Texture analysis as a tool for medical decision support. P. 2 Classification of liver disorders based on computed tomography images

• Autorzy: Duda D.

Warianty tytułu

PL

Analiza tekstur jako narzędzie wspomagania decyzji medycznych. Cz. 2 Klasyfikacja patologii wątroby na obrazach tomografii komputerowej

• Języki publikacji: EN

Abstrakty

EN

Texture analysis has already demonstrated its great potential in many digital image-based diagnostic systems. It allows to extract from an image many important diagnostic information, impossible to capture with only the visual appreciation. The first attempts to use a texture analysis (TA) as a tool for characterization of an image content took place in the 70’s of the last century. Since then a variety of methods have been proposed and found their application in many domains, also – in the medical field. However, it is still difficult to indicate a method that would ensure satisfactory results for any diagnostic problem. The present work gives an overview of the texture analysis methods, that have been applied for hepatic tissue characterization from Computed Tomography (CT) images. It includes details of about forty studies, presented over the past two decades, devoted to (semi)automatic detection or/and classification of different liver pathologies. Quoted systems are divided into three categories: (i) based on a single-image texture of non-enhanced CT images of the liver, (ii) based on a single-image texture of contrast-enhanced images, and (iii) based on a multiimage texture. The latter ones concern a simultaneous analysis of sets of textures, each of which corresponds to the same liver slice, but is related to a different contrast agent concentration in hepatic vessels.

PL

Analiza tekstur jest szeroko stosowana w wielu cyfrowych systemach wspomagania decyzji medycznych, na podstawie danych obrazowych. Pozwala ona wydobyć z obrazu istotne szczegóły, których nie można dostrzec podczas analizy wizualnej. Pierwsze próby analizy tekstur miały miejsce w latach siedemdziesiątych ubiegłego wieku. Od tamtej pory zaproponowano wiele metod analizy tekstur. Trudno jest jednak wskazać metodę uniwersalna, która zapewniłaby zadowalające wyniki dla każdego problemu diagnostycznego. Niniejsza praca stanowi przegląd metod analizy tekstur, stosowanych do opisu tkanki wątrobowej na obrazach tomografii komputerowej. Przedstawia informacje o około czterdziestu systemach diagnostycznych, zaproponowanych w ciągu ostatnich dwóch dekad, poświęconych (pół)automatycznemu wykrywaniu lub / i klasyfikacji schorzeń wątroby. Opisywane systemy zostały podzielone na trzy kategorie: (i) opierające się na teksturze pojedynczego obrazu, pozyskanego bez podawania pacjentowi środka kontrastującego, (ii) opierające się ´na teksturze pojedynczego obrazu, pozyskanego po podaniu pacjentowi środka kontrastującego, oraz (iii) opierające się na jednoczesnej analizie wielu tekstur. Te ostatnie odnoszą się do analizy zestawów tekstur przedstawiających ten sam wycinek wątroby, lecz odpowiadających różnym stężeniom środka kontrastowego w jej naczyniach krwionośnych.

Słowa kluczowe

EN

medical imaging; image analysis; texture; feature selection; computer aided diagnosis; CAD; medical decision support; liver; computed tomography; CT

PL

obrazowanie medyczne; analiza obrazów; tekstura; selekcja cech; diagnoza; wątroba; tomografia komputerowa; wspomaganie decyzji medycznych

• Wydawca: Oficyna Wydawnicza Politechniki Białostockiej
• Czasopismo: Advances in Computer Science Research
• Rocznik: 2014
• Tom: Nr 11
• Strony: 85--108
• Opis fizyczny: Bibliogr. 89 poz., tab.

Twórcy

autor

Duda D.

