Mr. Wade Schwartzkopf
Graduate Student
The Department of Electrical and Computer Engineering
The University of Texas at Austin
Tuesday, April 18th, 10:00 AM, ENS 537
Chromosome imaging is an invaluable tool for doctors and cytogenetic technicians. Extra chromosomes, missing chromosomes, broken chromosomes, and translocations (parts of chromosomes breaking off and attaching to other chromosomes) are excellent indicators of radiation, cancer, and a wide variety of other medical conditions. There are currently over 325 clinical cytogenetics laboratories in the United States performing over 250,000 diagnostic studies each year.
Recently a 5-fluorophore combinatorial labeling technique (M-FISH) was published in which each class of chromosome absorbs a different combination of fluorophores. This results in a multispectral image, in which each class of chromosomes has distinct spectral components. Although M-FISH presents significantly more information than was available in traditional grayscale chromosome images, to date, little work has been done in automated chromosome analysis to take advantage of this multispectral information.
This work proposes to develop formal methods of image segmentation that take advantage of the multispectral information in M-FISH images. In particular, we will (1) extend traditional chromosome segmentation and classification algorithms to the multispectral images produced by M-FISH, (2) combine chromosome segmentation and classification for a more robust chromosome identification system, and (3) develop formal methods for automated detection of the anomalies in chromosomes that can be discovered with M-FISH imaging.
A list of Telecommunications and Signal Processing Seminars is available at from the ECE department Web pages under "Seminars". The Web address for the Telecommunications and Signal Processing Seminars is http://anchovy.ece.utexas.edu/seminars