Journal of Medical Systems

, 40:33 | Cite as

A Computer-Aided Diagnosis Scheme For Detection Of Fatty Liver In Vivo Based On Ultrasound Kurtosis Imaging

  • Hsiang-Yang Ma
  • Zhuhuang Zhou
  • Shuicai Wu
  • Yung-Liang Wan
  • Po-Hsiang Tsui
Systems-Level Quality Improvement
Part of the following topical collections:
  1. Systems-Level Quality Improvement


Fatty liver disease is a common disease caused by alcoholism, obesity, and diabetes, resulting in triglyceride accumulation in hepatocytes. Kurtosis coefficient, a measure of the peakedness of the probability distribution, has been applied to the analysis of backscattered statistics for characterizing fatty liver. This study proposed ultrasound kurtosis imaging as a computer-aided diagnosis (CAD) method to visually and quantitatively stage the fatty liver. A total of 107 patients were recruited to participate in the experiments. The livers were scanned using a clinical ultrasound scanner with a 3.5-MHz curved transducer to acquire the raw ultrasound backscattered signals for kurtosis imaging. The kurtosis image was constructed using the sliding window technique. Experimental results showed that kurtosis imaging has the ability to visualize and quantify the variation of backscattered statistics caused by fatty infiltration. The kurtosis coefficient corresponding to liver parenchyma decreased from 5.41 ± 0.89 to 3.68 ± 0.12 with increasing the score of fatty liver from 0 (normal) to 3 (severe), indicating that fatty liver reduces the degree of peakedness of backscattered statistics. The best performance of kurtosis imaging was found when discriminating between normal and fatty livers with scores ≥1: the area under the curve (AUC) is 0.92 at a cutoff value of 4.36 (diagnostic accuracy =86.9 %, sensitivity =86.7 %, specificity =87.0 %). The current findings suggest that kurtosis imaging may be useful in designing CAD tools to assist in physicians in early detection of fatty liver.


Kurtosis imaging Backscattered statistics Fatty liver Ultrasound tissue characterization Computer-aided diagnosis 



This work was supported by the Ministry of Science and Technology (Taiwan) under Grant No. MOST 103-2221-E-182-001-MY3 and the Chang Gung Memorial Hospital (Linkou, Taiwan) under Grant Nos. CIRPD1E0021, CMRPD1C0711, and CMRPD1C0661.


