Search

In this study, an automated machine learning approach for the segmentation of MS lesions from multi- modal magnetic resonance images (mmMRI) is presented. The method is based on a U-Net like convolutional neural network (CNN) for 2D slice-based segmentation of 3D brain MRI volumes. The different modalities are encoded in sep- arate downsampling channels. The skip connections input feature maps to multi-scale feature fusion blocks at every stage of the network. These are followed by multi-scale feature upsampling blocks, which use the information from lesion shape and location. The CNN is evaluated on two publicly available datasets: The ISBI 2015 longitudinal MS lesion segmentation challenge dataset which contains 14 MS patients and the MICCAI 2016 MSSEG challenge dataset consisting of 15 MS patients. Regarding the ISBI Challenge, the proposed method was among the top performing ap- proaches to which open-access papers are available. The MICCAI dataset served to evaluate the robustness of the architecture against scanner variability and to show the improvements in performance after transfer learning.

Background Patients with advanced neuroendocrine tumors (NETs) of the midgut are suitable candidates for 177Lu-DOTATOC therapy. Integrated SPECT/CT systems have the potential to help improve the accuracy of patient-specific tumor dosimetry. Dose estimations to target organs are generally performed using the Medical Internal Radiation Dose scheme. We present a novel Monte Carlo-based voxel-wise dosimetry approach to determine organ- and tumor-specific total tumor doses (TTD). Methods A cohort of 14 patients with histologically confirmed metastasized NETs of the midgut (11 men, 3 women, 62.3 ± 11.0 years of age) underwent a total of 39 cycles of 177Lu-DOTATOC therapy (mean 2.8 cycles, SD ± 1 cycle). After the first cycle of therapy, regions of interest were defined manually on the SPECT/CT images for the kidneys, the spleen, and all 198 tracer-positive tumor lesions in the field of view. Four SPECT images, taken at 4 h, 24 h, 48 h and 72 h after injection of the radiopharmaceutical, were used to determine their effective half-lives in the structures of interest. The absorbed doses were calculated by a three-dimensional dosimetry method based on Monte Carlo simulations. TTD was calculated as the sum of all products of single tumor doses with single tumor volumes divided by the sum of all tumor volumes. Results The average dose values per cycle were 3.41 ± 1.28 Gy (1.91–6.22 Gy) for the kidneys, 4.40 ± 2.90 Gy (1.14–11.22 Gy) for the spleen, and 9.70 ± 8.96 Gy (1.47–39.49 Gy) for all 177Lu-DOTATOC-positive tumor lesions. Low- and intermediate-grade tumors (G 1–2) absorbed a higher TTD compared to high-grade tumors (G 3) (signed-rank test, p = p = 0.01). Higher TTD resulted in a significant decrease of CgA after therapy. Conclusion These results suggest that Monte Carlo-based voxel-wise dosimetry is a very promising tool for predicting the absorbed TTD based on histological and clinical parameters.

Human learning and intelligence work differently from the supervised pattern recognition approach adopted in most deep learning architectures. Humans seem to learn rich representations by exploration and imitation, build causal models of the world, and use both to flexibly solve new tasks. We suggest a simple but effective unsupervised model which develops such characteristics. The agent learns to represent the dynamical physical properties of its environment by intrinsically motivated exploration, and performs inference on this representation to reach goals. For this, a set of self-organizing maps which represent state-action pairs is combined with a causal model for sequence prediction. The proposed system is evaluated in the cartpole environment. After an initial phase of playful exploration, the agent can execute kinematic simulations of the environment's future, and use those for action planning. We demonstrate its performance on a set of several related, but different one-shot imitation tasks, which the agent flexibly solves in an active inference style., Comment: 27 pages, 5 figures

Background Ultrasound is the first-line imaging modality for detection and classification of thyroid nodules. Certain characteristics observable by ultrasound have recently been identified that may indicate malignancy. This retrospective cohort study was conducted to test the hypothesis that advanced thyroid carcinomas show distinctive clinical and sonographic characteristics. Using a neural network model as proof of concept, nine clinical/sonographic features served as input. Methods All 96 study enrollees had histologically confirmed thyroid carcinomas, categorized (n = 32, each) as follows: group 1, advanced carcinoma (ADV) marked by local invasion or distant metastasis; group 2, non-advanced papillary carcinoma (PTC); or group 3, non-advanced follicular carcinoma (FTC). Preoperative ultrasound profiles were obtained via standardized protocols. The neural network had nine input neurons and one hidden layer. Results Mean age and the number of male patients in group 1 were significantly higher compared with groups 2 (p = 0.005) or 3 (p p p ≤ 0.01). Network accuracy in discriminating advanced vs. non-advanced tumors was 84.4% (95% confidence interval [CI]: 75.5–91), with positive and negative predictive values of 87.1% (95% CI: 70.2–96.4) and 92.3% (95% CI: 83.0–97.5), respectively. Conclusions Our study has shown some evidence that advanced thyroid tumors demonstrate distinctive clinical and sonographic characteristics. Further prospective investigations with larger numbers of patients and multicenter design should be carried out to show whether a neural network incorporating these features may be an asset, helping to classify malignancies of the thyroid gland.

