Classification of scattering media within benign and malignant breast tumors based on ultrasound texture-feature-based and Nakagami-parameter images.

PURPOSE Benign and malignant tumors can be classified by using texture analysis of the ultrasound B-scan image to describe the variation in the echogenicity of scatterers. The recently proposed ultrasonic Nakagami parametric image has also been used to detect the concentrations and arrangements of scatterers for tumor characterization applications. B-scan-based texture analysis and the Nakagami parametric image are functionally complementary in ultrasonic tissue characterizations and this study aimed to combine these methods in order to improve the ability to characterize breast tumors. METHODS To validate this concept, radio-frequency data obtained from 130 clinical cases were used to construct the texture-feature parametric image and the Nakagami parametric image. Four texture-feature parameters based on a gray-level co-occurrence matrix (homogeneity, contrast, energy, and variance) and the Nakagami parameters of the benign and malignant tumors were calculated. The usefulness of an individual parameter was determined and scatter graphs indicated the relationship between two selected texture-feature parameters. Fisher's linear discriminant analysis was used to combine the selected texture-feature parameters with the Nakagami parameter. The performance in classifying tumors was evaluated based on the receiver operating characteristic curve. RESULTS The results indicated that there is a trade-off between sensitivity and specificity when using an individual texture-feature parameter or when combining two such correlated parameters to discriminate benign and malignant cases. However, the best performance was obtained when combining selected texture-feature parameters with the Nakagami parameter. CONCLUSIONS The study findings suggest that combining B-scan-based texture analysis and the Nakagami parametric image could improve the ability to classify benign and malignant breast tumors.

[1]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[2]  C. Metz.  Basic principles of ROC analysis. , 1978, Seminars in nuclear medicine.

[3]  S. Holm.  A Simple Sequentially Rejective Multiple Test Procedure , 1979 .

[4]  C. R. Hill,et al.  Acoustic properties of normal and cancerous human liver-I. Dependence on pathological condition. , 1981, Ultrasound in medicine & biology.

[5]  C R Hill,et al.  Tissue characterization from ultrasound B-scan data. , 1986, Ultrasound in medicine & biology.

[6]  Thijssen Jm,et al.  Ultrasonic tissue characterization and echographic imaging. , 1987 .

[7]  J. Thijssen.  Ultrasonic tissue characterisation and echographic imaging. , 1989, Physics in medicine and biology.

[8]  V. Jackson.  The role of US in breast imaging. , 1990, Radiology.

[9]  R. Waag,et al.  Nonlinear receiver compression effects on the amplitude distribution of backscattered ultrasonic signals , 1991, IEEE Transactions on Biomedical Engineering.

[10]  Yung-Chang Chen,et al.  Texture features for classification of ultrasonic liver images , 1992, IEEE Trans. Medical Imaging.

[11]  J.M. Reid,et al.  Use of non-Rayleigh statistics for the identification of tumors in ultrasonic B-scans of the breast , 1993, IEEE Trans. Medical Imaging.

[12]  S. Leinster,et al.  Immunocytochemical identification of cell types in benign and malignant breast diseases: variations in cell markers accompany the malignant state. , 1993, The journal of histochemistry and cytochemistry : official journal of the Histochemistry Society.

[13]  A. Stavros,et al.  Solid breast nodules: use of sonography to distinguish between benign and malignant lesions. , 1995, Radiology.

[14]  R. Tibshirani,et al.  Penalized Discriminant Analysis , 1995 .

[15]  J. Thijssen,et al.  Characterization of echographic image texture by cooccurrence matrix parameters. , 1997, Ultrasound in medicine & biology.

[16]  D. Chen,et al.  Computer-aided diagnosis applied to US of solid breast nodules by using neural networks. , 1999, Radiology.

[17]  B. Goldberg,et al.  Breast tumor vascularity identified by contrast enhanced ultrasound and pathology: initial results. , 2000, Ultrasonics.

[18]  P. Shankar.  A general statistical model for ultrasonic backscattering from tissues , 2000 .

[19]  B. Goldberg,et al.  Classification of ultrasonic B-mode images of breast masses using Nakagami distribution , 2001, IEEE Transactions on Ultrasonics, Ferroelectrics and Frequency Control.

[20]  Ruey-Feng Chang,et al.  Diagnosis of breast tumors with sonographic texture analysis using wavelet transform and neural networks. , 2002, Ultrasound in medicine & biology.

[21]  T. M. Kolb,et al.  Comparison of the performance of screening mammography, physical examination, and breast US and evaluation of factors that influence them: an analysis of 27,825 patient evaluations. , 2002, Radiology.

[22]  Radhika Sivaramakrishna,et al.  Texture analysis of lesions in breast ultrasound images. , 2002, Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society.

[23]  K. Han,et al.  Breast lesions on sonograms: computer-aided diagnosis with nearly setting-independent features and artificial neural networks. , 2003, Radiology.

[24]  Johan M. Thijssen,et al.  Ultrasonic speckle formation, analysis and processing applied to tissue characterization , 2003, Pattern Recognit. Lett..

[25]  Echogenicity of breast cancer: is it of prognostic value? , 2004, Breast.

[26]  P. Tsui,et al.  The effect of transducer characteristics on the estimation of Nakagami paramater as a function of scatterer concentration. , 2004, Ultrasound in medicine & biology.

[27]  E. S. de Paredes,et al.  Fibrous lesions of the breast: imaging-pathologic correlation. , 2005, Radiographics : a review publication of the Radiological Society of North America, Inc.

[28]  K. Cheng,et al.  The Representations of Sonographic Image Texture for Breast Cancer Using Co-occurrence Matrix , 2005 .

[29]  Jong Hyo Kim,et al.  Computerized scheme for assessing ultrasonographic features of breast masses. , 2005, Academic radiology.

[30]  André Victor Alvarenga,et al.  Complexity curve and grey level co-occurrence matrix in the texture evaluation of breast tumor on ultrasound images. , 2007, Medical physics.

[31]  Chien-Cheng Chang,et al.  Classification of breast masses by ultrasonic Nakagami imaging: a feasibility study , 2008, Physics in medicine and biology.

[32]  W. Moon,et al.  Ultrasound breast tumor image computer-aided diagnosis with texture and morphological features. , 2008, Academic radiology.

[33]  H. Chenga,et al.  Automated breast cancer detection and classification using ultrasound images A survey , 2009 .

[34]  Yin-Yin Liao,et al.  Classification of Benign and Malignant Breast Tumors by 2-D Analysis Based on Contour Description and Scatterer Characterization , 2010, IEEE Transactions on Medical Imaging.

[35]  Chih-Kuang Yeh,et al.  Classification of Benign and Malignant Breast Tumors by Ultrasound B-scan and Nakagami-based Images , 2010 .