Texture features for classification of ultrasonic liver images

The classification of ultrasonic liver images is studied, making use of the spatial gray-level dependence matrices, the Fourier power spectrum, the gray-level difference statistics, and the Laws texture energy measures. Features of these types are used to classify three sets of ultrasonic liver images-normal liver, hepatoma, and cirrhosis (30 samples each). The Bayes classifier and the Hotelling trace criterion are employed to evaluate the performance of these features. From the viewpoint of speed and accuracy of classification, it is found that these features do not perform well enough. Hence, a new texture feature set (multiresolution fractal features) based on multiple resolution imagery and the fractional Brownian motion model is proposed to detect diffuse liver diseases quickly and accurately. Fractal dimensions estimated at various resolutions of the image are gathered to form the feature vector. Texture information contained in the proposed feature vector is discussed. A real-time implementation of the algorithm produces about 90% correct classification for the three sets of ultrasonic liver images.

[1]  Michael Unser,et al.  Multiresolution Feature Extraction and Selection for Texture Segmentation , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Joseph Naor,et al.  Multiple Resolution Texture Analysis and Classification , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  S. Kay,et al.  Fractional Brownian Motion: A Maximum Likelihood Estimator and Its Application to Image Texture , 1986, IEEE Transactions on Medical Imaging.

[4]  James M. Keller,et al.  Texture description and segmentation through fractal geometry , 1989, Comput. Vis. Graph. Image Process..

[5]  Alex Pentland,et al.  Fractal-Based Description of Natural Scenes , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Azriel Rosenfeld,et al.  A Comparative Study of Texture Measures for Terrain Classification , 1975, IEEE Transactions on Systems, Man, and Cybernetics.

[7]  Julius T. Tou,et al.  Pattern Recognition Principles , 1974 .

[8]  Narendra Ahuja,et al.  A multiscale region detector , 1989, Comput. Vis. Graph. Image Process..

[9]  R. F. Wagner,et al.  Pattern Recognition Methods for Optimizing Multivariate Tissue Signatures in Diagnostic Ultrasound , 1986, Ultrasonic imaging.

[10]  J. Brickmann.  B. Mandelbrot: The Fractal Geometry of Nature, Freeman and Co., San Francisco 1982. 460 Seiten, Preis: £ 22,75. , 1985 .

[11]  J. Crowley.  A representation for visual information , 1981 .

[12]  Sing H. Lee,et al.  Optical Implementation Of The Hotelling Trace Criterion For Image Classification , 1984 .

[13]  Murray H. Loew,et al.  Application of pattern recognition techniques in ultrasound tissue characterization , 1990, [1990] Proceedings. 10th International Conference on Pattern Recognition.

[14]  Nazeih M. Botros.  A Microprocessor-Based Pattern Recognition Algorithm for In-Vivo Tissue Differentiation , 1988 .

[15]  R. F. Wagner,et al.  Quantitative ultrasonic detection and classification of diffuse liver disease. Comparison with human observer performance. , 1989, Investigative radiology.

[16]  Robert F Wagner,et al.  Unified Approach to the Detection and Classification of Speckle Texture in Diagnostic Ultrasound. , 1986, Optical engineering.

[17]  Michael F. Insana,et al.  Analysis of ultrasound image texture via generalized rician statistics , 1986 .

[18]  R. Voss.  Random Fractals: characterization and measurement , 1991 .

[19]  M. Fox,et al.  Fractal feature analysis and classification in medical imaging. , 1989, IEEE transactions on medical imaging.

[20]  George G. Lendaris,et al.  Diffraction-pattern sampling for automatic pattern recognition , 1970 .

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

[22]  Edward H. Adelson,et al.  The Laplacian Pyramid as a Compact Image Code , 1983, IEEE Trans. Commun..

[23]  Richard W. Conners,et al.  A Theoretical Comparison of Texture Algorithms , 1980, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[24]  Donald H. Foley.  Considerations of sample and feature size , 1972, IEEE Trans. Inf. Theory.

[25]  W. J. Lorenz,et al.  Diagnostic accuracy of computerized B‐scan texture analysis and conventional ultrasonography in diffuse parenchymal and malignant liver disease , 1985, Journal of clinical ultrasound : JCU.

[26]  Stéphane Mallat,et al.  A Theory for Multiresolution Signal Decomposition: The Wavelet Representation , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[27]  Donald S. Fussell,et al.  Computer rendering of stochastic models , 1982, Commun. ACM.

[28]  E. Feleppa,et al.  Relationship of Ultrasonic Spectral Parameters to Features of Tissue Microstructure , 1987, IEEE Transactions on Ultrasonics, Ferroelectrics and Frequency Control.

[29]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[30]  Azriel Rosenfeld,et al.  Experiments with texture classification using averages of local pattern matches , 1981, IEEE Transactions on Systems, Man, and Cybernetics.

[31]  William B. Thompson,et al.  Computer Diagnosis of Pneumoconiosis , 1974, IEEE Trans. Syst. Man Cybern..

[32]  R. D. Joseph,et al.  Pattern Recognition from Satellite Altitudes , 1968, IEEE Trans. Syst. Sci. Cybern..