Fusion of fuzzy statistical distributions for classification of thyroid ultrasound patterns

OBJECTIVE This paper proposes a novel approach for thyroid ultrasound pattern representation. Considering that texture and echogenicity are correlated with thyroid malignancy, the proposed approach encodes these sonographic features via a noise-resistant representation. This representation is suitable for the discrimination of nodules of high malignancy risk from normal thyroid parenchyma. MATERIALS AND METHODS The material used in this study includes a total of 250 thyroid ultrasound patterns obtained from 75 patients in Greece. The patterns are represented by fused vectors of fuzzy features. Ultrasound texture is represented by fuzzy local binary patterns, whereas echogenicity is represented by fuzzy intensity histograms. The encoded thyroid ultrasound patterns are discriminated by support vector classifiers. RESULTS The proposed approach was comprehensively evaluated using receiver operating characteristics (ROCs). The results show that the proposed fusion scheme outperforms previous thyroid ultrasound pattern representation methods proposed in the literature. The best classification accuracy was obtained with a polynomial kernel support vector machine, and reached 97.5% as estimated by the area under the ROC curve. CONCLUSIONS The fusion of fuzzy local binary patterns and fuzzy grey-level histogram features is more effective than the state of the art approaches for the representation of thyroid ultrasound patterns and can be effectively utilized for the detection of nodules of high malignancy risk in the context of an intelligent medical system.

[1]  R. M. Haralick,et al.  Textural features for image classification. IEEE Transaction on Systems, Man, and Cybernetics , 1973 .

[2]  J. Ravenel.  The Essential Physics of Medical Imaging, 2nd ed. , 2003 .

[3]  M. Pietikäinen,et al.  SOFT HISTOGRAMS FOR LOCAL BINARY PATTERNS , 2007 .

[4]  Mary M. Galloway,et al.  Texture analysis using gray level run lengths , 1974 .

[5]  B. Ripley,et al.  Pattern Recognition , 1968, Nature.

[6]  Sergios Theodoridis,et al.  Pattern Recognition, Third Edition , 2006 .

[7]  Vladimir Vapnik,et al.  Estimation of Dependences Based on Empirical Data: Springer Series in Statistics (Springer Series in Statistics) , 1982 .

[8]  John W. Sammon,et al.  A Nonlinear Mapping for Data Structure Analysis , 1969, IEEE Transactions on Computers.

[9]  Ronald R. Yager,et al.  Essentials of fuzzy modeling and control , 1994 .

[10]  Dimitrios K. Iakovidis,et al.  Noise-robust statistical feature distributions for texture analysis , 2008, 2008 16th European Signal Processing Conference.

[11]  Yee-Hong Yang,et al.  Texture characterization using robust statistics , 1994, Pattern Recognit..

[12]  D. Cavouras,et al.  Development of a support vector machine-based image analysis system for assessing the thyroid nodule malignancy risk on ultrasound. , 2005, Ultrasound in medicine & biology.

[13]  W Domschke,et al.  Standardized grey scale ultrasonography in Graves' disease: correlation to autoimmune activity. , 1999, European journal of endocrinology.

[14]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[15]  Dimitrios K. Iakovidis,et al.  An intelligent system for automatic detection of gastrointestinal adenomas in video endoscopy , 2006, Comput. Biol. Medicine.

[16]  Dimitris Maroulis,et al.  Ultrasound Image Processing and Analysis Framework , 2008 .

[17]  G. Medeiros-Neto,et al.  Combined ultrasonographic and cytological studies in the diagnosis of thyroid nodules. , 1999, Biochimie.

[18]  Hadi Hadizadeh,et al.  Random Texture Defect Detection Using 1-D Hidden Markov Models Based on Local Binary Patterns , 2008, IEICE Trans. Inf. Syst..

[19]  Charles X. Ling,et al.  AUC: A Better Measure than Accuracy in Comparing Learning Algorithms , 2003, Canadian Conference on AI.

[20]  Charles X. Ling,et al.  Using AUC and accuracy in evaluating learning algorithms , 2005, IEEE Transactions on Knowledge and Data Engineering.

