الفهرس 
A Computational intelligence system for medical image fusion
ContentsOnly 14 pages are availabe for public view
 |  | from | 86 |  |  |
| | | from | 86 | | |
Abstract
Medical Image Fusion (MIF) is a way of extracting information from multiple images obtained from single or multiple modalities to provide a high quality image in which complementary information are combined and redundant information are removed. MIF can improve the performance of medical diagnosis, treatment planning and image-guided surgery significantly through providing high-quality and rich-information medical images. In traditional MIF techniques, fused image is constructed by applying the simple averaging fusion rule across all the input source images, but these techniques suffer from common drawbacks such as: contrast reduction, edge blurring and image degradation. Several enhancements were performed to overcome these drawbacks by employing computational intelligence techniques in processing features of the source images to be fused, it includes genetic algorithms, swarm intelligence, and neural networks specially Pulse-coupled Neural Network (PCNN). PCNN based MIF techniques outperform the traditional methods in providing high-quality fused images due to its global coupling and pulse synchronization property. Regardless of the major role PCNN plays in measuring the contribution of each source image into the fused image, a careful selection of the features to be processed by the PCNN can radically improve the quality of the fused image