Ultrasound Texture Analysis Research Articles

Machine Learning on Ultrasound Texture Analysis Data for Characterizing of Salivary Glandular Tumors: A Feasibility Study.

Objective quantitative texture characteristics may be helpful in salivary glandular tumor differential diagnosis. This study uses machine learning (ML) to explore and validate the performance of ultrasound (US) texture features in diagnosing salivary glandular tumors. 122 patients with salivary glandular tumors, including 71 benign and 51 malignant tumors, are enrolled. Representative brightness mode US pictures are selected for further Gray Level Co-occurrence Matrix (GLCM) texture analysis. We use a t-test to test the significance and use the receiver operating characteristic curve method to find the optimal cut-point for these significant features. After splitting 80% of the data into a training set and 20% data into a testing set, we use five machine learning models, k-nearest Neighbors (kNN), Naïve Bayes, Logistic regression, Artificial Neural Networks (ANNs) and supportive vector machine (SVM), to explore and validate the performance of US GLCM texture features in diagnosing salivary glandular tumors. This study includes 49 female and 73 male patients, with a mean age of 53 years old, ranging from 21 to 93. We find that six GLCM texture features (contrast, inverse difference movement, entropy, dissimilarity, inverse difference and difference entropy) are significantly different between benign and malignant tumors (p < 0.05). In ML, the overall accuracy rates are 74.3% (95%CI: 59.8-88.8%), 94.3% (86.6-100%), 72% (54-89%), 84% (69.5-97.3%) and 73.5% (58.7-88.4%) for kNN, Naïve Bayes, Logistic regression, a one-node ANN and SVM, respectively. US texture analysis with ML has potential as an objective and valuable tool to make a differential diagnosis between benign and malignant salivary gland tumors.

Prediction of neonatal respiratory distress syndrome by Quantitative ultrasound texture analysis of fetal lung Observational cross section study

Prediction of neonatal respiratory distress syndrome by Quantitative ultrasound texture analysis of fetal lung Observational cross section study

A priori prediction of breast cancer response to neoadjuvant chemotherapy using quantitative ultrasound, texture derivative and molecular subtype

The purpose of this study was to investigate the performances of the tumor response prediction prior to neoadjuvant chemotherapy based on quantitative ultrasound, tumour core-margin, texture derivative analyses, and molecular parameters in a large cohort of patients (n = 208) with locally advanced and earlier-stage breast cancer and combined them to best determine tumour responses with machine learning approach. Two multi-features response prediction algorithms using a k-nearest neighbour and support vector machine were developed with leave-one-out and hold-out cross-validation methods to evaluate the performance of the response prediction models. In a leave-one-out approach, the quantitative ultrasound-texture analysis based model attained good classification performance with 80% of accuracy and AUC of 0.83. Including molecular subtype in the model improved the performance to 83% of accuracy and 0.87 of AUC. Due to limited number of samples in the training process, a model developed with a hold-out approach exhibited a slightly higher bias error in classification performance. The most relevant features selected in predicting the response groups are core-to-margin, texture-derivative, and molecular subtype. These results imply that that baseline tumour-margin, texture derivative analysis methods combined with molecular subtype can potentially be used for the prediction of ultimate treatment response in patients prior to neoadjuvant chemotherapy.

The effect of colorization on the fetal lung heterogeneity index.

No previous studies have quantitatively assessed the effect of color tones on ultrasound texture analysis techniques. Our objective was to compare heterogeneity index (HI) between fetal lung images captured in grayscale and those same images after conversion to Ice and Sepia. Fetal lung images were obtained during medically indicated ultrasound examinations. We observed that HI is affected by the application of color tones to ultrasound images of the fetal lung. Therefore, for each type of biological tissue and color tone, determination of distinct HI nomograms and cut off points is recommended.

Development of an equation to screen for solar hemorrhages from digital cushion ultrasound texture analysis in veal calves at slaughter.

