الفهرس 
ABSTRACTOnly 14 pages are availabe for public view
 |  | from | 104 |  |  |
| | | from | 104 | | |
Abstract
In many medical image modalities, the scanned image may suffer from noise, low contrast and different types of degradation. Image Fusion is considered one of the most promising fields that gains attention in recent years, especially in the field of medical imaging. In medical imaging, many cases are misclassified due to the lack of clarity of the scanned image. Image fusion is used to merge two or more images into a single image. The input images may be completely unclear or contain parts that suffers from noise, low contrast, or blurring. The result of image fusion is an image that is clearer than the input images. The features are collected independently from each source image then they are combined together to produce high quality image that is readable than any of the source images. The output image from the fusion is more accurate and informative than any of the source images. Image fusion is widely used in different fields to handle problems of low contrast, noise, blurring and different types of attacks and artifacts. Some examples of implementations of image fusion can be found on medical imaging and astronomy imaging. Also, it is very useful in different types of manufacturing to detect any defects.
Recently, image fusion has become one of the most promising fields in image processing since it plays an essential role in different applications, such as medical diagnosis and clarification of medical images. Multi-modal Medical Image Fusion (MMIF) enhances the quality of medical images by combining two or more medical images from different modalities to obtain an improved fused image that is clearer than the original ones. Choosing the best MMIF technique which produces the best quality is one of the important problems in the assessment of image fusion techniques. In this paper, a complete survey on MMIF techniques is presented, along with medical imaging modalities, medical image fusion steps and levels, and the assessment methodology of MMIF. There are several image modalities, such as Computed Tomography (CT), Positron Emission Tomography (PET), Magnetic Resonance Imaging (MRI), and Single Photon Emission Computed Tomography (SPECT). Medical image fusion techniques are categorized into six main categories: spatial domain, transform fusion, fuzzy logic, morphological methods, and sparse representation methods. The MMIF levels are pixel‐level, feature‐level, and decision‐level. The fusion quality evaluation metrics can be categorized as subjective/qualitative and objective/quantitative assessment methods. Furthermore, a detailed comparison between obtained results for significant MMIF techniques is also presented to highlight the pros and cons of each fusion technique.
The proposed technique depends on image super-resolution and three levels of fusion. The proposed technique suppresses the distortions in the source images and greatly enhances the visibility of the final fused image. It also produces an output image that is twice number of rows and twice number of columns, which make it clearer and the physician can easily read its contents. The method depends on applying the bicubic interpolation to the source images A and B to obtain two large images C and D, respectively, then convert these obtained images (C and D) to the wavelet domain and perform the fusion by taking the average of the coefficients. The output image is called F_1. In the other hand, the two source images A and B are directly fused using PCA to produce the fused image AB, then the bicubic interpolation is applied to the obtained image to obtain another large image called F_2. Finally, the two fused images F_1 and F_2 are fused together to produce the final fused image F.