A central question in neuroscience is how self-organizing dynamic interactions in the brain emerge on their relatively static structural backbone. Due to the complexity of spatial and temporal dependencies between different brain areas, fully comprehending the interplay between structure and function is still challenging and an area of intense research. In this paper we present a graph neural network (GNN) framework, to describe functional interactions based on the structural anatomical layout. A GNN allows us to process graph-structured spatio-temporal signals, providing a possibility to combine structural information derived from diffusion tensor imaging (DTI) with temporal neural activity profiles, like that observed in functional magnetic resonance imaging (fMRI). Moreover, dynamic interactions between different brain regions discovered by this data-driven approach can provide a multi-modal measure of causal connectivity strength. We assess the proposed model’s accuracy by evaluating its capabilities to replicate empirically observed neural activation profiles, and compare the performance to those of a vector auto regression (VAR), like that typically used in Granger causality. We show that GNNs are able to capture long-term dependencies in data and also computationally scale up to the analysis of large-scale networks. Finally we confirm that features learned by a GNN can generalize across MRI scanner types and acquisition protocols, by demonstrating that the performance on small datasets can be improved by pre-training the GNN on data from an earlier study. We conclude that the proposed multi-modal GNN framework can provide a novel perspective on the structure-function relationship in the brain. Accordingly this approach appears to be promising for the characterization of the information flow in brain networks.

It is generally assumed that the analysis of intracranial pressure (ICP) waveforms could be used for the detection of multiple cerebral pathophysiologies. A main obstacle for the analysis of ICP waveforms is given by the large variation of their generating signal, the arterial blood pressure (ABP). Using extended principal component analysis (PCA) we show that it is possible to distinguish between ICP waveforms generated by pathological ABP waveforms, e.g. in the case of a heart failure, without loosing information about the state of the cerebral compliance. We also create a dataset for ICP pulse classification that can be used to train models to distinguish between an intact and diminished cerebral compliance, as a function of the ICP-generating ABP pulse. As a baseline for classification we build a fully convolutional network (FCN) that reaches high performance with relatively few data.

Process monitoring and optimization in an industrial setting is a complex topic, a large amount of data is captured and its measurements are affected by many complex relations. There is, therefore, a growing necessity for methods to reduce its complexity and dimension such that it can be interpreted by humans. In this work we study the extraction of interpretable rules derived from components of a non-negative matrix factorization using real data.

Designing a multi-layer optical system with designated optical characteristics is an inverse design problem in which the resulting design is determined by several discrete and continuous parameters. In particular, we consider three design parameters to describe a multi-layer stack: Each layer's dielectric material and thickness as well as the total number of layers. Such a combination of both, discrete and continuous parameters is a challenging optimization problem that often requires a computationally expensive search for an optimal system design. Hence, most methods merely determine the optimal thicknesses of the system's layers. To incorporate layer material and the total number of layers as well, we propose a method that considers the stacking of consecutive layers as parameterized actions in a Markov decision process. We propose an exponentially transformed reward signal that eases policy optimization and adapt a recent variant of Q-learning for inverse design optimization. We demonstrate that our method outperforms human experts and a naive reinforcement learning algorithm concerning the achieved optical characteristics. Moreover, the learned Q-values contain information about the optical properties of multi-layer optical systems, thereby allowing physical interpretation or what-if analysis., Presented as a poster at the workshop on machine learning for engineering modeling, simulation and design @ NeurIPS 2020

In radionuclide therapies, dosimetry is used for determining patient-individual dose burden. Standard approaches provide whole organ doses only. For assessing dose heterogeneity inside organs, voxel-wise dosimetry based on 3D SPECT/CT imaging could be applied. Often, this is achieved by convolving voxel-wise time-activity-curves with appropriate dose-voxel-kernels (DVK). The DVKs are meant to model dose deposition, and can be more accurate if modelled for the specific tissue type under consideration. In literature, DVKs are often not adapted to these inhomogeneities, or simple approximation schemes are applied. For 26 patients, which had previously undergone a -PSMA or -DOTATOC therapy, decay maps, mass-density maps as well as tissue-type maps were derived from SPECT/CT acquisitions. These were used for a voxel-based dosimetry based on convolution with DVKs (each of size ) obtained by four different DVK methods proposed in literature. The simplest only considers a spatially constant soft-tissue DVK (herein named ‘constant’), while others either take into account only the local density of the center voxel of the DVK (herein named ‘center-voxel’) or scale each voxel linearly according to the proper mass density deduced from the CT image (herein named ‘density’) or considered both the local mass density as well as the direct path between the center voxel and any voxel in its surrounding (herein named ‘percentage’). Deviations between resulting dose values and those from full Monte-Carlo simulations (MC simulations) were compared for selected organs and tissue-types. For each DVK method, inter-patient variability was considerable showing both under- and over-estimation of energy dose compared to the MC result for all tissue densities higher than soft tissue. In kidneys and spleen, ‘constant’ and ‘density’-scaled DVKs achieved estimated doses with smallest deviations to the full MC gold standard (∼ underestimation). For low and high density tissue types such as lung and adipose or bone tissue, alternative DVK methods like ‘center-voxel’- and ‘percentage’- scaled achieved superior results, respectively. Concerning computational load, dose estimation with the DVK method ‘constant’ needs about 1.1 s per patient, center-voxel scaling amounts to 1.2 s, density scaling needs 1.4 s while percentage scaling consumes 860.3 s per patient. In this study encompassing a large patient cohort and four different DVK estimation methods, no single DVK-adaption method was consistently better than any other in case of soft tissue kernels. Hence in such cases the simplest DVK method, labeled ‘constant’, suffices. In case of tumors, often located in tissues of low (lung) or high (bone) density, more sophisticated DVK methods excel. The high inter-patient variability indicates that for evaluating new algorithms, a sufficiently large patient cohort needs to be involved.

