Neuro-Imaging Machine Learning Techniques for Alzheimer's Disease Diagnosis

Neuro-Imaging Machine Learning Techniques for Alzheimer's Disease Diagnosis

Gehad Ismail Sayed (Cairo University, Egypt & Scientific Research Group in Egypt (SRGE), Egypt) and Aboul Ella Hassanien (Cairo University, Egypt & Scientific Research Group in Egypt (SRGE), Egypt)
Copyright: © 2017 |Pages: 19
DOI: 10.4018/978-1-5225-2229-4.ch022
OnDemand PDF Download:
$30.00
List Price: $37.50

Abstract

Alzheimer's disease (AD) is considered one of the most common dementia's forms affecting senior's age staring from 65 and over. The standard method for identifying AD are usually based on behavioral, neuropsychological and cognitive tests and sometimes followed by a brain scan. Advanced medical imagining modalities such as MRI and pattern recognition techniques are became good tools for predicting AD. In this chapter, an automatic AD diagnosis system from MRI images based on using machine learning tools is proposed. A bench mark dataset is used to evaluate the performance of the proposed system. The adopted dataset consists of 20 patients for each diagnosis case including cognitive impairment, Alzheimer's disease and normal. Several evaluation measurements are used to evaluate the robustness of the proposed diagnosis system. The experimental results reveal the good performance of the proposed system.
Chapter Preview
Top

Background

Several machine learning systems for AD diagnosis are developed and proposed in literature. The proposed system in (Davatzikos, Fan, Wu, Shen, & Resnick, 2008), starts from segmenting the MRI image into grey matter (GM), white matter (WM) and cerebrospinal fluid (CSF) regions, then using Pearson correlation coefficient and a leave-one-out procedure in order to discriminate normal and MCI images. A watershed clustering algorithm is used to determine brain regions.

In the other hand, the proposed system in (Magnin et al., 2009), first cluster the image into multiple regions by using anatomically labeled brain template to get probability of GM, WM, and CSF, then SVM is used to classify the subjects and statistical procedures based on using bootstrap resampling method into AD and control subjects (CS). Likewise, the proposed system in (Robinson, Hammers, Ericsson, Edwards, & Rueckert, 2010), it uses the principal component analysis (PCA) and maximum uncertainty linear discriminant analysis followed by classifier fusion in order to classify.

Moreover, Zhang et al. in (Zhang, Wang, Zhou, Yuan, & Shen, 2011) extracted different bio-markers modality to accurately distinguish between AD or MCI and healthy subject controls. The authors use a kernel combination method and atlas warping algorithm. Moreover they apply SVM to evaluate the classification accuracy, using a 10-fold cross-validation. In (Cuingnet et al., 2011), An automatic classification system used to distinguish between patients with MCI or AD and elderly controls (CN) from structural T1-weighted MRI and it has compared with 10 methods based on ADNI database.

Complete Chapter List

Search this Book:
Reset