Abstract
A novel method of multiscale texture analysis based on neural networks (NNs) has been developed and applied to the automated classification of benign and malignant focal liver lesions in ultrasound images. Our method is unique in the sense that it integrates a process of selection of multiscale texture features and a process of classification by a NN for effective classification. We developed an automated method that selects a set of multiscale texture features in the wavelet domain which maximize the performance of the NN for a given classification task. For the automated classification of benign and malignant focal liver lesions, regions of interest (ROIs) extracted from within the lesions were decomposed into subimages by wavelet packets. Multiscale texture features that quantify the homogeneity of the echogenicity were calculated from these subimages and were combined by a NN. A subset of the multiscale features was selected that yielded the highest performance in the classification of lesions. In an analysis of a set of ROIs extracted from hemangiomas (benign lesions), and from hepatocellular carcinomas and metastases (malignant lesions), the multiscale features yielded a high performance in distinguishing the benign from the malignant lesions. Therefore, our new multiscale texture analysis method based on NNs has the promise of increasing the accuracy of diagnosis of focal liver lesions in ultrasound images.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Chang, T. and Kuo, C.-C.J. (1993), “Texture analysis and classification with tree-structured wavelet transform,”IEEE Trans Image Processingvol. 2, pp. 429–441.
Unser, M. (1995), “Texture classification and segmentation using wavelet frames,”IEEE Trans Image Processingvol. 4, pp. 1549–1560.
Unser, M. and Eden, M. (1989), “Multiresolution feature extraction and selection for texture segmentation,”IEEE Transactions on Pattern Analysis and Machine Intelligencevol. 11, pp. 717–728.
Ros, P.R. (1994), “Malignant liver tumors,” in Gore, R.M., Levine, M.S., and Laufer, I (Eds.)Textbook of Gastrointestinal Radiology vol. 2.Saunders: Philadelphia, pp. 1897–1946.
Jeffrey, R.B. and Ralls, P.W. (1995)Sonography of the abdomenNew York: Raven Press.
Coifman, R.R. and Wickerhauser, M.V. (1992), “Entropy-based algorithms for best basis selection,”IEEE Trans Information Theoryvol. 38, pp. 1713–1716.
Yoshida, H. and Casalino, D. (2000), “Classification of focal liver lesions in ultrasonic images based on echo texture analysis,”Proc SPIE 3982pp. 252–256.
Haykin, S. (1999)Neural networks: a comprehensive foundationNew Jersey: Prentice Hall.
Wright, I.A. and Gough, N.A. (1999), “Artificial neural network analysis of common femoral artery Doppler shift signals: classification of proximal disease,”Ultrasound Med Biolvol. 25, pp. 735–743.
Nakamura, K., Yoshida, H., Engelmann, R., MacMahon, H., Katsuragawa, S., Ishida, T., Ashizawa, K., and Doi, K. (2000), “Computerized analysis of the likelihood of malignancy in solitary pulmonary nodules by use of artificial neural networks,”Radiologyvol. 214, pp. 823–830.
Ashizawa, K., MacMahon, H., Ishida, T., Nakamura, K., Vyborny, C.J., Katsuragawa, S., and Doi, K. (1999), “Effect of an artificial neural network on radiologists’ performance in the differential diagnosis of interstitial lung disease using chest radiographs,”Am JRoentgenolvol. 172, pp. 1311–1315.
Ashizawa, K., Ishida, T., MacMahon, H., Vyborny, C.J., Katsuragawa, S., and Doi, K. (1999), “Artificial neural networks in chest radiography: application to the differential diagnosis of interstitial lung disease,”Acad Radiolvol. 6, pp. 2–9.
Huo, Z., Giger, M.L., Vyborny, C.J., Bick, U., Lu, P., Wolverton, D.E., and Schmidt, R.A. (1995), “Analysis of spiculation in the computerized classification of mammographic masses,”Med Physvol. 22, pp. 1569–1579.
Huo, Z., Giger, M.L., Vyborny, C.J., Wolverton, D.E., Schmidt, R.A., and Doi, K. (1998), “Automated computerized classification of malignant and benign masses on digitized mammograms,”Acad Radiolvol. 5, pp. 155–168.
Jiang, Y., Nishikawa, R.M., Wolverton, D.E., Metz, C.E., Giger, M.L., Schmidt, R.A., Vyborny, C.J., and Doi, K. (1996), “Malignant and benign clustered microcalcifications: automated feature analysis and classification,”Radiologyvol. 198, pp. 671–678.
Katsuragawa, S., Doi, K., Nakamori, N., and MacMahon, H. (1990), “Image feature analysis and computer-aided diagnosis in digital radiography: effect of digital parameters on the accuracy of computerized analysis of interstitial disease in digital chest radiographs,”Med Physvol. 17, pp. 72–78.
Verterli, M. and Kovacevic, J. (1995)Wavelets and Subband CodingNJ: Englewood Cliffs.
Fukunaga, K. (1990)Introduction to Statistical Pattern RecognitionSan Diego: Academic Press.
Wu, Y.C., Doi, K., Giger, M.L., Metz, C.E., and Zhang, W. (1994), “Reduction of false positives in computerized detection of lung nodules in chest radiographs using artificial neural networks, discriminant analysis, and a rule-based scheme,”.J Digit Imagingvol. 7, pp. 196–207.
Efron, E. (1982)The Jackknife the Bootstrap and Other Resampling PlansPhiladelphia: Society for Industrial and Applied Mathematics.
Zhang, W., Yoshida, H., Nishikawa, R.M., and Doi, K. (1998), “Optimally weighted wavelet transform based on supervised training for detection of microcalcifications in digital mammograms,”Medical Physicsvol. 25, pp. 949–956.
Metz, C.E. (1986), “ROC methodology in radiologic imaging,”Invest Radiolvol. 21, pp. 720–733.
Metz, C.E. (1989), “Some practical issues of experimental design and data analysis in radiological ROC studies,”Invest Radiolvol. 24, pp. 234–245.
Metz, C.E., Herman, B.A., and Shen, J.H. (1998), “Maximum likelihood estimation of receiver operating characteristic (ROC) curves from continuously-distributed data,”Stat Medvol. 17, pp. 1033–1053.
Daubechies, I. (1992)Ten Lectures on WaveletsPhiladelphia: Society for Industrial and Applied Mathematics.
Jain, A.K. (1989)Fundamentals of Digital Image ProcessingNew Jersey: Prentice Hall.
Doi, K., MacMahon, H., Giger, M.L., and Hoffmann, K.R. (Eds.) (1999)Computer-Aided Diagnosis in Medical ImagingExcerpta Medica: International Congress Series I182, Elsevier: Amsterdam.
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer Science+Business Media New York
About this chapter
Cite this chapter
Yoshida, H. (2001). Neural Network for Classification of Focal Liver Lesions in Ultrasound Images. In: Jain, L., De Wilde, P. (eds) Practical Applications of Computational Intelligence Techniques. International Series in Intelligent Technologies, vol 16. Springer, Dordrecht. https://doi.org/10.1007/978-94-010-0678-1_12
Download citation
DOI: https://doi.org/10.1007/978-94-010-0678-1_12
Publisher Name: Springer, Dordrecht
Print ISBN: 978-94-010-3868-3
Online ISBN: 978-94-010-0678-1
eBook Packages: Springer Book Archive