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

Journal of Digital Imaging - Tập 27 - Trang 520-537 - 2014
Jitendra Virmani1, Vinod Kumar2, Naveen Kalra3, Niranjan Khandelwal3
1Department of Electronics and Communication Engineering, Jaypee University of Information Technology, 173234 Himachal Pradesh, India
2Department of Electrical Engineering, Indian Institute of Technology Roorkee, Roorkee, India
3Department of Radiodiagnosis and Imaging, Post-Graduate Institute of Medical Education and Research, Chandigarh, 160012 India

Tóm tắt

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.

Tài liệu tham khảo

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

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

Thông tin
Thông tin xuất bản

Journal of Digital Imaging

Tập 27

520-537

Thông tin tác giả