Prostate cances is one of the most frequent cancers in men and is a major cause of mortality in the most of countries including my country. In many diagnostic and treatment procedure of prostate disease, TRUS(Transrectal Ultrasound) images are being used because those cost is low. Prostate images have been used in the diagnosis of prostate using TRUS images being relatively cheap. Image inspection method which we can check the prostate structure the most correctly is MRI(Magnetic Resonance Imaging), but it is hard to apply it to all the patients because of the cost. So, they use mostly TRUS images acquired from prostate ultrasound inspection and which are cheap and easy to inspect the prostate in the process of treating and diagnosing the prostate cancer. Ultrasound images are recorded with 3 dimension and one diagnostic exam is made with a number of the images. A doctor can see 2 dimensional images on the monitor sequentially and 3 dimensional ones to diagnose a disease. To display the images, 2-d images are used with raw 2-d ones, but 3-d images need to be segmented by the prostates and their backgrounds to be seen from different angles and with cut images of inner side.
Traditionally, in the hospital the doctors saw the TRUS images by their eyes and manually segmented the boundary between the prostate and nonprostate. But the manually segmenting process not only needed too much time but also had different boundaries according to the doctor. To cope the problems, some automatic segmentations of the prostate have been studied to generate the constant segmentation results and get the belief from patients. Besides, on detecting the boundary, the ones in the middle of all images are easy to find the boundary but the base and apex of the images are hard to do it since there are lots of uncertain boundary. Accurate detection of prostate boundaries is a challenging and difficult task due to weak prostate boundaries, speckle noises and the short range of gray levels. Nevertheless, many studies have been studied. The studies used different techniques which are SVM(Support Vector Machine) learning, SIFT(Scalar Invariant Feature Transform), Gabor texture feature and snake-like contour method. Besides, the studies includes 2 dimension or 3 dimension images, and CT(Computed Tomography) and MRI images.
In this thesis, we propose the method that applies an average shape model and detects the boundary, and shows its superiority compared to the existing methods with experiments. The method has 4 steps. First, it finds the probe using edge distribution. Second, it finds two straight lines connected with the probe. Third, it puts the shape model to the image using the position of the probe and straight lines. Finally, it finds the boundary between the prostate and nonprostate surrounding the shape model which has a main line, an outer 10% line and an inner 10% line. As a result of our experiments, it shows that the boundary never falls short of the existing methods or human expert''s segmentation. And also, its searching speed is too fast because the method searches a smaller area that other methods.