Shear wave elastography for characterization of breast lesions: Shearlet transform and local binary pattern histogram techniques. (1st December 2017)

• Record Type: Journal Article
• Authors: Acharya, U. Rajendra; Ng, Wei Lin; Rahmat, Kartini; Sudarshan, Vidya K.; Koh, Joel E.W.; Tan, Jen Hong; Hagiwara, Yuki; Gertych, Arkadiusz; Fadzli, Farhana; Yeong, Chai Hong; Ng, Kwan Hoong
• Is Part Of: Computers in biology and medicine. Volume 91(2017)
• Page Start: 13
• Page End: 20
• Publication Date: 2017-12-01
• Subjects: Breast lesions -- Benign -- Malignant -- Shear wave elastography -- Shearlet transform -- Local binary pattern; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2017.10.001
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: Shear wave elastography (SWE) examination using ultrasound elastography (USE) is a popular imaging procedure for obtaining elasticity information of breast lesions. Elasticity parameters obtained through SWE can be used as biomarkers that can distinguish malignant breast lesions from benign ones. Furthermore, the elasticity parameters extracted from SWE can speed up the diagnosis and possibly reduce human errors. In this paper, Shearlet transform and local binary pattern histograms (LBPH) are proposed as an original algorithm to differentiate malignant and benign breast lesions. First, Shearlet transform is applied on the SWE images to acquire low frequency, horizontal and vertical cone coefficients. Next, LBPH features are extracted from the Shearlet transform coefficients and subjected to dimensionality reduction using locality sensitivity discriminating analysis (LSDA). The reduced LSDA components are ranked and then fed to several classifiers for the automated classification of breast lesions. A probabilistic neural network classifier trained only with seven top ranked features performed best, and achieved 98.08% accuracy, 98.63% sensitivity, and 97.59% specificity in distinguishing malignant from benign breast lesions. The high sensitivity and specificity of our system indicates that it can be employed as a primary screening tool for faster diagnosis of breast malignancies, thereby possibly reducing the mortality rate due to breast cancer. Graphical abstract: Highlights: Classification of benign and malignant SWE images. Shearlet transform and local binary pattern histogram performed. LSDA is used for feature reduction. Obtained accuracy of 98.08% using 7 features with PNN classifier.