Paper Info
Title
Genetic Algorithm Automated Generation of Multivariate Color Tables for Visualization of Multimodal Medical Data Sets.
Abstract
In many applications there is a need to visualize multidimensional data sets. Using spatial relationships alone, display is limited to two or three dimensions. The use of color, in addition to spatial relationships, increases the dimensionality of the data that can be effectively visualized. Use of color is usually achieved through the application of color tables. The generation of color tables is not an easy task, and since color space is relatively large it is nearly impossible for an individual to consider all of the possible options. A genetic algorithm was developed to automate this task, generating color tables for the joint display of high-resolution and dynamic contrast-enhanced magnetic resonance imaging and F-18-FDG positron emission tomography data sets. The results are promising, producing new color tables that meet defined requirements. lighting in the room, the color of the background, and the gamma and black offset of the display device. When generating color tables using the genetic algorithm described in this paper these factors are ignored. It is assumed that gamma corrections as well as other corrections for viewing conditions will be applied to the color table prior to deploying it into the environment. The color tables generated are intended for a general audience, and are not tuned towards any one individual. This has to be so if the color tables are to be deployed in a clinical setting. It is a necessity however, to consider the task that the images produced by the application of the color table are going to be used for. See (1) for a full demonstration of how a properly designed color table can aid a task while an improperly designed one can complicate matters. Because of this, it is first necessary to define the task at hand and then the requirements of the color tables that will aid in this task. 1.2. The Task - Multimodality Breast Cancer Imaging
Year
Venue
Keywords
2006
Color Imaging Conference
three dimensions,high resolution,spatial relationships,genetic algorithm,magnetic resonance image,breast cancer,color space
Field
DocType
Citations 
Computer vision,Data set,Color space,Computer science,Visualization,Multivariate statistics,Curse of dimensionality,Positron emission tomography,Artificial intelligence,Genetic algorithm,Color quantization
Conference
1
PageRank 
References 
Authors
0.48
3
3
Name
Order
Citations
PageRank
Karl G. Baum1134.71
Maria Helguera252.66
Andrzej Król3184.99