• Faculty of Computer Science, Bialystok University of Technology, Białystok, Poland

Bibliografia

• [1] Calvien P.A.: Malignant Liver Tumors: Current and Emerging Therapies, Second Edition, Jones and Bartlett Publishers, Inc., London, UK, 2004.
• [2] Lencioni, R., Cioni, D., Batolozzi, C.: Focal Liver Lesions: Detection, Characterization, Ablation (Medical Radiology / Diagnostic Imaging), Springer-Verlag Berlin-Heidelberg, 2005.
• [3] Duda, D.: Texture analysis as a tool for medical decision support. Part 1: Recent applications for cancer early detection, Advances in Computer Science Research 11, 2014, pp. 61-84.
• [4] Haralick, R. M., Shanmugam K., Dinstein I.: Textural features for image classification, IEEE Trans. Syst., Man, Cybern., Syst 3, 1973, pp. 610-621.
• [5] Bankman, I.N.: Handbook of Medical Image Processing and Analysis, Second Edition, Academic Press, 2008.
• [6] Conners, R.W., Harlow, C.A.: Toward a structural textural analyzer based on statistical methods, Comput. Vision Graph. 12(3) 1980, pp. 224-256.
• [7] Galloway, M.M.: Texture analysis using gray level run lengths, Comput. Vision Graph. 4(2), 1975, pp. 172-179.
• [8] Chu, A., Sehgal, C.M., Greenleaf, J.F.: Use of gray value distribution of run lengths for texture analysis, Pattern Recognition Letters, 11(6), 1990, pp. 415- 420.
• [9] Albregtsen, F., Nielsen, B., Danielsen, H.E.: Adaptive gray level run length features from class distance matrices, Proc. 15th Int. Conf. on Pattern Recognition, 3, 2000, pp. 738-741.
• [10] Weszka, J.S., Dyer, C.R., Rosenfeld, A.: A Comparative Study of Texture Measures for Terrain Classification, IEEE Trans. Systems, Man, Cybernetics, 6, 1976, pp. 269-285.
• [11] Lerski, R.A., Straughan, K., Shad, L., Boyce, D., Bluml, S., Zuna, I.: MR Image Texture Analysis – An Approach to Tissue Characterization, Magn. Reson. Imaging 11(8), 1993, pp. 873-887.
• [12] Horng, M.H., Sun, Y.N., Lin, X.Z.: Texture feature coding method for classifi- cation of liver sonography, Comput. Med. Imag. Grap 26(1), 2002, pp. 33-42.
• [13] Gonzalez, R.C., Woods, R.E.: Digital Image Processing, Second edition, Reading, MA: Addison-Wesley, 2002.
• [14] Mandelbrot, B.: The Fractal Geometry of Nature, block W. H. Freeman and Co., NY, 1982.
• [15] Chen, C., Daponte, J.S., Fox, M.D.: Fractal feature analysis and classification in medical imaging, IEEE Trans. Med. Imag. 8(2), 1989, pp. 133-142.
• [16] Chen, E.L., Chung, P.C., Chen, C.L., Tsai, H.M., Chang, C.I.: An automatic diagnostic system for CT liver image classification, IEEE Trans. Biomed. Eng. 45(6), 1998, pp. 783-794.
• [17] Li, J., Du, Q.: An improved box-counting method for image fractal dimension estimation, Pattern Recognition 42(11), 2009, pp. 2460-2469.
• [18] Sankar, D., Thomas. T.: Fractal Features based on Differential Box Counting Method for the Categorization of Digital Mammograms, International Journal of Computer Information Systems and Industrial Management Applications 2, 2010, pp. 11-19.
• [19] Landini, G., Rippin, J.W.: Notes on the implementation of the mass-radius method of fractal dimension estimation, Comput. Appl. Biosci. 9(5), 1993, pp. 547-550.
• [20] Jones, C.L., Jelinek, H.F.: Wavelet packet fractal analysis of neuronal morphology, Methods 24(4), 2001, pp. 347-458.
