Classification of Alzheimer’s Disease in PET Scans using MFCC and SVM

Abstract

Unlike age-related dementia, Alzheimer's disease is more progressive and causes rapid deterioration in a patient's cognitive functions. Before its first clinical manifestation, it is evident that the damaging brain process has already been commenced much earlier in life. This asymptomatic period could have spanned as long as a decade or more. Although there is not yet an ultimate cure for the disease, the sooner it is diagnosed, the more chance that available therapeutic measures could improve the patient's quality of life. Standard medical questionnaire and medical imaging are the principal means of identifying early Alzheimer's disease. Despite a great effort having been made in analyzing structural atrophy in the human brain by using CT and MRI, the recent attempts have reached high accuracy and precision but relatively poor sensitivity. Functional imaging such as PET is of much lower spatial resolution but promising modality taken to elevate this limitation. This paper presents a classification method for early detection of the disease from PET scans drawn from the Thai population. However, instead of conventional structural analysis, this study performed clustering on unwrapped signals, transformed from imaging data by using Mel-Frequency Cepstral Coefficients (MFCC), by a generic Support Vector Machine (SVM) classifier. The experimental results reported herein indicate that, with the optimal MFCC order, the proposed method could identify subjects with Alzheimer's from controls, with high accuracy, precision, and specificity. With a cross-validation ratio of 8:2 and a linear SVM kernel, the classification accuracy, sensitivity, and specificity were 96.51, 93.98, and 97.77, respectively, and increased as the MFCC orders.

Language Impairment in Alzheimer’s Disease—Robust and Explainable Evidence for AD-Related Deterioration of Spontaneous Speech Through Multilingual Machine Learning

“…Typically, up to the first 14 coefficients are used as they represent the lower range frequencies of the vocal tract and yield most of the information (Hernández-Domínguez et al, 2018). This has been shown to be effective at identifying AD patients in previous literature (Dessouky et al, 2014;Rudzicz et al, 2014;Satt et al, 2014;Fraser et al, 2018;Panyavaraporn and Paramate, 2018;de la Fuente Garcia et al, 2020;Meghanani and Ramakrishnan, 2021). From this new representation, the first 14 coefficients of the MFC are extracted and the mean, variance, skewness and kurtosis are calculated for the energy (static coefficient), velocity (first differential), and acceleration (second differential).…”

Medical documents classification using topic modeling

“…Several researches were conducted on health information systems and medical data [9][10][11][12][13][14][15]. Some researchers worked on the classification of different diseases such as diabetics [11], Alzheimer [12], cancer [13,14] while others compared several classification and data mining algorithms on health data [15] whether these data were in English, Arabic [16], or multilingual [17,18]. There are many applications on topic modeling that were applied in different domains by different topic modeling approaches.…”

Structural adaptive anisotropic NAS-RIF for biomedical image restoration

“…It is worth noting here, that the anisotropic metric (g) preserves imaging structures via gradients and their moments, while disregarding noise by local aggregation. The resultant orientation pattern thus robustly represents local structure of image appearance, which in turn plays a major role in preserving image characteristics, pertinent to typical analyses, e.g., segmentation, edge detection, and fusion [3][4][5][6].…”

“…or subject motion.Certain degradations such as contrast, noise, and blur were shown associated with diminished performance and appreciation of radiographic imagery [2]. Provided various assumptions on and extents of degradations, higher-level vision strategieshave often been incorporated to assist analyses,e.g., recognition [3], fusion [4], segmentation [5],and modeling [6], etc.However, depending on certain types of analyses, imaging fi delity, i.e., luminance, contrast, and structural appearance remains imperative to their performance, which could be undermined by ill-considered enhancements.Restoration of the "true" image involves identifying the underlying degrading model, such as noises or a Point Spread Function (PSF) and then performing the respective inverse operations (Fig 1). Among stateof-the-arts approaches, deconvolution is characterized by computing procedure that corrects an image, for the infl uence of instrumental PSF and possibly noises.…”