A novel method and software for automatically classifying Alzheimer’s disease patients by magnetic resonance imaging analysis

Previtali, Fabio; Bertolazzi, Paola; Felici, G.; Weitschek, Emanuel

doi:10.1016/j.cmpb.2017.03.006

Cited by 42 publications

(20 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although different neuroimaging techniques (e.g., Magnetic Resonance Imaging, Positron Emission Tomography) can be used for aiding the diagnosis of dementia providing quantitative data about the brain abnormalities [ 57 , 58 ], EEG is non-invasive, besides being cheaper, simpler and faster to use than other imaging devices [ 13 , 14 ]. For this reason, automated EEG signal analysis plays an important role in detecting dementia in the early stages, as well as in classifying disease severity [ 59 – 61 ].…”

Section: Discussionmentioning

confidence: 99%

Combining EEG signal processing with supervised methods for Alzheimer’s patients classification

Fiscon

Weitschek

Cialini

et al. 2018

BMC Med Inform Decis Mak

112

View full text Add to dashboard Cite

BackgroundAlzheimer’s Disease (AD) is a neurodegenaritive disorder characterized by a progressive dementia, for which actually no cure is known. An early detection of patients affected by AD can be obtained by analyzing their electroencephalography (EEG) signals, which show a reduction of the complexity, a perturbation of the synchrony, and a slowing down of the rhythms.MethodsIn this work, we apply a procedure that exploits feature extraction and classification techniques to EEG signals, whose aim is to distinguish patient affected by AD from the ones affected by Mild Cognitive Impairment (MCI) and healthy control (HC) samples. Specifically, we perform a time-frequency analysis by applying both the Fourier and Wavelet Transforms on 109 samples belonging to AD, MCI, and HC classes. The classification procedure is designed with the following steps: (i) preprocessing of EEG signals; (ii) feature extraction by means of the Discrete Fourier and Wavelet Transforms; and (iii) classification with tree-based supervised methods.ResultsBy applying our procedure, we are able to extract reliable human-interpretable classification models that allow to automatically assign the patients into their belonging class. In particular, by exploiting a Wavelet feature extraction we achieve 83%, 92%, and 79% of accuracy when dealing with HC vs AD, HC vs MCI, and MCI vs AD classification problems, respectively.ConclusionsFinally, by comparing the classification performances with both feature extraction methods, we find out that Wavelets analysis outperforms Fourier. Hence, we suggest it in combination with supervised methods for automatic patients classification based on their EEG signals for aiding the medical diagnosis of dementia.

show abstract

Section: Discussionmentioning

confidence: 99%

Combining EEG signal processing with supervised methods for Alzheimer’s patients classification

Fiscon

Weitschek

Cialini

et al. 2018

BMC Med Inform Decis Mak

112

View full text Add to dashboard Cite

show abstract

“…In paper [18] they have used support vector machine (SVM) with the use of two different data sets (OASIS and ADNI). They achieved outperform results than other state-of-the-art techniques on two established data sets while using binary classification (case vs control).…”

Section: F Deep Autoencoder (Da)mentioning

confidence: 99%

“…in [18] used the machine learning SVM techniques for classifying the AD patient from MRI with the use of two different data sets (OASIS and ADNI). They achieved outperform results then other state-of-the-art techniques on two established data sets while using binary classification (case vs control) with the accuracy of 100% from ADNI and 97% from OASIS dataset.…”

Section: Conclusion and Future Scopementioning

confidence: 99%

Alzheimer’s Disease Diagnosis using Deep Learning Techniques

Salehi¹,

Baglat²,

Gupta³

2020

IJEAT

View full text Add to dashboard Cite

Deep learning is one of the machine learning approach which has shown promising results and performance as compare to traditional algorithms of machine learning in terms of high dimensional data of MRI brain image. In this article the application of deep learning in medical field is addressed. A thorough review of various algorithms of deep learning for diagnosis of Alzheimer's disease is done, in which this disease is a progressive brain disorder that destroy the brain memory gradually, it is a common disease in older adults which is caused by dementia. It has been obtained in most research papers that the most widely used and represented algorithm is Convolutional Neural Networks (CNN) when it deals with brain image analysis. After study of various related papers for diagnosing of AD, we have come to this point and suggested that the AD prediction at earlier stages can be increased by using an advance deep learning techniques in different dataset (ADNI, OASIS) combining to one.

show abstract

“…In contrast with the problem complexity, the performance of such schemes is directly analogous to the amount and the quality of labeled data which are used at the training phase. In a large variety of scientific domains, such as object detection [ 1 ], speech recognition [ 2 ], web page categorization [ 3 ], and computer-aided medical diagnosis [ 4 , 5 , 6 ] vast pools of unlabeled data are often available. Though, in most cases labeling data can be costly and time-consuming, as human effort and expertise are required to annotate the available data.…”

Section: Introductionmentioning

confidence: 99%

Combination of Active Learning and Semi-Supervised Learning under a Self-Training Scheme

Fazakis

Kanas

Aridas

et al. 2019

Entropy

View full text Add to dashboard Cite

One of the major aspects affecting the performance of the classification algorithms is the amount of labeled data which is available during the training phase. It is widely accepted that the labeling procedure of vast amounts of data is both expensive and time-consuming since it requires the employment of human expertise. For a wide variety of scientific fields, unlabeled examples are easy to collect but hard to handle in a useful manner, thus improving the contained information for a subject dataset. In this context, a variety of learning methods have been studied in the literature aiming to efficiently utilize the vast amounts of unlabeled data during the learning process. The most common approaches tackle problems of this kind by individually applying active learning or semi-supervised learning methods. In this work, a combination of active learning and semi-supervised learning methods is proposed, under a common self-training scheme, in order to efficiently utilize the available unlabeled data. The effective and robust metrics of the entropy and the distribution of probabilities of the unlabeled set, to select the most sufficient unlabeled examples for the augmentation of the initial labeled set, are used. The superiority of the proposed scheme is validated by comparing it against the base approaches of supervised, semi-supervised, and active learning in the wide range of fifty-five benchmark datasets.

show abstract

A novel method and software for automatically classifying Alzheimer’s disease patients by magnetic resonance imaging analysis

Cited by 42 publications

References 23 publications

Combining EEG signal processing with supervised methods for Alzheimer’s patients classification

Combining EEG signal processing with supervised methods for Alzheimer’s patients classification

Alzheimer’s Disease Diagnosis using Deep Learning Techniques

Combination of Active Learning and Semi-Supervised Learning under a Self-Training Scheme

Contact Info

Product

Resources

About