• [21] Pentland, A.P.: Fractal-Based Description of Natural Scenes, IEEE Trans. Pattern Anal. Mach. Intell. PAMI-6(6), 1984, pp. 661-674.
• [22] Maragos, P., Sun, F.K.: Measuring the Fractal Dimension of Signals: Morphological Covers and Iterative Optimization, IEEE Trans. Signal Process. 41(1), 1993, pp. 108-121.
• [23] Backes, A.R., Bruno, O.M.: A new approach to estimate fractal dimension of texture images, In Elmoataz, A., Lezoray, O., Nouboud, F., Mammass, D. (Ed): Lect. Notes Comput. Sc. 5099, Springer, 2008, pp. 136-143.
• [24] Kilic, K.I., Abiyev, R.H.: Exploiting the synergy between fractal dimension and lacunarity for improved texture recognition, Signal Processing 91(10), 2011, pp. 2332-2344.
• [25] Mallat, S.G.: A theory for multiresolution signal decomposition: The wavelet representation, IEEE Trans. Pattern Anal. Mach. Intell. 11(7), 1989, pp. 674- 693.
• [26] Laws, K.I.: Textured image segmentation, PhD thesis, University of Southern California, 1980.
• [27] Mir, A.H., Hanmandlu, M., Tandon, S.N.: Texture analysis of CT images, IEEE Eng. Med, Biol. Mag. 14(6) 1995, pp. 781-786.
• [28] Husain, S.A., Shigeru E.: Use of Neural Networks for feature based recognition of liver region on CT images, Proc. of the IEEE NNSP Work. 2, 2000, pp. 831- 840.
• [29] Sariyanni, C.P.A., Asvestas, P., Matsopoulos, G.K., Nikita, K.S., Nikita, A.S., Kelekis, D.: A fractal analysis of CT liver images for the discrimination of hepatic lesions: A comparative study, Proc. of the 23rd Annual EMBS Int. Conf., 2001, pp. 1557-1560.
• [30] Gletsos, M., Mougiakakou, S.G., Matsopoulos, G.K., Nikita, K.S., Nikita, A.S., Kelekis, D.: A computer-aided diagnostic system to characterize CT focal liver lesions: design and optimization of a Neural Network classifier, IEEE Trans. Inf. Technol. Biomed. 7(3), 2003, pp. 153-162.
• [31] Valavanis, I., Mougiakakou, S.G., Nikita, K.S., Nikita, A.: Computer aided diagnosis of CT focal liver lesions by an ensemble of Neural Network and statistical classifiers, Proc. of the IEEE IJCNN Conf. 3, 2004, pp. 1929-1934.
• [32] Mala, K., Sadasivam, V.: Automatic segmentation and classification of diffused liver diseases using wavelet based texture analysis and Neural Network, Proc. of the Annual IEEE INDICON Conf., 2005, pp. 216-219.
• [33] Huang, Y.L., Chen, J.H., Shen, W.C.: Diagnosis of hepatic tumors with texture analysis in nonenhanced computed tomography images, Acad. Radiol. 13(6), 2006, pp. 713-720.
• [34] Stoitsis, J., Valavanis, I., Mougiakakou, S.G., Golemati, S., Nikita, A., Nikita, K.S.: Computer aided diagnosis based on medical image processing and artifi- cial intelligence methods, Nucl. Instrum. Methods Phys. Res., Sect. A 569(2), 2006, pp. 591-595.
• [35] Mougiakakou, S.G., Valavanis, I.K., Nikita, A., Nikita, K.S.: Differential diagnosis of CT focal liver lesions using texture features, feature selection and ensemble driven classifiers, Artif. Intell. Med. 41(1), 2007, pp. 25-37.
• [36] Ganeshan, B., Miles, K.A., Young, R.C., Chatwin, C.R.: Texture analysis in non-contrast enhanced CT: impact of malignancy on texture in apparently disease-free areas of the liver, Eur. J. Radiol. 70(1), 2009, pp. 101-110.
