Skip to main content

Advertisement

SpringerLink
Log in

Neural Network Ensemble Based CAD System for Focal Liver Lesions from B-Mode Ultrasound

  • Published:
Journal of Digital Imaging Aims and scope Submit manuscript

Abstract

A neural network ensemble (NNE) based computer-aided diagnostic (CAD) system to assist radiologists in differential diagnosis between focal liver lesions (FLLs), including (1) typical and atypical cases of Cyst, hemangioma (HEM) and metastatic carcinoma (MET) lesions, (2) small and large hepatocellular carcinoma (HCC) lesions, along with (3) normal (NOR) liver tissue is proposed in the present work. Expert radiologists, visualize the textural characteristics of regions inside and outside the lesions to differentiate between different FLLs, accordingly texture features computed from inside lesion regions of interest (IROIs) and texture ratio features computed from IROIs and surrounding lesion regions of interests (SROIs) are taken as input. Principal component analysis (PCA) is used for reducing the dimensionality of the feature space before classifier design. The first step of classification module consists of a five class PCA-NN based primary classifier which yields probability outputs for five liver image classes. The second step of classification module consists of ten binary PCA-NN based secondary classifiers for NOR/Cyst, NOR/HEM, NOR/HCC, NOR/MET, Cyst/HEM, Cyst/HCC, Cyst/MET, HEM/HCC, HEM/MET and HCC/MET classes. The probability outputs of five class PCA-NN based primary classifier is used to determine the first two most probable classes for a test instance, based on which it is directed to the corresponding binary PCA-NN based secondary classifier for crisp classification between two classes. By including the second step of the classification module, classification accuracy increases from 88.7 % to 95 %. The promising results obtained by the proposed system indicate its usefulness to assist radiologists in differential diagnosis of FLLs.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9

Similar content being viewed by others

Abbreviations

Anechoic FLL:

Anechoic focal liver lesion: The focal liver lesion which appears without echoes on ultrasound.

Atypical cyst:

Atypical cyst: Appears with irregular, thickened wall and internal echoes.

Atypical FLL:

Atypical focal liver lesion: Focal liver lesion with non-specific sonographic appearance.

Atypical HEM:

Atypical hemangioma: Appears as isoechoic or even hypoechoic lesion.

Atypical MET:

Atypical metastasis: Appearance is extremely variable, ranging from anechoic, hypoechoic, isoechoic, hyperechoic and even with mixed echogenicity.

Benign FLL:

Benign focal liver lesion: Non-cancerous focal liver lesion.

B-mode US:

B-mode ultrasound: Brightness-mode ultrasound is a two-dimensional representation of echo-producing interfaces in a single plane.

CYST:

Liver cyst: Abnormal fluid filled sacs in the liver.

FLL:

Focal liver lesion: Focal liver lesion refers to area of liver tissue damage.

FOS:

First-order statistics: First-order statistics estimates the properties of individual pixel values. These statistics do not consider the spatial interaction that exsisits between the image pixels.

FPS:

Fourier power spectrum: Texture description by means of fourier descriptors provides the means of multi-scale representation, but these descriptors lack spatial localization.

GLCM:

Gray level co-occurrence matrix: Second-order statistics estimates the properties of any texture by considering the spatial interation between two pixels at a time.

GLRLM:

Gray level run length matrix: Higher-order statistics estimates the properties of any texture by considering the spatial interation between a number of pixels at a time.

GWT:

Gabor wavelet transform: Another method of multi-scale texture description with good spatial localization.

HCC:

Hepatocellular carcinoma: The most common primary malignant focal liver lesion.

HEM:

Hemangioma: The most common primary benign focal liver lesion.

Hyperechoic FLL:

Hyperechoic focal liver lesion: The focal liver lesion with more echogenicity as compared to the surrounding liver parenchyma.

Hypoechoic FLL:

Hypoechoic focal liver lesion: The focal liver lesion with less echogenicity as compared to the surrounding liver parenchyma.

