Carlton Chu

Automatic classification of MR scans in Alzheimer's disease

To be diagnostically useful, structural MRI must reliably distinguish Alzheimers 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.

Decoding Neuronal Ensembles in the Human Hippocampus

Summary Background The hippocampus underpins our ability to navigate, to form and recollect memories, and to imagine future experiences. How activity across millions of hippocampal neurons supports these functions is a fundamental question in neuroscience, wherein the size, sparseness, and organization of the hippocampal neural code are debated. Results Here, by using multivariate pattern classification and high spatial resolution functional MRI, we decoded activity across the population of neurons in the human medial temporal lobe while participants navigated in a virtual reality environment. Remarkably, we could accurately predict the position of an individual within this environment solely from the pattern of activity in his hippocampus even when visual input and task were held constant. Moreover, we observed a dissociation between responses in the hippocampus and parahippocampal gyrus, suggesting that they play differing roles in navigation. Conclusions These results show that highly abstracted representations of space are expressed in the human hippocampus. Furthermore, our findings have implications for understanding the hippocampal population code and suggest that, contrary to current consensus, neuronal ensembles representing place memories must be large and have an anisotropic structure.

Bayesian decoding of brain images.

This paper introduces a multivariate Bayesian (MVB) scheme to decode or recognise brain states from neuroimages. It resolves the ill-posed many-to-one mapping, from voxel values or data features to a target variable, using a parametric empirical or hierarchical Bayesian model. This model is inverted using standard variational techniques, in this case expectation maximisation, to furnish the model evidence and the conditional density of the models parameters. This allows one to compare different models or hypotheses about the mapping from functional or structural anatomy to perceptual and behavioural consequences (or their deficits). We frame this approach in terms of decoding measured brain states to predict or classify outcomes using the rhetoric established in pattern classification of neuroimaging data. However, the aim of MVB is not to predict (because the outcomes are known) but to enable inference on different models of structure-function mappings; such as distributed and sparse representations. This allows one to optimise the model itself and produce predictions that outperform standard pattern classification approaches, like support vector machines. Technically, the model inversion and inference uses the same empirical Bayesian procedures developed for ill-posed inverse problems (e.g., source reconstruction in EEG). However, the MVB scheme used here extends this approach to include a greedy search for sparse solutions. It reduces the problem to the same form used in Gaussian process modelling, which affords a generic and efficient scheme for model optimisation and evaluating model evidence. We illustrate MVB using simulated and real data, with a special focus on model comparison; where models can differ in the form of the mapping (i.e., neuronal representation) within one region, or in the (combination of) regions per se.

Prognostic and Diagnostic Potential of the Structural Neuroanatomy of Depression

Background Depression is experienced as a persistent low mood or anhedonia accompanied by behavioural and cognitive disturbances which impair day to day functioning. However, the diagnosis is largely based on self-reported symptoms, and there are no neurobiological markers to guide the choice of treatment. In the present study, we examined the prognostic and diagnostic potential of the structural neural correlates of depression. Methodology and Principal Findings Subjects were 37 patients with major depressive disorder (mean age 43.2 years), medication-free, in an acute depressive episode, and 37 healthy individuals. Following the MRI scan, 30 patients underwent treatment with the antidepressant medication fluoxetine or cognitive behavioural therapy (CBT). Of the patients who subsequently achieved clinical remission with antidepressant medication, the whole brain structural neuroanatomy predicted 88.9% of the clinical response, prior to the initiation of treatment (88.9% patients in clinical remission (sensitivity) and 88.9% patients with residual symptoms (specificity), p = 0.01). Accuracy of the structural neuroanatomy as a diagnostic marker though was 67.6% (64.9% patients (sensitivity) and 70.3% healthy individuals (specificity), p = 0.027). Conclusions and Significance The structural neuroanatomy of depression shows high predictive potential for clinical response to antidepressant medication, while its diagnostic potential is more limited. The present findings provide initial steps towards the development of neurobiological prognostic markers for depression.

Interpreting scan data acquired from multiple scanners: A study with Alzheimer's disease

Large, multi-site studies utilizing MRI-derived measures from multiple scanners present an opportunity to advance research by pooling data. On the other hand, it remains unclear whether or not the potential confound introduced by different scanners and upgrades will devalue the integrity of any results. Although there are studies of scanner differences for the purpose of calibration and quality control, the current literature is devoid of studies that describe the analysis of multi-scanner data with regard to the interaction of scanner(s) with effects of interest. We investigated a data-set of 136 subjects, 62 patients with mild to moderate Alzheimers disease and 74 cognitively normal elderly controls, with MRI scans from one center that were acquired over 10 years with 6 different scanners and multiple upgrades over time. We used a whole-brain voxel-wise analysis to evaluate the effect of scanner, effect of disease, and the interaction of scanner and disease for the 6 different scanners. The effect of disease in patients showed the expected significant reduction of grey matter in the medial temporal lobe. Scanner differences were substantially less than the group differences and only significant in the thalamus. There was no significant interaction of scanner with disease group. We describe the rationale for concluding that our results were not confounded by scanner differences. Similar analyses in other multi-scanner data-sets could be used to justify the pooling of data when needed, such as in studies of rare disorders or in multi-center designs.

