Analysis of structural brain MRI and multi-parameter classification for Alzheimer’s disease

Abstract

Incorporating with machine learning technology, neuroimaging markers which extracted from structural Magnetic Resonance Images (sMRI), can help distinguish Alzheimer's Disease (AD) patients from Healthy Controls (HC). In the present study, we aim to investigate differences in atrophic regions between HC and AD and apply machine learning methods to classify these two groups. T1-weighted sMRI scans of 158 patients with AD and 145 age-matched HC were acquired from the ADNI database. Five kinds of parameters (i.e. cortical thickness, surface area, gray matter volume, curvature and sulcal depth) were obtained through the preprocessing steps. The recursive feature elimination (RFE) method for support vector machine (SVM) and leave-one-out cross validation (LOOCV) were applied to determine the optimal feature dimensions. Each kind of parameter was trained by SVM algorithm to acquire a classifier, which was used to classify HC and AD ultimately. Moreover, the ROC curves were depicted for testing the classifiers' performance and the SVM classifiers of two-dimensional spaces took the top two important features as classification features for separating HC and AD to the maximum extent. The results showed that the decreased cortical thickness and gray matter volume dramatically exhibited the trend of atrophy. The key differences between AD and HC existed in the cortical thickness and gray matter volume of the entorhinal cortex and medial orbitofrontal cortex. In terms of classification results, an optimal accuracy of 90.76% was obtained via multi-parameter combination (i.e. cortical thickness, gray matter volume and surface area). Meanwhile, the receiver operating characteristic (ROC) curves and area under the curve (AUC) were also verified multi-parameter combination could reach a better classification performance (AUC=0.94) after the SVM-RFE method. The results could be well prove that multi-parameter combination could provide more useful classified features from multivariate anatomical structure than single parameter. In addition, as cortical thickness and multi-parameter combination contained more important classified information with fewer feature dimensions after feature selection, it could be optimum to separate HC from AD to take the top two important features of them to construct SVM classifiers in two-dimensional space. The proposed work is a promising approach suggesting an important role for machine-learning based diagnostic image analysis for clinical practice.

β‐amyloid and tau drive early Alzheimer’s disease decline while glucose hypometabolism drives late decline

“…Indeed, AD is characterized by impaired brain insulin signaling 55 . In line with this finding, type 2 diabetes mellitus, hyperlipidemia, obesity, and other metabolic diseases increase the risk of developing AD 12,39 . Indeed the metabolic abnormalities present in AD are often likened to a form of diabetes of the brain 56 .…”

“…Indeed, some research groups have demonstrated that the distribution of tau tangles 10 and hypometabolism (due to low glucose uptake) are more strongly correlated with cognitive performance than Aβ 11 . Moreover, brain atrophy is also suggested to be highly correlated with AD progression 12 . However, it remains unclear whether disturbances in each arm of the A/T/N framework contribute equally to the progression of AD symptoms or if these factors instead have varying impacts at different stages of AD progression.…”

Imaging biomarkers in neurodegeneration: current and future practices

“…With this increase of data, there has been a shift from the use of ML algorithms such as support vector machines (SVMs) and k nearest neighbours (KNN) to more DL-based studies, mostly convolutional neural networks (CNNS) [205,214,215]. Along with feature selection methods, these models combine different sMRI cortical and subcortical volumetric measures to identify disease subtypes [216]. Neural networks (NNs) based on sMRI and cognitive scores can predict the conversion of MCI to AD (cMCI) and distinguish between stable MCI and cMCI [214,217,218].…”

Comparison of Transfer Learning and Conventional Machine Learning Applied to Structural Brain MRI for the Early Diagnosis and Prognosis of Alzheimer's Disease

“…Many studies in literature evaluated the potential of conventional ML in automatically classifying AD vs. CN and MCIc vs. MCInc using only structural brain-MRI data [e.g., (11,12,33,(45)(46)(47)(48)(49)(50)(51)(52)(53)(54)(55)(56)(57)(58)], obtaining a classification performance higher than 0.80 With the purpose to compare deep/transfer learning and conventional ML methods on the same dataset of brain-MRI data, in the present study, we implemented and assessed different deep/transfer-learning methods for the automatic early diagnosis and prognosis of AD, including very popular pre-trained systems and training from scratch a new deep learning method. We then compared their performances with different conventional ML methods implemented and assessed for the same diagnostic and prognostic task.…”