Ensemble of ROI-based convolutional neural network classifiers for staging the Alzheimer disease spectrum from magnetic resonance imaging

Patches from three orthogonal views of selected cerebral regions can be utilized to learn convolutional neural network (CNN) models for staging the Alzheimer disease (AD) spectrum including preclinical AD, mild cognitive impairment due to AD, and dementia due to AD and normal controls. Hippocampi, amygdalae and insulae were selected from the volumetric analysis of structured magnetic resonance images (MRIs). Three-view patches (TVPs) from these regions were fed to the CNN for training. MRIs were classified with the SoftMax-normalized scores of individual model predictions on TVPs. The significance of each region of interest (ROI) for staging the AD spectrum was evaluated and reported. The results of the ensemble classifier are compared with state-of-the-art methods using the same evaluation metrics. Patch-based ROI ensembles provide comparable diagnostic performance for AD staging. In this work, TVP-based ROI analysis using a CNN provides informative landmarks in cerebral MRIs and may have significance in clinical studies and computer-aided diagnosis system design.

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

[2]  Giovanni Montana,et al.  Predicting Alzheimer's disease: a neuroimaging study with 3D convolutional neural networks , 2015, ICPRAM 2015.

[3]  D. Y. Lee,et al.  APOE Promoter Polymorphism-219T/G is an Effect Modifier of the Influence of APOE ε4 on Alzheimer’s Disease Risk in a Multiracial Sample , 2019, Journal of clinical medicine.

[4]  Seong-Whan Lee,et al.  Hierarchical feature representation and multimodal fusion with deep learning for AD/MCI diagnosis , 2014, NeuroImage.

[5]  G. Mok,et al.  The use of back propagation neural networks and 18F-Florbetapir PET for early detection of Alzheimer’s disease using Alzheimer’s Disease Neuroimaging Initiative database , 2019, PloS one.

[6]  Daoqiang Zhang,et al.  Multimodal classification of Alzheimer's disease and mild cognitive impairment , 2011, NeuroImage.

[7]  Dinggang Shen,et al.  A Robust Deep Model for Improved Classification of AD/MCI Patients , 2015, IEEE Journal of Biomedical and Health Informatics.

[8]  Nils Gessert,et al.  Skin Lesion Classification Using CNNs With Patch-Based Attention and Diagnosis-Guided Loss Weighting , 2019, IEEE Transactions on Biomedical Engineering.

[9]  William W. Seeley,et al.  Anterior insula degeneration in frontotemporal dementia , 2010, Brain Structure and Function.

[10]  Kichang Kwak,et al.  Multimodal Discrimination of Alzheimer’s Disease Based on Regional Cortical Atrophy and Hypometabolism , 2015, PloS one.

[11]  Yaozong Gao,et al.  Alzheimer's Disease Diagnosis Using Landmark-Based Features From Longitudinal Structural MR Images , 2017, IEEE Journal of Biomedical and Health Informatics.

[12]  Tianqi Chen,et al.  Empirical Evaluation of Rectified Activations in Convolutional Network , 2015, ArXiv.

[13]  A. Dale,et al.  High‐resolution intersubject averaging and a coordinate system for the cortical surface , 1999, Human brain mapping.

[14]  D. Chicco,et al.  The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation , 2020, BMC Genomics.

[15]  D. Dickson,et al.  The neuropathological diagnosis of Alzheimer’s disease , 2019, Molecular Neurodegeneration.

[16]  Yulia Dodonova,et al.  Residual and plain convolutional neural networks for 3D brain MRI classification , 2017, 2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017).

[17]  Alfredo Illanes,et al.  Patch Based Texture Classification of Thyroid Ultrasound Images using Convolutional Neural Network , 2019, 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[18]  Eman N. Marzban,et al.  Alzheimer’s disease diagnosis from diffusion tensor images using convolutional neural networks , 2020, PloS one.

[19]  D. Chitradevi,et al.  Analysis of brain sub regions using optimization techniques and deep learning method in Alzheimer disease , 2020, Appl. Soft Comput..