The thrombus causing a stroke can be seen on the susceptibility weighted angiography (SWAN) magnetic resonance imaging (MRI) sequence. But it is very small and hard to detect by humans. Up to date the thrombus is identified by trained human experts. But as stroke needs quick treatment, an automatic detection of the thrombus would be useful to speed up the diagnosis of acute stroke. We propose a method for automatic thrombus detection from SWAN using three separate U-Nets which work on the axial, coronal and sagittal planes.

In any radiotherapy, the absorbed dose needs to be estimated based on two factors, the time-integrated activity of the administered radiopharmaceutical and the patient-specific dose kernel. In this study, we consider the uncertainty with which such absorbed dose estimation can be achieved in a clinical environment. To calculate the total error of dose estimation we considered the following aspects: The error resulting from computing the time-integrated activity, the difference between the S-value and the patient specific full Monte Carlo simulation, the error from segmenting the volume-of-interest (kidney) and the intrinsic error of the activimeter. The total relative error in dose estimation can amount to 25.0% and is composed of the error of the time-integrated activity 17.1%, the error of the S-value 16.7%, the segmentation error 5.4% and the activimeter accuracy 5.0%. Errors from estimating the time-integrated activity and approximations applied to dose kernel computations contribute about equally and represent the dominant contributions far exceeding the contributions from VOI segmentation and activimeter accuracy.

We present a new method for decomposing two-dimensional data arrays with empirical mode decomposition (EMD). It performs envelope surface interpolation based on Green's functions in tension (GiT) to extract bi-dimensional intrinsic mode functions (BIMFs). The new method is called GiT-BEMD and outperforms existing bi-dimensional ensemble EMD (BEEMD) variants in terms of computational costs and quality of extracted intrinsic modes. More specifically, it is easy to implement, much faster than BEEMD, very robust and free from processing artifacts. GiT-BEMD is applied to fMRI data recorded during a contour integration task. Features extracted from resulting volume intrinsic mode functions (VIMFs) achieve higher classification accuracy compared to the canonical BEEMD. The new method thus provides a valuable alternative to existing mode decomposition methods for analyzing images.

A novel Score-based Physarum Learner algorithm for learning Bayesian Network structure from data is introduced and shown to outperform common score based structure learning algorithms for some benchmark data sets. The Score-based Physarum Learner first initializes a fully connected Physarum-Maze with random conductances. In each Physarum Solver iteration, the source and sink nodes are changed randomly, and the conductances are updated. Connections exceeding a predefined conductance threshold are considered as Bayesian Network edges, and the score of the connected nodes are examined in both directions. A positive or negative feedback is given to the edge conductance based on the calculated scores. Due to randomness in selecting connections for evaluation, an ensemble of Score-based Physarum Learner is used to build the final Bayesian Network structure.

In cognitive neuroscience, extracting characteristic textures and features from functional imaging modalities which could be useful in identifying particular cognitive states across different conditions is still an important field of study. This paper explores the potential of two-dimensional ensemble empirical mode decomposition (2DEEMD) to extract such textures, so-called bidimensional intrinsic mode functions (BIMFs), of functional biomedical images, especially functional magnetic resonance images (fMRI) taken while performing a contour integration task. To identify most informative textures, i.e. BIMFs, a support vector machine (SVM) as well as a random forest (RF) classifier is trained for two different stimulus/response conditions. Classification performance is used to estimate the discriminative power of extracted BIMFs. The latter are then analyzed according to their spatial distribution of brain activations related with contour integration. Results distinctly show the participation of frontal brain areas in contour integration. Employing features generated from textures represented by BIMFs exhibit superior classification performance when compared with a canonical general linear model (GLM) analysis employing statistical parametric mapping (SPM).

In this paper we propose a new method for volatile time series forecasting using Independent Component Analysis (ICA) algorithms and Savitzky-Golay filtering as preprocessing tools. The preprocessed data will be introduce in a based radial basis functions (RBF) Artificial Neural Network (ANN) and the prediction result will be compared with the one we get without these preprocessing tools or the classical Principal Component Analysis (PCA) tool.

