Detection of CT-Liver Lesions using Otsu Algorithm and Morphological Operations

The incidence of liver lesions has increaseddramatically in recent years. Early diagnosis is the best solution for rescuing patients exposed to this type of cancer. The aims of this study are to diagnosis early stages of liver lesions to increase the information for proper diagnose, by designing an effective and accurse method to detect the lesions which uses to enhance the CT images resolution and reduce the noise that may affect computed tomography (CT)-abdomen images and calculate values of intensities of anatomical structures of the liver in the so called histogram to determine the extent of intensities of the infected and non-infected regions also design simple method to compute histogram and probabilities of each intensity level to separate regions using the set threshold which applied for all pixels of the image to segment the lesions regions. The methodology was included the use of Digital Image Processing techniques, First CT-abdomen images database were acquired from local hospital and registered image from online atlas database, the noises were removed using smoothing and sharpening filters. These filters were estimated to select best performance filters, Evaluation were implemented using two common parameters mean square error (MSE) and signal to noise ratio (SNR), the evaluation conducted [5*5], [7*7],[9*9] for both smoothing and sharpening filter. Sharpen filter with size [9*9] showed better results in both parameters. Secondly, the histogram was calculated which represent the intensities of each elements in the image. After that the mathematical modeling of Otsu method which was used to calculate threshold values for affected regions detection. After lesions segmentation stage, morphological operations were used to enhance the lesions boundaries. The obtain results evaluate the criterion for maximizing the between class variance to extract the segmented lesions with goodness factor called entropy parameter, which compute the randomness in an image and it gave values between (0.6739-0.9706) which indicated the effectiveness of the method in detecting liver lesions.