Analysis of Elastographic and B-mode Features at Sonoelastography for Breast Tumor Classification
Journal
Ultrasound in Medicine and Biology
Journal Volume
35
Journal Issue
11
Pages
1794-1802
Date Issued
2009
Author(s)
Abstract
The purpose of this study was to evaluate the accuracy of neural network analysis of elastographic features at sonoelastography for the classification of biopsy-proved benign and malignant breast tumors. Sonoelastography of 181 solid breast masses (113 benign and 68 malignant tumors) was performed for 181 patients (mean age, 47 years; range, 24-75 years). After the manual segmentation of the tumors, five elastographic features (strain difference, strain ratio, mean, median and mode) and six B-mode features (orientation, undulation, angularity, average gradient, gradient variance and intensity variance) were computed. A neural network was used to classify tumors by the use of these features. The Student's t test and receiver operating characteristic (ROC) curve analysis were used for statistical analysis. Area under ROC curve (Az) values of the three elastographic features- mean (0.87), median (0.86) and mode (0.83)-were significantly higher than the Az values for the six B-mode features (0.54-0.69) (p < 0.01). Accuracy, sensitivity, specificity and Az of the neural network for the classification of solid breast tumors were 86.2% (156/181), 83.8% (57/68), 87.6% (99/113) and 0.84 for the elastographic features, respectively, and 82.3% (149/181), 70.6% (48/68), 89.4% (101/113) and 0.78 for the B-mode features, respectively, and 90.6% (164/181), 95.6% (65/68), 87.6% (99/113) and 0.92 for the combination of the elastographic and B-mode features, respectively. We conclude that sonoelastographic images and neural network analysis of features has the potential to increase the accuracy of the use of ultrasound for the classification of benign and malignant breast tumors. (E-mail: rfchang@csie.ntu.edu.tw). ? 2009 World Federation for Ultrasound in Medicine & Biology.
SDGs
Other Subjects
Average gradient; BI-RADS; Breast tumor; Elastography; Gradient variance; Malignant tumors; Manual segmentation; Mean ages; Neural network analysis; Receiver operating characteristic curve analysis; ROC curves; Solid breast mass; Sonoelastography; Statistical analysis; Strain ratios; T-tests; Acoustic waves; Electric network analysis; Oncology; Tumors; Ultrasonics; Neural networks; adult; aged; article; artificial neural network; B scan; breast biopsy; breast cancer; breast tumor; controlled study; diagnostic accuracy; diagnostic value; elastography; female; human; human tissue; major clinical study; priority journal; sensitivity and specificity; solid tumor; statistical analysis; statistical parameters; tumor classification; Adult; Aged; Breast Neoplasms; Elasticity Imaging Techniques; Female; Humans; Image Interpretation, Computer-Assisted; Middle Aged; Neural Networks (Computer); Sensitivity and Specificity; Ultrasonography, Doppler, Color; Ultrasonography, Mammary; Young Adult
Type
journal article