In this work, a linear procedure to perform the intensity normalization of FP-CIT SPECT brain images is presented. This proposed methodology is based on the fact that the histogram of intensity values can be fitted accurately using a positive skewed α-stable distribution. Then, the predicted α-stable parameters and the location-scale property are used to linearly transform the intensity values in each voxel. This transformation is performed such that the new histograms in each image have a pre-specified α-stable distribution with desired location and dispersion values. The proposed methodology is compared with a similar approach assuming Gaussian distribution and the widely used specific-to-nonspecific ratio. In this work, we show that the linear normalization method using the α-stable distribution outperforms those existing methods.

Objective: This paper explores the importance of the latent symmetry of the brain in computer-aided systems for diagnosing Alzheimer's disease (AD). Symmetry and asymmetry are studied from two points of view: (i) the development of an effective classifier within the scope of machine learning techniques, and (ii) the assessment of its relevance to the AD diagnosis in the early stages of the disease. Methods: The proposed methodology is based on eigenimage decomposition of single-photon emission-computed tomography images, using an eigenspace extension to accommodate odd and even eigenvectors separately. This feature extraction technique allows for support-vector-machine classification and image analysis. Results: Identification of AD patterns is improved when the latent symmetry of the brain is considered, with an estimated 92.78% accuracy (92.86% sensitivity, 92.68% specificity) using a linear kernel and a leave-one-out cross validation strategy. Also, asymmetries may be used to define a test for AD that is very specific (90.24% specificity) but not especially sensitive. Conclusions: Two main conclusions are derived from the analysis of the eigenimage spectrum. Firstly, the recognition of AD patterns is improved when considering only the symmetric part of the spectrum. Secondly, asymmetries in the hypo-metabolic patterns, when present, are more pronounced in subjects with AD.

The analysis of nonlinear and nonstationary time series is still a challenge, as most classical time series analysis techniques are restricted to data that is, at least, stationary. Empirical mode decomposition (EMD) in combination with a Hilbert spectral transform, together called Hilbert-Huang transform (HHT), alleviates this problem in a purely data-driven manner. EMD adaptively and locally decomposes such time series into a sum of oscillatory modes, called Intrinsic mode functions (IMF) and a nonstationary component called residuum. In this contribution, we propose an EMD-based method, called Sliding empirical mode decomposition (SEMD), which, with a reasonable computational effort, extends the application area of EMD to a true on-line analysis of time series comprising a huge amount of data if recorded with a high sampling rate. Using nonlinear and nonstationary toy data, we demonstrate the good performance of the proposed algorithm. We also show that the new method extracts component signals that fulfill all criteria of an IMF very well and that it exhibits excellent reconstruction quality. The method itself will be refined further by a weighted version, called weighted sliding empirical mode decomposition (wSEMD), which reduces the computational effort even more while preserving the reconstruction quality.

In this work we present a new method to reduce artifacts, produced by high-density objects, especially metal implants, in X-ray cone beam computed tomography (CBCT). These artifacts influence clinical diagnostics and treatments using CT data, if metal objects are located in the field of view (FOV). Our novel method reduces metal artifacts by virtually replacing the metal objects with tissue objects of the same shape. First, the considered objects must be segmented in the original 2D projection data as well as in a reconstructed 3D volume. The attenuation coefficients of the segmented voxels are replaced with adequate attenuation coefficients of tissue (or water), then the required parts of the volume are projected onto the segmented 2D pixels, to replace the original information. This corrected 2D data can then be reconstructed with reduced artifacts, i. e. all metal objects virtually vanished. After the reconstruction, the segmented 3D metal objects were re-inserted into the corrected 3D volume. Our method was developed for mobile C-arm CBCTs; as it is necessary that they are of low weight, the C-arm results in unpredictable distortion. This misalignment between the original 2D data and the forward projection of the reconstructed 3D volume must be adjusted before the correction of the segmented 2D pixels. We applied this technique to clinical data and will now present the results.

We propose a determinant criterion to constrain the solutions of non-negative matrix factorization problems and achieve unique and optimal solutions in a general setting, provided an exact solution exists. We demonstrate how optimal solutions are obtained by a heuristic named detNMF in an illustrative example and discuss the difference to sparsity constraints. Furthermore, an intuitive explanation of multi-layer techniques is discussed also.

In this work we present an approach to understand neuronal mechanisms underlying perceptual learning. Experimental results achieved with stimulus patterns of coherently moving dots are considered to build a simple neuronal model. The design of the model is made transparent and underlying behavioral assumptions made explicit. The key aspect of the suggested neuronal model is the learning algorithm used: We evaluated an implementation of Hebbian learning and are thus able to provide a straight-forward model capable to explain the neuronal dynamics underlying perceptual learning. Moreover, the simulation results suggest a very simple explanation for the aspect of "sub-threshold" learning (Watanabe et al. in Nature 413:844-884, 2001) as well as the relearning of motion discrimination after damage to primary visual cortex as recently reported (Huxlin et al. in J Neurosci 29:3981-3991, 2009) and at least indicate that perceptual learning might only occur when accompanied by conscious percepts.The online version of this article (doi:10.1007/s11571-010-9134-9) contains supplementary material, which is available to authorized users.

