only HC data. HC data defined herein included birth history prior to that of the current pregnancy as well as, from the current pregnancy, a clinical cervical length assessment and physical examination data. METHODS: The study population included 248 full-term births (FTBs) and 26 sPTBs. QUS scans (Siemens S2000 and MC9-4) were performed by registered diagnostic medical sonographers using a standard cervical length approach. Two cervical QUS scans were conducted at 20 ± 2 and 24 ± 2 wk of gestation. Multiple QUS features were evaluated from calibrated raw radiofrequency backscattered ultrasonic signals. Two statistical models designed to determine sPTB risk were compared: (i) HC data alone and (ii) combined HC and QUS data. Model comparisons included a likelihood ratio test, cross-validated receiver operating characteristic area under the curve, sensitivity and specificity. The study's birth outcomes were only FTBs and sPTBs; medically induced pre-term births were not included. DISCUSSION: Combined HC and QUS data identified women at risk of sPTB with better AUC (0.68, 95% confidence interval [CI]: 0.57-0.78) compared with HC data alone (0.53, 95% CI: 0.40-0.66) and HC data + cervical length at 18-20 wk of gestation (average AUC = 0.51, 95% CI: 0.38-0.64). A likelihood ratio test for significance of QUS features in the classification model was highly statistically significant (p < 0.01). CONCLUSION: Even with only 26 sPTBs among 274 births, value was added in predicting sPTB when QUS data were included with HC data.

Direct Comparison of Quantitative US versus Controlled Attenuation Parameter for Liver Fat Assessment Using MRI Proton Density Fat Fraction as the Reference Standard in Patients Suspected of Having NAFLD.

Background MRI-derived proton density fat fraction (PDFF) is an accurate, reliable, and safe biologic marker for use in the noninvasive diagnosis of hepatic steatosis in patients with nonalcoholic fatty liver disease (NAFLD). Because of the cost and limited availability of MRI, it is necessary to develop an accurate method to diagnose NAFLD with potential point-of-care access. Purpose To compare the diagnostic accuracy of the quantitative US (QUS) fat fraction (FF) estimator with that of the controlled attenuation parameter (CAP) in the diagnosis of NAFLD using contemporaneous MRI-derived PDFF as the reference standard. Materials and Methods Participants with or suspected of having NAFLD were prospectively recruited at the NAFLD Research Center between July 2015 and July 2019. All participants underwent MRI-derived PDFF measurement, transient elastography with CAP measurement, and QUS. QUS FF was derived using computed QUS parameters from the acquired radiofrequency US data using a calibrated reference phantom. The area under the receiver operating characteristic curve (AUC) was calculated to assess the accuracy of QUS FF and CAP in the diagnosis of hepatic steatosis (defined as MRI-derived PDFF ≥ 5%). AUCs were compared using the DeLong test. Results A total of 123 participants were included (mean age, 52 years ± 13 [SD]; 67 [54%] women). Of these participants, 100 (81%) had MRI-derived PDFF of 5% or more. QUS FF had a significantly higher AUC for diagnosis of NAFLD than did CAP (0.92 [95% CI: 0.87, 0.98] vs 0.79 [95% CI: 0.67, 0.90], P = .03). QUS FF had a sensitivity of 98% (98 of 100) and a specificity of 48% (11 of 23). CAP had a sensitivity of 87% (87 of 100) and a specificity of 57% (13 of 23). Conclusion The quantitative US fat fraction estimator is more accurate than the controlled attenuation parameter in the diagnosis of hepatic steatosis in patients with or suspected of having nonalcoholic fatty liver disease. © RSNA, 2022 Online supplemental material is available for this article. See also the editorial by Ito in this issue.

Liver Fat Assessment in Multiview Sonography Using Transfer Learning With Convolutional Neural Networks.

