Efficient DWT-based fusion techniques using genetic algorithm for optimal parameter estimation

Advancements in technology have revolutionized almost every aspect of medical imaging. With the rapid developments in high technology and modern instrumentation, medical image fusion has become a vital aid for medical diagnosis, treatment and research. Medical imaging is the process, which produces images of internal aspects of the body by either invasive or noninvasive techniques. To support more accurate clinical information, medical images are required by the physicians for diagnosis and treatment (Goshtas and Nikolov 2007; Dammavalam et al. 2012). In the field of medical image processing and analysis, radiologists require high-resolution medical images with information such as region, tissue and visualization to help with improved disease diagnosis and computer assisted surgery (National Brain Tumor Society 2015; American Brain Tumor Association 2015). These requirements cannot be resolved with single modality medical images, because each of the imaging technique is designed to capture only specific aspects of the human anatomy. Computed tomography (CT) is more popularly used for recognizing the bone structure and tumor region, the soft tissue information is more visible in magnetic resonance image (MRI), positron emission tomography (PET) is useful in the diagnosis of brain disease, brain tumors, strokes, and neuron-damaging diseases (dementia) while single photon emission computed tomography (SPECT) conveys clear information in blood flow analysis during active/inactive state of the brain (American Brain Tumor Association 2015). For efficient disease diagnosis, complementary information from multiple modalities becomes necessary (Nishele 2015). Thus, fusion of multimodality medical images has become a promising and very challenging research area in recent years (Wang et al. 2005; Brainimages&information2015).This research work focuses on designing a fusion system for complementary information retrieval and analysis for the images acquired from multiple sensors of the patient during nearly same timeframes.