A novel method called binNMF is introduced which aimed to extract hidden information from multivariate binary data sets. The method treats the problem in the spirit of blind source separation: The data are assumed to be generated by a superposition of several simultaneously acting sources or elementary causes which are not observable directly. The superposition process is based on a minimum of assumptions and reversed to identify the underlying sources. The method is motivated, developed, and demonstrated in the context of binary wafer test data which evolve during microchip fabrication.

Kernel principal component analysis (KPCA) is widely used in classification, feature extraction and denoising applications. In the latter it is unavoidable to deal with the pre-image problem which constitutes the most complex step in the whole processing chain. One of the methods to tackle this problem is an iterative solution based on a fixed-point algorithm. An alternative strategy considers an algebraic approach that relies on the solution of an under-determined system of equations. In this work we present a method that uses this algebraic approach to estimate a good starting point to the fixed-point iteration. We will demonstrate that this hybrid solution for the pre-image shows better performance than the other two methods. Further we extend the applicability of KPCA to one-dimensional signals which occur in many signal processing applications. We show that artefact removal from such data can be treated on the same footing as denoising. We finally apply the algorithm to denoise the famous USPS data set and to extract EOG interferences from single channel EEG recordings.

Motivation: Modern machine learning methods based on matrix decomposition techniques, like independent component analysis (ICA) or non-negative matrix factorization (NMF), provide new and efficient analysis tools which are currently explored to analyze gene expression profiles. These exploratory feature extraction techniques yield expression modes (ICA) or metagenes (NMF). These extracted features are considered indicative of underlying regulatory processes. They can as well be applied to the classification of gene expression datasets by grouping samples into different categories for diagnostic purposes or group genes into functional categories for further investigation of related metabolic pathways and regulatory networks. Results: In this study we focus on unsupervised matrix factorization techniques and apply ICA and sparse NMF to microarray datasets. The latter monitor the gene expression levels of human peripheral blood cells during differentiation from monocytes to macrophages. We show that these tools are able to identify relevant signatures in the deduced component matrices and extract informative sets of marker genes from these gene expression profiles. The methods rely on the joint discriminative power of a set of marker genes rather than on single marker genes. With these sets of marker genes, corroborated by leave-one-out or random forest cross-validation, the datasets could easily be classified into related diagnostic categories. The latter correspond to either monocytes versus macrophages or healthy vs Niemann Pick C disease patients. Supplementary information: Supplementary data are available at Bioinformatics online. Contact: elmar.lang@biologie.uni-regensburg.de

In this paper we present denoising algorithms for enhancing noisy signals based on Local ICA (LICA), Delayed AMUSE (dAMUSE) and Kernel PCA (KPCA). The algorithm LICA relies on applying ICA locally to clusters of signals embedded in a high-dimensional feature space of delayed coordinates. The components resembling the signals can be detected by various criteria like estimators of kurtosis or the variance of autocorrelations depending on the statistical nature of the signal. The algorithm proposed can be applied favorably to the problem of denoising multi-dimensional data. Another projective subspace denoising method using delayed coordinates has been proposed recently with the algorithm dAMUSE. It combines the solution of blind source separation problems with denoising efforts in an elegant way and proofs to be very efficient and fast. Finally, KPCA represents a non-linear projective subspace method that is well suited for denoising also. Besides illustrative applications to toy examples and images, we provide an application of all algorithms considered to the analysis of protein NMR spectra.

In this work, we present a method to extract high-amplitude artefacts from single channel electroencephalogram (EEG) signals. The method is called local singular spectrum analysis (local SSA). It is based on a principal component analysis (PCA) applied to clusters of the multidimensional signals obtained after embedding the signals in their time-delayed coordinates. The decomposition of the multidimensional signals in each cluster is achieved by relating the largest eigenvalues with the large amplitude artefact component of the embedded signal. Then by reverting the clustering and embedding processes, the high-amplitude artefact can be extracted. Subtracting it from the original signal a corrected EEG signal results. The algorithm is applied to segments of real EEG recordings containing paroxysmal epileptiform activity contaminated by large EOG artefacts. We will show that the method can be applied also in parallel to correct all channels that present high-amplitude artefacts like ocular movement interferences or high-amplitude low frequency baseline drifts. The extracted artefacts as well as the corrected EEG will be presented.

In underdetermined blind source separation, more sources are to be extracted from less observed mixtures without knowing both sources and mixing matrix. k-means-style clustering algorithms are commonly used to do this algorithmically given sufficiently sparse sources, but in any case other than deterministic sources, this lacks theoretical justification. After establishing that mean-based algorithms converge to wrong solutions in practice, we propose a median-based clustering scheme. Theoretical justification as well as algorithmic realizations (both online and batch) are given and illustrated by some examples.

Multidimensional proton nuclear magnetic resonance spectra of biomolecules dissolved in aqueous solutions are usually contaminated by an intense water artifact. We discuss the application of a generalized eigenvalue decomposition (GEVD) method using a matrix pencil to solve the blind source separation (BSS) problem of removing the intense solvent peak and related artifacts. The method explores correlation matrices of the signals and their filtered versions in the frequency domain and implements a two-step algebraic procedure to solve the GEVD. Two-dimensional nuclear Overhauser enhancement spectroscopy (2D NOESY) of dissolved proteins is studied. Results are compared to those obtained with the SOBI [Belouchrani et al., IEEE Trans. Signal Process. 45(2) (1997) 434-444] algorithm which jointly diagonalizes several time-delayed correlation matrices and to those of the fastICA [Hyvarinen and Oja, Neural Comput. 9 (1996) 1483-1492] algorithm which exploits higher order statistical dependencies of random variables.