Claw disorders are a relevant welfare issue in the cattle industry, fast and accurate diagnoses are essential for successful treatment and prevention. The present study aimed to develop an equation to assess the presence of solar hemorrhages from real-time ultrasound images texture analysis at slaughter. Eighty-eight hind feet were collected at the slaughterhouse from 44 Holstein male veal calves. The claws were trimmed by a veterinarian hoof-trimmer, approximately 30 min after the calves' slaughter, and classified into healthy and affected by solar hemorrhages. At the same time, ultrasound images were collected for each claw. Sole soft tissues' thickness was measured, and texture analysis was performed using MaZda software. The resulting parameters from sole soft tissues' measurements and texture analysis were screened with a stepwise linear discriminant analysis using the absence or presence (0/1) of solar hemorrhages as the dependent variable. Results from the stepwise analysis identified 9 variables (among 279) as predictors, and an equation was developed and used to predict the presence or absence of solar hemorrhages on the scanned claws by binary measure: values ≤0.5 counted as 0, while those >0.5 as 1. Validation of the equation was performed by testing predicted lesions (LESpred) against the clinically evaluated lesions (LESeval) with a confusion matrix, a ROC analysis, and a precision-recall curve. Results of the present study suggest that the equation proposed has a good potential for detecting effectively hemorrhages of the sole by ultrasound imaging texture means, and could be used to monitor unsatisfactory housing and management conditions at the farm level, and for early management intervention and prevention.

Recent developments in fetal lung ultrasound

Fetal ultrasound has been employed for years to help evaluate fetal growth and development and to monitor pregnancy. Furthermore, fetal lung maturity has been assessed pre-natally by examination of the amniotic fluid, usually obtained by transabdominal amniocentesis, for lecithin, lecithin/sphingomyelin ratio, or “P” factor (fluorescent polarization measurement for lipids.) Quantitative ultrasound texture analysis of fetal lung has been proposed in previous studies as a promising noninvasive method to predict fetal lung maturity, fetal lung hypoplasia, and neonatal respiratory morbidity. This technique utilizes standard fetal lung images, which are easily obtained by sonographers during routine ultrasound examinations. Additional information then can be extracted from these images by applying quantitative processing methods that characterize the tissue. This presentation discusses how to differentiate preterm (&amp;lt;37 weeks of gestation) from term (≥37 weeks of gestation) fetal lungs by quantitative texture analysis of ultrasound images. This quantification is based on the extent of heterogeneity associated with lung maturity by employing a unique, novel noninvasive technique to determine the Heterogeneity Index (HI) in ultrasound images. The HI values are then compared in sonograms of immature lungs with mature lungs. Conceptual advances for the possibility of integrating this technology in handheld ultraportable systems for point-of-care ultrasound (POCUS) are also presented.

Identify the triple-negative and non-triple-negative breast cancer by using texture features of medicale ultrasonic image: A STROBE-compliant study.

The study aimed to explore the value of ultrasound (US) texture analysis in the differential diagnosis of triple-negative breast cancer (TNBC) and non-TNBC.Retrospective analysis was done on 93 patients with breast cancer (35 patients with TNBC and 38 patients with non-TNBC) who were admitted to Taizhou people's hospital from July 2015 to June 2019. All lesions were pathologically proven at surgery. US images of all patients were collected. Texture analysis of US images was performed using MaZda software package. The differences between textural features in TNBC and non-TNBC were assessed. Receiver operating characteristic curve analysis was used to compare the diagnostic performance of textural parameters showing significant difference.Five optimal texture feature parameters were extracted from gray level run-length matrix, including gray level non-uniformity (GLNU) in horizontal direction, vertical gray level non-uniformity, GLNU in the 45 degree direction, run length non-uniformity in 135 degree direction, GLNU in the 135 degree direction. All these texture parameters were statistically higher in TNBC than in non-TNBC (P <.05). Receiver operating characteristic curve analysis indicated that at a threshold of 268.9068, GLNU in horizontal direction exhibited best diagnostic performance for differentiating TNBC from non-TNBC. Logistic regression model established based on all these parameters showed a sensitivity of 69.3%, specificity of 91.4% and area under the curve of 0.834.US texture features were significantly different between TNBC and non-TNBC, US texture analysis can be used for preliminary differentiation of TNBC from non-TNBC.

