Automatic placement of outer volume suppression slices in MR spectroscopic imaging of the human brain.

Spatial suppression of peripheral regions (outer volume suppression) is used in MR spectroscopic imaging to reduce contamination from strong lipid and water signals. The manual placement of outer volume suppression slices requires significant operator interaction, which is time consuming and introduces variability in volume coverage. Placing a large number of outer volume saturation bands for volumetric MR spectroscopic imaging studies is particularly challenging and time consuming and becomes unmanageable as the number of suppression bands increases. In this study, a method is presented that automatically segments a high-resolution MR image in order to identify the peripheral lipid-containing regions. This method computes an optimized placement of suppression bands in three dimensions and is based on the maximization of a criterion function. This criterion function maximizes coverage of peripheral lipid-containing areas and minimizes suppression of cortical brain regions and regions outside of the head. Computer simulation demonstrates automatic placement of 16 suppression slices to form a convex hull that covers peripheral lipid-containing regions above the base of the brain. In vivo metabolite mapping obtained with short echo time proton-echo-planar spectroscopic imaging shows that the automatic method yields a placement of suppression slices that is very similar to that of a skilled human operator in terms of lipid suppression and usable brain voxels.

Multimodal and Multi-tissue Measures of Connectivity Revealed by Joint Independent Component Analysis.

The human brain functions as an efficient system where signals arising from gray matter are transported via white matter tracts to other regions of the brain to facilitate human behavior. However, with a few exceptions, functional and structural neuroimaging data are typically optimized to maximize the quantification of signals arising from a single source. For example, functional magnetic resonance imaging (FMRI) is typically used as an index of gray matter functioning whereas diffusion tensor imaging (DTI) is typically used to determine white matter properties. While it is likely that these signals arising from different tissue sources contain complementary information, the signal processing algorithms necessary for the fusion of neuroimaging data across imaging modalities are still in a nascent stage. In the current paper we present a data-driven method for combining measures of functional connectivity arising from gray matter sources (FMRI resting state data) with different measures of white matter connectivity (DTI). Specifically, a joint independent component analysis (J-ICA) was used to combine these measures of functional connectivity following intensive signal processing and feature extraction within each of the individual modalities. Our results indicate that one of the most predominantly used measures of functional connectivity (activity in the default mode network) is highly dependent on the integrity of white matter connections between the two hemispheres (corpus callosum) and within the cingulate bundles. Importantly, the discovery of this complex relationship of connectivity was entirely facilitated by the signal processing and fusion techniques presented herein and could not have been revealed through separate analyses of both data types as is typically performed in the majority of neuroimaging experiments. We conclude by discussing future applications of this technique to other areas of neuroimaging and examining potential limitations of the methods.

fMRI pattern classification using neuroanatomically constrained boosting.

Pattern classification in functional MRI (fMRI) is a novel methodology to automatically identify differences in distributed neural substrates resulting from cognitive tasks. Reliable pattern classification is challenging due to the high dimensionality of fMRI data, the small number of available data sets, interindividual differences, and dependence on the acquisition methodology. Thus, most previous fMRI classification methods were applied in individual subjects. In this study, we developed a novel approach to improve multiclass classification across groups of subjects, field strengths, and fMRI methods. Spatially normalized activation maps were segmented into functional areas using a neuroanatomical atlas and each map was classified separately using local classifiers. A single multiclass output was applied using a weighted aggregation of the classifier's outputs. An Adaboost technique was applied, modified to find the optimal aggregation of a set of spatially distributed classifiers. This Adaboost combined the region-specific classifiers to achieve improved classification accuracy with respect to conventional techniques. Multiclass classification accuracy was assessed in an fMRI group study with interleaved motor, visual, auditory, and cognitive task design. Data were acquired across 18 subjects at different field strengths (1.5 T, 4 T), with different pulse sequence parameters (voxel size and readout bandwidth). Misclassification rates of the boosted classifier were between 3.5% and 10%, whereas for the single classifier, these were between 15% and 23%, suggesting that the boosted classifier provides a better generalization ability together with better robustness. The high computational speed of boosting classification makes it attractive for real-time fMRI to facilitate online interpretation of dynamically changing activation patterns.

Boosted ARTMAP: modifications to fuzzy ARTMAP motivated by boosting theory.

In this paper, several modifications to the Fuzzy ARTMAP neural network architecture are proposed for conducting classification in complex, possibly noisy, environments. The goal of these modifications is to improve upon the generalization performance of Fuzzy ART-based neural networks, such as Fuzzy ARTMAP, in these situations. One of the major difficulties of employing Fuzzy ARTMAP on such learning problems involves over-fitting of the training data. Structural risk minimization is a machine-learning framework that addresses the issue of over-fitting by providing a backbone for analysis as well as an impetus for the design of better learning algorithms. The theory of structural risk minimization reveals a trade-off between training error and classifier complexity in reducing generalization error, which will be exploited in the learning algorithms proposed in this paper. Boosted ART extends Fuzzy ART by allowing the spatial extent of each cluster formed to be adjusted independently. Boosted ARTMAP generalizes upon Fuzzy ARTMAP by allowing non-zero training error in an effort to reduce the hypothesis complexity and hence improve overall generalization performance. Although Boosted ARTMAP is strictly speaking not a boosting algorithm, the changes it encompasses were motivated by the goals that one strives to achieve when employing boosting. Boosted ARTMAP is an on-line learner, it does not require excessive parameter tuning to operate, and it reduces precisely to Fuzzy ARTMAP for particular parameter values. Another architecture described in this paper is Structural Boosted ARTMAP, which uses both Boosted ART and Boosted ARTMAP to perform structural risk minimization learning. Structural Boosted ARTMAP will allow comparison of the capabilities of off-line versus on-line learning as well as empirical risk minimization versus structural risk minimization using Fuzzy ARTMAP-based neural network architectures. Both empirical and theoretical results are presented to enhance the understanding of these architectures.

A learning algorithm for applying synthesized stable dynamics to system identification.

In this paper the models discussed by Cohen are extended by introducing an input term. This allows the resulting models to be utilized for system identification tasks. This approach gives a direct way to encode qualitative information such as attractor dimension into the model. We prove that this model is stable in the sense that a bounded input leads to a bounded state when a minor restriction is imposed on the Lyapunov function. By employing this stability result, we are able to find a learning algorithm which guarantees convergence to a set of parameters for which the error between the model trajectories and the desired trajectories vanishes.

Order of Search in Fuzzy ART and Fuzzy ARTMAP: Effect of the Choice Parameter.

This paper focuses on two ART architectures, the Fuzzy ART and the Fuzzy ARTMAP. Fuzzy ART is a pattern clustering machine, while Fuzzy ARTMAP is a pattern classification machine. Our study concentrates on the order according to which categories in Fuzzy ART, or the ART(a) model of Fuzzy ARTMAP are chosen. Our work provides a geometrical, and clearer understanding of why, and in what order, these categories are chosen for various ranges of the choice parameter of the Fuzzy ART module. This understanding serves as a powerful tool in developing properties of learning pertaining to these neural network architectures; to strengthen this argument, it is worth mentioning that the order according to which categories are chosen in ART 1 and ARTMAP provided a valuable tool in proving important properties about these architectures. Copyright 1996 Elsevier Science Ltd.