Detection of early stages of Alzheimer's disease based on MEG activity with a randomized convolutional neural network

The early detection of Alzheimer's disease can potentially make eventual treatments more effective. This work presents a deep learning model to detect early symptoms of Alzheimer's disease using synchronization measures obtained with magnetoencephalography. The proposed model is a novel deep learning architecture based on an ensemble of randomized blocks formed by a sequence of 2D-convolutional, batch-normalization and pooling layers. An important challenge is to avoid overfitting, as the number of features is very high (25755) compared to the number of samples (132 patients). To address this issue the model uses an ensemble of identical sub-models all sharing weights, with a final stage that performs an average across sub-models. To facilitate the exploration of the feature space, each sub-model receives a random permutation of features. The features correspond to magnetic signals reflecting neural activity and are arranged in a matrix structure interpreted as a 2D image that is processed by 2D convolutional networks. The proposed detection model is a binary classifier (disease/non-disease), which compared to other deep learning architectures and classic machine learning classifiers, such as random forest and support vector machine, obtains the best classification performance results with an average F1-score of 0.92. To perform the comparison a strict validation procedure is proposed, and a thorough study of results is provided.

[1]  Haruhiko Kishima,et al.  Automatic diagnosis of neurological diseases using MEG signals with a deep neural network , 2019, Scientific Reports.

[2]  Guozhong An,et al.  The Effects of Adding Noise During Backpropagation Training on a Generalization Performance , 1996, Neural Computation.

[3]  R. Petersen.  Clinical practice. Mild cognitive impairment. , 2011, The New England journal of medicine.

[4]  Zhuowen Tu,et al.  Generalizing Pooling Functions in Convolutional Neural Networks: Mixed, Gated, and Tree , 2015, AISTATS.

[5]  Qi Sun,et al.  Analysis of Alzheimer’s Disease Based on the Random Neural Network Cluster in fMRI , 2018, Front. Neuroinform..

[6]  Vishnu Naresh Boddeti,et al.  Perturbative Neural Networks , 2018, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[7]  Wei Wu,et al.  Bayesian Machine Learning: EEG\/MEG signal processing measurements , 2016, IEEE Signal Processing Magazine.

[8]  Robert Oostenveld,et al.  FieldTrip: Open Source Software for Advanced Analysis of MEG, EEG, and Invasive Electrophysiological Data , 2010, Comput. Intell. Neurosci..

[9]  Gustavo E. A. P. A. Batista,et al.  A study of the behavior of several methods for balancing machine learning training data , 2004, SKDD.

[10]  Frank Rudzicz,et al.  Machine learning for MEG during speech tasks , 2019, Scientific Reports.

[11]  Jaime Lloret,et al.  Deep Learning Model for Multimedia Quality of Experience Prediction Based on Network Flow Packets , 2018, IEEE Communications Magazine.

[12]  Tatsuhiko Tsunoda,et al.  DeepInsight: A methodology to transform a non-image data to an image for convolution neural network architecture , 2019, Scientific Reports.

[13]  Xiangyu Zhang,et al.  ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[14]  C. Ivan,et al.  Convolutional Neural Networks on Randomized Data , 2019, CVPR Workshops.

[15]  Dimitrios Pantazis,et al.  Dynamics of scene representations in the human brain revealed by magnetoencephalography and deep neural networks , 2015, NeuroImage.

[16]  Onur Avci,et al.  1D Convolutional Neural Networks and Applications: A Survey , 2019, Mechanical Systems and Signal Processing.

[17]  Nitish Srivastava,et al.  Dropout: a simple way to prevent neural networks from overfitting , 2014, J. Mach. Learn. Res..

[18]  Jaime Lloret,et al.  Network Traffic Classifier With Convolutional and Recurrent Neural Networks for Internet of Things , 2017, IEEE Access.

[19]  Muhammad Usman,et al.  Early diagnosis of Alzheimer's disease using machine learning techniques: A review paper , 2015, 2015 7th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management (IC3K).