Isoechoic FLL:

Isoechoic focal liver lesion: The focal liver lesion with same echogenicity as that of the surrounding liver parenchyma.

LHCC:

Large hepatocellular carcinoma: HCC lesions (>2 cm), appearance as lesion with mixed echogenicity.

Malignant FLL:

Malignant focal liver lesion: Cancerous focal liver lesion.

MET:

Metastasis: The most common secondary malignant focal liver lesion.

NOR:

Normal liver: Normal liver has homogeneous texture with medium echogenicity (i.e., same or slightly increased echogenicity compared to the right kidney).

SHCC:

Small hepatocellular carcinoma: HCC lesions (<2 cm), appearance vary from hypoechoic to hyperechoic lesions.

Typical Cyst:

Typical cyst: Well-defined, round, anechoic lesion with posterior acoustic enhancement and thin imperceptible wall.

Typical FLL:

Typical focal liver lesion: Focal liver lesions with classic diagnostic sonographic appearance.

Typical HEM:

Typical hemangioma: Appears as a well-circumscribed uniformly hyperechoic lesion.

Typical MET:

Typical metastasis: Appears with ‘target’ or ‘bull’s-eye’ appearance.

References

  1. Namasivayam S, Salman K, Mittal PK, Martin D, Small WC: Hypervascular hepatic focal lesions: spectrum of imaging features. Curr Probl Diagn Radiol 36(3):107–123, 2007

    Article  PubMed  Google Scholar 

  2. Tiferes DA, D’lppolito G: Liver neoplasms: imaging characterization. Radiol Bras 41(2):119–127, 2008

    Article  Google Scholar 

  3. Wernecke K, Vassallo P: The distinction between benign and malignant liver tumors on sonography: value of a hypoechoic halo. Am J Radiol 159:1005–1009, 1992

    CAS  Google Scholar 

  4. Mittelstaedt CA: Ultrasound as a useful imaging modality for tumor detection and staging. Cancer Res 1980(40):3072–3078, 1980

    Google Scholar 

  5. Bates J: Abdominal Ultrasound How Why and When, 2nd edition. Churchill Livingstone, Oxford, 2004, pp 80–107

    Google Scholar 

  6. Soye JA, Mullan CP, Porter S, Beattie H, Barltrop AH, Nelson WM: The use of contrast-enhanced ultrasound in the characterization of focal liver lesions. Ulster Med J 76(1):22–25, 2007

    CAS  PubMed Central  PubMed  Google Scholar 

  7. Pen JH, Pelckmans PA, Van Maercke YM, Degryse HR, De Schepper AM: Clinical significance of focal echogenic liver lesions. Gastrointest Radiol 11(1):61–66, 1986

    Article  CAS  PubMed  Google Scholar 

  8. Colombo M, Ronchi G: Focal Liver Lesions—Detection, Characterization, Ablation. Springer, Berlin, 2005, pp 167–177

    Google Scholar 

  9. Harding J, Callaway M: Ultrasound of focal liver lesions. Rad Mag 36(424):33–34, 2010

    Google Scholar 

  10. Jeffery RB, Ralls PW: Sonography of Abdomen. Raven, New York, 1995

    Google Scholar 

  11. Tsurusaki M, Kawasaki R, Yamaguchi M, Sugimoto K, Fukumoto T, Ku Y, Sugimura K: Atypical hemangioma mimicking hepatocellular carcinoma with a special note on radiological and pathological findings. Jpn J Radiol 27(3):156–160, 2009

    Article  PubMed  Google Scholar 

  12. Sandulescu L, Saftoiu A, Dumitrescu D, Ciurea T: Real-time contrast-enhanced and real-time virtual sonography in the assessment of benign liver lesions. J Gastrointest Liver Dis 17(4):475–478, 2008