OBJECTIVES: To develop and evaluate deep learning models devised for liver fat assessment based on ultrasound (US) images acquired from four different liver views: transverse plane (hepatic veins at the confluence with the inferior vena cava, right portal vein, right posterior portal vein) and sagittal plane (liver/kidney). METHODS: US images (four separate views) were acquired from 135 participants with known or suspected nonalcoholic fatty liver disease. Proton density fat fraction (PDFF) values derived from chemical shift-encoded magnetic resonance imaging served as ground truth. Transfer learning with a deep convolutional neural network (CNN) was applied to develop models for diagnosis of fatty liver (PDFF ≥ 5%), diagnosis of advanced steatosis (PDFF ≥ 10%), and PDFF quantification for each liver view separately. In addition, an ensemble model based on all four liver view models was investigated. Diagnostic performance was assessed using the area under the receiver operating characteristics curve (AUC), and quantification was assessed using the Spearman correlation coefficient (SCC). RESULTS: The most accurate single view was the right posterior portal vein, with an SCC of 0.78 for quantifying PDFF and AUC values of 0.90 (PDFF ≥ 5%) and 0.79 (PDFF ≥ 10%). The ensemble of models achieved an SCC of 0.81 and AUCs of 0.91 (PDFF ≥ 5%) and 0.86 (PDFF ≥ 10%). CONCLUSION: Deep learning-based analysis of US images from different liver views can help assess liver fat.

Investigation of the Effects of Cardiovascular Therapeutic Ultrasound Applied in Female and Male Rats' Hearts of Different Ages.

This study investigates the role of age and sex on the cardiovascular effects of 3.5-MHz pulsed ultrasound (US) in a rat model. Ultrasonic bursts of 2.0-MPa peak rarefactional pressure amplitude (equivalent to an in vitro spatial-peak temporal-peak intensity of ~270 W/cm2 and a mechanical index of 1.1) were delivered in five consecutive 10-s intervals, one interval for each pulse repetition frequency (PRF) (6, 5, 4, 5, and 6 Hz; always the same order) for a total exposure duration of 50 consecutive seconds. Sixty F344 rats were split into 12 groups in a 3×2×2 factorial design (three ages, male versus female, and US application versus control). This study is the first study on US-induced cardiac effects that contains data across three age groups of rats (premenopause, fertile, and postmenopause) to mimic the fertile and nonfertile human window. US was applied transthoracically, while heart rate, stroke volume, ejection fraction, temperature, and other physiologic parameters were recorded at baseline and after exposure. Significant decreases in cardiac output compared to respective control groups were observed in multiple experimental groups, spanning both females and males. A negative chronotropic effect was observed in young male (~7%) and female (~16%) rats, in five-month-old male (~9%) and female (~15%) rats, and in old rats where the effect was not statistically significant. Younger groups and, to a lesser extent, lower weight groups generally had more significant effects. The pathophysiology of US-induced cardiovascular effects appears to be multifactorial and not strictly related to hormones, menopause, weight, sex, or age, individually.

Ultrasound Scattering From Cell-Pellet Biophantoms and Ex Vivo Tumors Provides Insight Into the Cellular Structure Involved in Scattering.

The histologically identifiable cellular structure(s) involved in ultrasonic scattering is(are) yet to be uniquely identified. The study quantifies six possible cellular scattering parameters, namely, cell and nucleus radii and their respective cell and nucleus volume fractions as well as a combination of cell and nucleus radii and their volume fraction. The six cellular parameters are each derived from four cell lines (4T1, JC, LMTK, and MAT) and two tissue types (cell-pellet biophantom and ex vivo tumor). Optical histology and quantitative ultrasound (QUS), both independent approaches, are used to yield these cellular parameters. QUS scatterer parameters are experimentally determined using two ultrasonic scattering models: the spherical Gaussian model (GM) and the structure factor model (SFM) to yield insight about scattering from nuclei only and cells only. GM is a classical ultrasonic scattering model to evaluate QUS parameters and is well adapted for diluted media. SFM is adapted for dense media to estimate reasonably well scatterer parameters of cellular structures from ex vivo tissue. Nucleus and cell radii and volume fractions are measured optically from histology. They were used as inputs to calculate BSC for scattering from cells, nuclei, and both cells and nuclei. The QUS-derived scatterers (radii and volume fractions) distributions were then compared to the optical histology scatterer parameters derived from these calculated BSCs. The results suggest scattering from cells only (LMTK and MAT) or both cells and nuclei (4T1 and JC) for cell-pellet biophantoms and scattering from nuclei only for tumors.

