Title :
Empirical Analysis of Libs Images for Ovarian Cancer Detection
Author :
Tameze, Claude ; Vincelette, Robert ; Melikechi, Noureddine ; Zeljkovic, Vesna ; Izquierdo, Ebroul
Author_Institution :
Delaware State Univ., Dover
Abstract :
To develop a way to detect early epithelial ovarian cancer we expose blood samples to a laser. Using Laser induced breakdown spectroscopy, (LIBS) plasma images of the blood samples are generated and analyzed. In this paper we compare the images from blood specimens of cancer free mice to those of transgenic mice; that is, mice that are currently developing epithelial ovarian cancer and are approximately the same age as the disease free mice. Our ultimate goal is to look for changes in the shape and edges of the image that might indicate the presence of cancer. To analyze the images we use a nonlinear diffusion filter for enhancement of relevant image edges and removal of noise and irrelevant texture.
Keywords :
biological organs; biomedical optical imaging; cancer; edge detection; gynaecology; image enhancement; laser applications in medicine; medical image processing; nonlinear filters; tumours; LIBS images; blood samples; cancer free mice; early epithelial ovarian cancer detection; image edge enhancement; irrelevant texture removal; laser induced breakdown spectroscopy; noise removal; nonlinear diffusion filter; transgenic mice; Blood; Cancer detection; Diseases; Electric breakdown; Image analysis; Image texture analysis; Mice; Plasmas; Shape; Spectroscopy;
Conference_Titel :
Image Analysis for Multimedia Interactive Services, 2007. WIAMIS '07. Eighth International Workshop on
Conference_Location :
Santorini
Print_ISBN :
0-7695-2818-X
Electronic_ISBN :
0-7695-2818-X
DOI :
10.1109/WIAMIS.2007.40
