Automatic Segmentation and Classification of Liver Abnormalities Using Fractal Dimension

Abnormalities in the liver include masses which can be benign or malignant. Due to the presence of these abnormalities, the regularity of the liver structure is altered, which changes its fractal dimension. In this paper, we present a computer aided diagnostic system for classifying liver abnormalities from abdominal CT images using fractal dimension features. We integrate different methods for liver segmentation and abnormality classification and propose an attempt that combines different techniques in order to compensate their individual weaknesses and to exploit their strengths. Classification is based on fractal dimension, with six different features being employed for extracted regions of interest. Experimental results confirm that our approach is robust, fast and able to effectively detect the presence of abnormalities in the liver.

[1]  David G. Stork,et al.  Pattern Classification , 1973 .

[2]  S. Casciaro,et al.  Fully Automatic Liver Segmentation through Graph-Cut Technique , 2007, 2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[3]  M. Yaffe,et al.  Characterisation of mammographic parenchymal pattern by fractal dimension. , 1990, Physics in medicine and biology.

[4]  Yeong-Gil Shin,et al.  Efficient liver segmentation using a level-set method with optimal detection of the initial liver boundary from level-set speed images , 2007, Comput. Methods Programs Biomed..

[5]  N. Obuchowski,et al.  Quantitative classification of breast tumors in digitized mammograms. , 1996, Medical physics.

[6]  Yoshinobu Sato,et al.  Automated liver segmentation using multislice CT images , 2003, Systems and Computers in Japan.

[7]  Jianwu Xu,et al.  Computer-aided measurement of liver volumes in CT by means of geodesic active contour segmentation coupled with level-set algorithms. , 2010, Medical physics.

[8]  S. S. Kumar,et al.  Diagnosis of Liver Tumor from CT Images Using Fast Discrete Curvelet Transform , 2010 .

[9]  James M. Keller,et al.  Texture description and segmentation through fractal geometry , 1989, Comput. Vis. Graph. Image Process..

[10]  C. Sparrow.  The Fractal Geometry of Nature , 1984 .

[11]  Shigeo Abe DrEng.  Pattern Classification , 2001, Springer London.

[12]  J. R. Landis,et al.  The measurement of observer agreement for categorical data. , 1977, Biometrics.

[13]  Yen-Wei Chen,et al.  Automated Segmentation of the Liver from 3D CT Images Using Probabilistic Atlas and Multi-level Statistical Shape Model , 2007, MICCAI.

[14]  Yo-Sung Ho,et al.  Automatic liver segmentation for volume measurement in CT Images , 2006, J. Vis. Commun. Image Represent..

[15]  Ibrahima Faye,et al.  Digital Mammograms Classification Using a Wavelet Based Feature Extraction Method , 2009, 2009 Second International Conference on Computer and Electrical Engineering.

[16]  Ahmed M. Anter,et al.  Automatic mammogram segmentation and computer aided diagnoses for breast tissue density according to BIRADS dictionary , 2012, Int. J. Comput. Aided Eng. Technol..

[17]  J. Furst,et al.  A Hybrid Approach for Liver Segmentation , 2007 .

[18]  Yung-Chang Chen,et al.  Texture features for classification of ultrasonic liver images , 1992, IEEE Trans. Medical Imaging.

[19]  E-Liang Chen,et al.  An automatic diagnostic system for CT liver image classification , 1998, IEEE Transactions on Biomedical Engineering.

[20]  B. Garra,et al.  Improving the Distinction between Benign and Malignant Breast Lesions: The Value of Sonographic Texture Analysis , 1993 .

[21]  Aboul Ella Hassanien,et al.  Level set-based CT liver image segmentation with watershed and artificial neural networks , 2012, HIS.