Automatic classification of MR scans in Alzheimer’s disease

By Stefan Klöppel, Cynthia M. Stonnington, Carlton Chu, Bogdan Draganski, Rachael I. Scahill, Jonathan D. Rohrer, Nick C Fox, Clifford R. Jack Jr., John Ashburner, Richard S. J. Frackowiak. 2008

1,241 citations recorded by the source corpus.

To be diagnostically useful, structural MRI must reliably distinguish Alzheimer’s disease (AD) from normal aging in individual scans. Recent advances in statistical learning theory have led to the application of support vector machines to MRI for detection of a variety of disease states. The aims of this study were to assess how successfully support vector machines assigned individual diagnoses and to determine whether data-sets combined from multiple scanners and different centres could be used to obtain effective classification of scans. We used linear support vector machines to classify the grey matter segment of T1-weighted MR scans from pathologically proven AD patients and cognitively normal elderly individuals obtained from two centres with different scanning equipment. Because the clinical diagnosis of mild AD is difficult we also tested the ability of support vector machines to differentiate control scans from patients without post-mortem confirmation. Finally we sought to use these methods to differentiate scans between patients suffering from AD from those with frontotemporal lobar degeneration. Up to 96% of pathologically verified AD patients were correctly classified using whole brain images. Data from different centres were successfully combined achieving comparable results from the separate analyses. Importantly, data from one centre could be used to train a support vector machine to accurately differentiate AD and normal ageing scans obtained from another centre with different subjects and different scanner equipment. Patients with mild, clinically probable AD and age/sex matched controls were correctly separated in 89% of cases which is compatible with published diagnosis rates in the best clinical centres. This method correctly assigned 89% of patients with post-mortem confirmed diagnosis of either AD or frontotemporal lobar degeneration to their respective group. Our study leads to three conclusions: Firstly, support vector machines successfully separate patients with AD from healthy aging subjects. Secondly, they perform well in the differential diagnosis of two different forms of dementia. Thirdly, the method is robust and can be generalized across different centres. This suggests an important role for computer based diagnostic image analysis for clinical practice.

Subfields: Neurology, Physiology, Psychiatry and Mental health

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Neurology

In Physiology

In Psychiatry and Mental health

Citations in the corpus

Visualizing Deep Neural Network Decisions: Prediction Difference Analysis (2017, methodology): “…medical image classiﬁcation speciﬁcally, a widely used method for visualizing feature importances is to simply plot the weights of a linear classiﬁer (Klöppel et al., 2008; Ecker et al., 2010), or the p-values of these weights (determined by permutation testing) (Mourao-Miranda et al., 2005;…”
Random Forest ensembles for detection and prediction of Alzheimer's disease with a good between-cohort robustness (2014, background): “A large number of studies addressing the use of pattern recognition methods in image-based detection of AD have been published in recent years (Gray et al., 2013; Liu et al., 2012; Cuingnet et al., 2011; Klöppel et al., 2008).”
Automated detection of brain atrophy patterns based on MRI for the prediction of Alzheimer's disease (2010, background): “The study of Kloeppel et al. (2008) demonstrated the potential of SVM classi ﬁ cation for the iden-ti ﬁ cation of AD in a multi-centre setting.”
Spatial regularization of SVM for the detection of diffusion alterations associated with stroke outcome (2011, methodology): “Theses approaches allow capturing complex multivariate relationships in the data and have been successfully applied to the individual classification of a variety of neurological conditions (Lao et al., 2004; Fan et al., 2007; Klöppel et al., 2008a; Vemuri et al., 2008).”
Imaging based enrichment criteria using deep learning algorithms for efficient clinical trials in MCI (2015, background): “Keywords: Clinical trials; Sample enrichment; Deep learning; Alzheimer’s disease”
Identifying major depression using whole-brain functional connectivity: a multivariate pattern analysis. (2012, background): “tural or functional brain images (Klöppel et al., 2008; Craddock et al., 2009; Desikan et al., 2009; Shen et al., 2010; Zhou et al., 2010a; Ardekani et al., 2011).”
Brain imaging in Alzheimer disease. (2012, background): “The overall pattern of atrophy is used in clinical practice and there is interest in automated pattern classification of MRI to predict AD at an early stage and to distinguish it from other dementias (Kloppel et al. 2008; Misra et al. 2009; Vemuri et al. 2009).”
Multi-Modal Neuroimaging Feature Learning for Multi-Class Diagnosis of Alzheimer’s Disease (2014, methodology): “As a result, although the diagnosis of AD should be naturally modeled as a multiclass classification problem, it was normally simplified as a set of binary classification tasks [23, 28] that distinguish AD or MCI subjects from NC subjects.”