Dongbing Zhang
School of Computer Science and Technology, Huaibei Normal University, Huaibei 235000, China
Xinggang Zhang
School of Computer and Information Technology, Nanyang Normal University, Nanyang 473061, China
Yihua Lan
Guangwei Wang
School of Computer and Information Science, Hubei Engineering University, Xiaogan 432000, China
ABSTRACT
Current clinical method often uses B-ultrasound for the diagnosis of fatty liver, which basically rely on the doctor observation. Therefore, automatic recognition of fatty liver from the B-ultrasound images has significance value of clinical application. According to the characteristics of fatty liver in B-ultrasound images, this paper proposed five useful features to formulate the new feature vector, which include the near-field echo density, the average gray ratio from the near to far field, as well as three texture features from the gray level co-occurrence matrix and the neighborhood gray-tone difference matrix such as angle second moment, entropy and busyness. These features are chosen carefully, which have good characteristic for distinguishing fatty liver. Based on the support vector machine classification of these feature vectors, the experiments show that the proposed method achieves a good recognition rate of normal liver and fatty liver, which is 91.7% and 98.7% respectively. Compare with the previous work, our experimental data is much more abundant, and the recognition rate is higher as well. Furthermore, with the proposed method, the reader could obtain fatty liver classifier easily.
PDF References Citation
How to cite this article
Dongbing Zhang, Xinggang Zhang, Yihua Lan and Guangwei Wang, 2013. Fatty Liver Recognition Based on Computer Vision. Journal of Applied Sciences, 13: 2730-2734.
DOI: 10.3923/jas.2013.2730.2734
URL: https://scialert.net/abstract/?doi=jas.2013.2730.2734
DOI: 10.3923/jas.2013.2730.2734
URL: https://scialert.net/abstract/?doi=jas.2013.2730.2734
REFERENCES
- Linares, P.A., P.J. McCullagh, N.D. Black and J. Dornan, 2003. Characterization of ultrasonic images of the placenta based on textural features. Proceedings of the 4th Annual IEEE Conference on Information Technology Applications in Biomedicine, April 24-26, 2003, Birmingham, pp: 211-214.
CrossRef - Yeh, W.C., S.W. Huang and P.C. Li, 2003. Liver fibrosis grade classification with B-mode ultrasound. Ultrasound Med. Biol., 9: 1229-1235.
CrossRefDirect Link - Horng, M.H., Y.N. Sun and X.Z. Lin, 2002. Texture feature coding method for classification of liver sonography. Comput. Med. Imag. Graphics, 26: 33-42.
CrossRefDirect Link - Horng, M.H., Y.N. Sun and X.Z. Lin, 1998. A diagnostic image system for assessing the severity of chronic liver disease. Proceedings of the 20th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Volume 3, October 29-November 1, 1998, Hong Kong, pp: 1672-1675.
CrossRef - Wu, C.M., Y.C. Chen and K.S. Hsieh, 1992. Texture features for classification of ultrasonic liver images. IEEE Trans. Med. Imag., 11: 142-152.
CrossRefDirect Link - Haralick, R.M., K. Shanmugam and I.H. Dinstein, 1973. Textural features for image classification. IEEE Trans. Syst. Man Cybern., SMC-3: 610-621.
CrossRefDirect Link - Amadasun, M. and R. King, 1989. Textural features corresponding to textural properties. IEEE Trans. Syst. Man Cyberuetics, 19: 1264-1274.
CrossRef