Positive chronotropic effect caused by transthoracic ultrasound in heart of rats.

Pulsed ultrasound can produce chronotropic and inotropic effects on the heart with potential therapeutic applications. Fourteen 3-month-old female rats were exposed transthoracically to 3.5-MHz 2.0-MPa peak rarefactional pressure amplitude ultrasonic pulses of increasing 5-s duration pulse repetition frequency (PRF) sequences. An increase in the heart rate was observed following each PRF sequence: an ∼50% increase after the 4-5-6 Hz sequence, an ∼57% increase after the 5-6-7 Hz sequence, and an ∼48% increase after the 6-7-8 Hz sequence. Other cardiac parameters showed a normal or indicated a compensatory decrease at 3 and 15 min post-ultrasound compared to control.

A 10% Tomato Diet Selectively Reduces Radiation-Induced Damage in TRAMP Mice.

BACKGROUND: Tomatoes contain carotenoids that have the potential to alter the effects of external beam radiation therapy (EBRT). OBJECTIVES: We hypothesized that dietary lyophilized tomato paste (TP) would reduce apoptosis within carotenoid-containing nonneoplastic tissues in EBRT-treated TRansgenic Adenocarcinoma of the Mouse Prostate (TRAMP) mice. METHODS: Male TRAMP mice (n = 73) were provided an AIN-93G diet or a modified AIN-93G diet containing 10% TP (wt:wt) at 4 wk of age. Prostate tumor growth was monitored by ultrasound. The caudal half of the mouse was irradiated with 7.5 Gy (Rad) or 0 Gy (sham) at 24 wk of age or after the tumor volume exceeded 1000 mm3 with a Cobalt-60 source. Mice were euthanized 24 h postradiation. Carotenoids and α-tocopherol were measured by HPLC and compared by a t test. Tissues were assessed for radiation-induced changes (hematoxylin and eosin) and apoptosis [cleaved caspase-3 (CC3)] and compared by Kruskal-Wallis test or Freedman-Lane's permutation test. RESULTS: Serum concentrations of lycopene (52% lower), phytoene (26% lower), and α-tocopherol (22% lower) were decreased in TP-fed irradiated mice (TP-Rad) compared with TP-fed sham mice (P < 0.05). CC3 scores increased within the prostate tumor with radiation treatments (P < 0.05), but were not affected by tomato consumption. In nonneoplastic tissues, TP-Rad had a lower percentage of CC3-positive cells within the cranial (67% lower) and caudal (75% lower) duodenum than irradiated mice on the control diet (Rad) (P < 0.005). Likewise, CC3 scores within the dorsolateral prostate of TP-Rad trended toward lower scores than for Rad (P = 0.07). CONCLUSIONS: TP selectively reduces radiation-induced apoptosis in extratumoral tissues without decreasing radiation-induced apoptosis within the prostate tumor in TRAMP mice. Additional studies are needed to confirm and expand upon these findings.

Therapeutic Ultrasound in Cardiovascular Medicine.

An advantage of therapeutic ultrasound (US) is the ability to cause controlled biological effects noninvasively. Depending on the magnitude and frequency of exposure parameters, US can interact in different ways with a variety of biological tissues. The development and clinical utility of therapeutic US techniques are now rapidly growing, especially with regard to the application of US pulses for cardiac pacing and the potential treatment of cardiovascular diseases. This review outlines the basic principles of US-based therapy in cardiology, including the acoustic properties of the cardiovascular tissue, and the use of US in therapeutic cardiovascular medicine.

Dietary Tomato or Lycopene Do Not Reduce Castration-Resistant Prostate Cancer Progression in a Murine Model.