In this work a generalized version of AMUSE, called dAMUSE is proposed. The main modification consists in embedding the observed mixed signals in a high-dimensional feature space of delayed coordinates. With the embedded signals a matrix pencil is formed and its generalized eigendecomposition is computed similar to the algorithm AMUSE. We show that in this case the uncorrelated output signals are filtered versions of the unknown source signals. Further, denoising the data can be achieved conveniently in parallel with the signal separation. Numerical simulations using artificially mixed signals are presented to show the performance of the method. Further results of a heart rate variability (HRV) study are discussed showing that the output signals are related with LF (low frequency) and HF (high frequency) fluctuations. Finally, an application to separate artifacts from 2D NOESY NMR spectra and to denoise the reconstructed artefact-free spectra is presented also.

NMF is a blind source separation technique decomposing multivariate non-negative data sets into meaningful non-negative basis components and non-negative weights. There are still open problems to be solved: uniqueness and model order selection as well as developing efficient NMF algorithms for large scale problems. Addressing uniqueness issues, we propose a Bayesian optimality criterion (BOC) for NMF solutions which can be derived in the absence of prior knowledge. Furthermore, we present a new Variational Bayes NMF algorithm VBNMF which is a straight forward generalization of the canonical Lee–Seung method for the Euclidean NMF problem and demonstrate its ability to automatically detect the actual number of components in non-negative data.

A nonlinear, recurrent neural network model of the visual cortex is presented. Orientation maps emerge from adaptable afferent as well as plastic local intracortical circuits driven by random input stimuli. Lateral coupling structures self-organize into DOG profiles under the influence of pronounced emerging cortical activity blobs. The model’s simplified architecture and features are modeled to largely mimik neurobiological findings.

We present a simplified binocular neural network model of the primary visual cortex with separate ON/OFF-pathways and modifiable afferent as well as intracortical synaptic couplings. Random as well as natural image stimuli drive the weight adaptation which follows Hebbian learning rules stabilized with constant norm and constant sum constraints. The simulations consider the development of orientation and ocular dominance maps under different conditions concerning stimulus patterns and lateral couplings. With random input patterns realistic orientation maps with ± 1/2-vortices mostly develop and plastic lateral couplings self-organize into mexican hat type structures on average. Using natural greyscale images as input patterns, realistic orientation maps develop as well and the lateral coupling profiles of the cortical neurons represent the two point correlations of the input image used

To answer the question about the way our visual system processes images it has to work with every day, it is necessary to investigate the statistical structure of these pictures. For this purpose we investigated several ensembles of artificial and real-world greyscale images to find different invariance properties: translation invariance by determining an average pair-correlation function, scale invariance by investigating the power spectrum and the coarse graining of the images, and a new hierarchical invariance recently proposed [D. L. Ruderman, Network 5, 517 (1994)]. The results of our work indicated that the assumption of translational invariance can be taken for granted. Our results concerning the scale invariance are qualitatively the same as those found by Ruderman and others. The deviations of the distributions of the logarithmically transformed images from a Gaussian distribution cannot be seen as clearly as stated by Ruderman. This results from the fact that for a correct determination of the deviations the non-linear transformation must be considered. Depending on the preprocessing of the images the results concerning the hierarchical invariance differed widely. It seems that this new invariance can be confirmed only for logarithmically transformed images.

Biomedical signals are in general non-linear and non-stationary. empirical mode decomposition in conjunction with a Hilbert-Huang Transform provides a fully adaptive and data-driven technique to extract intrinsic mode functions. The latter represent a complete set of locally orthogonal basis functions to represent non-linear and non-stationary time series. Large scale biomedical time series necessitate an online analysis, which is presented in this contribution. It shortly reviews the technique of EMD and related algorithms, discusses the recently proposed weighted sliding EMD algorithm (wSEMD) and, additionally, proposes a more sophisticated implementation of the weighting process. As an application to biomedical signals we will show that wSEMD in combination with mutual information could be used to detect temporal correlations of arterial blood pressure and intracranial pressure monitored at a neurosurgical intensive care unit. We will demonstrate that the wSEMD technique renders itself much more flexible than the Fourier based method used in Faltermeier et al. (Acta Neurochir Suppl, 114, 35–38, 2012).

