Share
تشخيص ورم الكبد من الصور المقطعية باستخدام معالجة الصور الرقمية == Diagnosis of Liver Tumor from Computed Tomography Images using Digital Image Processing
Author name:
انتظار مالك هادي
Supervisor name:
علياء حسين علي
General topic:
Physics
Specific topic:
Image Processing
Degree:
Master
University:
University of Baghdad - Ibn Al-Haytham College Of Education For Pure Sciences - Physics Department
Language:
English
University location:
Baghdad
First pages:
26T1792 - p.pdf
Abstract:
This work aims to detect and diagnoses liver tumors from Computed Tomography images using digital image processing, this is a modern technique which depends on using computer in addition to textural analysis to obtain an accurate liver diagnosis, despite the method's difficulty that came from liver's position in the abdomen among the other organs. This method will enable the surgeon to detect the tumor and then easing treatment also it helps physicians and radiologists to identify the affected parts of the liver in order to protect the normal parts as much as possible from exposure to radiation. This work describes a new 2D liver segmentation method for purpose of segmented as a treatment for liver tumors. Liver segmentation is not only the key process for volume computation but also fundamental for further processing to get more anatomy information for individual patient. Due to the low contrast, blurred edges, large variability in shape and complex context with clutter features surrounding the liver that characterize the CT liver images. The method has been implemented in MATLAB and a Graphical User Interface was created. These imaging studies have contained a total of 22 CT images, including five Haemangioma, five Cyst, five Cirrhosis, five carcinomas and two healthy livers. Calculating the area of the abnormal part (tumor), an algorithm has been created to colored images depending on the boundary. The images have been transformed from RGB color space to HSV color space to identifying different colors in fabric by analyzing the HSV color space. This helps to separate abnormal part in to K - clusters. The method is very effective and gives the best result for classification process. Since it depend on the color of the texture and on the distance between the classes. The 2D segmentation process which is based on the hybrid method which is the combination of modified k - Mean (which depend on the distance and color), and the statistical structure which is the first order statistical feature. The statistical features are : Mean, Variance, Standard deviation, Skewness, Kurtosis, Energy and Entropy, and the geometrical feature which are area and the irregularity. These features together helps to diagnose the liver tumor and to classify these tumor