  1. 1.
    Hamer, O.W., Aguirre, D.A., Casola, G., Lavine, J.E., Woenckhaus, M., and Sirlin, G.B., Fatty liver: imaging patterns and pitfalls. Radiographics. 26:1637–1653, 2006.PubMedCrossRefGoogle Scholar
  2. 2.
    Sumida, Y., Nakajima, A., and Itoh, Y., Limitations of liver biopsy and non-invasive diagnostic tests for the diagnosis of nonalcoholic fatty liver disease/nonalcoholic steatohepatitis. World J. Gastroenterol. 20:475–485, 2014.PubMedPubMedCentralCrossRefGoogle Scholar
  3. 3.
    Nalbantoglu, I.L., and Brunt, E.M., Role of liver biopsy in nonalcoholic fatty liver disease. World J. Gastroenterol. 20:9026–9037, 2014.PubMedPubMedCentralGoogle Scholar
  4. 4.
    Chan, D.F., Li, A.M., Chu, W.C., Chan, M.H., Wong, E.M., Liu, E.K., Chan, I.H., Yin, J., Lam, C.W., Fok, T.F., and Nelson, E.A., Hepatic steatosis in obese Chinese children. Int. J. Obes. Relat. Metab. Disord. 28:1257–1263, 2004.PubMedCrossRefGoogle Scholar
  5. 5.
    Thijssen, J.M., Starke, A., Weijers, G., Haudum, A., Herzog, K., Wohlsein, P., Rehage, J., and De Korte, C.L., Computer-aided B-mode ultrasound diagnosis of hepatic steatosis: a feasibility study. IEEE Trans. Ultrason. Ferroelectr. Freq. Control. 55:1343–1354, 2008.PubMedCrossRefGoogle Scholar
  6. 6.
    Ho, M.C., Lee, Y.H., Jeng, Y.M., Chen, C.N., Chang, K.J., and Tsui, P.H., Relationship between ultrasound backscattered statistics and the concentration of fatty droplets in livers: an animal study. PloS One. 8:e63543, 2013.PubMedPubMedCentralCrossRefGoogle Scholar
  7. 7.
    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. 39:123–130, 2015.PubMedCrossRefGoogle Scholar
  8. 8.
    Ghoshal, G., Lavarello, R.J., Kemmerer, J.P., Miller, R.J., and Oelze, M.L., Ex vivo study of quantitative ultrasound parameters in fatty rabbit livers. Ultrasound Med. Biol. 38:2238–2248, 2012.PubMedPubMedCentralCrossRefGoogle Scholar
  9. 9.
    Shankar, P.M., A general statistical model for ultrasonic backscattering from tissues. IEEE Trans. Ultrason. Ferroelectr. Freq. Control. 47:727–736, 2000.CrossRefGoogle Scholar
  10. 10.
    Zhou, Z., Huang, C.C., Shung, K.K., Tsui, P.H., Fang, J., Ma, H.Y., Wu, S., and Lin, C.C., Entropic imaging of cataract lens: an in vitro study. PLoS One. 9:e96195, 2014.PubMedPubMedCentralCrossRefGoogle Scholar
  11. 11.
    Kuc, R., Ultrasonic tissue characterization using kurtosis. IEEE Trans. Ultrason. Ferroelectr. Freq. Control. 33:273–279, 1986.PubMedCrossRefGoogle Scholar
  12. 12.
    Xie, X., Luo, Y., Quan, J., Chen, K., and Lin, J., SD rats' fatty liver tissue classification based on ultrasound radiofrequency signal. In: Jin, D., and Lin, S. (Eds.), Advances in computer science and information engineering. Springer-Verlag, Berlin Heidelberg, Germany, pp. 643–647, 2012.CrossRefGoogle Scholar
  13. 13.
    Suzuki, K., Hayashi, N., Sasaki, Y., Kono, M., Kasahara, A., Imai, Y., Fusamoto, H., and Kamada, T., Evaluation of structural change in diffuse liver disease with frequency domain analysis of ultrasound. Hepatology. 17:1041–1046, 1993.PubMedCrossRefGoogle Scholar
  14. 14.
    Wan, Y.L., Tai, D.I., Chiang, B.H., Ma, H.Y., Chen, C.K., and Tsui, P.H., Effects of fatty infiltration in human livers on the backscattered statistics of ultrasound imaging. Proc. Inst. Mech. Eng. H. - J. Eng. Med. 229:419–428, 2015.CrossRefGoogle Scholar
  15. 15.
    Li, M.L., Li, D.W., Liu, H.L., Lin, M.S., Ultrasonic Nakagami visualization of HIFU-induced thermal lesions. In: IEEE Ultrasonics Symposium (IUS), IEEE, pp. 2251–2253. San Diego, 2010.Google Scholar
  16. 16.
    Yang, X., Rossi, P., Bruner, D.W., Tridandapani, S., Shelton, J., and Liu, T., Noninvasive evaluation of vaginal fibrosis following radiotherapy for gynecologic malignancies: a feasibility study with ultrasound B-mode and nakagami parameter imaging. Med. Phys. 40:022901, 2013.PubMedPubMedCentralCrossRefGoogle Scholar
  17. 17.
    Tsui, P.H., and Chang, C.C., Imaging local scatterer concentrations by the nakagami statistical model. Ultrasound Med. Biol. 33:608–619, 2007.PubMedCrossRefGoogle Scholar
  18. 18.
    Tsui, P.H., Ma, H.Y., Zhou, Z., Ho, M.C., and Lee, Y.H., Window-modulated compounding nakagami imaging for ultrasound tissue characterization. Ultrasonics. 54:1448–1459, 2014.PubMedCrossRefGoogle Scholar
  19. 19.
    Liao, Y.Y., Li, C.H., Tsui, P.H., Chang, C.C., Kuo, W.H., Chang, K.J., and Yeh, C.K., Discrimination of breast microcalcifications using a strain-compounding technique with ultrasound speckle factor imaging. IEEE Trans. Ultrason. Ferroelectr. Freq. Control. 61:955–965, 2014.PubMedCrossRefGoogle Scholar
  20. 20.
    Osawa, H., and Mori, Y., Sonographic diagnosis of fatty liver using a histogram technique that compares liver and renal cortical echo amplitudes. J. Clin. Ultrasound. 24:25–29, 1996.PubMedCrossRefGoogle Scholar
