Hierarchical classification of normal, fatty and heterogeneous liver diseases from ultrasound images using serial and parallel feature fusion

• Autorzy: Alivar A. , Danyali H. , Helfroush M. S.

Identyfikatory

DOI

10.1016/j.bbe.2016.07.003

• Języki publikacji: EN

Abstrakty

EN

This study presents a computer-aided diagnostic system for hierarchical classification of normal, fatty, and heterogeneous liver ultrasound images using feature fusion techniques. Both spatial and transform domain based features are used in the classification, since they have positive effects on the classification accuracy. After extracting gray level co-occurrence matrix and completed local binary pattern features as spatial domain features and a number of statistical features of 2-D wavelet packet transform sub-images and 2-D Gabor filter banks transformed images as transform domain features, particle swarm optimization algorithm is used to select dominant features of the parallel and serial fused feature spaces. Classification is performed in two steps: First, focal livers are classified from the diffused ones and second, normal livers are distinguished from the fatty ones. For the used database, the maximum classification accuracy of 100% and 98.86% is achieved by serial and parallel feature fusion modes, respectively, using leave-one-out cross validation (LOOCV) method and support vector machine (SVM) classifier.

Słowa kluczowe

EN

wavelet packet transform; Gabor filter bank; gray level co-occurrence matrix; completed local binary pattern; feature fusion; fatty liver

PL

pakietowa transformacja falkowa; filtr Gabora; połączenie cech; stłuszczenie wątroby

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2016
• Tom: Vol. 36, no. 4
• Strony: 697--707
• Opis fizyczny: Bibliogr. 28 poz., rys., tab.

Twórcy

autor

Alivar A.

• Department of Electrical and Electronics Engineering, Shiraz University of Technology, Shiraz, Iran

autor

Danyali H.

• Department of Electrical and Electronics Engineering, Shiraz University of Technology, Shiraz, Iran

autor

Helfroush M. S.

• Department of Electrical and Electronics Engineering, Shiraz University of Technology, Shiraz, Iran