Kernel regression for fMRI pattern prediction

This paper introduces two kernel-based regression schemes to decode or predict brain states from functional brain scans as part of the Pittsburgh Brain Activity Interpretation Competition (PBAIC) 2007, in which our team was awarded first place. Our procedure involved image realignment, spatial smoothing, detrending of low-frequency drifts, and application of multivariate linear and non-linear kernel regression methods: namely kernel ridge regression (KRR) and relevance vector regression (RVR). RVR is based on a Bayesian framework, which automatically determines a sparse solution through maximization of marginal likelihood. KRR is the dual-form formulation of ridge regression, which solves regression problems with high dimensional data in a computationally efficient way. Feature selection based on prior knowledge about human brain function was also used. Post-processing by constrained deconvolution and re-convolution was used to furnish the prediction. This paper also contains a detailed description of how prior knowledge was used to fine tune predictions of specific “feature ratings,” which we believe is one of the key factors in our prediction accuracy. The impact of pre-processing was also evaluated, demonstrating that different pre-processing may lead to significantly different accuracies. Although the original work was aimed at the PBAIC, many techniques described in this paper can be generally applied to any fMRI decoding works to increase the prediction accuracy.

Foraging under competition: the neural basis of input-matching in humans.

Input-matching is a key mechanism by which animals optimally distribute themselves across habitats to maximize net gains based on the changing input values of food supply rate and competition. To examine the neural systems that underlie this rule in humans, we created a continuous-input foraging task where subjects had to decide to stay or switch between two habitats presented on the left and right of the screen. The subjects decision to stay or switch was based on changing input values of reward-token supply rate and competition density. High density of competition or low-reward token rate was associated with decreased chance of winning. Therefore, subjects attempted to maximize their gains by switching to habitats that possessed low competition density and higher token rate. When it was increasingly disadvantageous to be in a habitat, we observed increased activity in brain regions that underlie preparatory motor actions, including the dorsal anterior cingulate cortex and the supplementary motor area, as well as the insula, which we speculate may be involved in the conscious urge to switch habitats. Conversely, being in an advantageous habitat is associated with activity in the reward systems, namely the striatum and medial prefrontal cortex. Moreover, amygdala and dorsal putamen activity steered interindividual preferences in competition avoidance and pursuing reward. Our results suggest that input-matching decisions are made as a net function of activity in a distributed set of neural systems. Furthermore, we speculate that switching behaviors are related to individual differences in competition avoidance and reward drive.

Utilizing temporal information in fMRI decoding: Classifier using kernel regression methods

This paper describes a general kernel regression approach to predict experimental conditions from activity patterns acquired with functional magnetic resonance image (fMRI). The standard approach is to use classifiers that predict conditions from activity patterns. Our approach involves training different regression machines for each experimental condition, so that a predicted temporal profile is computed for each condition. A decision function is then used to classify the responses from the testing volumes into the corresponding category, by comparing the predicted temporal profile elicited by each event, against a canonical hemodynamic response function. This approach utilizes the temporal information in the fMRI signal and maintains more training samples in order to improve the classification accuracy over an existing strategy. This paper also introduces efficient techniques of temporal compaction, which operate directly on kernel matrices for kernel classification algorithms such as the support vector machine (SVM). Temporal compacting can convert the kernel computed from each fMRI volume directly into the kernel computed from beta-maps, average of volumes or spatial-temporal kernel. The proposed method was applied to three different datasets. The first one is a block-design experiment with three conditions of image stimuli. The method outperformed the SVM classifiers of three different types of temporal compaction in single-subject leave-one-block-out cross-validation. Our method achieved 100% classification accuracy for six of the subjects and an average of 94% accuracy across all 16 subjects, exceeding the best SVM classification result, which was 83% accuracy (p=0.008). The second dataset is also a block-design experiment with two conditions of visual attention (left or right). Our method yielded 96% accuracy and SVM yielded 92% (p=0.005). The third dataset is from a fast event-related experiment with two categories of visual objects. Our method achieved 77% accuracy, compared with 72% using SVM (p=0.0006).

A plea for confidence intervals and consideration of generalizability in diagnostic studies

Sir, Many thanks for letting us respond to the interesting letter concerning our recent paper. We are grateful for the chance to clarify the points raised, which suggest our conclusions were too optimistic. In our paper (Kloppel et al. , 2008), we used MRI scans from pathologically proven cases of Alzheimers disease and frontotemporal lobar degeneration (FTLD) to validate trained sets for a machine learning-based support vector machine (SVM) approach to the categorization of structural scans from normal and each other. This rigorous approach substantially limited the number of available subjects, which we made perfectly clear in our article, but which was unavoidable given our novel approach. Frost and colleagues are right to point out that such low numbers result in larger confidence intervals than if we were able to include more scans. This is an object of our further empirical studies—what is the improvement in classification gained using this technique with greater numbers of scans in the trained set? The graph below (Fig. 1 …

Kernel methods for fMRI pattern prediction

In this paper, we present an effective computational approach for learning patterns of brain activity from the fMRI data. The procedure involved correcting motion artifacts, spatial smoothing, removing low frequency drifts and applying multivariate linear and non-linear kernel methods. Two novel techniques are applied: one utilizes the cosine transform to remove low-frequency drifts over time and the other involves using prior knowledge about the spatial contribution of different brain regions for the various tasks. Our experiment results on the PBAIC2007 competition data set show a great improvement for brain activity prediction, especially on some sensory experience such as hearing and vision.