[20]  Aggelos K. Katsaggelos,et al.  Neuroimaging modality fusion in Alzheimer’s classification using convolutional neural networks , 2018, PloS one.

[21]  Dinggang Shen,et al.  Landmark‐based deep multi‐instance learning for brain disease diagnosis , 2018, Medical Image Anal..

[22]  Ran R. Hassin,et al.  Can Consumers Make Affordable Care Affordable? The Value of Choice Architecture , 2013, PloS one.

[23]  P. Liu,et al.  Novel Pathways Revealed in Bursa of Fabricius Transcriptome in Response to Extraintestinal Pathogenic Escherichia coli (ExPEC) Infection , 2015, PloS one.

[24]  Denise C. Park,et al.  Toward defining the preclinical stages of Alzheimer’s disease: Recommendations from the National Institute on Aging-Alzheimer's Association workgroups on diagnostic guidelines for Alzheimer's disease , 2011, Alzheimer's & Dementia.

[25]  Ming Yang,et al.  Classification of Alzheimer’s Disease Based on Eight-Layer Convolutional Neural Network with Leaky Rectified Linear Unit and Max Pooling , 2018, Journal of Medical Systems.

[26]  2020 Alzheimer's disease facts and figures , 2020, Alzheimer's & dementia : the journal of the Alzheimer's Association.

[27]  S. Black,et al.  Beyond the hippocampus , 2001, Neurology.

[28]  Alexander Hammers,et al.  On brain atlas choice and automatic segmentation methods: a comparison of MAPER & FreeSurfer using three atlas databases , 2020, Scientific Reports.

[29]  Ayman El-Baz,et al.  Alzheimer's disease diagnostics by adaptation of 3D convolutional network , 2016, 2016 IEEE International Conference on Image Processing (ICIP).

[30]  John Seibyl,et al.  Cerebral amyloid-β PET with florbetaben (18F) in patients with Alzheimer's disease and healthy controls: a multicentre phase 2 diagnostic study , 2011, The Lancet Neurology.

[31]  H. Hampel,et al.  Biological markers for early detection and pharmacological treatment of Alzheimer's disease , 2009, Dialogues in clinical neuroscience.

[32]  M. Gilardi,et al.  Magnetic resonance imaging biomarkers for the early diagnosis of Alzheimer's disease: a machine learning approach , 2015, Front. Neurosci..

[33]  Yoshua Bengio,et al.  Understanding the difficulty of training deep feedforward neural networks , 2010, AISTATS.

[34]  A M Dale,et al.  Measuring the thickness of the human cerebral cortex from magnetic resonance images. , 2000, Proceedings of the National Academy of Sciences of the United States of America.

[35]  Dong Yu,et al.  Deep Learning: Methods and Applications , 2014, Found. Trends Signal Process..

[36]  Jenny Benois-Pineau,et al.  Classification of sMRI for Alzheimer's disease Diagnosis with CNN: Single Siamese Networks with 2D+? Approach and Fusion on ADNI , 2017, ICMR.

[37]  Kanghan Oh,et al.  Classification and Visualization of Alzheimer’s Disease using Volumetric Convolutional Neural Network and Transfer Learning , 2019, Scientific Reports.

[38]  Mohamad Habes,et al.  A deep learning model for early prediction of Alzheimer's disease dementia based on hippocampal magnetic resonance imaging data , 2019, Alzheimer's & Dementia.

[39]  Shihui Ying,et al.  Multimodal Neuroimaging Feature Learning With Multimodal Stacked Deep Polynomial Networks for Diagnosis of Alzheimer's Disease , 2018, IEEE Journal of Biomedical and Health Informatics.

[40]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[41]  L. Arata,et al.  Destructive and optical non-destructive grape ripening assessment: Agronomic comparison and cost-benefit analysis , 2019, PloS one.

[42]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[43]  Pierrick Coupé,et al.  Patch-Based DTI Grading: Application to Alzheimer's Disease Classification , 2016, Patch-MI@MICCAI.

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

[45]  B. Seltzer,et al.  Conventional MRI volumetric measures of parietal and insular cortex in Alzheimer's disease , 1996, Progress in Neuro-Psychopharmacology and Biological Psychiatry.

