Automated quantification of ultrasonic fatty liver texture based on curvelet transform and SVD

• Autorzy: Bharath R. , Mishra P. K. , Rajalakshmi P.

Identyfikatory

DOI

10.1016/j.bbe.2017.12.004

• Języki publikacji: EN

Abstrakty

EN

Fatty liver is a prevalent disease and is the major cause for the dysfunction of the liver. If fatty liver is untreated, it may progress into chronic diseases like cirrhosis, hepatocellular carcinoma, liver cancer, etc. Early and accurate detection of fatty liver is crucial to prevent the fatty liver progressing into chronic diseases. Based on the severity of fat, the liver is categorized into four classes, namely Normal, Grade I, Grade II and Grade III respectively. Ultrasound scanning is the widely used imaging modality for diagnosing the fatty liver. The ultrasonic texture of liver parenchyma is specific to the severity of fat present in the liver and hence we formulated the quantification of fatty liver as a texture discrimination problem. In this paper, we propose a novel algorithm to discriminate the texture of fatty liver based on curvelet transform and SVD. Initially, the texture image is decomposed into sub-band images with curvelet transform enhancing gradients and curves in the texture, then an absolute mean of the singular values are extracted from each curvelet decomposed image, and used it as a feature representation for the texture. Finally, a cubic SVM classifier is used to classify the texture based on the extracted features. Tested on a database of 1000 image textures with 250 image textures belonging to each class, the proposed algorithm gave an accuracy of 96.9% in classifying the four grades of fat in the liver.

Słowa kluczowe

EN

fatty liver; curvelet transform; SVD; texture features; SVM classifier; computer aided diagnosis

PL

stłuszczenie wątroby; transformata falkowa; SVD; cechy teksturalne; klasyfikator SVM; diagnoza wspomagana komputerowo

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2018
• Tom: Vol. 38, no. 1
• Strony: 145--157
• Opis fizyczny: Bibliogr. 55 poz., rys., tab., wykr.

Twórcy

autor

Bharath R.

• WiNet Research Lab, Department of Electrical Engineering, Indian Institute of Technology Hyderabad, Kandi, Sangareddy, Telangana, India

autor

Mishra P. K.

• WiNet Research Lab, Department of Electrical Engineering, Indian Institute of Technology Hyderabad, Kandi, Sangareddy, Telangana, India

autor

Rajalakshmi P.

• WiNet Research Lab, Department of Electrical Engineering, Indian Institute of Technology Hyderabad, Kandi, Sangareddy, Telangana, India