BACKGROUND: Dietary tomato products or lycopene protect against prostate carcinogenesis, but their impact on the emergence of castration-resistant prostate cancer (CRPC) is unknown. OBJECTIVE: We hypothesized that tomato or lycopene products would reduce the emergence of CRPC. METHODS: Transgenic adenocarcinoma of the mouse prostate (TRAMP) mice were castrated at 12-13 wk and the emergence of CRPC was monitored by ultrasound in each study. In Study 1, TRAMP mice (n = 80) were weaned onto an AIN-93G-based control diet (Con-L, n = 28), a 10% tomato powder diet (TP-L, 10% lyophilized w/w, n = 26), or a control diet followed by a tomato powder diet after castration (TP-Int1, n = 26). In Study 2, TRAMP mice (n = 85) were randomized onto a control diet with placebo beadlets (Con-Int, n = 29), a tomato diet with placebo beadlets (TP-Int2, n = 29), or a control diet with lycopene beadlets (Lyc-Int, n = 27) following castration (aged 12 wk). Tumor incidence and growth were monitored by ultrasound beginning at an age of 10 wk. Mice were euthanized 4 wk after tumor detection or aged 30 wk if no tumor was detected. Tissue weights were compared by ANOVA followed by Dunnett's test. Tumor volumes were compared using generalized linear mixed model regression. RESULTS: Ultrasound estimates for the in vivo tumor volume were strongly correlated with tumor weight at necropsy (R2 = 0.75 and 0.94, P <0.001 for both Studies 1 and 2, respectively). Dietary treatments after castration did not significantly impact cancer incidence, time to tumor detection, or final tumor weight. CONCLUSIONS: In contrast to studies of de novo carcinogenesis in multiple preclinical models, tomato components had no significant impact on the emergence of CRPC in the TRAMP model. It is possible that specific mutant subclones of prostate cancer may continue to show some antiproliferative response to tomato components, but further studies are needed to confirm this.

Reasons Why Pregnant Women Participate in Ultrasound Research Involving Transvaginal Scans.

OBJECTIVES: The aim of this study was to explore the motivations of pregnant women in participating in an ultrasound study and the acceptability of vaginal ultrasound examinations. METHODS: A prospective sample of 270 women were asked one question: "Can you tell me what motivated you to participate in the study?" The data were then analyzed through a qualitative thematic analysis with an inductive approach. In addition to the thematic analysis, quantification of the data was performed to enhance the qualitative result. RESULTS: Through the thematic analysis, 5 themes emerged from the responses of the participants: altruism, research, personal experience, personal benefit, and finding out. All responses were relatively short, and some responses included more than one theme. CONCLUSIONS: Vaginal ultrasound examinations were acceptable to the participants, and pregnant women had many motivations to participate. Regardless of race, ethnicity, or insurance status, the women in our study were altruistic and curious about our research.

Assessment of Hepatic Steatosis in Nonalcoholic Fatty Liver Disease by Using Quantitative US.

Background Advanced confounder-corrected chemical shift-encoded MRI-derived proton density fat fraction (PDFF) is a leading parameter for fat fraction quantification in nonalcoholic fatty liver disease (NAFLD). Because of the limited availability of this MRI technique, there is a need to develop and validate alternative parameters to assess liver fat. Purpose To assess relationship of quantitative US parameters to MRI PDFF and to develop multivariable quantitative US models to detect hepatic steatosis and quantify hepatic fat. Materials and Methods Adults with known NAFLD or who were suspected of having NAFLD were prospectively recruited between August 2015 and February 2019. Participants underwent quantitative US and chemical shift-encoded MRI liver examinations. Liver biopsies were performed if clinically indicated. The correlation between seven quantitative US parameters and MRI PDFF was evaluated. By using leave-one-out cross validation, two quantitative US multivariable models were evaluated: a classifier to differentiate participants with NAFLD versus participants without NAFLD and a fat fraction estimator. Classifier performance was summarized by area under the receiver operating characteristic curve and area under the precision-recall curve. Fat fraction estimator performance was evaluated by correlation, linearity, and bias. Results Included were 102 participants (mean age, 52 years ± 13 [standard deviation]; 53 women), 78 with NAFLD (MRI PDFF ≥ 5%). A two-variable classifier yielded a cross-validated area under the receiver operating characteristic curve of 0.89 (95% confidence interval: 0.82, 0.96) and an area under the precision-recall curve of 0.96 (95% confidence interval: 0.93, 0.99). The cross-validated fat fraction predicted by a two-variable fat fraction estimator was correlated with MRI PDFF (Spearman ρ = 0.82 [P < .001]; Pearson r = 0.76 [P < .001]). The mean bias was 0.02% (P = .97), and 95% limits of agreement were ±12.0%. The predicted fat fraction was linear with MRI PDFF (R 2 = 0.63; slope, 0.69; intercept, 4.3%) for MRI PDFF of 34% or less. Conclusion A multivariable quantitative US approach yielded excellent correlation with MRI proton density fat fraction for hepatic steatosis assessment in nonalcoholic fatty liver disease. © RSNA, 2020 Online supplemental material is available for this article.