• [37] Mougiakakou, S.G., Valavanis, I.K., Mouravliansky, N.A., Nikita, A., Nikita, K.S.: DIAGNOSIS: A telematics-enabled system for medical image archiving, management, and diagnosis assistance, IEEE Trans. Instrum. Meas. 58(7), 2009, pp. 2113-2120.
• [38] Kumar, S.S, Moni, R.S. Rajeesh, J.: An automatic computer-aided diagnosis system for liver tumours on computed tomography images, Comput. Electr. Eng. 39(5), 2013, pp. 1516-1526.
• [39] Specht, D.F.: Probabilistic Neural Networks, Neural Networks 3(1), 1990, pp. 109-118.
• [40] Fahlman, S.E.: Fast learning variations on back-propagation: An empirical study, Proc. of the 1988 Connectionist Models Summer School, MorganKaufmann, Los Altos CA, 1988.
• [41] Beale, M., Demuth, H.: Fuzzy system toolbox for use with Matlab, PWS Publishing Company, 1994.
• [42] Jain, A.K., Duin, R.P.W., Mao, J.: Statistical pattern recognition: A review, IEEE Trans. Pattern Anal. Machine Intell. 22(1), 2000, pp. 4-37.
• [43] Pudil, P., Novovicova, J., Kittler, J.: Floating search methods in feature selection, Pattern Recogn. Lett. 15(11), 1994, pp. 1119-1125.
• [44] Siedlecki W., Sklansky, J.: A note on genetic algorithms for large-scale feature selection, Pattern Recogn. Lett. 10(5), 1989, pp. 335-347.
• [45] Goldberg, D.: Genetic Algorithms in Search, Optimization and Machine Learning, Addison-Wesley Longman Publishing Co., Inc. Boston, MA, USA, 1989.
• [46] Fukunaga, K.: Introduction to Statistical Pattern recognition, Second edition, Academin Press, San Diego, CA, USA, 1990.
• [47] Vapnik, V.N.: The Nature of Statistical Learning Theory, Second Edition, Springer, NY, 2000.
• [48] Duda, R., Hart P., Stork D.: Pattern Recognition, Second Edition, John Willey and Sons, 2001.
• [49] Do, M.N., Vetterli, M.: The contourlet transform: an efficient directional multiresolution image representation, IEEE Trans. Image Process. 14(12), 2005, pp. 2091-2106.
• [50] Nguyen, T.T., Liu, Y., Chauris, H., Oraintara, S.: Implementational aspects of the contourlet filter bank and application in image coding, EURASIP J. Adv. Signal Process., 2008.
• [51] Pearson, K.: On lines and planes of closest fit to systems of points in space, Phil. Mag. 2(6), 1901, pp. 559-572.
• [52] Hanley, J.A.: Receiver operating characteristic (ROC) methodology: the state of the art, Crit. Rev. Diagn. Imaging 29(3), 1989, pp. 307-335.
• [53] Kretowski, M.: Tissue modeling and classification in biomedical imaging, Ph.D. Dissertation, University of Rennes 1, Rennes, France and Bialystok Technical University, Bialystok, Poland, 2002.
• [54] Bobrowski, L., Kretowski, M.: Induction of multivariate decision trees by using dipolar criteria, In Zighed, D.A., Komorowski, J., Zytkow J. (Ed): Lect. Notes Artif. Int. 1910, Springer-Verlag Berlin Heidelberg, 2000, pp. 331-336.
• [55] Bilello, M., Gokturk, S.B., Desser, T., Napel, S., Jeffrey, R.B., Beaulieu, C.F.: Automatic detection and classification of hypodense hepatic lesions on contrastenhanced venous-phase CT, Med. Phys. 31(9), 2004, 2584-2593.
• [56] Lambrou, Y., Linney, A.D., Todd-Pokropek, A.: Wavelet transform analysis and classification of the liver from computed tomography datasets, Proc. of the 6th Int. IEEE EMBS Special Topic Conf., 2006.