    Google Scholar 

  13. Nielsen MB, Bang N: Contrast enhanced ultrasound in liver imaging. Eur J Radiol 51:S3–S8, 2004

    Article  PubMed  Google Scholar 

  14. Marsh JI, Gibney RG, Li DKB: Hepatic hemangioma the presence of fatty infiltration: an atypical sonographic appearance. Gastrointest Radiol 14:262–264, 1989

    Article  CAS  PubMed  Google Scholar 

  15. Mittal D, Kumar V, Saxena SC, Khandelwal N, Kalra N: Neural network based focal liver lesion diagnosis using ultrasound images. Int J Comput Med Imaging Graph 35(4):315–323, 2011

    Article  Google Scholar 

  16. Virmani J, Kumar V, Kalra N, Khandelwal N: Characterization of primary and secondary malignant liver lesions from B-mode ultrasound. J Digit Imaging 26(6):1058–1070, 2013

    Article  PubMed  Google Scholar 

  17. Vilgrain V, Boulos L, Vullierme MP, Denys A, Terris B, Menu Y: Imaging of atypical hemangiomas of the liver with pathologic correlation. Radiographics 20(2):379–397, 2000

    Article  CAS  PubMed  Google Scholar 

  18. Virmani J, Kumar V, Kalra N, Khandelwal N: SVM-based characterization of liver ultrasound images using wavelet packet texture descriptors. J Digit Imaging 26(3):530–543, 2013

    Article  PubMed Central  PubMed  Google Scholar 

  19. Minhas F, Sabih D, Hussain M: Automated classification of liver disorders using ultrasound images. J Med Syst 36(5):3163–3172, 2011

    Article  PubMed  Google Scholar 

  20. Virmani J, Kumar V, Kalra N, Khandelwal N: Prediction of liver cirrhosis based on multiresolution texture descriptors from B-mode ultrasound. Int J Converg Comput 1(1):19–37, 2013

    Article  Google Scholar 

  21. Virmani J, Kumar V, Kalra N, Khandelwal N: PCA-SVM based CAD system for focal liver lesions from B-mode ultrasound. Def Sci J 63(5):478–486, 2013

    Article  Google Scholar 

  22. Virmani J, Kumar V, Kalra N, Khandelwal N: A comparative study of computer-aided classification systems for focal hepatic lesions from B-mode ultrasound. J Med Eng Technol 37(4):292–306, 2013

    Article  PubMed  Google Scholar 

  23. Yoshida H, Casalino DD, Keserci B, Coskun A, Ozturk O, Savranlar A: Wavelet packet based texture analysis for differentiation between benign and malignant liver tumors in ultrasound images. Phys Med Biol 48:3735–3753, 2003

    Article  PubMed  Google Scholar 

  24. Scheible W, Gossink BB, Leopold G: Gray scale echo graphic patterns of hepatic metastatic disease. Am J Roentgenol 129:983–987, 1977

    Article  CAS  Google Scholar 

  25. Albrecht T, Hohmann J, Oldenburg A, Wolf K: Detection and characterisation of liver metastases. Eur Radiol Suppl 14(S8):25–P33, 2004

    Article  Google Scholar 

  26. Di Martino M, De Filippis G, De Santis A, Geiger D, Del Monte M, Lombardo CV, Rossi M, Corradini SG, Mennini G, Catalano C: Hepatocellular carcinoma in cirrhotic patients: prospective comparison of US, CT and MR imaging. Eur Radiol 23(4):887–896, 2013

    Article  PubMed  Google Scholar 

  27. Kimura Y, Fukada R, Katagiri S, Matsuda Y: Evaluation of hyperechoic liver tumors in MHTS. J Med Syst 17(3/4):127–132, 1993

    Article  CAS  PubMed  Google Scholar 

  28. Sujana S, Swarnamani S, Suresh S: Application of artificial neural networks for the classification of liver lesions by image texture parameters. Ultrasound Med Biol 22(9):1177–1181, 1996

