Nonnegative Canonical Polyadic Decomposition for Tissue-Type Differentiation in Gliomas.

Magnetic resonance spectroscopic imaging (MRSI) reveals chemical information that characterizes different tissue types in brain tumors. Blind source separation techniques are used to extract the tissue-specific profiles and their corresponding distribution from the MRSI data. We focus on automatic detection of the tumor, necrotic and normal brain tissue types by constructing a 3D MRSI tensor from in vivo 2D-MRSI data of individual glioma patients. Nonnegative canonical polyadic decomposition (NCPD) is applied to the MRSI tensor to differentiate various tissue types. An in vivo study shows that NCPD has better performance in identifying tumor and necrotic tissue type in glioma patients compared to previous matrix-based decompositions, such as nonnegative matrix factorization and hierarchical nonnegative matrix factorization.

Tensor based tumor tissue type differentiation using magnetic resonance spectroscopic imaging.

Magnetic resonance spectroscopic imaging (MRSI) has the potential to characterise different tissue types in brain tumors. Blind source separation techniques are used to extract the specific tissue profiles and their corresponding distribution from the MRSI data. A 3-dimensional MRSI tensor is constructed from in vivo 2D-MRSI data of individual tumor patients. Non-negative canonical polyadic decomposition (NCPD) with common factor in mode-1 and mode-2 and l(1) regularization on mode-3 is applied on the MRSI tensor to differentiate various tissue types. Initial in vivo study shows that NCPD has better performance in identifying tumor and necrotic tissue type in high grade glioma patients compared to previous matrix-based decompositions, such as non-negative matrix factorization and hierarchical non-negative matrix factorization.

A geometric Newton method for Oja's vector field.

Newton's method for solving the matrix equation F(X) identical to AX-XX(T) AX = 0 runs up against the fact that its zeros are not isolated. This is due to a symmetry of F by the action of the orthogonal group. We show how differential-geometric techniques can be exploited to remove this symmetry and obtain a "geometric" Newton algorithm that finds the zeros of F. The geometric Newton method does not suffer from the degeneracy issue that stands in the way of the original Newton method.

Canonical decomposition of ictal scalp EEG reliably detects the seizure onset zone.

Long-term electroencephalographic (EEG) recordings are important in the presurgical evaluation of refractory partial epilepsy for the delineation of the irritative and ictal onset zones. In this paper we introduce a new algorithm for an automatic, fast and objective localizing of the ictal onset zone in ictal EEG recordings. We extracted the potential distribution of the ictal activity from EEG using the higher order canonical decomposition method, also referred to as the CP model. The CP model decomposes in a unique way a higher order tensor in a minimal sum of rank-1 'atoms'. We showed that only one atom is related to the seizure activity. Simulation experiments demonstrated that the method correctly extracted the potential distribution of the ictal activity even with low signal-to-noise ratios. In 37 ictal EEGs, the CP method correctly localized the seizure onset zone in 34 (92%) and visual assessment in 21 cases (57%) (p=0.00024). The CP method is a fast method to delineate the ictal onset zone in ictal EEGs and is more sensitive than visual interpretation of the ictal EEGs.

Efficiently updating and tracking the dominant kernel principal components.

The dominant set of eigenvectors of the symmetrical kernel Gram matrix is used in many important kernel methods (like e.g. kernel Principal Component Analysis, feature approximation, denoising, compression, prediction) in the machine learning area. Yet in the case of dynamic and/or large-scale data, the batch calculation nature and computational demands of the eigenvector decomposition limit these methods in numerous applications. In this paper we present an efficient incremental approach for fast calculation of the dominant kernel eigenbasis, which allows us to track the kernel eigenspace dynamically. Experiments show that our updating scheme delivers a numerically stable and accurate approximation for eigenvalues and eigenvectors at every iteration in comparison to the batch algorithm.

Detection of fast neuronal signals in the motor cortex from functional near infrared spectroscopy measurements using independent component analysis.

Fast changes, in the range of milliseconds, in the optical properties of cerebral tissue are associated with brain activity and can be detected using non-invasive near-infrared spectroscopy (NIRS). These changes are assumed to be caused by changes in the light scattering properties of the neuronal tissue. The aim of this study was to develop highly sensitive data analysis algorithms to detect this fast signal, which is small compared with other physiological signals. A frequency-domain tissue oximeter, whose laser diodes were intensity modulated at 110 MHz, was used. The amplitude, mean intensity and phase of the modulated optical signal were measured at a sample rate of 96 Hz. The probe, consisting of four crossed source detector pairs was placed above the motor cortex, contralateral to the hand performing a tapping exercise consisting of alternating rest and tapping periods of 20 s each. An adaptive filter was used to remove the arterial pulsatility from the optical signals. Independent component analysis allowed further separation of a signal component containing the fast signal. In nine out of 14 subjects, a significant fast neuronal signal related to the finger tapping was found in the intensity signals. In the phase signals, indications of the fast signal were found in only two subjects.

Fetal electrocardiogram extraction by blind source subspace separation.

In this paper, we propose the emerging technique of independent component analysis, also known as blind source separation, as an interesting tool for the extraction of the antepartum fetal electrocardiogram from multilead cutaneous potential recordings. The technique is illustrated by means of a real-life example.