Mid-trimester prediction of spontaneous preterm birth with automated cervical quantitative ultrasound texture analysis and cervical length: a prospective study

The objective of this study was to evaluate a novel automated test based on ultrasound cervical texture analysis to predict spontaneous Preterm Birth (sPTB) alone and in combination with Cervical Length (CL). General population singleton pregnancies between 18 + 0 and 24 + 6 weeks’ gestation were assessed prospectively at two centers. Cervical ultrasound images were evaluated and the occurrence of sPTB before weeks 37 + 0 and 34 + 0 were recorded. CL was measured on-site. The automated texture analysis test was applied offline to all images. Their performance to predict the occurrence of sPTB before 37 + 0 and 34 + 0 weeks was evaluated separately and in combination on 633 recruited patients. AUC for sPTB prediction before weeks 37 and 34 respectively were as follows: 55.5% and 65.3% for CL, 63.4% and 66.3% for texture analysis, 67.5% and 76.7% when combined. The new test improved detection rates of CL at similar low FPR. Combining the two increased detection rate compared to CL alone from 13.0 to 30.4% for sPTB < 37 and from 14.3 to 42.9% sPTB < 34. Texture analysis of cervical ultrasound improved sPTB detection rate compared to cervical length for similar FPR, and the two combined together increased significantly prediction performance. This results should be confirmed in larger cohorts.

Pore texture analysis in automated 3D breast ultrasound images for implanted lightweight hernia mesh identification: a preliminary study

BackgroundPrecise visualization of meshes and their position would greatly aid in mesh shrinkage evaluation, hernia recurrence risk assessment, and the preoperative planning of salvage repair. Lightweight (LW) meshes are able to preserve abdominal wall compliance by generating less post-implantation fibrosis and rigidity. However, conventional 3D imaging techniques such as computed tomography (CT) and magnetic resonance imaging (MRI) cannot visualize the LW meshes. Patients sometimes have to undergo a second-look operation for visualizing the mesh implants. The goal of this work is to investigate the potential advantages of Automated 3D breast ultrasound (ABUS) pore texture analysis for implanted LW hernia mesh identification.MethodsIn vitro, the appearances of four different flat meshes in both ABUS and 2D hand-held ultrasound (HHUS) images were evaluated and compared. In vivo, pore texture patterns of 87 hernia regions were analyzed both in ABUS images and their corresponding HHUS images.ResultsIn vitro studies, the imaging results of ABUS for implanted LW meshes are much more visualized and effective in comparison to HHUS. In vivo, the inter-class distance of 40 texture features was calculated. The texture features of 2D sectional plans (axial and sagittal plane) have no significant contribution to implanted LW mesh identification. Significant contribution was observed in coronal plane. However, since the mesh may have spatial variation such as shrinkage after implantation surgery, the inter-class distance of 3D coronal plane pore texture features are bigger than 2D coronal plane, so the contribution of 3D coronal plane pore texture features are more valuable than 2D coronal plane for implanted LW mesh identification. The use of 3D pore texture features significantly improved the robustness of the identification method in distinguishing between LW mesh and fascia.ConclusionsAn innovative new ABUS provides additional pore texture visualization, by separating the LW mesh from the fascia tissues. Therefore, ABUS has the potential to provides more accurate features to characterize pore texture patterns, and ultimately provide more accurate measures for implanted LW mesh identification.

Quantitative Ultrasound Texture Analysis to Assess the Spastic Muscles in Stroke Patients

This study aimed to investigate the feasibility of sonoelastography for determining echotexture in post-stroke patients. Moreover, the relationships of muscle echotexture features, muscle stiffness, and functional performance in spastic muscle were explored. The study population comprised 22 males with stroke. The echotexture features (entropy and energy) of the biceps brachii muscles (BBM) in both arms were extracted by local binary pattern (LBP) from ultrasound images, whereas the stiffness of BBM was assessed by shear wave velocity (SWV) in the transverse and longitudinal planes. The Fugl–Meyer assessment (FMA) was used to assess the functional performance of the upper arm. The results showed that echotexture was more inhomogeneous in the paretic BBM than in the non-paretic BBM. SWV was significantly faster in paretic BBM than in non-paretic BBM. Both echotexture features were significantly correlated with SWV in the longitudinal plane. The feature of energy was significantly negatively correlated with FMA in the longitudinal plane and was significantly positively correlated with the duration from stroke onset in the transverse plane. The echotexture extracted by LBP may be a promising approach for quantitative assessment of the spastic BBM in post-stroke patients.