NMR spectroscopy in biology and medicine is generally performed in aqueous solutions, thus in 1 H NMR spectroscopy, the dominant signal often stems from the partly suppressed solvent and can be many orders of magnitude larger than the resonances of interest. Strong solvent signals lead to a disappearance of weak resonances of interest close to the solvent artifact and to base plane variations all over the spectrum. The AUREMOL-SSA/ALS approach for automated solvent artifact removal and baseline correction has been originally developed for multi-dimensional NMR spectroscopy. Here, we describe the necessary adaptations for an automated application to one-dimensional NMR spectra. Its core algorithm is still based on singular spectrum analysis (SSA) applied on time domain signals (FIDs) and it is still combined with an automated baseline correction (ALS) in the frequency domain. However, both steps (SSA and ALS) have been modified in order to achieve optimal results when dealing with one-dimensional spectra. The performance of the method has been tested on one-dimensional synthetic and experimental spectra including the back-calculated spectrum of HPr protein and an experimental spectrum of a human urine sample. The latter has been recorded with the typically used NOESY-type 1D pulse sequence including water pre-saturation. Furthermore, the fully automated AUREMOL-SSA/ALS procedure includes the managing of oversampled, digitally filtered and zero-filled data and the correction of the frequency domain phase shift caused by the group delay time shift from the digital finite response filtering.

The p-substituents of 2,6-dimethyl-N-(2,2,5,5-tetramethylcyclopentylidene)anilines are modified without interfering reactions at the CN double bond. The resultant series (5 – 8, 10 – 19) shows a strong (ca. —4.7 kcal/mol) steric acceleration of (E/Z) diastereotopomerization by front strain along the CN double bond but also the usual electronic substituent dependence, characterized by a Hammett sp– correlation (Q = +2.7). Conversely, the substituent constant for lithium at the p-position of 7 may be estimated. The volume of activation is 1.5(8) cm3 mol–1 for 5. The π donor quality of the imino group corresponds to ca. 55 (±8)% of Pπ character as evaluated by spectral (13C NMR of 5 and 13, IR of 13) and reactivity data (of 13).

Strong solvent signals lead to a disappearance of weak protein signals close to the solvent resonance frequency and to base plane variations all over the spectrum. AUREMOL-SSA provides an automated approach for solvent artifact removal from multidimensional NMR protein spectra. Its core algorithm is based on singular spectrum analysis (SSA) in the time domain and is combined with an automated base plane correction in the frequency domain. The performance of the method has been tested on synthetic and experimental spectra including two-dimensional NOESY and TOCSY spectra and a three-dimensional (1)H,(13)C-HCCH-TOCSY spectrum. It can also be applied to frequency domain spectra since an optional inverse Fourier transformation is included in the algorithm.

(E,Z) Equilibria, 15[1]. – Syntheses and Lability of the Configuration of 2-Iminoindan Derivatives with Front Strain Syntheses and properties are described for sterically shielded imines R2C = NR (3c, e, g–k), which are rather inert toward nucleophiles. Nucleophilic attack at the nitrogen atom of 3k is indicated by the formation of the azine 4. (E,Z) Configurational diastereotopomerization (anti/syn) is strongly dependent on N substituents [CH3, phenyl, 1-naphthyl, acetyl, Si(CH3)3, cyano, SC6H5, SOC6H5, SO2C6H5, and nitro]. It is accelerated by front strain along the CN bond in 3a–c, e, g, h, j, and k and provides an energetic basis (by ΔG≠ and ΔΔG≠ values) for the gauging of force-field parameters. This (E,Z) stereo-mutation is characterized by a vanishing solvent dependence and a positive volume of activation (+10.2 cm3 mol-1 for 3a). In contrast to other π acceptor substituents, the N-nitro group in 31 retards (E,Z) interconversion.

In this paper, we propose an embedding technique for univariate single-channel biomedical signals to apply projective subspace techniques. Biomedical signals are often recorded as 1-D time series; hence, they need to be transformed to multidimensional signal vectors for subspace techniques to be applicable. The transformation can be achieved by embedding an observed signal in its delayed coordinates. We propose the application of two nonlinear subspace techniques to embedded multidimensional signals and discuss their relation. The techniques consist of modified versions of singular-spectrum analysis (SSA) and kernel principal component analysis (KPCA). For illustrative purposes, both nonlinear subspace projection techniques are applied to an electroencephalogram (EEG) signal recorded in the frontal channel to extract its dominant electrooculogram (EOG) interference. Furthermore, to evaluate the performance of the algorithms, an experimental study with artificially mixed signals is presented and discussed.

In this paper a novel constrained-stability least-mean-squares (LMS) algorithm for filtering speech sounds is proposed in the adaptive noise cancellation (ANC) problem. It is based on the minimization of the squared Euclidean norm of the weight vector change under a stability constraint over the a posteriori estimation errors. To this purpose, the Lagrangian methodology has been used in order to propose a nonlinear adaptation in terms of the product of differential input and error. Convergence analysis is also studied in terms of the evolution of the natural modes to the optimal Wiener-Hopf solution so that the stability performance depends exclusively on the adaptation parameter mu and the eigenvalues of the difference matrix DeltaR(1). The algorithm shows superior performance over the referenced algorithms in the ANC problem of speech discontinuous transmission systems, which are characterized by rapid transitions of the desired signal. The experimental analysis carried out on the AURORA 3 speech databases provides an extensive performance evaluation together with an exhaustive comparison to the standard LMS algorithms, i.e., the normalized LMS (NLMS), and other recently reported LMS algorithms such as the modified NLMS, the error nonlinearity LMS, or the normalized data nonlinearity LMS adaptation.

