End-To-End Alzheimer’s Disease Diagnosis and Biomarker Identification

Abstract

As shown in computer vision, the power of deep learning lies in automatically learning relevant and powerful features for any perdition task, which is made possible through end-to-end architectures. However, deep learning approaches applied for classifying medical images do not adhere to this architecture as they rely on several pre-and post-processing steps. This shortcoming can be explained by the relatively small number of available labeled subjects, the high dimensionality of neuroimaging data, and difficulties in interpreting the results of deep learning methods. In this paper, we propose a simple 3D Convolutional Neural Networks and exploit its model parameters to tailor the end-to-end architecture for the diagnosis of Alzheimer's disease (AD). Our model can diagnose AD with an accuracy of 94.1% on the popular ADNI dataset using only MRI data, which outperforms the previous state-of-the-art. Based on the learned model, we identify the disease biomarkers, the results of which were in accordance with the literature. We further transfer the learned model to diagnose mild cognitive impairment (MCI), the prodromal stage of AD, which yield better results compared to other methods.

Forecasting the progression of Alzheimer's disease using neural networks and a novel preprocessing algorithm

“…For example, Esmaeilzadeh et al achieved an accuracy of 94.1% using 3D convolutional neural networks to diagnose AD on a dataset with 841 patients. [30] Similar results were obtained by Long et al, who used a support vector machine to diagnose AD based on an MRI scan dataset (n = 427 patients; mean best accuracy = 96.5%) [31] and Zhang et al, who used MRI scans, FDG-PET scans, and CSF biomarkers to diagnose AD (n = 202 patients; AD vs. NL accuracy = 93.2%, MCI vs. NL accuracy = 76.4%). [32] However, the focus of these earlier studies was to use current medical data to diagnose a patient's present cognitive state, in effect demonstrating that a computer can replicate a doctor's clinical decision-making.…”

“…Previous work published by others has shown that machine learning algorithms can accurately classify a patient's current cognitive state (normal, MCI, or dementia) using contemporaneous clinical data. [30][31][32] This project has extended this previous work by looking at how past and present clinical data can be used to predict a patient's future cognitive state and by developing machine learning models that can correlate clinical data obtained from patients at one time point with the progression of AD in the future. Several of the machine-learning models used in this project were effective at predicting the progression of AD, both in cognitively normal patients and patients suffering from MCI.…”

Confounder-Aware Visualization of ConvNets

“…The development of deep-learning technologies in medicine is advancing rapidly [1]. Leveraging labeled big data and enhanced computational power, deep convolutional neural networks have been applied in many neuroscience studies to accurately classify patients with brain diseases from normal controls based on their MR images [1,2]. State-of-the-art saliency visualization techniques are used to interpret the trained model and to visualize specific brain regions that significantly contribute to the classification [2].…”

Testing the Robustness of Attribution Methods for Convolutional Neural Networks in MRI-Based Alzheimer’s Disease Classification

“…Here, we occlude a volumetric patch which is shifted over the entire MRI volume. Although the occlusion method results commonly in much coarser heatmaps (depending on the size of the patch), we included this method because it has been used several times in MRI-based AD classification [7,8,9,12].…”