Combining Unsupervised and Supervised Deep Learning for Alzheimer's Disease Detection by Fractional Anisotropy Imaging

We propose a new approach for Alzheimer's disease (AD) detection using diffusion tensor imaging, specifically fractional anisotropy (FA) images, based on a combination of unsupervised and supervised deep learning techniques. Our method involves training a 3D convolutional autoencoder to learn low-dimensional representations of FA images in an unsupervised manner and using the learned representations to pre-train a supervised 3D convolutional classifier to predict the presence or absence of AD. Unsupervised pre-training can improve the classifier's performance, especially when difficult-to-collect labeled data are limited. We evaluate our approach on the OASIS-3 dataset and demonstrate promising performance.

[1]  Yazid Cherfa,et al.  Multi-modality MRI for Alzheimer's disease detection using deep learning. , 2022, Physical and engineering sciences in medicine.

[2]  Heta Acharya,et al.  Alzheimer Disease Classification Using Transfer Learning , 2021, 2021 5th International Conference on Computing Methodologies and Communication (ICCMC).

[3]  E. Lella,et al.  An Ensemble Learning Approach Based on Diffusion Tensor Imaging Measures for Alzheimer’s Disease Classification , 2021, Electronics.

[4]  Jian Shi,et al.  Differentiable Data Augmentation with Kornia , 2020, ArXiv.

[5]  Ananda S. Chowdhury,et al.  DTI based Alzheimer's disease classification with rank modulated fusion of CNNs and random forest , 2020, Expert Syst. Appl..

[6]  Gennaro Vessio,et al.  Ensembling complex network 'perspectives' for mild cognitive impairment detection with artificial neural networks , 2020, Pattern Recognit. Lett..

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

[8]  S. Ourselin,et al.  TorchIO: A Python library for efficient loading, preprocessing, augmentation and patch-based sampling of medical images in deep learning , 2020, Comput. Methods Programs Biomed..

[9]  S. Marino,et al.  Diffusion tensor imaging of white matter degeneration in early stage of Alzheimer's disease: a review , 2020, The International journal of neuroscience.

[10]  Ivanei E. Bramati,et al.  Fractional Anisotropy changes in Parahippocampal Cingulum due to Alzheimer’s Disease , 2020, Scientific Reports.

[11]  Ernesto Estrada,et al.  Communicability distance reveals hidden patterns of Alzheimer’s disease , 2020, bioRxiv.

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

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

[14]  Marcia Hon,et al.  Transfer Learning With Intelligent Training Data Selection for Prediction of Alzheimer’s Disease , 2019, IEEE Access.

[15]  Rachna Jain,et al.  Convolutional neural network based Alzheimer’s disease classification from magnetic resonance brain images , 2019, Cognitive Systems Research.

[16]  Daniel S. Marcus,et al.  OASIS-3: LONGITUDINAL NEUROIMAGING, CLINICAL, AND COGNITIVE DATASET FOR NORMAL AGING AND ALZHEIMER’S DISEASE , 2018, Alzheimer's & Dementia.

[17]  Yan Wang,et al.  A Novel Multimodal MRI Analysis for Alzheimer's Disease Based on Convolutional Neural Network , 2018, 2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[18]  Jenny Benois-Pineau,et al.  Classification of Alzheimer Disease on Imaging Modalities with Deep CNNs Using Cross-Modal Transfer Learning , 2018, 2018 IEEE 31st International Symposium on Computer-Based Medical Systems (CBMS).

[19]  Jenny Benois-Pineau,et al.  3D CNN-based classification using sMRI and MD-DTI images for Alzheimer disease studies , 2018, ArXiv.

[20]  Nicholay Topin,et al.  Super-Convergence: Very Fast Training of Residual Networks Using Large Learning Rates , 2017, ArXiv.

[21]  Ayman El-Baz,et al.  Alzheimer's Disease Diagnostics by a Deeply Supervised Adaptable 3D Convolutional Network , 2016, ArXiv.

[22]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[23]  Maxime Descoteaux,et al.  Dipy, a library for the analysis of diffusion MRI data , 2014, Front. Neuroinform..

[24]  Byungkyu Brian Park,et al.  Classification of diffusion tensor images for the early detection of Alzheimer's disease , 2013, Comput. Biol. Medicine.

[25]  C. Jack,et al.  Effectiveness of regional DTI measures in distinguishing Alzheimer's disease, MCI, and normal aging☆ , 2013, NeuroImage: Clinical.

[26]  M. Filippi,et al.  Robust Automated Detection of Microstructural White Matter Degeneration in Alzheimer’s Disease Using Machine Learning Classification of Multicenter DTI Data , 2013, PloS one.

[27]  Victor Alves,et al.  A hitchhiker's guide to diffusion tensor imaging , 2012, Front. Neurosci..

[28]  C. Sorg,et al.  Prediction of Alzheimer's disease using individual structural connectivity networks , 2012, Neurobiology of Aging.

[29]  Giuseppe Placidi,et al.  MRI: Essentials for Innovative Technologies , 2012 .

[30]  A. Alexander,et al.  Diffusion tensor imaging of the brain , 2007, Neurotherapeutics.

[31]  P. Lauterbur,et al.  Image Formation by Induced Local Interactions: Examples Employing Nuclear Magnetic Resonance , 1973, Nature.

[32]  M. G. Sumithra,et al.  DEMNET: A Deep Learning Model for Early Diagnosis of Alzheimer Diseases and Dementia From MR Images , 2021, IEEE Access.

[33]  Alzheimer's Disease Neuroimaging Initiative,et al.  CBIR system using Capsule Networks and 3D CNN for Alzheimer's disease diagnosis , 2019, Informatics in Medicine Unlocked.

[34]  D. Selkoe.  Alzheimer's disease. , 2011, Cold Spring Harbor perspectives in biology.