Classification of Breast Ultrasound Tomography by Using Textural Analysis

Background: Ultrasound imaging has become one of the most widely utilized adjunct tools in breast cancer screening due to its advantages. The computer-aided detection of breast ultrasound is rapid development via significant features extracted from images. Objectives: The main aim was to identify features of breast ultrasound image that can facilitate reasonable classification of ultrasound images between malignant and benign lesions. Patients and Methods: This research was a retrospective study in which 85 cases (35 malignant [positive group] and 50 benign [negative group] with diagnostic reports) with ultrasound images were collected. The B-mode ultrasound images have manually selected regions of interest (ROI) for estimated features of an image. Then, a fractal dimensional (FD) image was generated from the original ROI by using the box-counting method. Both FD and ROI images were extracted features, including mean, standard deviation, skewness, and kurtosis. These extracted features were tested as significant by t-test, receiver operating characteristic (ROC) analysis and Kappa coefficient. Results: The statistical analysis revealed that the mean texture of images performed the best in differentiating benign versus malignant tumors. As determined by the ROC analysis, the appropriate qualitative values for the mean and the LR model were 0.85 and 0.5, respectively. The sensitivity, specificity, accuracy, positive predicted value (PPV), negative predicted value (NPV), and Kappa for the mean was 0.77, 0.84, 0.81, 0.77, 0.84, and 0.61, respectively. Conclusion: The presented method was efficient in classifying malignant and benign tumors using image textures. Future studies on breast ultrasound texture analysis could focus on investigations of edge detection, texture estimation, classification models, and image features.

Quantitative Ultrasound Texture Analysis of Fetal Lung Versus Fetal Pulmonary Artery Doppler as a Predictor of Neonatal Respiratory Distress Syndrome (RDS)

Purpose: To evaluate the role of fetal pulmonary artery Doppler indices and quantitative ultrasound texture analysis of the fetal lung (quantus FLM) in prediction of neonatal respiratory distress syndrome. Method: This Observational prospective cross sectional study included 40 pregnant women between 28 and 40 weeks gestation. The diagnostic accuracy of MPA Doppler measurements (pulsatility index (PI), resistance index (RI) and acceleration time/ejection time (AT/ET) for diagnosis of neonatal RDS was tested by comparing the Doppler findings with the clinical outcome. Results: Of the 40 eligible fetuses, 9 (22%) developed neonatal RDS There was a significant correlation between the AT/ET and the development of the RDS as the AT/ET was significantly lower in the RDS +ve group (mean 0.27) in comparison to the RDS-ve group (mean 0.34) (P 0.001). While both PI and RI showed no statistically significant difference in between the two groups. A cutoff value of 0.3 for AT/ET predicted the development of RDS (sensitivity: 77.78%, specificity: 83.87%). Quantus FLM predicted the development of neonatal RDS with high sensitivity, specificity, positive predictive value, negative predictive value and accuracy (88.98%, 90.32%, 72.7%, 96.6% and 90%respectively). The area under curve was 0.896. Conclusion: Neonatal RDS can be predicted using the MPA AT/ET and quantitative ultrasound texture analysis of the fetal lung (quantus FLM) with high sensitivity and specificity.

Carotid artery displacement and cardiovascular disease risk in the Multi-Ethnic Study of Atherosclerosis.

