Hallgatói dolgozatok (IK)

Állandó link (URI) ehhez a kategóriához

https://hdl.handle.net/2437/33

Böngészés

Hallgatói dolgozatok (IK) Szerző szerinti böngészés "Abok, Adija Beatrice"

Megjelenítve 1 - 2 (Összesen 2)
  • Nincs kép
    TételKorlátozottan hozzáférhető
    CT Image Segmentation in Medical Applications
    Abok, Adija Beatrice; Harangi, Balázs; DE--Informatikai Kar
    My thesis is about CT IMAGE SEGMENTATION IN MEDICAL APPLICATIONS, I discussed medical images, their segmentation, the methods and techniques involved in achieving this as well as implementing a segmentation technique by writing a program to detect abnormalities. I created and implemented a computer program using MATLAB which segments medical images for easier identification. I used the Global Thresholding technique in which I manually set the threshold value to be 0.7 for the entire image. Pixels with intensity values less than that 0.7 were represented in white while those greater than that value represented the black pixels. Also In extracting the tumour regions, I took advantage of the fact that the density/solidity of a tumor is higher than that of the brain and set a condition that areas with 30% higher density than that of the whole image are considered a tumour. I used the 30% value in order to pick up smaller tumours. In the future, I plan to improve my software by using a more automated segmentation technique.
  • Nincs kép
    TételKorlátozottan hozzáférhető
    CT Image Segmentation in Medical Applications
    Abok, Adija Beatrice; Harangi, Balázs; DE--Informatikai Kar
    My thesis is about segmentation of medical images in particular, computed tomography. I discussed medical images, their segmentations, the methods and techniques involved in achieving this as well as implementing a segmentation technique by writing a program to detect abnormalities.I created and implemented a computer program using MATLAB which segments medical images for easier identification. I used the Global Thresholding technique in which I manually set the threshold value to be 0.7 for the entire image. Pixels with intensity values less than that 0.7 were represented in white while those greater than that value represented the black pixels.Also In extracting the tumor regions, I took advantage of the fact that the density/solidity of tumor is higher than that of the brain and set a condition that areas with 30% higher density than that of the whole image is considered a tumor. I used the 30% value in order to pick up smaller tumors.