[20]  Matthias Bethge,et al.  Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet , 2019, ICLR.

[21]  Giulio Ruffini,et al.  EEG-driven RNN Classification for Prognosis of Neurodegeneration in At-Risk Patients , 2016, ICANN.

[22]  Jingdong Wang,et al.  Random Shifting for CNN: a Solution to Reduce Information Loss in Down-Sampling Layers , 2017, IJCAI.

[23]  S. Taulu,et al.  Spatiotemporal signal space separation method for rejecting nearby interference in MEG measurements , 2006, Physics in medicine and biology.

[24]  Krisztian Buza,et al.  Resting State fMRI Functional Connectivity-Based Classification Using a Convolutional Neural Network Architecture , 2017, Front. Neuroinform..

[25]  Rok Blagus,et al.  SMOTE for high-dimensional class-imbalanced data , 2013, BMC Bioinformatics.

[26]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[27]  Sergey Ioffe,et al.  Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift , 2015, ICML.

[28]  Di Guo,et al.  Convolutional Neural Networks-Based MRI Image Analysis for the Alzheimer’s Disease Prediction From Mild Cognitive Impairment , 2018, Front. Neurosci..

[29]  Geoffrey J McLachlan,et al.  Selection bias in gene extraction on the basis of microarray gene-expression data , 2002, Proceedings of the National Academy of Sciences of the United States of America.

[30]  Ankita Sharma,et al.  A Comprehensive Review of Magnetoencephalography (MEG) Studies for Brain Functionality in Healthy Aging and Alzheimer's Disease (AD) , 2018, Front. Comput. Neurosci..

[31]  Zhe Feng,et al.  A general introduction to adjustment for multiple comparisons. , 2017, Journal of thoracic disease.

[32]  Fernando Maestú,et al.  The Role of Magnetoencephalography in the Early Stages of Alzheimer’s Disease , 2018, Front. Neurosci..

[33]  David Barber,et al.  Bayesian Classification With Gaussian Processes , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[34]  James T. Becker,et al.  A multicenter study of the early detection of synaptic dysfunction in Mild Cognitive Impairment using Magnetoencephalography-derived functional connectivity , 2015, NeuroImage: Clinical.

[35]  R. Petersen,et al.  Mild cognitive impairment , 2006, The Lancet.

[36]  Dip Nandi,et al.  Alzheimer's Disease and Dementia Detection from 3D Brain MRI Data Using Deep Convolutional Neural Networks , 2018, 2018 3rd International Conference for Convergence in Technology (I2CT).

[37]  Giulio Ruffini,et al.  Deep learning using EEG spectrograms for prognosis in idiopathic rapid eye movement behavior disorder (RBD) , 2018 .

[38]  Jürgen Dammers,et al.  Deep Learning Approach for Automatic Classification of Ocular and Cardiac Artifacts in MEG Data , 2018 .

[39]  Hanna-Leena Halme,et al.  Adaptive neural network classifier for decoding MEG signals , 2018, NeuroImage.

[40]  Christopher M. Bishop,et al.  Current address: Microsoft Research, , 2022 .

[41]  Emily H. Trittschuh,et al.  Using Varying Diagnostic Criteria to Examine Mild Cognitive Impairment Prevalence and Predict Dementia Incidence in a Community-Based Sample. , 2019, Journal of Alzheimer's disease : JAD.

[42]  R. Petersen.  Mild cognitive impairment as a diagnostic entity , 2004, Journal of internal medicine.

[43]  Chee Kheong Siew,et al.  Extreme learning machine: Theory and applications , 2006, Neurocomputing.

[44]  Jean-François Gagnon,et al.  Deep learning with EEG spectrograms in rapid eye movement behavior disorder , 2018 .

[45]  Zenghui Wang,et al.  Deep Convolutional Neural Networks for Image Classification: A Comprehensive Review , 2017, Neural Computation.