Bibliografia

• [1] Suganya R, Rajaram S. Classification of liver diseases from ultrasound images using a hybrid kohonen SOM and LPND speckle reduction method. 2012 IEEE International Conference on Signal Processing, Computing and Control ISPCC; 2012. http://dx.doi.org/10.1109/ISPCC.2012.6224368.
• [2] Içer S, Coşkun A, Ikizceli T. Quantitative grading using grey relational analysis on ultrasonographic images of a fatty liver. J Med Syst 2012;36:2521–8. http://dx.doi.org/10.1007/s10916-011-9724-z.
• [3] Kadah YM, Farag AA, Zurada JM, Badawi AM, Youssef ABM. Classification algorithms for quantitative tissue characterization of diffuse liver disease from ultrasound images. IEEE Trans Med Imaging 1996;15:466–78. http://dx.doi.org/10.1109/42.511750.
• [4] Virmani J, Kumar V, Kalra N, Khandelwal N. SVM-based characterization of liver ultrasound images using wavelet packet texture descriptors. J Digit Imaging 2013;26:530–43. http://dx.doi.org/10.1007/s10278-012-9537-8.
• [5] Owjimehr M, Danyali H, Helfroush MS. An improved method for liver diseases detection by ultrasound image analysis. J Med Signals Sens 2015;5:21–9.
• [6] Owjimehr M, Danyali H, Helfroush MS. Fully automatic segmentation and classification of liver diseases from ultrasound images using completed LBP textute features. 22nd Iran Conf Electr Eng Tehran 2014; 1956–60. http://dx.doi.org/10.1109/IranianCEE.2014.6999862.
• [7] Andrade A, Silva JS, Santos J, Belo-Soares P. Classifier approaches for liver steatosis using ultrasound images. Procedia Technol 2012;5:763–70. http://dx.doi.org/10.1016/j.protcy.2012.09.084.
• [8] Huang Y, Han X, Tian X, Zhao Z, Zhao J, Hao D. Texture analysis of ultrasonic liver images based on spatial domain methods. 2010 3rd Int. Congr. Image Signal Process., vol. 2. IEEE; 2010. p. 562–5. http://dx.doi.org/10.1109/CISP.2010.5647275.
• [9] Ribeiro R, Tato Marinho R, Sanches JM. Global and local detection of liver steatosis from ultrasound. Proc Annu Int Conf IEEE Eng Med Biol Soc EMBS 2012;6547–50. http://dx.doi.org/10.1109/EMBC.2012.6347494.
• [10] Minhas FUAA, Sabih D, Hussain M. Automated classification of liver disorders using ultrasound images. J Med Syst 2012;36:3163–72. http://dx.doi.org/10.1007/s10916-011-9724-z.
• [11] Singh M, Singh S, Gupta S. An information fusion based method for liver classification using texture analysis of ultrasound images. Inf Fusion 2013. http://dx.doi.org/10.1016/j.inffus.2013.05.007.
• [12] Wu C, Lee W, Chen Y, Hsieh K. Evolution-based hierarchical feature fusion for ultrasonic liver tissue characterization. IEEE J Biomed Heal Inf 2013;17:967–76.
• [13] Alivar A, Daniali H, Helfroush MS. Classification of liver diseases using ultrasound images based on feature combination. 2014 4th Int Conf Comput Knowl Eng 2014;669–72. http://dx.doi.org/10.1109/ICCKE.2014.6993434.
• [14] Dasarathy BV. Decision Fusion. computers; 1994.
• [15] Yang J, Yang JY, Zhang D, Lu JF. Feature fusion: parallel strategy vs. serial strategy. Pattern Recognit 2003;36: 1369–81. http://dx.doi.org/10.1016/S0031-3203(02)00262-5.
• [16] Mangai U, Samanta S, Das S, Chowdhury P. A survey of decision fusion and feature fusion strategies for pattern classification. IETE Tech Rev 2010;27:293. http://dx.doi.org/10.4103/0256-4602.64604.
• [17] Wu C-C, Lee W-L, Chen Y-C, Lai C-H, Hsieh K-S. Ultrasonic liver tissue characterization by feature fusion. Expert Syst Appl 2012;39:9389–97. http://dx.doi.org/10.1016/j.eswa.2012.02.128.
• [18] Kuncheva LI, Bezdek JC, Duin RPW. Decision templates for multiple classifier fusion: an experimental comparison. Pattern Recognit 2001;34:299–314. http://dx.doi.org/10.1016/S0031-3203(99)00223-X.
• 19] Triguero I, Vens C. Labelling strategies for hierarchical multi-label classification techniques. Pattern Recognit 2016;56:170–83. http://dx.doi.org/10.1016/j.patcog.2016.02.017.
• [20] Zhang F, Du B, Zhang L, Zhang L. Hierarchical feature learning with dropout k-means for hyperspectral image classification. Neurocomputing 2016;187:75–82. http://dx.doi.org/10.1016/j.neucom.2015.07.132.
• [21] Liu K, Zeng Z, To Yee Ng V. A hierarchical ensemble of ECOC for cancer classification based on multi-class microarray data. Inf Sci 2016;349–350:102–18. http://dx.doi.org/10.1016/j.ins.2016.02.028.
• [22] Haralick RM, Shanmugam K, Dinstein I. Textural features for image classification. IEEE Trans Syst Man Cybern 1973;3. http://dx.doi.org/10.1109/TSMC.1973.4309314.
• [23] Ojala T, Pietikäinen M, Harwood D. A comparative study of texture measures with classification based on featured distributions. Pattern Recognit 1996;29:51–9. http://dx.doi.org/10.1016/0031-3203(95)00067-4.
• [24] Zhang D. A completed modeling of local binary pattern operator for texture classification. IEEE Trans Image Process 2010;19:1657–63. http://dx.doi.org/10.1109/TIP.2010.2044957.
• [25] Guyon I. An introduction to variable and feature selection. J Mach Learn Res 2003;3:1157–82. http://dx.doi.org/10.1023/A:1012487302797.
• [26] DASH M, LIU H. Feature selection for classification. Intell Data Anal 1997;1:131–56. http://dx.doi.org/10.1016/S1088-467X(97)00008-5.
• [27] Eberhart R, Kennedy J. A new optimizer using particle swarm theory. MHS'95 Proc Sixth Int Symp Micro Mach Hum Sci 1995;39–43. http://dx.doi.org/10.1109/MHS.1995.494215.
• [28] Chang C-C, Lin C-J. LIBSVM: a library for support vector machines; 2001, http://www.csie.ntu.edu.tw/cjlin/libsvm [accessed 01.01.13].

Uwagi

PL

Opracowanie ze środków MNiSW w ramach umowy 812/P-DUN/2016 na działalność upowszechniającą naukę.