Executive Summary : | Alzheimer's disease (AD) is a major neurodegenerative dementia for elderly persons which leads to memory loss, confusion, problem in learning and poor judgment. Most of Alzheimer's patient exhibits wandering behavior as a physical and emotional outlet that increases the likelihood of accidents, serious injury and even death. Among forty four millions of Alzheimer's patients worldwide, only one fourth of them are diagnosed. As a matter of fact, early detection and subsequent diagnosis of AD has generated serious concern amongst the medical practitioners. In connection to this, prior detection of AD from different brain images has emerged as one of the thrust areas of medical image processing in recent times. Pathological studies have encountered some abnormal growth in specific regions of human brain for the persons with dementia. In metacognitive learning process, the cognitive component is controlled by choosing the best learning strategies by implementing self regulation. Analysis of MRI scans for AD detection is classified into two sections, namely whole brain morphometric method and region of interest (ROI) method where volumetric measurements are done for specific brain regions. The whole brain tissue loss may be estimated by some efficient edge detection technique using novel fuzzy logic. The gray matter or white matter differences and VBM using SPM may be employed to determine AD. Similarly, the hippocampus classification may also be achieved by some powerful machine learning algorithms. For the purpose of extracting critical AD features from Electroencephalography (EEG) signals, a time-frequency analysis and the multi-resolution capability of wavelets has emerged as a preferable choice in recent times. There are investigation techniques of EEG compression process to recover ROI data with the quality required by clinical constraints that may be used to calculate tissue loss in AD. Iron accumulation occurs in specific regions of brain for both normal aging and neurodegenerative disorders. Deposed iron changes the magnetic susceptibility of tissues and MRI signal phase is altered. It allows estimation of susceptibility differences using quantitative susceptibility mapping (QSM) for normal aging. Brain images signifying deposed iron can be used to estimate the possible occurrence of AD. Functional brain connectivity modeled by a sparse inverse covariance estimation (SICE) technique may also be implemented to investigate the trace of AD. |