[21]  G. van Kaick,et al.  Quantification and classification of echographic findings in the thyroid gland by computerized B-mode texture analysis. , 1989, European journal of radiology.

[22]  Kazutoshi Okamura,et al.  Quantitative analyses of sonographic images of the parotid gland in patients with Sjögren's syndrome. , 2006, Ultrasound in medicine & biology.

[23]  B. Julesz.  Textons, the elements of texture perception, and their interactions , 1981, Nature.

[24]  Efstratios G. Keramidas.  Master of Science Thesis Ultrasound Image Processing and Analysis Framework , 2007 .

[25]  Joel H. Saltz,et al.  Pathological Image Analysis Using the GPU: Stroma Classification for Neuroblastoma , 2007, 2007 IEEE International Conference on Bioinformatics and Biomedicine (BIBM 2007).

[26]  Radim Sára,et al.  Different types of image texture features in ultrasound of patients with lymphocytic thyroiditis , 2003, ISICT.

[27]  H Morifuji.  [Analysis of ultrasound B-mode histogram in thyroid tumors]. , 1989, Nihon Geka Gakkai zasshi.

[28]  R. Sára,et al.  Image texture analysis of sonograms in chronic inflammations of thyroid gland. , 2003, Ultrasound in medicine & biology.

[29]  Matti Pietikäinen,et al.  A comparative study of texture measures with classification based on featured distributions , 1996, Pattern Recognit..

[30]  J C Bamber,et al.  Adaptive filtering for reduction of speckle in ultrasonic pulse-echo images. , 1986, Ultrasonics.

[31]  Horst Bischof,et al.  On-line boosting-based car detection from aerial images , 2008 .

[32]  C. V. Jawahar,et al.  Fuzzy statistics of digital images , 1996, IEEE Signal Processing Letters.

[33]  Jasjit S. Suri,et al.  Handbook of Biomedical Image Analysis , 2005 .

[34]  J. Bushberg.  The Essential Physics of Medical Imaging , 2001 .

[35]  Anna Crescenzi,et al.  Risk of malignancy in nonpalpable thyroid nodules: predictive value of ultrasound and color-Doppler features. , 2002, The Journal of clinical endocrinology and metabolism.

[36]  V. Vapnik.  Estimation of Dependences Based on Empirical Data , 2006 .

[37]  Costas S. Iliopoulos,et al.  An algorithm for mapping short reads to a dynamically changing genomic sequence , 2010, 2010 IEEE International Conference on Bioinformatics and Biomedicine (BIBM).

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

[39]  Skouroliakou Catherine,et al.  Quantitative image analysis in sonograms of the thyroid gland , 2006 .

[40]  Dimitrios K. Iakovidis,et al.  Efficient and Effective Ultrasound Image Analysis Scheme for Thyroid Nodule Detection , 2007, ICIAR.

[41]  Charles Grant,et al.  Diagnostic Ultrasound, 3rd ed , 2006 .

[42]  C. V. Jawahar,et al.  Incorporation of gray-level imprecision in representation and processing of digital images , 1996, Pattern Recognit. Lett..

[43]  Nikos Dimitropoulos,et al.  Computational Characterization of Thyroid Tissue in the Radon Domain , 2007, Twentieth IEEE International Symposium on Computer-Based Medical Systems (CBMS'07).

[44]  Ron Kikinis,et al.  Segmentation of Meningiomas and Low Grade Gliomas in MRI , 1999, MICCAI.

[45]  D. Taverner.  Diagnostic Ultrasound , 1966, Nature.

[46]  Nikos Dimitropoulos,et al.  Thyroid Texture Representation via Noise Resistant Image Features , 2008, 2008 21st IEEE International Symposium on Computer-Based Medical Systems.

[47]  G E Mailloux,et al.  Local histogram information content of ultrasound B-mode echographic texture. , 1985, Ultrasound in medicine & biology.

[48]  G. Mailloux,et al.  Computer analysis of echographic textures in hashimoto disease of the thyroid , 1986, Journal of clinical ultrasound : JCU.

[49]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .