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

Ferri, Raffaele; Babiloni, Claudio; Karami, Vania; Triggiani, Antonio Ivano; Carducci, F.; Noce, Giuseppe; Lizio, Roberta; Pascarelli, Maria Teresa; Soricelli, Andrea; Amenta, Francesco; Bozzao, Alessandro; Romano, Andrea; Giubilei, Franco; Percio, Claudio Del; Stocchi, Fabrizio; Frisoni, Giovanni B.; Nobili, Flavio; Patanè, Luca; Arena, Paolo

doi:10.1016/j.clinph.2020.09.015

Cited by 45 publications

(16 citation statements)

References 78 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Numerous ML methods have been used to classify and predict AD stages with promising results (Haller, Lövblad et al 2011, Falahati, Westman et al 2014, Rathore, Habes et al 2017. While some studies have made use of a single screening modality, such as MRI (Fan, Batmanghelich et al 2008, Kloppel, Stonnington et al 2008, Cuingnet, Gerardin et al 2011, Liu, Zhang et al 2012, Tong, Wolz et al 2014, or electroencephalography (EEG) (Blinowska, Rakowski et al 2017, Farina, Emek-Savaş et al 2020, Ferri, Babiloni et al 2020, Oltu, Akşahin et al 2021, others have used a combination of multiple imaging techniques including MRI, PET, and cerebrospinal fluid (CSF) biomarkers (Zhang, Wang et al 2011, Gray, Aljabar et al 2013, Jie, Zhang et al 2013, Young, Modat et al 2013, Teipel, Kurth et al 2015, Yun, Kwak et al 2015, Samper-González, Burgos et al 2018. Although many of those studies presented interesting and promising results in AD classification, most focused on a so-called two-class problem.…”

Section: Introductionmentioning

confidence: 99%

Brain simulation augments machine-learning-based classification of dementia

Triebkorn

Stefanovski

Dhindsa

et al. 2021

Preprint

View full text Add to dashboard Cite

IntroductionWhile the prevalence of neurodegenerative diseases and dementia increases, our knowledge of the underlying pathomechanisms and related diagnostic biomarkers, outcome predictors, or therapeutic targets remains limited. In this article, we show how computational multi-scale brain network modeling using The Virtual Brain (TVB) simulation platform supports revealing potential disease mechanisms and can lead to improved diagnostics.MethodsTVB allows standardized large-scale structural connectivity (SC)-based modeling and simulation of whole-brain dynamics. We combine TVB with a cause-and-effect model for amyloid-beta, and machine-learning classification with support vector machines and random forests. The amyloid-beta burden as quantified from individual AV-45 PET scans informs parameters of local excitation/inhibition balance. We use magnetic resonance imaging (MRI), positron emission tomography (PET, specifically Amyloid-beta (Abeta) binding tracer AV-45-PET, and Tau-protein (Tau) binding AV-1451-PET) from 33 participants of Alzheimer’s Disease Neuroimaging Initiative study 3 (ADNI3). The frequency compositions of simulated local field potentials (LFP) are under investigation for their potential to classify individuals between Alzheimer’s disease (AD), Mild Cognitive Impairment (MCI), and healthy controls (HC) using support vector machines and random forest classifiers.ResultsThe combination of empirical features (subcortical volumetry, AV-45- and AV-1451-PET standard uptake value ratio, SUVR per region) and simulated features (mean LFP frequency per brain region) significantly outperformed the classification accuracy of empirical data alone by about 10% in the accuracy index of weighted F1-score (empirical 64.34% vs. combined 74.28%). There was no significant difference between empirical and simulated features alone. The features with the highest feature importance showed high biological plausibility with respect to the AD-typical spatial distribution of the features. This was demonstrated for all feature types, e.g., increased importance indices for the left entorhinal cortex as the most important Tau-feature, the left dorsal temporopolar cortex for Abeta, the right thalamus for LFP frequency, and the right putamen for volume.DiscussionIn summary, here we suggest a strategy and provide proof of concept for TVB-inferred mechanistic biomarkers that are direct indicators of pathogenic processes in neurodegenerative disease. We show how the cause-and-effect implementation of local hyperexcitation caused by Abeta can improve the machine-learning-driven classification of AD. This proves TVBs ability to decode information in empirical data by means of SC-based brain simulation.

show abstract

Section: Introductionmentioning

confidence: 99%

Brain simulation augments machine-learning-based classification of dementia

Triebkorn

Stefanovski

Dhindsa

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…The proposed approach for 4-way classification achieved accuracies of 98.88, 98.01, and 98.14% using the GoogleNet, ResNet-18, and ResNet-152 pre-trained networks, respectively. All three architectures performed better than other models that are proposed to classify AD MRI data, such as the stacked autoenconder (SAE) models (Gupta et al, 2013;Ferri et al, 2021). Furthermore, Valliani and Soni (2017) proposed a pre-trained deep ResNet to classify AD MRI imaging in order to demonstrate that training on biomedical imaging was not necessary for the task and achieved modest accuracy.…”

Section: Methodologies For Ad Imaging Classification Cnnmentioning

confidence: 98%

“…Therefore, the need for processing large images renders MLPs a non-optimal option. MLPs also require flattened vector inputs for image processing, so spatial information becomes lost (Feng et al, 2019). Finally, MLPs also run the risk of overfitting training data, leading to poor generalizability (Caruana et al, 2001).…”

Section: Background Multilayer Perceptron Neural Networkmentioning

confidence: 99%

Deep Convolutional Neural Networks With Ensemble Learning and Generative Adversarial Networks for Alzheimer’s Disease Image Data Classification

Logan

Williams

Silva

et al. 2021

Front. Aging Neurosci.

View full text Add to dashboard Cite

Recent advancements in deep learning (DL) have made possible new methodologies for analyzing massive datasets with intriguing implications in healthcare. Convolutional neural networks (CNN), which have proven to be successful supervised algorithms for classifying imaging data, are of particular interest in the neuroscience community for their utility in the classification of Alzheimer’s disease (AD). AD is the leading cause of dementia in the aging population. There remains a critical unmet need for early detection of AD pathogenesis based on non-invasive neuroimaging techniques, such as magnetic resonance imaging (MRI) and positron emission tomography (PET). In this comprehensive review, we explore potential interdisciplinary approaches for early detection and provide insight into recent advances on AD classification using 3D CNN architectures for multi-modal PET/MRI data. We also consider the application of generative adversarial networks (GANs) to overcome pitfalls associated with limited data. Finally, we discuss increasing the robustness of CNNs by combining them with ensemble learning (EL).

show abstract

“…The autoencoder’s main aim is to reconstruct the inputs such that the difference between the input and the output is minimized. The learning in autoencoder is compressed and distributed (encoding) ( Ferri et al, 2021 ). The training of autoencoder involves three steps:…”

Section: Methodsmentioning

confidence: 99%

Improving the Classification of Alzheimer’s Disease Using Hybrid Gene Selection Pipeline and Deep Learning

et al. 2021

View full text Add to dashboard Cite

Alzheimer’s is a progressive, irreversible, neurodegenerative brain disease. Even with prominent symptoms, it takes years to notice, decode, and reveal Alzheimer’s. However, advancements in technologies, such as imaging techniques, help in early diagnosis. Still, sometimes the results are inaccurate, which delays the treatment. Thus, the research in recent times focused on identifying the molecular biomarkers that differentiate the genotype and phenotype characteristics. However, the gene expression dataset’s generated features are huge, 1,000 or even more than 10,000. To overcome such a curse of dimensionality, feature selection techniques are introduced. We designed a gene selection pipeline combining a filter, wrapper, and unsupervised method to select the relevant genes. We combined the minimum Redundancy and maximum Relevance (mRmR), Wrapper-based Particle Swarm Optimization (WPSO), and Auto encoder to select the relevant features. We used the GSE5281 Alzheimer’s dataset from the Gene Expression Omnibus We implemented an Improved Deep Belief Network (IDBN) with simple stopping criteria after choosing the relevant genes. We used a Bayesian Optimization technique to tune the hyperparameters in the Improved Deep Belief Network. The tabulated results show that the proposed pipeline shows promising results.

show abstract

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

Cited by 45 publications

References 78 publications

Brain simulation augments machine-learning-based classification of dementia

Brain simulation augments machine-learning-based classification of dementia

Deep Convolutional Neural Networks With Ensemble Learning and Generative Adversarial Networks for Alzheimer’s Disease Image Data Classification

Improving the Classification of Alzheimer’s Disease Using Hybrid Gene Selection Pipeline and Deep Learning

Contact Info

Product

Resources

About