    Article  CAS  PubMed  Google Scholar 

  29. Poonguzhali S, Deepalakshmi, Ravindran G: Optimal feature selection and automatic classification of abnormal masses in ultrasound liver images. In: Proceedings of IEEE International Conference on Signal Processing, Communications and Networking, ICSCN’07, 503–506, 2007

  30. Kim SH, Lee JM, Kim KG, Kim JH, Lee JY, Han JK, Choi BI: Computer-aided image analysis of focal hepatic lesions in ultrasonography: preliminary results. Abdom Imaging 34(2):183–191, 2009

    Article  PubMed  Google Scholar 

  31. Huang YL, Wang KL, Chen DR: Diagnosis of breast tumors with ultrasonic texture analysis using support vector machines. Neural Comput Appl 15:164–169, 2006

    Article  Google Scholar 

  32. Nandi RJ, Nandi AK, Rangayyan RM, Scutt D: Classification of breast masses in mammograms using genetic programming and feature selection. Med Biol Eng Comput 44(8):683–694, 2006

    Article  CAS  PubMed  Google Scholar 

  33. Diao XF, Zhang XY, Wang TF, Chen SP, Yang Y, Zhong L: Highly sensitive computer aided diagnosis system for breast tumor based on color Doppler flow images. J Med Syst 35(5):801–809, 2011

    Article  PubMed  Google Scholar 

  34. Moayedi F, Azimifar Z, Boostani R, Katebi S: Contourlet based mammography mass classification. In: Proceedings of ICIAR 2007. LNCS 4633:923–934, 2007

    Google Scholar 

  35. Alto H, Rangayyan R: An indexed atlas of digital mammograms for computer-aided diagnosis of breast cancer. Ann Telecommun 58:820–835, 2003

    Google Scholar 

  36. Huang YL, Chen DR, Jiang YR, Kuo J, Wu HK, Moon WK: Computer-aided diagnosis using morphological features for classifying breast lesions on ultrasound. Ultrasound Obstet Gynecol 32:565–572, 2008

    Article  PubMed  Google Scholar 

  37. André T, Rangayyan R: Classification of breast masses in mammograms using neural networks with shape, edge sharpness, and texture features. J Electron Imaging 15(01):684481, 2006

    Article  Google Scholar 

  38. Rangayyan RM, Nguyen TM: Pattern classification of breast masses via fractal analysis of their contours. Int Congr Ser 1281:1041–1046, 2005

    Article  Google Scholar 

  39. Lee WL, Hsieh KS, Chen YC: A study of ultrasonic liver images classification with artificial neural networks based on fractal geometry and multiresolution analysis. Biomed Eng Appl Basis Commun 16(2):59–67, 2004

    Article  Google Scholar 

  40. Badawi AM, Derbala AS, Youssef ABM: Fuzzy logic algorithm for quantitative tissue characterization of diffuse liver diseases from ultrasound images. Int J Med Inform 55:135–147, 1999

    Article  CAS  PubMed  Google Scholar 

  41. Fukunaga K: Introduction to Statistical Pattern Recognition. Academic, New York, 1990

    Google Scholar 

  42. Kadah YM, Farag AA, Zurada JM, Badawi AM, Youssef AM: Classification algorithms for quantitative tissue characterization of diffuse liver disease from ultrasound images. IEEE Trans Med Imaging 15(4):466–478, 1996

    Article  CAS  PubMed  Google Scholar 

  43. Virmani J, Kumar V, Kalra N, Khandelwal N: A rapid approach for prediction of liver cirrhosis based on first order statistics. In: Proceedings of IEEE International Conference on Multimedia, Signal Processing and Communication Technologies, IMPACT-2011, 212–215, 2011

  44. Haralick R, Shanmugam K, Dinstein I: Textural features for image classification. IEEE Trans Syst Man Cybern SMC-3(6):610–121, 1973

    Article  Google Scholar 

  45. Virmani J, Kumar V, Kalra N, Khandelwal N: Prediction of cirrhosis based on singular value decomposition of gray level cooccurrence matrix and a neural network classifier. In: Proceedings of IEEE International Conference on Developments in E-systems Engineering, DeSe-2011, 146–151, 2011