  21. 21.
    Cloutier, G., Daronatand, M., Savery, D., Garcia, D., Durand, L.G., and Foster, F.S., Non-gaussian statistics and temporal variations of the ultrasound signal backscattered by blood at frequencies between 10 and 58 MHz. J. Acoust. Soc. Am. 116:566–577, 2004.PubMedCrossRefGoogle Scholar
  22. 22.
    Ehman, R.L., Science to practice: can MR elastography be used to detect early steatohepatitis in fatty liver disease? Radiology. 253:1–3, 2009.PubMedCrossRefGoogle Scholar
  23. 23.
    Charlton, M., Nonalcoholic fatty liver disease: a review of current understanding and future impact. Clin. Gastroenterol. Hepatol. 2:1048–1058, 2004.PubMedCrossRefGoogle Scholar
  24. 24.
    Adams, L.A., Angulo, P., and Lindor, K.D., Nonalcoholic fatty liver disease. Can. Med. Assoc. J. 172:899–905, 2005.CrossRefGoogle Scholar
  25. 25.
    Chen, J., Talwalkar, J.A., Yin, M., Glaser, K.J., Sanderson, S.O., and Ehman, R.L., Early detection of nonalcoholic steatohepatitis in patients with nonalcoholic fatty liver disease by using MR elastography. Radiology. 259:749–756, 2011.PubMedPubMedCentralCrossRefGoogle Scholar
  26. 26.
    Nadarajah, S., Statistical distributions of potential interest in ultrasound speckle analysis. Phys. Med. Biol. 52:N213–N227, 2007.PubMedCrossRefGoogle Scholar
  27. 27.
    Nillesen, M.M., Lopata, R.G., Gerrits, I.H., Kapusta, L., Thijssen, J.M., and de Korte, C.L., Modeling envelope statistics of blood and myocardium for segmentation of echocardiographic images. Ultrasound Med. Biol. 34:674–680, 2008.PubMedCrossRefGoogle Scholar
  28. 28.
    Destrempes, F., and Cloutier, G., A critical review and uniformized representation of statistical distributions modeling the ultrasound echo envelope. Ultrasound Med. Biol. 36:1037–1051, 2010.PubMedCrossRefGoogle Scholar
  29. 29.
    Mamou, J., Coron, A., Oelze, M.L., Saegusa-Beecroft, E., Hata, M., Lee, P., Machi, J., Yanagihara, E., Laugier, P., and Feleppa, E.J., Three-dimensional high-frequency backscatter and envelope quantification of cancerous human lymph nodes. Ultrasound Med. Biol. 37:345–357, 2011.PubMedPubMedCentralCrossRefGoogle Scholar
  30. 30.
    Shankar, P.M., A statistical model for the ultrasonic backscattered echo from tissue containing microcalcifications. IEEE Trans. Ultrason. Ferroelectr. Freq. Control. 60:932–942, 2013.PubMedCrossRefGoogle Scholar
  31. 31.
    Larrue, A., and Noble, J.A., Modeling of errors in nakagami imaging: illustration on breast mass characterization. Ultrasound Med. Biol. 40:917–930, 2014.PubMedCrossRefGoogle Scholar
  32. 32.
    Tsui, P.H., Wan, Y.L., and Chen, C.K., Ultrasound imaging of the larynx and vocal folds: recent applications and developments. Curr. Opin. Otolaryngol. Head Neck Surg. 20:437–442, 2012.PubMedCrossRefGoogle Scholar
  33. 33.
    Tsui, P.H., and Wang, S.H., The effect of transducer characteristics on the estimation of nakagami paramater as a function of scatterer concentration. Ultrasound Med. Biol. 30:1345–1353, 2004.PubMedCrossRefGoogle Scholar
  34. 34.
    Toyoda, H., Kumada, T., Kamiyama, N., Shiraki, K., Takase, K., Yamaguchi, T., and Hachiya, H., B-mode ultrasound with algorithm based on statistical analysis of signals: evaluation of liver fibrosis in patients with chronic hepatitis C. Am. J. Roentgenol. 193:1037–1043, 2009.CrossRefGoogle Scholar
  35. 35.
    Kramer, C., Jaspers, N., Nierhoff, D., Kuhr, K., Bowe, A., Goeser, T., and Michels, G., Acoustic structure quantification ultrasound software proves imprecise in assessing liver fibrosis or cirrhosis in parenchymal liver diseases. Ultrasound Med. Biol. 40:2811–2818, 2014.PubMedCrossRefGoogle Scholar
  36. 36.
    Lin, S.C., Heba, E., Wolfson, T., Ang, B., Gamst, A., Han, A., Erdman Jr., J.W., O'Brien Jr., W.D., Andre, M.P., Sirlin, C.B., and Loomba, R., Noninvasive diagnosis of nonalcoholic fatty liver disease and quantification of liver fat using a new quantitative ultrasound technique. Clin. Gastroenterol. Hepatol. 13:1337–1345, 2015.PubMedCrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2015

Authors and Affiliations

  1. 1.Department of Medical Imaging and Radiological Sciences, College of MedicineChang Gung UniversityTaoyuanTaiwan
  2. 2.Graduate Institute of Clinical Medical Sciences, College of MedicineChang Gung UniversityTaoyuanTaiwan
  3. 3.College of Life Science and BioengineeringBeijing University of TechnologyBeijingChina
  4. 4.Department of Medical Imaging and InterventionChang Gung Memorial HospitalTaoyuanTaiwan
  5. 5.Institute for Radiological ResearchChang Gung University and Chang Gung Memorial HospitalTaoyuanTaiwan

Personalised recommendations