Search

Computer-assisted tools can aid in the detection of Alzheimer disease (AD) which is a progressive neurodegenerative disorder that can lead to cognitive impairments and eventually death. The accumulated effects due to AD can cause changes in the appearance of grey matter, white matter and cerebrospinal fluid in brain Magnetic Resonance (MR) images. This study aims to use Kernel Density Estimation (KDE) technique to analyse the textural changes from single slice brain MR images for the detection of AD. The preprocessed, skull stripped T1-weighted MR brain images are obtained from the publicly available OASIS database. A single axial slice per subject is chosen from a volumetric image for further processing to reduce the computational load. Multivariate KDE technique is applied to each pixel, by considering the changes in the neighbourhood based on selected bandwidth to obtain corresponding density estimates. Statistical features quantifying the distribution of density estimates are extracted to characterise textural variations in images. Linear discriminant analysis (LDA) classifier is implemented with ten-fold cross-validation for detecting AD. An optimum bandwidth of 18 for the KDE technique is selected based on the classification performance. Out of seven extracted texture features, three are found to be statistically significant in distinguishing AD. The classification with LDA yields an accuracy of 72.3% with a sensitivity of 80.6% for identifying AD from healthy subjects. The proposed method is efficient in detecting AD by revealing the textural changes within the brain slice without the involvement of any segmentation technique. Thus, the novel KDE-based texture analysis proves to be an effective tool for the automated diagnosis of AD from single slice brain MR images.

Mild Cognitive Impairment (MCI) is the asymptomatic, preclinical transitional stage among aging and Alzheimer’s Disease (AD). Detection of MCI can ensure the timely intervention required to manage the disease’s severity. Morphological alterations of Lateral Ventricle (LV) is considered as a significant biomarker for disease diagnosis. This research aims to analyze the shape alterations of the LV region using Fractional Order Jacobi Fourier Moment (FOJFM) features, which are categorized by their generic nature and capabilities to perform time-frequency analysis. T1-weighted transaxial view brain MR images (HC = 92 and MCI = 63) are obtained from publicly available Open Access Series of Imaging Studies (OASIS) database. The LV region is delineated using Weighted Level Set (WLS) segmentation method and results are compared to Ground Truth (GT) images. FOJFM features are employed to characterize the morphometry of LV region. From this segmented region, 200 features are computed by varying the value of order and fractional parameters. Random Forest (RF) and Support Vector Machine (SVM) classifiers are used to differentiate Healthy Control (HC) and MCI subjects. Results show that WLSE is able to delineate the LV structure. The segmented region shows good correlation with the GT area. FOJFM features are observed to be statistically significant in discriminating HC and MCI subjects with p