학술논문

A Grid Computing Approach to Subtraction Radiography
Document Type
Conference
Source
2006 International Conference on Image Processing Image Processing, 2006 IEEE International Conference on. :3325-3328 Oct, 2006
Subject
Signal Processing and Analysis
Computing and Processing
Grid computing
Diagnostic radiography
Image registration
Diseases
Dentistry
Mutual information
Histograms
Lesions
Genetic algorithms
Concurrent computing
Parallel processing
Language
ISSN
1522-4880
2381-8549
Abstract
Digital subtraction is a common technique used in radiographic studies of periapical lesions and other dental disorders for which the treatment must be evaluated over time. This paper presents a fast and reliable parallel image registration method for subtracting two digitized radiographs where an unpredicted mismatch is present. An optimal affine transformation is found using an adaptive Genetic Algorithm (GA) as the optimization strategy and a correlation ratio as the similarity measure. The parallel GA implemented takes advantage of the CPU idle cycles of a computational grid, resulting in an application that exploits an existent infrastructure and with a computational time of about twenty seconds when processing pairs of standard intra-oral radiographs.