A novel approach for automatic detection and classification of suspicious lesions in breast ultrasound images

• Autorzy: Karimi B. , Krzyżak A.

Identyfikatory

DOI

10.2478/jaiscr-2014-0019

• Języki publikacji: EN

Abstrakty

EN

In this research, a new method for automatic detection and classification of suspected breast cancer lesions using ultrasound images is proposed. In this fully automated method, de-noising using fuzzy logic and correlation among ultrasound images taken from different angles is used. Feature selection using combination of sequential backward search, sequential forward search and distance-based methods is obtained. A new segmentation method based on automatic selection of seed points and region growing is proposed and classification of lesions into two malignant and benign classes using combination of AdaBoost, Artificial Neural Network and Fuzzy Support Vector Machine classifiers and majority voting is implemented.

Słowa kluczowe

EN

automatic detection; classification; breast cancer; cancer lesions; ultrasound images; AdaBoost; artificial neural network; Fuzzy Support Vector Machine

• Wydawca: University of Social Sciences
• Czasopismo: Journal of Artificial Intelligence and Soft Computing Research
• Rocznik: 2013
• Tom: Vol. 3, No. 4
• Strony: 265--276
• Opis fizyczny: Bibliogr. 33 poz., rys.

Twórcy

autor

Karimi B.

• Department of Computer Science and Software Engineering, Concordia University Montreal, QC H3G 1M8, Canada

autor

Krzyżak A.

• Department of Computer Science and Software Engineering, Concordia University Montreal, QC H3G 1M8, Canada

