الفهرس 
IMAGE REGISTRATION TECHNIQUESOnly 14 pages are availabe for public view
 |  | from | 179 |  |  |
| | | from | 179 | | |
Abstract
Medical image registration and fusion are gaining increasing importance in clinical practice as clinicians seek to integrate the complementary information provided by different modalities. The present work introduces an overview about image registration and image fusion techniques. These techniques are implemented and applied to a set of promising medical applications. In addition, performance measures for both registration and fusion techniques are compared. Three image registration techniques are implemented and applied to Magnetic Resonance (MR) and Computed Tomography (CT) images. The first technique is based on cross-correlation. The second one depends on selecting control points from both the reference and the input images. The last technique is based on maximization of mutual information between the two images. The application of the selected techniques to CT and MR images has shown that registration based on maximization of mutual information has given the best results and can be used efficiently for registeration of CT and MR images. Four different image fusion techniques are implemented and applied to CT, MR, and Positron Emission Tomography (PET) images. These are the Laplacian Pyramid, the Wavelet Transform, the Computationally Efficient Pixel-level Image Fusion (CEMIF) method, and the Multi-focus Technique based on Spatial Frequency. Fusion of MR and CT images is applied to facilitate detection of hepatic lesions, acute intra-cerebral hemorrhage, and detection of hemorrhagic transformation in hyper acute ischemic stroke. In addition, fusion of CT and PET is utilized to facilitate detection of colon cancer. Head and neck cancer can be early diagnosed via fusion of early and delayed CT scans. In all fusion applications, the fused image has better eye perception than both source images. Thus image fusion can help clinicians to get exact diagnosis by merging images taken from different sources. These qualitative results were verified using three measures of performance. The entropy measures have proved that the fused image has higher information content than source images. The improvement in spatial frequency was a good index to the success of fusion techniques. It has been shown that Wavelet technique was the best among other techniques in applications including detection of intra-cerebral hemorrhage, hepatic lesions, and in fusion of early and delayed CT scans. The Multi-Focus technique has shown better results in detection of hemorrhagic transformation in hyper-acute ischemic stroke. CT-PET fusion for colon cancer detection was achieved wit high accuracy using Laplacian Pyramid technique