Classification of Alzheimer Disease using Gabor Texture Feature of Hippocampus Region

Abstract

Abstract-The aim of this research is to propose a methodology to classify the subjects into Alzheimer disease and normal control on the basis of visual features from hippocampus region. All three dimensional MRI images were spatially normalized to the MNI/ICBM atlas space. Then, hippocampus region was extracted from brain structural MRI images, followed by application of two dimensional Gabor filter in three scales and eight orientations for texture computation. Texture features were represented on slice by slice basis by mean and standard deviation of magnitude of Gabor response. Classification between Alzheimer disease and normal control was performed with linear support vector machine. This study analyzes the performance of Gabor texture feature along each projection (axial, coronal and sagittal) separately as well as combination of all projections. The experimental results from both single projection (axial) as well as combination of all projections (axial, coronal and sagittal), demonstrated better classification performance over other existing method. Hence, this methodology could be used as diagnostic measure for the detection of Alzheimer disease.

Magnetic resonance imaging texture predicts progression to dementia due to Alzheimer disease earlier than hippocampal volume

“…10 Texture is widely applied in medical image analysis, such as classification of multiple sclerosis 11 and grading of brain tumours. 12,13 Many studies have also applied texture to the classification of Alzheimer disease, [14][15][16][17][18][19][20][21][22][23] under the working hypothesis that accumulated neuropathology in Alzheimer disease will be reflected as signal intensity changes associated with neuronal damage in brain tissue. Of these, 2 studies also applied texture to predicting progression from MCI to Alzheimer disease, 14,20 suggesting that textural changes in early stages may be a valuable predictive marker of imminent progression.…”

Uncovering Brain Chaos with Hypergraph-Based Framework

“…The deletion of vertex or edges indicated the shrinkage of the brain. In this way, the framework identifies the abnormal subject with Alzheimer's disease [35]. It has been inferred that by viewing the hypergraph structure itself the physician will notify the abnormal changes in the brain region.…”

Radiological images and machine learning: Trends, perspectives, and prospects

“…This section provides a general description of machine learning techniques and will help understanding their applications in the field of radiology, as described in subsequent sections. [46,45] roughness, granulation, and homogeneity Gabor features [47,48,49] Co-occurrence [50] Curvelet-based [51,52] Wavelet-based [ The linear model uses linear functions to separate the data yet is not suitable for non-linear cases. SVM is one way to separate non-linear models using different kernel functions.…”