Avalia\c{c}\~ao da doen\c{c}a de Alzheimer pela an\'alise multiespectral de imagens DW-MR por redes RBF como alternativa aos mapas ADC

TL;DR

This paper explores using multispectral diffusion-weighted MRI images and RBF neural networks to classify and analyze Alzheimer's disease, offering a potential non-invasive diagnostic alternative.

Contribution

It introduces a novel approach combining multispectral MRI analysis with RBF neural networks for early Alzheimer's detection.

Findings

Effective classification of brain images using RBF networks

Improved analysis of cerebrospinal fluid areas

Potential non-invasive diagnostic method

Abstract

Alzheimer's disease is the most common cause of dementia, yet difficult to accurately diagnose without the use of invasive techniques, particularly at the beginning of the disease. This work addresses the classification and analysis of multispectral synthetic images composed by diffusion-weighted magnetic resonance brain volumes for evaluation of the area of cerebrospinal fluid and its correlation with the progression of Alzheimer's disease. A 1.5 T MR imaging system was used to acquire all the images presented. The classification methods are based on multilayer perceptrons and classifiers of radial basis function networks. It is assumed that the classes of interest can be separated by hyperquadrics. A polynomial network of degree 2 is used to classify the original volumes, generating a ground-truth volume. The classification results are used to improve the usual analysis by the map of apparent diffusion coefficients.