  46. Virmani J, Kumar V, Kalra N, Khandelwal N: SVM-based characterisation of liver cirrhosis by singular value decomposition of GLCM matrix. Int J Artif Intell Soft Comput 4(1):276–296, 2013

    Article  Google Scholar 

  47. Galloway RMM: Texture analysis using gray level run lengths. Comput Graph Image Process 4:172–179, 1975

    Article  Google Scholar 

  48. Chu A, Sehgal CM, Greenleaf JF: Use of gray value distribution of run lengths for texture analysis. Pattern Recogn Lett 11:415–420, 1990

    Article  Google Scholar 

  49. Dasarathy BV, Holder EB: Image characterizations based on joint gray level-run length distributions. Pattern Recogn Lett 12:497–502, 1991

    Article  Google Scholar 

  50. Lee C, Chen S H: Gabor wavelets and SVM classifier for liver diseases classification from CT images. In: Proceedings of IEEE International Conference on Systems, Man, and Cybernetics, 548–552, 2006

  51. Laws KI: Rapid texture identification. SPIE Proc Semin Image Process Missile Guid 238:376–380, 1980

    Article  Google Scholar 

  52. Sharma M, Markou M, Singh S: Evaluation of texture methods for image analysis. In: Proceedings of the Seventh Australian and New Zealand Intelligent Information Systems Conference, 117–121, 2001

  53. Virmani J, Kumar V, Kalra N, Khandelwal N: Prediction of cirrhosis from liver ultrasound B-mode images based on Laws’ masks analysis. In: Proceedings of IEEE International Conference on Image Information Processing, ICIIP-2011, 1–5, 2011

  54. Kadir A, Nugroho LE, Susanto A, Santosa PI: Performance improvement of leaf identification system using principal component analysis. Int J Adv Sci Technol 44:113–124, 2012

    Google Scholar 

  55. Du C, Linker R, Shaviv A: Identification of agricultural Mediterranean soils using mid-infrared photoacoustic spectroscopy. Geoderma 143(1–2):85–90, 2008

    Article  CAS  Google Scholar 

Download references

Acknowledgements

The author Jitendra Virmani would like to acknowledge Ministry of Human Resource Development (MHRD), India for financial support. The authors wish to acknowledge the Department of Electronics and Communication Engineering, Jaypee University of Information Technology, Waknaghat, Himachal Pardesh, India, the Department of Electrical Engineering, Indian Institute of Technology, Roorkee, India and Department of Radiodiagnosis and Imaging, Postgraduate Institute of Medical Education and Research, Chandigarh, India for their constant patronage and support in carrying out this research work. The authors would like to thank the anonymous reviewers for their substantive and informed review, which led to significant improvements in the manuscript.

Author information

Authors and Affiliations

  1. Department of Electronics and Communication Engineering, Jaypee University of Information Technology, Waknaghat, Solan, 173234 Himachal Pradesh, India

    Jitendra Virmani

  2. Department of Electrical Engineering, Indian Institute of Technology-Roorkee, Roorkee, 247667 Uttarakhand, India

    Vinod Kumar

  3. Department of Radiodiagnosis and Imaging, Post-Graduate Institute of Medical Education and Research, Sector-12, Chandigarh, 160012 India

    Naveen Kalra & Niranjan Khandelwal

Authors
  1. Jitendra Virmani
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Vinod Kumar
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Naveen Kalra
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Niranjan Khandelwal
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Jitendra Virmani.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Virmani, J., Kumar, V., Kalra, N. et al. Neural Network Ensemble Based CAD System for Focal Liver Lesions from B-Mode Ultrasound. J Digit Imaging 27, 520–537 (2014). https://doi.org/10.1007/s10278-014-9685-0

Download citation

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10278-014-9685-0

Keywords

Search

Navigation