• [57] Smutek, D., Tesar, L., Kobatake, H., Nawano, S., Svacina, S.: Automatic internal medicine diagnostics using statistical imaging methods, Proc. of the 19th Int. IEEE CBMS Symp., 2006, pp. 405-412.
• [58] Mala, K., Sadasivam, V., Alagappan, S.: Neural Network based texture analysis of liver tumor from Computed Tomography images," Int. J. Biol. Life Sci. 2(1), 2007, pp. 33-40.
• [59] Lee, C.C., Shih, C.Y.: Classification of liver disease from CT image using radial basis function Neural Network, Proc. of the IEEE CSIE World Congress 7, 2009, pp. 656-660.
• [60] Miles, K.A., Ganeshan, B., Griffiths, M.R., Young, R.C., Chatwin, C.R.: Colorectal cancer: texture analysis of portal phase hepatic CT images as a potential marker of survival, Radiology 250(2), 2009, pp. 444-452.
• [61] Wang, L., Zhang, Z., Liu, J., Jiang, B., Duan, X., Xie, Q., Hu, D., Li, Z.: Classi- fication of hepatic tissues from CT images based on texture features and multiclass Support Vector Machines, In Yu, W., He, H., Zhang, N. (Ed): Lect. Notes Comput. Sc. 5552 part 2, Springer-Verlag Berlin Heidelberg, 2009, pp. 374-381.
• [62] Mala, K., Sadasivam, V.: Classification of fatty and cirrhosis liver using wavelet-based statistical texture features and Neural Network classifier, Int. J. Softw. Inform. 4(2), 2010, pp. 151-163.
• [63] Kayaalti, O, Aksebzeci, B.H., Karahan, I.O., Deniz, K., Ozturk, M., Yilmaz, B., Kara, S., Asyali, M.H.: Liver fibrosis staging using CT image texture analysis and soft computing, Appl. Soft Comput. 25, 2014, pp. 399-413.
• [64] Rao, S.X., Lambregts, D.M.J., Schnerr, R.S., van Ommen, W., van Nijnatten, T.J.A., Martens, M.H., Heijnen, L.A., Backes, W.H., Verhoef, C., Zeng, M.S., Beets, G.L., Beets-Tan, R.G.H.: Whole-liver CT texture analysis in colorectal cancer: Does the presence of liver metastases affect the texture of the remaining liver? United European Gastroenterol. J. 2(6), 2014, pp. 530-538.
• [65] Simpson, A.L., Do, R.K., Parada, E.P., Miga, M.I., Jarnagin, W.R.: Texture feature analysis for prediction of postoperative liver failure prior to surgery, Proc. SPIE, 9034, 903414, 2014.
• [66] Chakraborty, D.P.: Maximum likelihood analysis of free-response receiver operating characteristic (FROC) data, Med. Phys. 16(4), 1989, pp. 561-568.
• [67] Manjunath, B.S., Ma, W.Y.: Texture features for browsing and retrieval of image data, IEEE Trans. Pattern Anal. Machine Intell. 18(8), 1996, pp. 837-842.
• [68] Clausi, D.A., Jernigan, M.E.: Designing Gabor filters for optimal texture separability, Pattern Recognition 33(11), 2000, pp. 1835-1849.
• [69] Liu, Y., Zheng, Y.F.: One-against-all multi-class SVM classification using reliability measures, Proc. 2005 IEEE Int. Joint Conf. on Neural Networks 2, 2005, pp. 849-854.
• [70] Hsu, C.W., Lin, C.J.: A comparison of methods for multiclass support vector machines, IEEE Trans. Neural Netw. 13(2), 2002, pp. 415-425.
• [71] Amadasun, M., King, R.: Textural features corresponding to textural properties, IEEE Trans. Syst. Man Cybern. 19(5), 1989, pp. 1264-1274.
• [72] Van de Wouwer, G., Scheunders, P., Van Dyck, D.V.: Statistical texture characterization from discrete wavelet representations, IEEE Trans. Image Process. 8(4), 1999, pp. 592-598.
