Stacked autoencoders as new models for an accurate Alzheimer’s disease classification support using resting-state EEG and MRI measurements

Autor: Vania Karami, Andrea Romano, Filippo Carducci, Antonio Ivano Triggiani, Flavio Nobili, Maria Teresa Pascarelli, Franco Giubilei, Giovanni B. Frisoni, Alessandro Bozzao, Giuseppe Noce, Andrea Soricelli, Claudio Babiloni, Luca Patané, Raffaele Ferri, Fabrizio Stocchi, Francesco Amenta, Paolo Arena, Claudio Del Percio, Roberta Lizio
Rok vydání: 2021
Předmět:
Neural Networks
Computer science
Alzheimer's Disease (AD)
Low-resolution brain electromagnetic tomography (LORETA)
Resting State Electroencephalography (rsEEG)
Stacked Artificial Neural Networks (ANNs) with Autoencoders
050105 experimental psychology
Structural magnetic resonance imaging
Computer
03 medical and health sciences
0302 clinical medicine
Alzheimer Disease
Physiology (medical)
Healthy control
Brain
Electroencephalography
Humans
Magnetic Resonance Imaging
Retrospective Studies
Neural Networks
Computer
0501 psychology and cognitive sciences
Artificial neural network
business.industry
05 social sciences
Disease classification
Pattern recognition
Sensory Systems
Neurology
High resolution eeg
Resting state eeg
National database
Neurology (clinical)
Artificial intelligence
business
030217 neurology & neurosurgery
Zdroj: Clinical Neurophysiology. 132:232-245
ISSN: 1388-2457
DOI: 10.1016/j.clinph.2020.09.015
Popis: Objective This retrospective and exploratory study tested the accuracy of artificial neural networks (ANNs) at detecting Alzheimer’s disease patients with dementia (ADD) based on input variables extracted from resting-state electroencephalogram (rsEEG), structural magnetic resonance imaging (sMRI) or both. Methods For the classification exercise, the ANNs had two architectures that included stacked (autoencoding) hidden layers recreating input data in the output. The classification was based on LORETA source estimates from rsEEG activity recorded with 10–20 montage system (19 electrodes) and standard sMRI variables in 89 ADD and 45 healthy control participants taken from a national database. Results The ANN with stacked autoencoders and a deep leaning model representing both ADD and control participants showed classification accuracies in discriminating them of 80%, 85%, and 89% using rsEEG, sMRI, and rsEEG + sMRI features, respectively. The two ANNs with stacked autoencoders and a deep leaning model specialized for either ADD or control participants showed classification accuracies of 77%, 83%, and 86% using the same input features. Conclusions The two architectures of ANNs using stacked (autoencoding) hidden layers consistently reached moderate to high accuracy in the discrimination between ADD and healthy control participants as a function of the rsEEG and sMRI features employed. Significance The present results encourage future multi-centric, prospective and longitudinal cross-validation studies using high resolution EEG techniques and harmonized clinical procedures towards clinical applications of the present ANNs.
Databáze: OpenAIRE
Externí odkaz: