Convolutional Neural Networks for Classification of Alzheimer's Disease: Overview and Reproducible Evaluation

Abstract

Over 30 papers have proposed to use convolutional neural network (CNN) for AD classification from anatomical MRI. However, the classification performance is difficult to compare across studies due to variations in components such as participant selection, image preprocessing or validation procedure. Moreover, these studies are hardly reproducible because their frameworks are not publicly accessible and because implementation details are lacking. Lastly, some of these papers may report a biased performance due to inadequate or unclear validation or model selection procedures. In the present work, we aim to address these limitations through three main contributions. First, we performed a systematic literature review and found that more than half of the surveyed papers may have suffered from data leakage. Our second contribution is the extension of our open-source framework for classification of AD using CNN and T1-weighted MRI. Finally, we used this framework to rigorously compare different CNN architectures. The data was split into training/validation/test sets at the very beginning and only the training/validation sets were used for model selection. To avoid any overfitting, the test sets were left untouched until the end of the peer-review process. Overall, the different 3D approaches (3D-subject, 3D-ROI, 3D-patch) achieved similar performances while that of the 2D slice approach was lower. Of note, the different CNN approaches did not perform better than a SVM with voxel-based features. The different approaches generalized well to similar populations but not to datasets with different inclusion criteria or demographical characteristics.

References in corpus (14)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Scikit-learn: Machine Learning in Python
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• The Effectiveness of Data Augmentation in Image Classification using Deep Learning
• An overview of deep learning in medical imaging focusing on MRI
• On Calibration of Modern Neural Networks
• NIPS 2016 Tutorial: Generative Adversarial Networks
• A guide to convolution arithmetic for deep learning
• OpenML: networked science in machine learning
• Disease Prediction using Graph Convolutional Networks: Application to Autism Spectrum Disorder and Alzheimer's Disease
• Deep convolutional neural networks for brain image analysis on magnetic resonance imaging: a review
• Alzheimer's Disease Diagnostics by Adaptation of 3D Convolutional Network
• Reproducible evaluation of classification methods in Alzheimer's disease: framework and application to MRI and PET data
• Clinica: an open source software platform for reproducible clinical neuroscience studies

Cited by in corpus (37)

• How I failed machine learning in medical imaging -- shortcomings and recommendations
• Data Augmentation in High Dimensional Low Sample Size Setting Using a Geometry-Based Variational Autoencoder
• A multi-stream convolutional neural network for classification of progressive MCI in Alzheimer's disease using structural MRI images
• Bias in Machine Learning Models Can Be Significantly Mitigated by Careful Training: Evidence from Neuroimaging Studies
• Promises and pitfalls of deep neural networks in neuroimaging-based psychiatric research
• Combining 3D Image and Tabular Data via the Dynamic Affine Feature Map Transform
• Biceph-Net: A robust and lightweight framework for the diagnosis of Alzheimer's disease using 2D-MRI scans and deep similarity learning
• HyperFusion: A Hypernetwork Approach to Multimodal Integration of Tabular and Medical Imaging Data for Predictive Modeling
• AI for the prediction of early stages of Alzheimer's disease from neuroimaging biomarkers -- A narrative review of a growing field
• Machine Learning Workflow to Explain Black-box Models for Early Alzheimer's Disease Classification Evaluated for Multiple Datasets
• Towards better Interpretable and Generalizable AD detection using Collective Artificial Intelligence
• Axial multi-layer perceptron architecture for automatic segmentation of choroid plexus in multiple sclerosis
• On the design of convolutional neural networks for automatic detection of Alzheimer's disease
• Identifying Alzheimer Disease Dementia Levels Using Machine Learning Methods
• Anatomical Foundation Models for Brain MRIs
• Evaluation of pseudo-healthy image reconstruction for anomaly detection with deep generative models: Application to brain FDG PET
• Improving 3D convolutional neural network comprehensibility via interactive visualization of relevance maps: Evaluation in Alzheimer's disease
• Efficient Feature Extraction Using Light-Weight CNN Attention-Based Deep Learning Architectures for Ultrasound Fetal Plane Classification
• Explainable concept mappings of MRI: Revealing the mechanisms underlying deep learning-based brain disease classification
• Multimodal Representations Learning and Adversarial Hypergraph Fusion for Early Alzheimer's Disease Prediction
• Automatic quality control of brain T1-weighted magnetic resonance images for a clinical data warehouse
• Predicting Parkinson's disease trajectory using clinical and functional MRI features: a reproduction and replication study
• Automatic quality control in multi-centric fetal brain MRI super-resolution reconstruction
• Introducing DEFORMISE: A deep learning framework for dementia diagnosis in the elderly using optimized MRI slice selection
• Deep Grading based on Collective Artificial Intelligence for AD Diagnosis and Prognosis
• Automatic rating of incomplete hippocampal inversions evaluated across multiple cohorts
• Visualization approach to assess the robustness of neural networks for medical image classification
• Conditional Alignment and Uniformity for Contrastive Learning with Continuous Proxy Labels
• Embracing the Disharmony in Medical Imaging: A Simple and Effective Framework for Domain Adaptation
• Emergence of Transfer Learning towards Specific Identification of Alzheimer's Disease A Prospective Approach
• Benchmarking CNN on 3D Anatomical Brain MRI: Architectures, Data Augmentation and Deep Ensemble Learning
• Harnessing spatial homogeneity of neuroimaging data: patch individual filter layers for CNNs
• Dimensional Neuroimaging Endophenotypes: Neurobiological Representations of Disease Heterogeneity Through Machine Learning
• Longitudinal Pooling & Consistency Regularization to Model Disease Progression from MRIs
• Alzheimer's Disease Diagnosis via Deep Factorization Machine Models
• Adapting Machine Learning Diagnostic Models to New Populations Using a Small Amount of Data: Results from Clinical Neuroscience
• Hierarchical Variable Importance with Statistical Control for Medical Data-Based Prediction