Journal of Medical Systems

, 41:152 | Cite as

Extreme Learning Machine Framework for Risk Stratification of Fatty Liver Disease Using Ultrasound Tissue Characterization

  • Venkatanareshbabu Kuppili
  • Mainak Biswas
  • Aswini Sreekumar
  • Harman S. Suri
  • Luca Saba
  • Damodar Reddy Edla
  • Rui Tato Marinhoe
  • J. Miguel Sanches
  • Jasjit S. SuriEmail author
Image & Signal Processing
Part of the following topical collections:
  1. Image & Signal Processing


Fatty Liver Disease (FLD) is caused by the deposition of fat in liver cells and leads to deadly diseases such as liver cancer. Several FLD detection and characterization systems using machine learning (ML) based on Support Vector Machines (SVM) have been applied. These ML systems utilize large number of ultrasonic grayscale features, pooling strategy for selecting the best features and several combinations of training/testing. As result, they are computationally intensive, slow and do not guarantee high performance due to mismatch between grayscale features and classifier type. This study proposes a reliable and fast Extreme Learning Machine (ELM)-based tissue characterization system (a class of Symtosis) for risk stratification of ultrasound liver images. ELM is used to train single layer feed forward neural network (SLFFNN). The input-to-hidden layer weights are randomly generated reducing computational cost. The only weights to be trained are hidden-to-output layer which is done in a single pass (without any iteration) making ELM faster than conventional ML methods. Adapting four types of K-fold cross-validation (K = 2, 3, 5 and 10) protocols on three kinds of data sizes: S0-original, S4-four splits, S8-sixty four splits (a total of 12 cases) and 46 types of grayscale features, we stratify the FLD US images using ELM and benchmark against SVM. Using the US liver database of 63 patients (27 normal/36 abnormal), our results demonstrate superior performance of ELM compared to SVM, for all cross-validation protocols (K2, K3, K5 and K10) and all types of US data sets (S0, S4, and S8) in terms of sensitivity, specificity, accuracy and area under the curve (AUC). Using the K10 cross-validation protocol on S8 data set, ELM showed an accuracy of 96.75% compared to 89.01% for SVM, and correspondingly, the AUC: 0.97 and 0.91, respectively. Further experiments also showed the mean reliability of 99% for ELM classifier, along with the mean speed improvement of 40% using ELM against SVM. We validated the symtosis system using two class biometric facial public data demonstrating an accuracy of 100%.


Fatty liver disease Extreme learning machine Support vector machine Neural network Grayscale features Performance Reliability 



The authors of National Institute of Technology Goa, India would like to acknowledge Ministry of Human Resource department, Government of India and MediaLab Asia, Ministry of Electronics and Information Technology, Government of India for their kind support.

Compliance with Ethical Standards

Conflict of Interest

None of the authors have any conflict of interest.

Ethical Approval

All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Helsinki declaration and its later amendments or comparable ethical standards. Data was collected after IRB approval by Instituto Superior Tecnico (IST), University of Lisbon, Portugal and written informed consent provided by all the patients.