Novel technology permits quantification of common carotid artery (CCA) displacement, which is traditionally ignored. We evaluated associations with CCA displacement and cardiovascular disease (CVD) risk and events in a large, multi-ethnic cohort. Right CCA longitudinal displacement (LD), transverse displacement (TD), and grayscale median (GSM) were evaluated using ultrasound speckle-tracking and texture analysis software in 2050 participants. Regression analyses were used to define relationships between CCA LD, TD, GSM, and CVD risk factors. Cox proportional hazards models were used to assess relationships between LD, TD, and incident CVD events. Participants were mean (SD) 64 (10) years old. There were 791 cases with a CVD event over a 12-year median follow-up. The mean LD was 0.29 (0.20) mm. In multivariable models including age, sex, race/ethnicity, heart rate, and CVD risk factors, LD was associated positively with active smoking (β = 0.08, p < 0.001) and inversely with black (β = -0.08, p < 0.001), Chinese (β = -0.05, p < 0.001), and Hispanic (β = -0.04, p < 0.05) race/ethnicities relative to white individuals, heart rate (β = -0.03/10 beats/min, p < 0.001), and diastolic blood pressure (β = -0.01/5 mmHg, p < 0.05). In fully adjusted models, LD and TD were associated with GSM (p < 0.01), but neither predicted incident CVD events (LD: hazard ratio (HR) 0.77 [0.48 to 1.24], p = 0.3; TD: HR 1.12 [0.8 to 1.57], p = 0.5). CCA LD and TD are associated with race/ethnicity and CVD risk factors but not incident CVD events. LD and TD are not measures of arterial stiffness but their association with GSM suggests that lower LD and TD may be related to structural changes within the carotid arterial wall.

Radiomics of US texture features in differential diagnosis between triple-negative breast cancer and fibroadenoma

Triple-negative breast cancer (TNBC) is sometimes mistaken for fibroadenoma due to its tendency to show benign morphology on breast ultrasound (US) albeit its aggressive nature. This study aims to develop a radiomics score based on US texture analysis for differential diagnosis between TNBC and fibroadenoma, and to evaluate its diagnostic performance compared with pathologic results. We retrospectively included 715 pathology-proven fibroadenomas and 186 pathology-proven TNBCs which were examined by three different US machines. We developed the radiomics score by using penalized logistic regression with a least absolute shrinkage and selection operator (LASSO) analysis from 730 extracted features consisting of 14 intensity-based features, 132 textural features and 584 wavelet-based features. The constructed radiomics score showed significant difference between fibroadenoma and TNBC for all three US machines (p < 0.001). Although the radiomics score showed dependency on the type of US machine, we developed more elaborate radiomics score for a subgroup in which US examinations were performed with iU22. This subsequent radiomics score also showed good diagnostic performance, even for BI-RADS category 3 or 4a lesions (AUC 0.782) which were presumed as probably benign or low suspicious of malignancy by radiologists. It was expected to assist radiologist’s diagnosis and reduce the number of invasive biopsies, although US standardization should be overcome before clinical application.

Risk Marker Variability in Subclinical Carotid Plaques Based on Ultrasound is Influenced by Cardiac Phase, Echogenicity and Size

Identification of risk markers based on quantitative ultrasound texture analysis of carotid plaques has the ability to define vulnerable components that correlate with increased cardiovascular risk. However, data describing factors with the potential to influence the measurement variability of risk markers are limited. The aim of this study was to evaluate the influence of electrocardiogram-guided image selection, plaque echogenicity and area on carotid plaque risk markers and their variability in asymptomatic carotid plaques. Plaque risk markers were measured in 57 plaques during three consecutive heartbeats at two cardiac cycle time instants corresponding to the electrocardiogram R-wave (end diastole) and end of T-wave (end systole), resulting in six measurements for each plaque. Risk marker variability was quantified by computing the coefficient of variation (CV) across the three heartbeats. The CV was significantly higher for small plaques (area <15 mm2, 10%) than for large plaques (area >15 mm2, 6%) (p < 0.001) in measurements of area, and the CV for measurements of gray-scale median were higher for echolucent plaques (<40, 15%) than for echogenic plaques (>40, 9%) (p < 0.001). No significant differences were found between systole and diastole for the mean of any risk marker or the corresponding CV value. However, in a sub-analysis, the echolucent plaques were found to have a higher CV during systole compared with diastole. The variability also caused plaque type reclassification in 16% to 25% of the plaques depending on cutoff value. The results of this study indicate that echolucent and small plaques each contribute to increased risk marker variability. Based on these results, we recommend that measurements in diastole are preferred to reduce variation, although we found that it may not be possible to characterize small plaques accurately using contemporary applied risk markers.

