Laith R. Sultan

Vascularity Assessment of Thyroid Nodules by Quantitative Color Doppler Ultrasound

Our objective was to assess the role of quantitative Doppler vascularity in differentiating malignant and benign thyroid nodules. Color Doppler images of 100 nodules were analyzed for three metrics: vascular fraction area, mean flow velocity index and flow volume index in three regions (nodule center, nodule rim and surrounding parenchyma). Vascular fraction area and flow volume index were higher in malignant than benign nodules in both the central and rim regions, whereas flow velocity index was equivalent in both regions. Of the three vascularity metrics studied, the vascular fraction area of the central region was most effective in predicting malignancy, with a sensitivity of 0.90 ± 0.05, specificity of 0.88 ± 0.13, positive predictive value of 0.84 ± 0.14, negative predictive value of 0.92 ± 0.03 and accuracy of 0.89 ± 0.08. Quantitative Doppler vascularity of the nodule center yielded a high level of discrimination between benign and malignant nodules and, thus, has the greatest potential to contribute to gray-scale assessment of thyroid cancer.

Brachial artery vasomotion and transducer pressure effect on measurements by active contour segmentation on ultrasound

PURPOSE To use feed-forward active contours (snakes) to track and measure brachial artery vasomotion on ultrasound images recorded in both transverse and longitudinal views; and to compare the algorithms performance in each view. METHODS Longitudinal and transverse view ultrasound image sequences of 45 brachial arteries were segmented by feed-forward active contour (FFAC). The segmented regions were used to measure vasomotion artery diameter, cross-sectional area, and distention both as peak-to-peak diameter and as area. ECG waveforms were also simultaneously extracted frame-by-frame by thresholding a running finite-difference image between consecutive images. The arterial and ECG waveforms were compared as they traced each phase of the cardiac cycle. RESULTS FFAC successfully segmented arteries in longitudinal and transverse views in all 45 cases. The automated analysis took significantly less time than manual tracing, but produced superior, well-behaved arterial waveforms. Automated arterial measurements also had lower interobserver variability as measured by correlation, difference in mean values, and coefficient of variation. Although FFAC successfully segmented both the longitudinal and transverse images, transverse measurements were less variable. The cross-sectional area computed from the longitudinal images was 27% lower than the area measured from transverse images, possibly due to the compression of the artery along the image depth by transducer pressure. CONCLUSIONS FFAC is a robust and sensitive vasomotion segmentation algorithm in both transverse and longitudinal views. Transverse imaging may offer advantages over longitudinal imaging: transverse measurements are more consistent, possibly because the method is less sensitive to variations in transducer pressure during imaging.

Bayesian probability of malignancy with BI-RADS sonographic features.

The purpose of this study was to develop a quantitative approach for combining individual American College of Radiology Breast Imaging Reporting and Data System (BI‐RADS) sonographic features of breast masses for assessing the overall probability of malignancy.

Diagnostic accuracy of hepatorenal index in the detection and grading of hepatic steatosis

The objectives of our study were to assess the accuracy of hepatorenal index (HRI) in detection and grading of hepatic steatosis and to evaluate various factors that can affect the HRI measurement.

The diagnostic performance of leak-plugging automated segmentation versus manual tracing of breast lesions on ultrasound images:

Purpose To assess the diagnostic performance of a leak-plugging segmentation method that we have developed for delineating breast masses on ultrasound images. Materials and methods Fifty-two biopsy-proven breast lesion images were analyzed by three observers using the leak-plugging and manual segmentation methods. From each segmentation method, grayscale and morphological features were extracted and classified as malignant or benign by logistic regression analysis. The performance of leak-plugging and manual segmentations was compared by: size of the lesion, overlap area (Oa) between the margins, and area under the ROC curves (Az). Results The lesion size from leak-plugging segmentation correlated closely with that from manual tracing (R2 of 0.91). Oa was higher for leak plugging, 0.92 ± 0.01 and 0.86 ± 0.06 for benign and malignant masses, respectively, compared to 0.80 ± 0.04 and 0.73 ± 0.02 for manual tracings. Overall Oa between leak-plugging and manual segmentations was 0.79 ± 0.14 for benign and 0.73 ± 0.14 for malignant lesions. Az for leak plugging was consistently higher (0.910 ± 0.003) compared to 0.888 ± 0.012 for manual tracings. The coefficient of variation of Az between three observers was 0.29% for leak plugging compared to 1.3% for manual tracings. Conclusion The diagnostic performance, size measurements, and observer variability for automated leak-plugging segmentations were either comparable to or better than those of manual tracings.

Application of ARFI-SWV in Stiffness Measurement of the Abdominal Wall Musculature: A Pilot Feasibility Study

The purpose of this study was to assess the feasibility of acoustic radiation force impulse shear wave velocity and textural features for characterizing abdominal wall musculature and to identify subject-related and technique-related factors that can potentially affect measurements. Median shear wave velocity measurements for the right external abdominal oblique were the same (1.89 ± 0.16 m/s) for both the active group (healthy volunteers with active lifestyles) and the control group (age and body mass index-matched volunteers from an ongoing hernia study). When corrected for thickness, the ratio of right external abdominal oblique shear wave velocity -to-muscle thickness was significantly higher in the control group than in the active volunteers (4.33 s-1 versus 2.88 s-1; p value 0.006). From the textural features studied for right external abdominal oblique, 8 features were found to be statistically different between the active and control groups. In conclusion, shear wave velocity is a feasible and reliable technique to evaluate the stiffness of the abdominal wall musculature. Sonographic texture features add additional characterization of abdominal wall musculature.