[46]  Kun Ho Lee,et al.  3D-Deep Learning Based Automatic Diagnosis of Alzheimer’s Disease with Joint MMSE Prediction Using Resting-State fMRI , 2019, Neuroinformatics.

[47]  Dinggang Shen,et al.  Deep ensemble learning of sparse regression models for brain disease diagnosis , 2017, Medical Image Anal..

[48]  Dinggang Shen,et al.  Hierarchical Fully Convolutional Network for Joint Atrophy Localization and Alzheimer's Disease Diagnosis Using Structural MRI , 2020, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[49]  Eva Petkova,et al.  Web-Based Supplementary Materials for “ On Distance-Based Permutation Tests for Between-Group Comparisons ” , 2009 .

[50]  Seong-Whan Lee,et al.  Latent feature representation with stacked auto-encoder for AD/MCI diagnosis , 2013, Brain Structure and Function.

[51]  Andrea Chincarini,et al.  Local MRI analysis approach in the diagnosis of early and prodromal Alzheimer's disease , 2011, NeuroImage.

[52]  B. Lamb,et al.  Inflammation as a central mechanism in Alzheimer's disease , 2018, Alzheimer's & dementia.

[53]  Ji Zhang,et al.  Does network topology influence systemic risk contribution? A perspective from the industry indices in Chinese stock market , 2017, PloS one.

[54]  Sidong Liu,et al.  Multimodal Neuroimaging Feature Learning for Multiclass Diagnosis of Alzheimer's Disease , 2015, IEEE Transactions on Biomedical Engineering.

[55]  E. Frankó,et al.  Evaluating Alzheimer’s Disease Progression Using Rate of Regional Hippocampal Atrophy , 2013, PloS one.

[56]  Andrés Ortiz,et al.  Ensembles of Deep Learning Architectures for the Early Diagnosis of the Alzheimer's Disease , 2016, Int. J. Neural Syst..

[57]  Teeratorn Kadeethum,et al.  Physics-informed neural networks for solving nonlinear diffusivity and Biot’s equations , 2020, PloS one.

[58]  K M Heilman,et al.  Atrophy of the hippocampus, parietal cortex, and insula in Alzheimer's disease: a volumetric magnetic resonance imaging study. , 1997, Neuropsychiatry, neuropsychology, and behavioral neurology.

[59]  Chunxiang Jiang,et al.  Prediction and classification of Alzheimer disease based on quantification of MRI deformation , 2017, PloS one.

[60]  Daniel Smutek,et al.  Patch-based classification of thyroid nodules in ultrasound images using direction independent features extracted by two-threshold binary decomposition , 2019, Comput. Medical Imaging Graph..

[61]  Raymond Chiong,et al.  Deep learning to detect Alzheimer's disease from neuroimaging: A systematic literature review , 2019, Comput. Methods Programs Biomed..

[62]  Ho Yub Jung,et al.  Ensembles of Patch-Based Classifiers for Diagnosis of Alzheimer Diseases , 2019, IEEE Access.

[63]  Mita Nasipuri,et al.  Patch-based system for Classification of Breast Histology images using deep learning , 2019, Comput. Medical Imaging Graph..

[64]  Kun Ho Lee,et al.  Evaluation of Functional Decline in Alzheimer’s Dementia Using 3D Deep Learning and Group ICA for rs-fMRI Measurements , 2019, Front. Aging Neurosci..

[65]  Mercedes Atienza,et al.  Atrophy of amygdala and abnormal memory-related alpha oscillations over posterior cingulate predict conversion to Alzheimer’s disease , 2016, Scientific Reports.

[66]  Vijaya B. Kolachalama,et al.  ENHANCING DEEP LEARNING MODEL PERFORMANCE FOR AD DIAGNOSIS USING ROI-BASED SELECTION , 2019, Alzheimer's & Dementia.

[67]  Jinhui Tang,et al.  Patch-Set-Based Representation for Alignment-Free Image Set Classification , 2016, IEEE Transactions on Circuits and Systems for Video Technology.