Bibliografia

• [1] Takahashi Y, Fukusato T. Histopathology of nonalcoholic fatty liver disease/nonalcoholic steatohepatitis. World J Gastroenterol: WJG 2014;20(42):15539.
• [2] Bellentani S, Scaglioni F, Marino M, Bedogni G. Epidemiology of non-alcoholic fatty liver disease. Dig Dis 2010;28(1):155–61.
• [3] Marchesini G, Brizi M, Morselli-Labate AM, Bianchi G, Bugianesi E, McCullough AJ, et al. Association of nonalcoholic fatty liver disease with insulin resistance. Am J Med 1999;107(5):450–5.
• [4] Brunt EM, Janney CG, Di Bisceglie AM, Neuschwander-Tetri BA, Bacon BR. Nonalcoholic steatohepatitis: a proposal for grading and staging the histological lesions. Am J Gastroenterol 1999;94(9):2467–74.
• [5] Strauss S, Gavish E, Gottlieb P, Katsnelson L. Interobserver and intraobserver variability in the sonographic assessment of fatty liver. Am J Roentgenol 2007;189(6): W320–3.
• [6] Hernaez R, Lazo M, Bonekamp S, Kamel I, Brancati FL, Guallar E, et al. Diagnostic accuracy and reliability of ultrasonography for the detection of fatty liver: a metaanalysis. Hepatology 2011;54(3):1082–90.
• [7] Allan R, Thoirs K, Phillips M. Accuracy of ultrasound to identify chronic liver disease. World J Gastroenterol: WJG 2010;16(28):3510.
• [8] Raeth U, Schlaps D, Limberg B, Zuna I, Lorenz A, Van Kaick G, et al. Diagnostic accuracy of computerized Bscan texture analysis and conventional ultrasonography in diffuse parenchymal and malignant liver disease. J Clin Ultrasound 1985;13(2):87–99.
• [9] Selvan S, Ramakrishnan S. SVD-based modeling for image texture classification using wavelet transformation. IEEE Trans Image Process 2007;16(11):2688–96.
• [10] Goceri E, Shah ZK, Layman R, Jiang X, Gurcan MN. Quantification of liver fat: a comprehensive review. Comput Biol Med 2016;71:174–89.
• [11] Bharti P, Mittal D, Ananthasivan R. Computer-aided characterization and diagnosis of diffuse liver diseases based on ultrasound imaging: a review. Ultrasonic Imaging 2017;39(1):33–61.
• [12] Acharya UR, Faust O, Molinari F, Vinitha Sree S, Junnarkar SP, Sudarshan V. Ultrasound-based tissue characterization and classification of fatty liver disease: a screening and diagnostic paradigm. Knowl-Based Syst 2015;75:66–77.
• [13] Kadah YM, Farag AA, Zurada JM, Ahmed MB, Youssef A-BM. Classification algorithms for quantitative tissue characterization of diffuse liver disease from ultrasound images. IEEE Trans Med Imaging 1996;15(4):466–78.
• [14] Acharya UR, Fujita H, Sudarshan VK, Krishnan Mookiah MR, Koh JEW, Tan JH, et al. An integrated index for identification of fatty liver disease using radon transform and discrete cosine transform features in ultrasound images. Inf Fusion 2016;31:43–53.
• [15] Pavlopoulos S, Kyriacou E, Koutsouris D, Blekas K, Stafylopatis A, Zoumpoulis P. Fuzzy neural network-based texture analysis of ultrasonic images. IEEE Eng Med Biol Mag 2000;19(1):39–47.
• [16] Ribeiro RT, Marinho RT, Miguel Sanches J. An ultrasound- based computer-aided diagnosis tool for steatosis detection. IEEE J Biomed Health Inform 2014;18(4):1397–403.
• [17] Singh MS, Gupta SS. A new quantitative metric for liver classification from ultrasound images. Int J Comput Electr Eng 2012;4(4):605.
• [18] Lupsor M, Badea R, Vica C, Nedevschi S, Grigorescu M, Radu C, et al. Non-invasive steatosis assessment in NASH through the computerized processing of ultrasound images: attenuation versus textural parameters. 2010 IEEE International Conference on Automation Quality and Testing Robotics (AQTR), vol. 2. IEEE. 2010. pp. 1–6.
• [19] Ier S, Cokun A, Kizceli T. Quantitative grading using grey relational analysis on ultrasonographic images of a fatty liver. J Med Syst 2012;36(4):2521–8.
• [20] Mihailescu DM, Gui V, Toma CI, Popescu A, Sporea I. Automatic evaluation of steatosis by ultrasound image analysis. 2012 10th International Symposium on Electronics and Telecommunications (ISETC), IEEE. 2012. pp. 311–4.
• [21] Vicas C, Nedevschi S, Lupsor M, Badea R. Automatic detection of liver capsule using Gabor filters. Intelligent Computer Communication and Processing, 2009; 2009. pp. 133–40.
• [22] Liao Y-Y, Yang K-C, Lee M-J, Huang K-C, Chen J-D, Yeh C-K. Multifeature analysis of an ultrasound quantitative diagnostic index for classifying nonalcoholic fatty liver disease. Sci Rep 2016;6.
• [23] Bharath R, Rajalakshmi P. Deep scattering convolution network based features for ultrasonic fatty liver tissue characterization. Engineering in Medicine and Biology Society (EMBC); 2017. pp. 1982–5.
• [24] Bruna J, Mallat S. Invariant scattering convolution networks. IEEE Trans Pattern Anal Mach Intell 2013;35 (8):1872–86.
• [25] Wu C-C, Lee W-L, Chen Y-C, Hsieh K-S. Evolution-based hierarchical feature fusion for ultrasonic liver tissue characterization. IEEE J Biomed Health Inform 2013;17 (5):967–76.