• [73] Daugman, J.G.: Two-dimensional spectral analysis of cortical receptive field profiles, Vision Res. 20(10), 1980, pp. 847-856.
• [74] Duda, D., Kretowski, M., Bezy-Wendling, J.: Texture-based classification of hepatic primary tumors in multiphase CT, In Barillot, C., Haynor., D.R., Hellier, P. (Ed): Lect. Notes Comput. Sc. 3217 part 2, Springer-Verlag Berlin Heidelberg, 2004, pp. 1050-1051.
• [75] Duda, D., Kretowski, M., Bezy-Wendling, J.: Texture characterization for Hepatic Tumor Recognition in Multiphase CT, Biocybern. Biomed. Eng. 26(4), 2006, pp. 15-24.
• [76] Quatrehomme, A., Millet, I., Hoa, D., Subsol, G., Puech, W.: Assessing the classification of liver focal lesions by using multi-phase Computer Tomography scans, In Greenspan, H., Muller, H., Syeda-Mahmood, T. (Ed): Lect. Notes Comput. Sc 7723, Springer-Verlag Berlin Heidelberg, 2013, pp. 80-91.
• [77] Cross, G.R., Jain, A.K.: Markov random fields texture models, IEEE Trans. Pattern Anal. Mach. Intell. 5(1), 1985, pp. 25-39.
• [78] Unser, M.: Sum and difference histograms for texture classification. IEEE Trans. Pattern Anal. Mach. Intell. PAMI-8(1), 1986, pp. 118-125.
• [79] Chi, Y., Zhou, J., Venkatesh, S.K., Tian, Q., Liu, J.: Content-based image retrieval of multiphase CT images for focal liver lesion characterization, Med Phys. 40(10), 103502, 2013.
• [80] Chi, Y., Zhou, J., Venkatesh, S.K., Huang, S., Tian, Q., Hennedige, T., Liu, J.: Computer-aided focal liver lesion detection, Int. J. Comput. Assist. Radiol. Surg. 8(4), 2013, pp. 511-525.
• [81] Yushkevich, P.A., Piven, J., Hazlett, H.C., Smith, R.G., Ho, S., Gee, J.C., Gerig, G.: User-guided 3D active contour segmentation of anatomical structures: significantly improved efficiency and reliability, NeuroImage 31(3), 2006, pp. 1116-1128.
• [82] Manjunath, B.S., Salembier, P., Sikora, T. (Ed): Introduction to MPEG-7: Multimedia Content Description Interface, John Wiley & Sons, Inc., New York, NY, USA, 2002.
• [83] Ganeshan, B., Miles, K.A., Young, R.C., Chatwin, C.R.: Hepatic entropy and uniformity: additional parameters that can potentially increase the effectiveness of contrast enhancement during abdominal CT, Clin. Radiol. 62(8), 2007, 761- 768.
• [84] Ganeshan, B., Burnand, K., Young, R., Chatwin, C., Miles, K.: Dynamic contrast-enhanced texture analysis of the liver: initial assessment in colorectal cancer, Invest. Radiol. 46(3), 2011, pp. 160-168.
• [85] Ye, J., Sun, Y., Wang, S., Gu, L., Qian, L., Xu, J.: Multi-phase CT image based hepatic lesion diagnosis by SVM, Proc. of 2nd Int. BMEI Conf., 2009, pp. 1-5.
• [86] Duda, D., Kretowski, M., Bezy-Wendling, J.: Computer-Aided Diagnosis of Liver Tumors Based on Multi-Image Texture Analysis of Contrast-Enhanced CT,. Selection of the Most Appropriate Texture Features, Studies in Logic, Grammar and Rhetoric 35(48), 2013, pp. 49-70.
• [87] Draminski, M., Rada-Iglesias, A., Enroth, S., Wadelius, C., Koronacki, J., Komorowski, J.: Monte Carlo feature selection for supervised classification, Bioinformatics 24(1), 2008, pp. 110-117.
• [88] Quinlan, J.: C4.5: Programs for Machine Learning, Morgan Kaufmann, San Francisco, 1993.
• [89] Freund, Y., Shapire, R.: A decision-theoretic generalization of online learning and an application to boosting, J. Comput. Syst. Sci. 55, 1997, pp. 119-139.