Noninvasive Diagnosis of Nonalcoholic Fatty Liver Disease and Quantification of Liver Fat with Radiofrequency Ultrasound Data Using One-dimensional Convolutional Neural Networks.

Background Radiofrequency ultrasound data from the liver contain rich information about liver microstructure and composition. Deep learning might exploit such information to assess nonalcoholic fatty liver disease (NAFLD). Purpose To develop and evaluate deep learning algorithms that use radiofrequency data for NAFLD assessment, with MRI-derived proton density fat fraction (PDFF) as the reference. Materials and Methods A HIPAA-compliant secondary analysis of a single-center prospective study was performed for adult participants with NAFLD and control participants without liver disease. Participants in the parent study were recruited between February 2012 and March 2014 and underwent same-day US and MRI of the liver. Participants were randomly divided into an equal number of training and test groups. The training group was used to develop two algorithms via cross-validation: a classifier to diagnose NAFLD (MRI PDFF ≥ 5%) and a fat fraction estimator to predict MRI PDFF. Both algorithms used one-dimensional convolutional neural networks. The test group was used to evaluate the classifier for sensitivity, specificity, positive predictive value, negative predictive value, and accuracy and to evaluate the estimator for correlation, bias, limits of agreements, and linearity between predicted fat fraction and MRI PDFF. Results A total of 204 participants were analyzed, 140 had NAFLD (mean age, 52 years ± 14 [standard deviation]; 82 women) and 64 were control participants (mean age, 46 years ± 21; 42 women). In the test group, the classifier provided 96% (95% confidence interval [CI]: 90%, 99%) (98 of 102) accuracy for NAFLD diagnosis (sensitivity, 97% [95% CI: 90%, 100%], 68 of 70; specificity, 94% [95% CI: 79%, 99%], 30 of 32; positive predictive value, 97% [95% CI: 90%, 99%], 68 of 70; negative predictive value, 94% [95% CI: 79%, 98%], 30 of 32). The estimator-predicted fat fraction correlated with MRI PDFF (Pearson r = 0.85). The mean bias was 0.8% (P = .08), and 95% limits of agreement were -7.6% to 9.1%. The predicted fat fraction was linear with an MRI PDFF of 18% or less (r = 0.89, slope = 1.1, intercept = 1.3) and nonlinear with an MRI PDFF greater than 18%. Conclusion Deep learning algorithms using radiofrequency ultrasound data are accurate for diagnosis of nonalcoholic fatty liver disease and hepatic fat fraction quantification when other causes of steatosis are excluded. © RSNA, 2020 Online supplemental material is available for this article. See also the editorial by Lockhart and Smith in this issue.

A Phantom-Based Assessment of Repeatability and Reproducibility of Transvaginal Quantitative Ultrasound.

This article evaluated the repeatability and reproducibility (R&R) of quantitative ultrasound (QUS) biomarkers attenuation coefficient (AC) and backscatter coefficient (BSC) in transvaginal QUS reference phantoms for obstetric applications. Five phantoms were scanned by three sonographers according to the scanning protocol. Each sonographer scanned each phantom with four transvaginal transducers of the same model (MC9-4) and three probe cover types (latex cover, nonlatex cover, and no cover). The AC and BSC were estimated by using a reference phantom method. The R&R analysis was performed for the frequency-averaged AC and logBSC (= 10log10BSC) (5.4-5.8 MHz) by using three-factor random effects Analysis of Variance with interaction. The total R&R variabilities for AC and logBSC are small (AC: 0.042-0.065 dB/cm-MHz; logBSC: 0.50-0.68 dB), indicating high measurement precision. These values are small compared to the ranges of AC (0.28-0.99 dB/cm-MHz) and logBSC (-33.16 to -20.35 dB) of the five phantoms. The AC and logBSC biomarkers measured on transvaginal QUS phantoms using the reference phantom method are repeatable, and reproducible between sonographers, transducers, and probe covers.