  1. 1.
    Saverymuttu, S.H., Joseph, A.E., and Maxwell, J.D., Ultrasound scanning in the detection of hepatic fibrosis and steatosis. Br Med J (Clin Res Ed). 292(6512):13–15, 1986.CrossRefGoogle Scholar
  2. 2.
    Mohamed, W.S., Mostafa, A.M., Mohamed, K.M., and Serwah, A.H., The epidemiology of nonalcoholic fatty liver disease in adults by Clark, Jeanne M MD, MPH. J. Clin. Gastroenterol. 40:S5–S10, 2006.Google Scholar
  3. 3.
    Wieckowska, A., and Feldstein, A.E., Nonalcoholic fatty liver disease in the pediatric population: A review. Current opinion in pediatrics. 17(5):636–641, 2005.CrossRefPubMedGoogle Scholar
  4. 4.
    Ratziu, V., Charlotte, F., Heurtier, A., Gombert, S., Giral, P., Bruckert, E., Grimaldi, A., and Capron, F., Thierry Poynard, and LIDO study group, sampling variability of liver biopsy in nonalcoholic fatty liver disease. Gastroenterology. 128(7):1898–1906, 2005.CrossRefPubMedGoogle Scholar
  5. 5.
    Cheung, R.C., Complications of liver biopsy, gastrointestinal emergencies, gastrointestinal emergencies. In: Tham, T.C.K., Collins, J.S.A., and Soetikno, R. (Eds.). Blackwell, West Sussex, UK, pp. 72–79, 2009.Google Scholar
  6. 6.
    Saadeh, S., Younossi, Z.M., Remer, E.M., Gramlich, T., Ong, J.P., Hurley, M., Mullen, K.D., Cooper, J.N., and Sheridan, M.J., The utility of radiological imaging in nonalcoholic fatty liver disease. Gastroenterology. 123(3):745–750, 2009.CrossRefGoogle Scholar
  7. 7.
    Wang, D., Fang, Y., Hu, B., Cao, H., B-scan image feature extraction of fatty liver. In Internet Computing for Science and Engineering (ICICSE), 2012 Sixth International Conference. (2012) 188–192.Google Scholar
  8. 8.
    Yajima, Y., Ohta, K., Narui, T., Abe, R., Suzuki, H., and Ohtsuki, M., Ultrasonographical diagnosis of fatty liver: Significance of the liver-kidney contrast. Tohoku. J. Exp. Med. 139(1):43–50, 1983.CrossRefPubMedGoogle Scholar
  9. 9.
    Mathiesen, U.L., Franzen, L.E., Aselius, H., Resjö, M., Jacobsson, L., Foberg, U., Frydén, A., and Bodemar, G., Increased liver echogenicity at ultrasound examination reflects degree of steatosis but not of fibrosis in asymptomatic patients with mild/moderate abnormalities of liver transaminases. Dig. Liver Dis. 34(7):516–522, 2002.CrossRefPubMedGoogle Scholar
  10. 10.
    Mendler, M.H., Bouillet, P., Le Sidaner, A., Lavoine, E., Labrousse, F., Sautereau, D., and Pillegand, B., Dual-energy CT in the diagnosis and quantification of fatty liver: Limited clinical value in comparison to ultrasound scan and single-energy CT, with special reference to iron overload. J. Hepatol. 28(5):785–794, 1998.CrossRefPubMedGoogle Scholar
  11. 11.
    Acharya, U., and Rajendra, J., Suri, data mining framework for fatty liver disease classification in ultrasound: A hybrid feature extraction paradigm. Med. Phys. 39(7):4255–4264, 2012.CrossRefPubMedGoogle Scholar
  12. 12.
    Shensa, M.J., The discrete wavelet transform: The discrete wavelet transform: Wedding the atrous and Mallat algorithms. IEEE. Trans. Signal Process. 40(10, 1992):2464–2482.Google Scholar
  13. 13.
    Bruce, L.M., Koger, C.H., and Li, J., Dimensionality reduction of hyperspectral data using discrete wavelet transform feature extraction. IEEE. Trans. Geosci. Remote. Sens. 40(10):2331–2338, 2002.CrossRefGoogle Scholar
  14. 14.
    Manjunath, B.S., and Ma, W.Y., Texture features for browsing and retrieval of image data. IEEE. Trans. Pattern. Anal. Mach. Intellig. 18(8):837–842, 1996.CrossRefGoogle Scholar
  15. 15.
    Ishibuchi, H., Nakashima, T., and Murata, T., Performance evaluation of fuzzy classifier systems for multidimensional pattern classification problems. IEEE. Trans. Syst. Man. Cybern. Part B (Cybern.). 29(5):601–618, 1999.CrossRefGoogle Scholar
  16. 16.
    Kuncheva L., Fuzzy classifier design, Springer Science & Business Media; 2000 Apr 26.Google Scholar
  17. 17.
    Uebele, V., Abe, S., and Lan, M.-S., A neural-network-based fuzzy classifier. IEEE. Trans. Syst. Man. Cybern. 25(2):353–361, 1995.CrossRefGoogle Scholar
  18. 18.
    Antonini, M., Barlaud, M., Mathieu, P., and Daubechies, I., Image coding using wavelet transform. IEEE. Trans. Image. Process. 1(2):205–220, 1992.CrossRefPubMedGoogle Scholar
