The predictive value of cervical shear wave elastography in the outcome of labor induction

Introduction

Bishop score, the traditional method to assess cervical condition, is not a promising predictive tool of the outcome of labor induction. As an objective assessment tool, many cervical ultrasound measurements have been proposed to represent the individual components of the Bishop score, but none of them can measure the cervical stiffness. Cervical shear wave elastography is a novel tool to assess the cervical stiffness quantitatively.

Material and methods

A total of 475 women who required labor induction were studied prospectively. Prior to routine digital assessment of the Bishop score, transvaginal sonographic measurement of cervical length, posterior cervical angle, angle of progression and shear wave elastography was performed. Shear wave elastography measurement was made at the inner, middle and outer regions of the cervix to assess homogeneity. Association of labor induction outcomes including the overall cesarean section and subgroups of cesarean section for failure to enter active phase, with cervical sonographic parameters and the Bishop score, were assessed using multivariate regression analyses. The predictive accuracy of the outcomes using models based on ultrasound measurement and the Bishop score was compared using the area under the receiver‐operating characteristics curves.

Results

Among 475 women, 82 (17.3%) required cesarean section. Shear wave elasticity was significantly higher in the inner cervical region than in other regions, indicating a greater stiffness (P < 0.001). Both inner cervical shear wave elasticity and cervical length were independent predictors of overall cesarean section (respective adjusted odds ratio [95% CI] 1.338 [1.001‐1.598] and 1.717 [1.077‐1.663]) and cesarean section for failure to enter active phase (respective adjusted odds ratio [95% CI] 1.689 [1.234‐2.311] and 2.556 [1.462‐4.467]), after adjusting for other covariates. Outcome prediction models using inner cervical shear wave elasticity and cervical length, had increased area under curve compared with models using the Bishop score (0.888 vs 0.819, P = 0.009).

Conclusions

The cervix is not a homogenous structure, with the inner cervix having the highest stiffness, which is an independent predictor of overall cesarean section, and specifically for those indicated because of failure to enter active phase. Models based on shear wave elastography and cervical length had higher predictive accuracy than models based on the Bishop score.

Ultrasound IMT measurement on a multi-ethnic and multi-institutional database: our review and experience using four fully automated and one semi-automated methods

Automated and high performance carotid intima-media thickness (IMT) measurement is gaining increasing importance in clinical practice to assess the cardiovascular risk of patients. In this paper, we compare four fully automated IMT measurement techniques (CALEX, CAMES, CARES and CAUDLES) and one semi-automated technique (FOAM). We present our experience using these algorithms, whose lumen-intima and media-adventitia border estimation use different methods that can be: (a) edge-based; (b) training-based; (c) feature-based; or (d) directional Edge-Flow based. Our database (DB) consisted of 665 images that represented a multi-ethnic group and was acquired using four OEM scanners. The performance evaluation protocol adopted error measures, reproducibility measures, and Figure of Merit (FoM). FOAM showed the best performance, with an IMT bias equal to 0.025±0.225mm, and a FoM equal to 96.6%. Among the four automated methods, CARES showed the best results with a bias of 0.032±0.279mm, and a FoM to 95.6%, which was statistically comparable to that of FOAM performance in terms of accuracy and reproducibility. This is the first time that completely automated and user-driven techniques have been compared on a multi-ethnic dataset, acquired using multiple original equipment manufacturer (OEM) machines with different gain settings, representing normal and pathologic cases.

Atherosclerotic risk stratification strategy for carotid arteries using texture-based features

Plaques in the carotid artery result in stenosis, which is one of the main causes for stroke. Patients have to be carefully selected for stenosis treatments as they carry some risk. Since patients with symptomatic plaques have greater risk for strokes, an objective classification technique that classifies the plaques into symptomatic and asymptomatic classes is needed. We present a computer aided diagnostic (CAD) based ultrasound characterization methodology (a class of Atheromatic systems) that classifies the patient into symptomatic and asymptomatic classes using two kinds of datasets: (1) plaque regions in ultrasound carotids segmented semi-automatically and (2) far wall gray-scale intima-media thickness (IMT) regions along the common carotid artery segmented automatically. For both kinds of datasets, the protocol consists of estimating texture-based features in frameworks of local binary patterns (LBP) and Law's texture energy (LTE) and applying these features for obtaining the training parameters, which are then used for classification. Our database consists of 150 asymptomatic and 196 symptomatic plaque regions and 342 IMT wall regions. When using the Atheromatic-based system on semiautomatically determined plaque regions, support vector machine (SVM) classifier was adapted with highest accuracy of 83%. The accuracy registered was 89.5% on the far wall gray-scale IMT regions when using SVM, K-nearest neighbor (KNN) or radial basis probabilistic neural network (RBPNN) classifiers. LBP/LTE-based techniques on both kinds of carotid datasets are noninvasive, fast, objective and cost-effective for plaque characterization and, hence, will add more value to the existing carotid plaque diagnostics protocol. We have also proposed an index for each type of datasets: AtheromaticPi, for carotid plaque region, and AtheromaticWi, for IMT carotid wall region, based on the combination of the respective significant features. These indices show a separation between symptomatic and asymptomatic by 4.53 units and 4.42 units, respectively, thereby supporting the texture hypothesis classification.