Beta 1


Title Computer aided analysis of MR brain images
Author Wolff, Stefan
Supervisor Hansen, Per Skafte (Department of Informatics and Mathematical Modeling, Technical University of Denmark, DTU, DK-2800 Kgs. Lyngby, Denmark)
Institution Technical University of Denmark, DTU, DK-2800 Kgs. Lyngby, Denmark
Thesis level Master's thesis
Year 2001
Abstract The object of the work reported here is to provide a clinical expert (a radiologist) with an algorithmic tool that will assist in the detection of the first two of these. The algorithm analyzes 3D data sets, obtained as luminance level values representing the output from MR scans of the human brain. The data is organized as a voxel image, with a geometry representing a straightforward discretization of that of the brain under study. The only information available as to the category of a given voxel (gray matter, white matter, cerebro-spinal fluid, vascular tissue or background) is that of the luminance level. An automated segregation will suppress precisely the information sought by the present algorithm, while (time-consuming) human intervention would be tantamount to a solution of the problem addressed. The algorithms are developed with this limitation observed throughout.
Imprint Department of Informatics and Mathematical Modeling, Technical University of Denmark, DTU : DK-2800 Kgs. Lyngby, Denmark
Keywords Magnetic Resonance; Cortical Dysplasia; Gradient Correlation Algorithm; Voxel Images; Visualization
Fulltext
Original PDF imm766.pdf (1.21 MB)
Admin Creation date: 2006-06-22    Update date: 2012-12-20    Source: dtu    ID: 57990    Original MXD