  19. 19.
    Subramanya, M.B., Kumar, V., Mukherjee, S., and Saini, M., A CAD system for B-mode fatty liver ultrasound images using texture features. J. Med. Eng. Technol. 39(2):123–130, 2015.CrossRefPubMedGoogle Scholar
  20. 20.
    Ma, H.Y., Zhou, Z., Wu, S., Wan, Y.L., and Tsui, P.H., A computer-aided diagnosis scheme for detection of fatty liver in vivo based on ultrasound kurtosis imaging. J. Med. Syst. 40(1):33, 2016.CrossRefPubMedGoogle Scholar
  21. 21.
    Saba, L., Dey, N., Ashour, A.S., Samanta, S., Nath, S.S., Chakraborty, S., Sanches, J., Kumar, D., Marinho, R., and Suri, J.S., Automated stratification of liver disease in ultrasound: An online accurate feature classification paradigm. Comput. Methods. Programs. Biomed. 130:118–134, 2016.CrossRefPubMedGoogle Scholar
  22. 22.
    Vapnik VN, An overview of statistical learning theory, IEEE transactions on neural networks (10) (1999) 988–999.Google Scholar
  23. 23.
    Huang, G.-B., and Zhu, Q.-Y., Chee-Kheong Sie extreme learning machine: Theory and applications. Neurocomputing. 70(1):489–501, 2006.CrossRefGoogle Scholar
  24. 24.
    Huang, G.-B., Zhu, Q.-Y., and Siew, C.-K., Extreme learning machine: A new learning scheme of feedforward neural networks, in neural networks, 2004. Proceedings. IEEE. Int. Joint. Conference. 2(2004):985–990, 2004.Google Scholar
  25. 25.
    Rao, C.R., and Mitra, S.K., Generalized inverse of matrices and its applications. Wiley, New York, 1971.Google Scholar
  26. 26.
    Qayyum, A., MR spectroscopy of the liver: Principles and clinical applications. Radiographics. 29(6):1653–1664, 2009.CrossRefPubMedGoogle Scholar
  27. 27.
    Kadah, Y.M., Farag, A.A., Zurada, J.M., Badawi, A.M., and Youssef, A.M., Classification algorithms for quantitative tissue characterization of diffuse liver disease from ultrasound images. IEEE Trans. Med. Imaging. 15(4):466–478, 1996.CrossRefPubMedGoogle Scholar
  28. 28.
    Chorowski, J., Wang, J., and Zurada, J.M., Review and performance comparison of SVM-and ELM-based classifiers. Neurocomputing. 128:507–516, 2014.CrossRefGoogle Scholar
  29. 29.
    Acharya, U.R., Sree, S.V., Krishnan, M.M., Molinari, F., ZieleŸnik, W., Bardales, R.H., Witkowska, A., and Suri, J.S., Computer-aided diagnostic system for detection of Hashimoto thyroiditis on ultrasound images from a polish population. J. Ultrasound. Med. 33:245–253, 2014.CrossRefPubMedGoogle Scholar
  30. 30.
    Mohanty, A.K., Beberta, S., and Lenka, S.K., Classifying benign and malignant mass using GLCM and GLRLM based texture features from mammogram. Int. J. Eng. Res. Appl. 1(3):687–693, 2011.Google Scholar
  31. 31.
    Mohanaiah, P., and Sathyanarayana, L., GuruKumar, image texture feature extraction using GLCM approach. Int J. Sci. Res. Publ. 3(5):1, 2013.Google Scholar
  32. 32.
    Herman, P., Comparative analysis of spectral approaches to feature extraction for EEG-based motor imagery classification. IEEE Trans. Neural Syst. Rehabil. Eng. 16(4):317–326, 2008.CrossRefPubMedGoogle Scholar
  33. 33.
    Anuradha, K., Statistical feature extraction to classify oral cancers. J.Glob. Res. Comput. Sci. 4(2):8–12, 2013.Google Scholar
  34. 34.
    Barbu, T., Gabor filter-based face recognition technique. Proc. Rom. Acad. 11(3):277–283, 2010.Google Scholar
  35. 35.
    MacAusland, Ross, The Moore-Penrose Inverse and Least Squares, Math 420. Advanced Topics in Linear Algebra. (2014).Google Scholar
  36. 36.
    Mirmehdi M, Handbook of texture analysis, Imperial College Press. 2008.Google Scholar
  37. 37.
    Acharya, U.R., Mookiah, M.R., Sree, S.V., Afonso, D., Sanches, J., Shafique, S., Nicolaides, A., Pedro, L.M., e Fernandes, J.F., and Suri, J.S., Atherosclerotic plaque tissue characterization in 2D ultrasound longitudinal carotid scans for automated classification: A paradigm for stroke risk assessment. Med. Biol. Eng. Comput. 51(5):513–523, 2013.CrossRefPubMedGoogle Scholar
  38. 38.
    Acharya, R.U., Faust, O., Alvin, A.P., Sree, S.V., Molinari, F., Saba, L., Nicolaides, A., and Suri, J.S., Symptomatic vs. asymptomatic plaque classification in carotid ultrasound. J. Med. Syst. 36(3):1861–1871, 2012.CrossRefPubMedGoogle Scholar