Low fat but not soy protein isolate was an effective intervention to reduce nonalcoholic fatty liver disease progression in C57BL/6J mice: monitored by a novel quantitative ultrasound (QUS) method.

Untreated nonalcoholic fatty liver disease (NAFLD) and nonalcoholic steatohepatitis (NASH) lead to irreversible liver damage. We hypothesized that a low-fat diet (LFD) or a high-fat diet (HFD) with soy protein isolate (SPI) would be an effective intervention to halt or reverse NAFLD progression. To test these hypotheses, we conducted 2 studies. In the first study, we fed an HFD to 7-week-old C57BL/6J mice to induce NAFLD compared to an LFD (control). Hepatic steatosis was monitored by quantitative ultrasound (QUS) scans (in vivo and ex vivo). Animals were euthanized after 0, 2, 4, and 6 weeks of feeding. In the second study, 7-week-old mice were randomized onto an LFD or HFD with SPI intervention after 4 weeks of feeding HFD. Animals from each group were scanned with QUS and euthanized after 4, 9, and 12 weeks of feeding. Animals fed the HFD developed NAFLD (100%) and NASH (80%) characterized by increased liver weight, lipid accumulation, and histological scores for inflammation by 4 weeks in the first study. In the second study, the LFD ameliorated this NAFLD phenotype after 5 weeks of feeding; however, the SPI intervention failed to significantly attenuate NAFLD. QUS parameters were significantly increased with the HFDs (P < .05) and steatosis grade (P < .05) and were positively correlated with hepatic lipid concentrations. In conclusion, dietary modification may be effective at reversing NAFLD and NASH at early stages. Furthermore, QUS may become a valuable tool to track hepatic steatosis. Additional studies are needed to further evaluate the effectiveness of these interventions.

Inter-platform reproducibility of ultrasonic attenuation and backscatter coefficients in assessing NAFLD.

OBJECTIVES: To assess inter-platform reproducibility of ultrasonic attenuation coefficient (AC) and backscatter coefficient (BSC) estimates in adults with known/suspected nonalcoholic fatty liver disease (NAFLD). METHODS: This HIPAA-compliant prospective study was approved by an institutional review board; informed consent was obtained. Participants with known/suspected NAFLD were recruited and underwent same-day liver examinations with clinical ultrasound scanner platforms from two manufacturers. Each participant was scanned by the same trained sonographer who performed multiple data acquisitions in the right liver lobe using a lateral intercostal approach. Each data acquisition recorded a B-mode image and the underlying radio frequency (RF) data. AC and BSC were calculated using the reference phantom method. Inter-platform reproducibility was evaluated for AC and log-transformed BSC (logBSC = 10log10BSC) by intraclass correlation coefficient (ICC), Pearson's correlation, Bland-Altman analysis with computation of limits of agreement (LOAs), and within-subject coefficient of variation (wCV; applicable to AC). RESULTS: Sixty-four participants were enrolled. Mean AC values measured using the two platforms were 0.90 ± 0.13 and 0.94 ± 0.15 dB/cm/MHz while mean logBSC values were - 30.6 ± 5.0 and - 27.9 ± 5.6 dB, respectively. Inter-platform ICC was 0.77 for AC and 0.70 for log-transformed BSC in terms of absolute agreement. Pearson's correlation coefficient was 0.81 for AC and 0.80 for logBSC. Ninety-five percent LOAs were - 0.21 to 0.13 dB/cm/MHz for AC, and - 9.48 to 3.98 dB for logBSC. The wCV was 7% for AC. CONCLUSIONS: Hepatic AC and BSC are reproducible across two different ultrasound platforms in adults with known or suspected NAFLD. KEY POINTS: • Ultrasonic attenuation coefficient and backscatter coefficient are reproducible between two different ultrasound platforms in adults with NAFLD. • This inter-platform reproducibility may qualify quantitative ultrasound biomarkers for generalized clinical application in patients with suspected/known NAFLD.