Machine learning for diagnostic ultrasound of triple-negative breast cancer

PurposeEarly diagnosis of triple-negative (TN) breast cancer is important due to its aggressive biological characteristics, poor clinical outcomes, and limited options for therapy. The goal of this study is to evaluate the potential of machine learning with quantitative ultrasound image features for the diagnosis of TN breast cancer.MethodsUltrasonic and clinical data of 140 surgically confirmed breast cancer cases were analyzed retrospectively for the diagnosis of TN and non-TN (NTN) subtypes. The subtypes were classified based on the expression of estrogen receptor (ER), progesterone receptor (PR), and human epidermal growth factor receptor 2 (HER2). Ultrasound image features were measured from the grayscale and color Doppler images and used with logistic regression for classification by machine learning. Leave-one-out cross validation was used to train and test the differentiation. Diagnostic performance was measured by the area under receiver operating characteristic (ROC) curve, and sensitivity and specificity determined at the Youdons index.ResultsOf the twelve grayscale and Doppler features measured, eight were found to be statistically different for the TN and NTN subtypes (p < 0.05). The area under the ROC curve (AUC) of the statistically significant grayscale (GS) and color Doppler (CD) features was 0.85 and 0.65, respectively. The AUC increased to 0.88 when the GS and CD features were used together, with sensitivity of 86.96% and specificity of 82.91%. Consideration of patient age in the analysis did not improve discrimination of TN and NTN.ConclusionsThe analysis of breast ultrasound images by machine learning achieves high level of differentiation between the TN and NTN subtypes, exceeding the diagnostic performance by standard visual assessments of the images.

Abstract P30. Ultrasonic Mapping of the Abdominal Wall using ARFI-SWV: A Prospective Trial to Determine the Physiologic Basis for Reconstruction

PURPOSE: Current indices of risk evaluation for abdominal wall reconstruction focus on thickness and fat measurements, but do not address abdominal wall elasticity and texture assessment. Acoustic-Radiation-Forced-ImpulseShear-Wave-Velocity (ARFI-SWV) is a novel technology to assess skeletal muscle tissue characteristics. This technique has not assessed the abdominal wall physiology for reconstructive patients on a plastic surgery service.

Feed-forward active contour analysis for improved brachial artery reactivity testing

The object of this study was to utilize a novel feed-forward active contour (FFAC) algorithm to find a reproducible technique for analysis of brachial artery reactivity. Flow-mediated dilation (FMD) is an important marker of vascular endothelial function but has not been adopted for widespread clinical use given its technical limitations, including inter-observer variability and differences in technique across clinical sites. We developed a novel FFAC algorithm with the goal of validating a more reliable standard. Forty-six healthy volunteers underwent FMD measurement according to the standard technique. Ultrasound videos lasting 5–10 seconds each were obtained pre-cuff inflation and at minutes 1 through 5 post-cuff deflation in longitudinal and transverse views. Automated segmentation using the FFAC algorithm with initial boundary definition from three different observers was used to analyze the images to measure diameter/cross-sectional area over the cardiac cycle. The %FMD was calculated for average, minimum, and maximum diameters/areas. Using the FFAC algorithm, the population-specific coefficient of variation (CV) at end-diastole was 3.24% for transverse compared to 9.96% for longitudinal measurements; the subject-specific CV was 15.03% compared to 57.41%, respectively. For longitudinal measurements made via the conventional method, the population-specific CV was 4.77% and subject-specific CV was 117.79%. The intraclass correlation coefficient (ICC) for transverse measurements was 0.97 (95% CI: 0.95–0.98) compared to 0.90 (95% CI: 0.84–0.94) for longitudinal measurements with FFAC and 0.72 (95% CI: 0.51–0.84) for conventional measurements. In conclusion, transverse views using the novel FFAC method provide less inter-observer variability than traditional longitudinal views. Improved reproducibility may allow adoption of FMD testing in a clinical setting. The FFAC algorithm is a robust technique that should be evaluated further for its ability to replace the more limited conventional technique for measurement of FMD.

SU-D-134-06: Statistical Methods for Breast Mass Classification by Ultrasound Imaging

PURPOSE The overall goal of this study is to develop a computer-based image analysis system for breast ultrasound that may aid physicians in differentiating benign and malignant masses with higher confidence and thus help in reducing unnecessary biopsies. Towards this goal we describe an approach that combines two independent probabilistic classifiers to improve diagnosis of breast masses. METHODS B-scan images of 266 patients with biopsy proven breast masses were analyzed for margin grayscale and shape features. These features were used with two statistical methods, logistic regression and naive Bayes, to classify the lesions as malignant and benign. The diagnostic performance of the ultrasound image features was evaluated by using them alone and by combining them with mammographic BI-RADS categories and patient age. The probability predictions of the two classifiers were compared to assess consensus between them. The performances of the classifiers were evaluated using area under the curve (AUC) of the ROC Receiver Operating Characteristic. Training and testing were performed using leave-one-out validation. RESULTS The results showed that combined features outperformed the individual features. Logistic regression performed slightly better than naive Bayes (AUC: 0.902 ± 0.023 vs. 0.865 ± 0.027, p < 0.03). The agreement between the two models at different decision thresholds was stable at ∼88 %. The reaming 12% were treated as the cases that needed further diagnostic investigation. Treating each algorithm as an independent observer and using the consensus between the two models as the criterion for mass differentiation demonstrated a reduction in biopsy by 48% could be achieved at the cost of missed malignancies in 2% cases. CONCLUSION Computer-based image analysis of breast ultrasound images can aid the differentiation of benign and malignant masses and help in improving biopsy yields. NIH grant R01 CA130946.