Document Type : Original Paper
M.Sc. in Medical Physics, Tehran University of Medical Sciences, Tehran, Iran.
Assistant Professor, Physics and Biomedical Engineering Dept. Tehran University of Medical Sciences, Tehran, Iran.
Assistant Professor, Physics and Biomedical Engineering Dept. Tehran University of Medical Sciences, Tehran, Iran. Research Center for Science & Technology in Medicine, Imam Khomeini Hospital, Tehran, Iran.
Assistant Professor, Radiology Dept., Tehran University of Medical Sciences, Tehran, Iran.
Introduction: A major problem facing the patients with chronic liver diseases is the diagnostic procedure.
The conventional diagnostic method depends mainly on needle biopsy which is an invasive method. There
are some approaches to develop a reliable noninvasive method of evaluating histological changes in
sonograms. The main characteristic used to distinguish between the normal, hepatitis and cirrhosis liver is the
texture of liver surface. The problem of defining a set of meaningful features that explores the characteristics
of the texture, leads to several methods of determining tissue texture. Some of these methods, which have
been developed so far, are based on wavelet transform. The selection of wavelet transform type affects the
accuracy of determining the texture. In this study, an optimal wavelet transform called Gabor wavelet was
introduced and three different methods of determining tissue texture were evaluated. These include statistical,
dyadic wavelet transform and Gabor wavelet transform methods.
Materials and Methods: The proposed algorithm was applied to differentiate ultrasonic liver images into
two disease states (hepatitis and cirrhosis) and normal liver. In this experiment, 50 liver sample images for
each three states which already been proven by needle biopsy were used. These images are taken from a
Toshiba Sonolayer SSA250A device using a 3.75 MHz transducer. For each image, a region of interest (ROI)
with 75×35 pixels is selected. The ROI is chosen to include only liver tissue without major blood vessel or
The classification method used for this work is "Minimum Distance", where the distance is calculated
between feature vectors of test image and reference images. In order to evaluate the diagnostic results, two
quantities named “Sensitivity” and “Specificity” were calculated for each method.
Results: The obtained results show that Gabor wavelet has 85% and dyadic wavelet has 77% sensitivity in
the hepatitis liver images. On the other hand, Gabor wavelet shows 86% sensitivity in the cirrhosis liver
images, while dyadic wavelet has 78%. The specificity of Gabor wavelet in the hepatitis and cirrhosis liver
images is 77% and 79% respectively, while the specificity of dyadic wavelet is 65% and 72%, respectively.
Discussion and Conclusion: Based on this experiment, the Gabor wavelet is more appropriate than the
dyadic wavelet and statistical based method for the texture classification as it leads to higher classification
accuracy, because the dyadic wavelet loses some middle-band information, while the Gabor wavelet
preserves it. Based on what was observed, the most significant information regarding the texture is mainly
located in the middle-frequency bands of wavelet decomposition. Therefore, using Gabor wavelet, a more
flexible decomposition of the entire frequency band can be achieved leading to a superior differentiation of
the texture information.