  39. 39.
    Acharya, U.R., Faust, O., Sree, S.V., Molinari, F., Saba, L., Nicolaides, A., and Suri, J.S., An accurate and generalized approach to plaque characterization in 346 carotid ultrasound scans. IEEE. Trans. Instrum. Meas. 61(4):1045–1053, 2012.CrossRefGoogle Scholar
  40. 40.
    Shrivastava, V.K., Computer-aided diagnosis of psoriasis skin images with HOS, texture and color features: A first comparative study of its kind. Comput Meth. Programs Biomed. 126:98–109, 2016.CrossRefGoogle Scholar
  41. 41.
    Shrivastava, V.K., Londhe, N.D., Sonawane, R.S., and Suri, J.S., Reliable and accurate psoriasis disease classification in dermatology images using comprehensive feature space in machine learning paradigm. Expert Syst. Appl. 42:6184–6195, 2015.CrossRefGoogle Scholar
  42. 42.
    Douali, N., Abdennour, M., Sasso, M., Miette, V., Tordjman, J., Bedossa, P., Veyrie, N., Poitou, C., Aron-Wisnewsky, J., Clément, K. and Jaulent, M.C. Noninvasive diagnosis of nonalcoholic steatohepatitis disease based on clinical decision support system. MedInfo. 192:1178, 2013.Google Scholar
  43. 43.
    Vanderbeck, S., Bockhorst, J., Komorowski, R., Kleiner, D.E., and Gawrieh, S., Automatic classification of white regions in liver biopsies by supervised machine learning. Hum. Pathol. 45(4):785–792, 2014.CrossRefPubMedGoogle Scholar
  44. 44.
    Liu, X., Song, J.L., Wang, S.H., Zhao, J.W., and Chen, Y.Q., Learning to diagnose cirrhosis with liver capsule guided ultrasound image classification. Sensors. 17(1):149, 2017.CrossRefPubMedCentralGoogle Scholar
  45. 45.
    LeCun, Y., Bengio, Y., and Hinton, G. Deep learning. Nature. 521(7553):436–444, 2015.Google Scholar
  46. 46.
    Huang, G.-B., Extreme learning machine for regression and multiclass classification. IEEE. Trans. Syst. Man. Cybern. Part B (Cybern). 42(2):513–529, 2012.CrossRefGoogle Scholar
  47. 47.
    Zhu, Q.-Y., Evolutionary extreme learning machine. Pattern. Recogn. 38(10):1759–1763, 2005.CrossRefGoogle Scholar
  48. 48.
    Li Mao, Lidong Zhang, Xingyang Liu, Chaofeng Li, Hong Yang, Improved Extreme Learning Machine and Its Application in Image Quality Assessment. Mathematical Problems in Engineering. (2014).Google Scholar
  49. 49.
    Tang, J., Deng, C., and Huang, G.-B., Extreme learning machine for multilayer perceptron. IEEE. Trans. Neural Netw. Learn. Syst. 27(4):809–821, 2016.CrossRefPubMedGoogle Scholar
  50. 50.
    Demuth, H.B., Beale, M.H., De Jess, O. and Hagan, M.T., Neural network design, Martin Hagan, 2014.Google Scholar
  51. 51.
    El-Baz A, Suri JS, Big Data in Medical Imaging, CRC Press, 2018 (to appear).Google Scholar
  52. 52.
    El-Baz AS, Saba L, Suri JS. Abdomen and thoracic imaging. Springer, 2014.Google Scholar
  53. 53.
    El-Baz A, Gimel’farb G, Suri JS, Stochastic modeling for medical image analysis, CRC Press, 2015.Google Scholar
  54. 54.
    Esses SJ, Lu X, Zhao T, Shanbhogue K, Dane B, Bruno M, Chandarana H. Automated image quality evaluation of T2-weighted liver MRI utilizing deep learning architecture, Journal of Magnetic Resonance Imaging, (2017).Google Scholar

Copyright information

© Springer Science+Business Media, LLC 2017

Authors and Affiliations

  • Venkatanareshbabu Kuppili
    • 1
    • 2
  • Mainak Biswas
    • 1
  • Aswini Sreekumar
    • 1
  • Harman S. Suri
    • 2
    • 3
    • 4
  • Luca Saba
    • 5
  • Damodar Reddy Edla
    • 1
  • Rui Tato Marinhoe
    • 6
  • J. Miguel Sanches
    • 7
  • Jasjit S. Suri
    • 2
    Email author
  1. 1.Department of Computer Science and EngineeringNational Institute of Technology GoaFarmagudiIndia
  2. 2.Global Biomedical Technologies, Inc.RosevilleUSA
  3. 3.Brown UniversityProvidenceUSA
  4. 4.Mira LomaSacramentoUSA
  5. 5.Department of RadiologyAzienda Ospedaliero Universitaria (A.O.U.)CagliariItaly
  6. 6.Liver Unit, Department of Gastroenterology and Hepatology, Hospital de Santa MariaMedical School of LisbonLisbonPortugal
  7. 7.Bioengineering Department, Instituto Superior Tecnico (IST)University of LisbonLisbonPortugal

Personalised recommendations