Ultrasound despeckling by anisotropic diffusion and total variation methods for liver fibrosis diagnostics

Anisotropic diffusion method and a total variation method for B-mode ultrasound image speckle filtering were compared for the problem of liver fibrosis diagnostics. An effective stopping criterion to control the strength of image filtering with the anisotropic diffusion algorithm and the regularization parameter estimation method for the proposed total variation algorithm were introduced. The comparison of two speckle filtering techniques demonstrated the advantage of anisotropic diffusion algorithm. Liver fibrosis diagnostics was performed using image texture analysis based on 10-20 textural characteristics. Siemens ACUSON S2000 ultrasound images of liver for 60 patients were used to determine the fibrosis according to the METAVIR score. A two-step algorithm includes elastography based F4 stage detection and F0–(F1,F2,F3) separation using ultrasound texture analysis. The classification was performed with Random Forest classifier. A comparison with deep convolutional neural networks was also performed. It was found that speckle filtering procedure in some cases enhances the texture-based classification and increases the total accuracy value up to 5% and makes the classification more robust and independent from the train–test set selection.

OP05.07: Prediction and utility of neonatal respiratory morbidity by quantitative lung texture analysis in pregnancies at risk for preterm/early term delivery

Prediction of neonatal respiratory morbidity can be useful to plan timing and place of delivery in complicated pregnancies and the justification of a first or repeat dose of antenatal corticosteroid in patients at risk for preterm & early term deliveries. This is especially so in resource and access restricted populations. The limited positive predictive performance of current diagnostic tests together with the risks of an invasive procedure, limits the use of fetal lung maturity assessment. This study was undertaken to evaluate the prediction and utility of information provided by a new method of quantitative ultrasound texture analysis (quantusFLM®) of fetal lung maturity in preterm and early term (<39.0 weeks) deliveries. Plans for intervention in pregnancies at risk for preterm and early term deliveries were analysed before and after information from a quantitative test for fetal lung maturity was made available to the clinician. Information was provided to multiple centres from a centralised imaging facility. Fetal lung ultrasound images were obtained at 25.0-38.6 weeks of gestation in the 48 hours prior to planned delivery, stored in DICOM format and analysed with quantusFLM®. Perinatal neonatal respiratory morbidity, defined as either respiratory distress syndrome or transient tachypnea of the newborn, was recorded. The performance of the test in altering decisions of timing and place of delivery and the specificity, negative predictable value of the test to predict neonatal respiratory morbidity were evaluated. A total of 100 patients were assessed. Quantitative textural analysis of the lung predicted neonatal respiratory morbidity with a specificity of 97% and a negative predictive value of 97%. Post test decision making was significantly altered in about one in three patients. quantusFLM® predicted neonatal respiratory morbidity with a higher accuracy than that of previously reported other tests with the advantage of being a non-invasive method.

Ultrasound texture analysis: Association with lymph node metastasis of papillary thyroid microcarcinoma.

This retrospective study aimed to evaluate whether ultrasound texture analysis is useful to predict lymph node metastasis in patients with papillary thyroid microcarcinoma (PTMC).This study was approved by the Institutional Review Board, and the need to obtain informed consent was waived. Between May and July 2013, 361 patients (mean age, 43.8 ± 11.3 years; range, 16–72 years) who underwent staging ultrasound (US) and subsequent thyroidectomy for conventional PTMC ≤ 10 mm between May and July 2013 were included. Each PTMC was manually segmented and its histogram parameters (Mean, Standard deviation, Skewness, Kurtosis, and Entropy) were extracted with Matlab software. The mean values of histogram parameters and clinical and US features were compared according to lymph node metastasis using the independent t-test and Chi-square test. Multivariate logistic regression analysis was performed to identify the independent factors associated with lymph node metastasis. Tumors with lymph node metastasis (n = 117) had significantly higher entropy compared to those without lymph node metastasis (n = 244) (mean±standard deviation, 6.268±0.407 vs. 6.171±.0.405; P = .035). No additional histogram parameters showed differences in mean values according to lymph node metastasis. Entropy was not independently associated with lymph node metastasis on multivariate logistic regression analysis (Odds ratio, 0.977 [95% confidence interval (CI), 0.482–1.980]; P = .949). Younger age (Odds ratio, 0.962 [95% CI, 0.940–0.984]; P = .001) and lymph node metastasis on US (Odds ratio, 7.325 [95% CI, 3.573–15.020]; P < .001) were independently associated with lymph node metastasis. Texture analysis was not useful in predicting lymph node metastasis in patients with PTMC.