• [26] Alivar A, Danyali H, Helfroush MS. Hierarchical classification of normal, fatty and heterogeneous liver diseases from ultrasound images using serial and parallel feature fusion. Biocybernet Biomed Eng 2016;36(4):697–707.
• [27] Singh M, Singh S, Gupta S. An information fusion based method for liver classification using texture analysis of ultrasound images. Inf Fusion 2014;19:91–6.
• [28] Ribeiro RT, Marinho RT, Miguel Sanches J. Classification and staging of chronic liver disease from multimodal data. IEEE Trans Biomed Eng 2013;60(5):1336–44.
• [29] Andrade A, Silva JS, Santos J, Belo-Soares P. Classifier approaches for liver steatosis using ultrasound images. Proc Technol 2012;5:763–70.
• [30] Ribeiro R, Sanches J. Fatty liver characterization and classification by ultrasound. IbPRIA. 2009. pp. 354–61.
• [31] Acharya UR, Fujita H, Bhat S, Raghavendra U, Gudigar A, Molinari F, et al. Decision support system for fatty liver disease using GIST descriptors extracted from ultrasound images. Inf Fusion 2016;29:32–9.
• [32] Wu C-M, Chen Y-C, Hsieh K-S. Texture features for classification of ultrasonic liver images. IEEE Trans Med Imaging 1992;11(2):141–52.
• [33] Lee W-L, Chen Y-C, Hsieh K-S. Ultrasonic liver tissues classification by fractal feature vector based on M-band wavelet transform. IEEE Trans Med Imaging 2003;22(3):382–92.
• [34] Acharya U, Rajendra S, Sree V, Ribeiro R, Krishnamurthi G, Marinho RT, et al. Data mining framework for fatty liver disease classification in ultrasound: a hybrid feature extraction paradigm. Med Phys 2012;39(7):4255–64.
• [35] Haralick RM, Shanmugam K. Textural features for image classification. IEEE Trans Syst Man Cybernet 1973;6:610–21.
• [36] Galloway MM. Texture analysis using gray level run lengths. Comput Graph Image Process 1975;4(2):172–9.
• [37] Tang X. Texture information in run-length matrices. IEEE Trans Image Process 1998;7(11):1602–9.
• [38] Oliva A, Torralba A. Modeling the shape of the scene: a holistic representation of the spatial envelope. Int J Comput Vis 2001;42(3):145–75.
• [39] Cands EJ, Donoho DL, Curvelets A. Surprisingly effective nonadaptive representation for objects with edges. Curve Surf, L. Schumaker et al, (1999).
• [40] Starck J-L, Cands EJ, Donoho DL. The curvelet transform for image denoising. IEEE Trans Image Process 2002;11(6):670–84.
• [41] Starck J-L, Donoho DL, Cands EJ. Astronomical image representation by the curvelet transform. Astron Astrophys 2003;398(2):785–800.
• [42] Starck J-L, Murtagh F, Cands EJ, Donoho DL. Gray and color image contrast enhancement by the curvelet transform. IEEE Trans Image Process 2003;12(6):706–17.
• [43] Nayak DR, Dash R, Majhi B, Prasad V. Automated pathological brain detection system: a fast discrete curvelet transform and probabilistic neural network based approach. Expert Syst Appl 2017;88:152–64.
• [44] Miri MS, Mahloojifar A. Retinal image analysis using curvelet transform and multistructure elements morphology by reconstruction. IEEE Trans Biomed Eng 2011;58(5):1183–92.
• [45] Acharya UR, Raghavendra U, Fujita H, Hagiwara Y, Koh JEW, Hong TJ, et al. Automated characterization of fatty liver disease and cirrhosis using curvelet transform and entropy features extracted from ultrasound images. Comput Biol Med 2016;79:250–8.
• [46] Candes E, Demanet L, Donoho D, Ying L. Fast discrete curvelet transforms. Multiscale Model Simul 2006;5(3): 861–99.
• [47] Qiao T, Ren J, Wang Z, Zabalza J, Sun M, Zhao H, et al. Effective denoising and classification of hyperspectral images using curvelet transform and singular spectrum analysis. IEEE Trans Geosci Remote Sens 2017;55 (1):119–33.
• [48] Dasgupta N, Carin L. Texture analysis with variational hidden Markov trees. IEEE Trans Signal Process 2006;54 (6):2353–6.
• [49] Do MN, Vetterli M. Wavelet-based texture retrieval using generalized Gaussian density and Kullback-Leibler distance. IEEE Trans Image Process 2002;11(2):146–58.
• [50] Van de Wouwer G, Scheunders P, Van Dyck D. Statistical texture characterization from discrete wavelet representations. IEEE Trans Image Process 1999;8(4):592–8.
• [51] Kakarala R, Ogunbona PO. Signal analysis using a multiresolution form of the singular value decomposition. IEEE Trans Image process 2001;10(5):724–35.
• [52] Jensen SH, Hansen PC, Hansen SD, Sorensen JA. Reduction of broad-band noise in speech by truncated QSVD. IEEE Trans Speech Audio Process 1995;3(6):439–48.
• [53] De Moor B. The singular value decomposition and long and short spaces of noisy matrices. IEEE Trans Signal Process 1993;41(9):2826–38.
• [54] Chang C-C, Lin C-J. LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol (TIST) 2011;2 (3):27.
• [55] Meng D, Zhang L, Cao G, Cao W, Zhang G, Hu B. Liver fibrosis classification based on transfer learning and FCNet for ultrasound images. IEEE Access 2017, March.

Uwagi

PL

Opracowanie rekordu w ramach umowy 509/P-DUN/2018 ze środków MNiSW przeznaczonych na działalność upowszechniającą naukę (2018).