Computer-Aided Strain Evaluation for Acoustic Radiation Force Impulse Imaging of Breast Masses

Abstract

Acoustic radiation force impulse (ARFI) is a newly developed elastography technique that uses acoustic radiation force to provide additional stiffness information to conventional sonography. A computer-aided diagnosis (CAD) system was proposed to automatically specify the tumor boundaries in ARFI images and quantify the statistical stiffness information to reduce user dependence. The level-set segmentation was used to delineate tumor boundaries in B-mode images, and the segmented boundaries were then mapped to the corresponding area in ARFI images for a gray-scale calculation. A total of 61 benign and 51 malignant tumors were evaluated in the experiment. The CAD system based on the proposed ARFI features achieved an accuracy of 80% (90/112), a sensitivity of 80% (41/51), and a specificity of 80% (49/61), which is significantly better than that of the quantitative B-mode features (p < 0.05). The ARFI features were further combined with the B-mode features, including shape and texture features, to further improve performance (area under the curve [AUC], 0.90 vs. 0.86). In conclusion, the CAD system based on the proposed ARFI features is a promising and efficient diagnostic method.

Quantitative breast mass classification based on the integration of B-mode features and strain features in elastography

“…StrainMean [19,25] is the sum of original gray-scale values (E(i, j)) divided by the number of pixels (TN) in the tumor area, T. This feature describes the average strain value of tissues within the tumor area to show whether a tumor is soft or hard. StrainVAR [19,25,30,31] interprets the strain composition using the mean and standard deviation (SD) of pixel values.…”

“…StrainVAR [19,25,30,31] interprets the strain composition using the mean and standard deviation (SD) of pixel values. StrainVAR is similar to SNRe, the elastographic signal-to-noise ratio, relates to the physical parameters of the ultrasound system used to acquire the data [30].…”

“…Burnside et al indicated that inter-observer variability was an influence factor to the diagnostic performance [17]. Prior CAD approach which extracted quantitative elasticity features from acoustic radiation force impulse imaging achieved an accuracy of 80% in classifying breast tumors [25]. In this study, we proposed an automatic procedure to extract strain features from quasi-static elastography in a CAD system for tumor classification.…”

Evaluation of a Computer-Aided Diagnosis System in the Classification of Lesions in Breast Strain Elastography Imaging

“…Computer-aided diagnosis (CAD) systems are emerging tools to give assistance in clinical use. In some studies, for example, the authors of [ 21 , 22 , 23 , 24 , 25 , 26 ] used the level set [ 27 ] for automatic segmentation on the lesion in the B-mode ultrasound. After that, the contour was mapped to the corresponding grey-scale elasticity image for the following calculation of tumor statistics.…”

Caracterização de lesões em imagens digitais de ultrassonografia e elastografia da mama utilizando técnicas inteligentes

“…Os Diversos outros estudos indicam o potencial da avaliação quantitativa das imagens elastográficas na melhoria da precisão diagnóstica, podendo evitar biópsias desnecessárias e ser útil na análise clínica (LO et al, 2014, 2015a, 2013aXIAO et al, 2013;ZHANG et al, 2014;ZHI et al, 2008). Outros estudos realizam a comparação entre mamografia, ultrassom convencional e elastografia (MOHEY; HASSAN, 2014;PARDAL et al, 2013;THOMAS et al, 2006;ZHI et al, 2007).…”