Bibliografia

• [1] R. Chang, W. Wu, W. Moon, and D. Chen. Automatic ultrasound segmentation and morphology based diagnosis of solid breast tumors. Breast Cancer Research and Treatment, 89(2):179–185, 2005.
• [2] D. Chen, Y. Huang, and S. Lin. Computer-aided diagnosis with textural features for breast lesions in sonograms. Computerized Medical Imaging and Graphics, 35:220–226, 2011.
• [3] Z. Dokur and T. Olmez. Segmentation of ultrasound images by using a hybrid neural network. Pattern Recognition Letters, 23(14):1825–1836, 2002.
• [4] R. Duda, P. Hart, and D. Stork. Pattern Classification. Wiley, New York, 2001.
• [5] D. Eigen, J. Rolfe, R. Fergus, and Y. LeCun. Understanding deep architectures using a recursive convolutional network. ArXiv e-prints, 2013.
• [6] R. Entrekin, P. Jackson, J. Jago, and B. Porter. Real time spatial compound imaging in breast ultrasound: technology and early clinical experience. Medicamundi, 43(3), 1990.
• [7] W. Gomez, W. Pereira, and A. Infantosi. Analysis of co-occurrence texture statistics as a function of gray-level quantization for classifying breast ultrasound. IEEE Transactions on Medical Imaging, 31, 2012.
• [8] S. Gupta, R. Chauhan, and S. Sexena. Robust non-homomorphic approach for speckle reduction in medical ultrasound images. Medical and Biological Engineering and Computing, 43:189–195, 2005.
• [9] F. J. Huang and Y. LeCun. Large-scale learning with svm and convolutional nets for generic object categorization. Proceedings of the 2006 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 1:284–291, 2006.
• [10] K. Ikedo, Y., F. D., T. Hara, H. Fujita, E. Takada, T. Endo, and T. Morita. Computerized mass detection in whole breast ultrasound. Medical Imaging, 6514, 2007.
• [11] A. Katouzian, E. Angelini, S. Carlier, J. Suri, N. Navab, and A. Laine. A state-of-the-art review on segmentation algorithms in intravascular ultrasound (ivus) images. IEEE Transactions on Information Technology in Biomedicine, 16(5):823–834, 2012.
• [12] L. Kuncheva. Combining Pattern Classifiers. Wiley-Interscience, Hoboken, New Jersey, 2004.
• [13] F. Lauera, C. Suen, and G. Bloch. A trainable feature extractor for handwritten digit recognition. Pattern Recognition, 40(6):1816–1824, 2007.
• [14] Y. LeCun, B. Boser, J. S. Denker, D. Henderson, R. E. Howard, W. Hubbard, and L. D. Jackel. Handwritten digit recognition with a backpropagation network. Advances in Neural Information Processing Systems, pages 396–404, 1990.
• [15] Y. LeCun, L. Bottou, Y. Bengio, and H. P. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11):2278–2324, 1998.
• [16] B. Liu, H. Cheng, J. Huang, J. Tian, J. Liu, and X. Tang. Automated segmentation of ultrasonic breast lesions using statistical texture classification and active contour based on probability distance. Ultrasound in Medicine & Biology, 35(8):1309–1324, 2009.
• [17] A. Madabhushi and D. Metaxas. Combining low-, high-level and empirical domain knowledge for automated segmentation of ultrasonic breast lesions. IEEE Transactions on Medical Imaging, 22(2):155–169, 2003.
• [18] M. Mancas, B. Gosselin, and B. Macq. Segmentation using a region growing thresholding. 4th Image Processing: Algorithms and Systems, 56:388–398, 2005.
• [19] Y. Meyer. Wavelets and Operators. Cambridge University Press, Cambridge, 1993.
• [20] W. Moon, C. Lo, J. Chang, C. Huang, J. Chen, and C. R. Computer-aided classification of breast masses using speckle features of automated breast ultrasound images. Medical Physics, 39, 2012.
• [21] W. Moon, Y. Shen, M. Bae, C. Huang, and J. Chen. Computer-aided tumor detection based on multi-scale blob detection algorithm in automated breast ultrasound images. Pattern Recognition, 32(7):1191–1200, 2013.
• [22] F. Sahba, M. Tizhoosh, and M. Salma. Segmentation of prostate boundaries using regional contrast enhancement. IEEE International Conference on Image Processing (ICIP), 2:1266–1269, 2005.
• [23] J. Shan, H. Cheng, and Y. Wang. A novel segmentation method for breast ultrasound images based on neutrosophic l-means clustering. Medical Physics, 39(9):5669–5682, 2012.
• [24] A. Sohail, P. Bhattacharya, S. Mudur, and S. Krishnamurthy. Classification of ultrasound medical images using distance based feature selection and fuzzy-svm. Pattern Recognition and Image Analysis, 6669:176–183, 2011.
• [25] U. Techavipoo, Q. Chen, T. Varghese, A. Zagzebski, and E. Madsen. Noise reduction using spatial-angular compounding for elastography. IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control, 51(5):510 – 520, 2004.
• [26] G. Treece, A. Gee, and R. Prager. Ultrasound compounding with automatic attenuation compensation using paired angle scans. Ultrasound in Medicine and Biology, 33(4):630–642, 2007.
• [27] H. Tu, J. Zagzebski, A. Gerig, Q. Chen, E. Madsen, and T. Hall. Optimization of angular and frequency compounding in ultrasonic attenuation estimation. Journal of the Acoustical Society of America, 117(5):3307–3318, 2005.
• [28] V. Ulagamuthalvi and D. Sridharan. Automatic identification of ultrasound liver cancer tumor using support vector machine. International Conference on Emerging Trends in Computer and Electronics Engineering, pages 41–43, 2012.
• [29] H. Yang, C. Chang, S. Huang, and P. Li. Correlations among acoustic, texture and morphological features for breast ultrasound cad. Ultrasound Imaging, 30(4):228–236, 2008.
• [30] M. Yap. A novel algorithm for initial lesion detection in ultrasound breast images. Journal of Applied Clinical Medical Physics, 9(4), 2008.
• [31] L. Zadeh. Fuzzy sets. Information and Control, 8(3):338–353, 1965.
• [32] L. Zadeh. The concept of a linguistic variable and its application to approximate reasoning. Information Science, 8:199–249, 1975.
• [33] M. Zhang. Novel Approaches to Image Segmentation Based on Neutrosophic Logic. PhD thesis, Utah State University, 2010.