The analysis of large-scale gene expression profiles is still a demanding and extensive task. Modern machine learning and data mining techniques developed in linear algebra, like Independent Component Analysis (ICA), become increasingly popular as appropriate tools for analyzing microarray data. We applied ICA to analyze kinetic gene expression profiles of human monocyte derived macrophages (MDM) from three different donors infected with Francisella tularensis holartica and compared them to more classical methods like hierarchical clustering. Results were compared using a pathway analysis tool, based on the Gene Ontology and the MeSH database. We could show that both methods lead to time-dependent gene regulatory patterns which fit well to known [email protected] induced immune responses. In comparison, the nonexclusive attribute of ICA results in a more detailed view and a higher resolution in time dependent behavior of the immune response genes. Additionally, we identified [email protected] as one of the main regulatory genes during response to F. tularensis infection.

NMR measurements of the spin-lattice relaxation rates of the 'H, 13C, and 14N nuclei and spin-echo self-diffusion coefficients are reported for tetrapentylammonium bromide in acetonitrile solutions Over a wide range of temperatures and concentrations. The results are discussed in terms of overall and segmental motions of the aliphatic chains of the organic ions. Order parameters characterizing the geometrical constraints upon local segmental motions are given also. Cationic self-diffusion coefficients are found to differ from those obtained with quasi-elastic neutron scattering techniques (QENS). The difference may be explained in terms of fast and slow modes contributing to the diffusion processes and their selective detection with QENS and NMR techniques.

Nonnegative Matrix Factorization (NMF) has proven to be a useful tool for the analysis of nonnegative multivariate data. However, it is known not to lead to unique results when applied to Blind Source Separation (BSS) problems. In this paper we present an extension of NMF capable of solving the BSS problem when the underlying sources are sufficiently sparse. In contrast to most well-established BSS methods, the devised algorithm is capable of solving the BSS problem in cases where the underlying sources are not independent or uncorrelated. As the proposed fitness function is discontinuous and possesses many local minima, we use a genetic algorithm for its minimization. Finally, we apply the devised algorithm to real world microarray data. Siemens AG, Corporate Technology, Munich - Biomarker DFG - GRK 638: Nonlinearity and Nonequilibrium in Condensed Matter DAAD-GRICES Acções Integradas Luso-Alemãs - GEVD-MP DAAD Acciones Integradas Hispano-Alemanas - Microarrays

Background The analysis of high-throughput gene expression data sets derived from microarray experiments still is a field of extensive investigation. Although new approaches and algorithms are published continuously, mostly conventional methods like hierarchical clustering algorithms or variance analysis tools are used. Here we take a closer look at independent component analysis (ICA) which is already discussed widely as a new analysis approach. However, deep exploration of its applicability and relevance to concrete biological problems is still missing. In this study, we investigate the relevance of ICA in gaining new insights into well characterized regulatory mechanisms of M-CSF dependent macrophage differentiation. Results Statistically independent gene expression modes (GEM) were extracted from observed gene expression signatures (GES) through ICA of different microarray experiments. From each GEM we deduced a group of genes, henceforth called sub-mode. These sub-modes were further analyzed with different database query and literature mining tools and then combined to form so called meta-modes. With them we performed a knowledge-based pathway analysis and reconstructed a well known signal cascade. Conclusion We show that ICA is an appropriate tool to uncover underlying biological mechanisms from microarray data. Most of the well known pathways of M-CSF dependent monocyte to macrophage differentiation can be identified by this unsupervised microarray data analysis. Moreover, recent research results like the involvement of proliferation associated cellular mechanisms during macrophage differentiation can be corroborated.

Medical image reconstruction from projections is computationally intensive task that demands solutions for reducing the processing delay in clinical diagnosis applications. This paper analyzes reconstruction methods combined with pre- and post-filtering for Single Photon Emission Computed Tomography (SPECT) in terms of convergence speed and image quality. The evaluation is performed by means of an image database taken from a concurrent study investigating the use of SPECT as a diagnostic tool for the early onset of Alzheimer-type dementia. Filtered backprojection (FBP) methods combined with frequency sampling 2D pre- and post-filtering provides a good trade-off between image quality and delay. Maximum likelihood expectation maximization (ML-EM) improves the quality of the reconstructed image but with a considerable increase in processing delay. To overcome this problem the ordered subsets expectation maximization (OS-EM) method is found to be an effective algorithm for reducing the computational cost with an image quality similar to ML-EM.

The dynamic properties of water molecules coordinated to simple ions (alkali and alkali-earth halides) and hydrophobic ions (tetraalkylammonium (TAA) halides) in supercooled solutions have been investigated with NMR. The study of spin-lattice relaxation rates and self-diffusion coefficients as functions of temperature, pressure Larmor frequency and concentration reveals characteristic features of molecular motions close to the low-temperature limit of the metastable phase (percolation transition and glass transition) and provides certain details of the local arrangement of water molecules in the coordination sphere of these ions. The intramolecular flexibility of the alkyl chains of the hydrated TAA cations has been investigated also. The dynamics of the methyl group reorientation provide a sensitive probe of structural differences in these solutions.