Quantitative Ultrasound Texture Analysis for Differentiating Preterm From Term Fetal Lungs.

To differentiate preterm (<37 weeks' gestation) from term (≥37 weeks' gestation) fetal lungs by using quantitative texture analysis of ultrasound images. This study retrospectively evaluated singleton gestations with valid dating at 20 weeks' gestational age (GA) or later between January 2015 and December 2015. Images were obtained from Voluson E8 ultrasound systems (GE Healthcare, Milwaukee, WI). A region of interest was selected in each fetal lung image at the level of the 4 heart chambers from an area that appeared most representative of the overall lung tissue and had the least shadow. Ultrasonic tissue heterogeneity (heterogeneity index) based on dynamic range calculation was determined for all lung images. This quantification was performed with a custom-made software program that used a dithering technique based on the Floyd-Steinberg algorithm, in which the pixels are transformed into a binary map. Regression analysis was used to determine the correlation and functional association between the heterogeneity index and GA. A receiver operating characteristic curve was used to identify the optimal heterogeneity index cutoff point for differentiating preterm from term fetal lungs. A total of 425 fetal lung ultrasound images (313 preterm and 112 term) were analyzed. Quantitative texture analysis predicted GA with sensitivity and specificity of 87.9% and 92.0%, respectively, based on the optimal receiver operating characteristic cutoff point. Quantitative ultrasound texture analysis of fetal lung tissue can differentiate preterm fetal lungs from term fetal lungs. Our data suggest that decreased fetal lung heterogeneity on ultrasound imaging is associated with preterm fetuses.

Prediction of neonatal respiratory morbidity by quantitative ultrasound lung texture analysis: a multicenter study

Prediction of neonatal respiratory morbidity may be useful to plan delivery in complicated pregnancies. The limited predictive performance of the current diagnostic tests together with the risks of an invasive procedure restricts the use of fetal lung maturity assessment. The objective of the study was to evaluate the performance of quantitative ultrasound texture analysis of the fetal lung (quantusFLM) to predict neonatal respiratory morbidity in preterm and early-term (<39.0 weeks) deliveries. This was a prospective multicenter study conducted in 20 centers worldwide. Fetal lung ultrasound images were obtained at 25.0-38.6 weeks of gestation within 48 hours of delivery, stored in Digital Imaging and Communication in Medicine format, and analyzed with quantusFLM. Physicians were blinded to the analysis. At delivery, perinatal outcomes and the occurrence of neonatal respiratory morbidity, defined as either respiratory distress syndrome or transient tachypnea of the newborn, were registered. The performance of the ultrasound texture analysis test to predict neonatal respiratory morbidity was evaluated. A total of 883 images were collected, but 17.3% were discarded because of poor image quality or exclusion criteria, leaving 730 observations for the final analysis. The prevalence of neonatal respiratory morbidity was 13.8% (101 of 730). The quantusFLM predicted neonatal respiratory morbidity with a sensitivity, specificity, positive and negative predictive values of 74.3% (75 of 101), 88.6% (557 of 629), 51.0% (75of147), and 95.5% (557 of 583), respectively. Accuracy was 86.5%(632 of 730) and positive and negative likelihood ratios were 6.5and 0.3, respectively. The quantusFLM predicted neonatal respiratory morbidity with an accuracy similar to that previously reported for other tests with the advantage of being a noninvasive technique.