Comparison and validation of tissue modelization and statistical classification methods in T1-weighted MR brain images.

This paper presents a validation study on statistical nonsupervised brain tissue classification techniques in magnetic resonance (MR) images. Several image models assuming different hypotheses regarding the intensity distribution model, the spatial model and the number of classes are assessed. The methods are tested on simulated data for which the classification ground truth is known. Different noise and intensity nonuniformities are added to simulate real imaging conditions. No enhancement of the image quality is considered either before or during the classification process. This way, the accuracy of the methods and their robustness against image artifacts are tested. Classification is also performed on real data where a quantitative validation compares the methods' results with an estimated ground truth from manual segmentations by experts. Validity of the various classification methods in the labeling of the image as well as in the tissue volume is estimated with different local and global measures. Results demonstrate that methods relying on both intensity and spatial information are more robust to noise and field inhomogeneities. We also demonstrate that partial volume is not perfectly modeled, even though methods that account for mixture classes outperform methods that only consider pure Gaussian classes. Finally, we show that simulated data results can also be extended to real data.

Approximate polytope ensemble for one-class classification

In this work, a new one-class classification ensemble strategy called approximate polytope ensemble is presented. The main contribution of the paper is threefold. First, the geometrical concept of convex hull is used to define the boundary of the target class defining the problem. Expansions and contractions of this geometrical structure are introduced in order to avoid over-fitting. Second, the decision whether a point belongs to the convex hull model in high dimensional spaces is approximated by means of random projections and an ensemble decision process. Finally, a tiling strategy is proposed in order to model non-convex structures. Experimental results show that the proposed strategy is significantly better than state of the art one-class classification methods on over 200 datasets.

The timing of exploratory decision-making revealed by single-trial topographic EEGanalyses.

Decision-making in an uncertain environment is driven by two major needs: exploring the environment to gather information or exploiting acquired knowledge to maximize reward. The neural processes underlying exploratory decision-making have been mainly studied by means of functional magnetic resonance imaging, overlooking any information about the time when decisions are made. Here, we carried out an electroencephalography (EEG) experiment, in order to detect the time when the brain generators responsible for these decisions have been sufficiently activated to lead to the next decision. Our analyses, based on a classification scheme, extract time-unlocked voltage topographies during reward presentation and use them to predict the type of decisions made on the subsequent trial. Classification accuracy, measured as the area under the Receiver Operator's Characteristic curve was on average 0.65 across 7 subjects. Classification accuracy was above chance levels already after 516 ms on average, across subjects. We speculate that decisions were already made before this critical period, as confirmed by a positive correlation with reaction times across subjects. On an individual subject basis, distributed source estimations were performed on the extracted topographies to statistically evaluate the neural correlates of decision-making. For trials leading to exploration, there was significantly higher activity in dorsolateral prefrontal cortex and the right supramarginal gyrus; areas responsible for modulating behavior under risk and deduction. No area was more active during exploitation. We show for the first time the temporal evolution of differential patterns of brain activation in an exploratory decision-making task on a single-trial basis.

Mixed spectral-structural classification of very high resolution images with summation kernels

In this paper, mixed spectral-structural kernel machines are proposed for the classification of very-high resolution images. The simultaneous use of multispectral and structural features (computed using morphological filters) allows a significant increase in classification accuracy of remote sensing images. Subsequently, weighted summation kernel support vector machines are proposed and applied in order to take into account the multiscale nature of the scene considered. Such classifiers use the Mercer property of kernel matrices to compute a new kernel matrix accounting simultaneously for two scale parameters. Tests on a Zurich QuickBird image show the relevance of the proposed method : using the mixed spectral-structural features, the classification accuracy increases of about 5%, achieving a Kappa index of 0.97. The multikernel approach proposed provide an overall accuracy of 98.90% with related Kappa index of 0.985.

Land use/cover classification in the Brazilian Amazon using satellite images

Land use/cover classification is one of the most important applications in remote sensing. However, mapping accurate land use/cover spatial distribution is a challenge, particularly in moist tropical regions, due to the complex biophysical environment and limitations of remote sensing data per se. This paper reviews experiments related to land use/cover classification in the Brazilian Amazon for a decade. Through comprehensive analysis of the classification results, it is concluded that spatial information inherent in remote sensing data plays an essential role in improving land use/cover classification. Incorporation of suitable textural images into multispectral bands and use of segmentation‑based method are valuable ways to improve land use/cover classification, especially for high spatial resolution images. Data fusion of multi‑resolution images within optical sensor data is vital for visual interpretation, but may not improve classification performance. In contrast, integration of optical and radar data did improve classification performance when the proper data fusion method was used. Among the classification algorithms available, the maximum likelihood classifier is still an important method for providing reasonably good accuracy, but nonparametric algorithms, such as classification tree analysis, have the potential to provide better results. However, they often require more time to achieve parametric optimization. Proper use of hierarchical‑based methods is fundamental for developing accurate land use/cover classification, mainly from historical remotely sensed data.

Spatial prediction of monthly wind speeds in complex terrain with adaptive general regression neural networks

This paper presents the general regression neural networks (GRNN) as a nonlinear regression method for the interpolation of monthly wind speeds in complex Alpine orography. GRNN is trained using data coming from Swiss meteorological networks to learn the statistical relationship between topographic features and wind speed. The terrain convexity, slope and exposure are considered by extracting features from the digital elevation model at different spatial scales using specialised convolution filters. A database of gridded monthly wind speeds is then constructed by applying GRNN in prediction mode during the period 1968-2008. This study demonstrates that using topographic features as inputs in GRNN significantly reduces cross-validation errors with respect to low-dimensional models integrating only geographical coordinates and terrain height for the interpolation of wind speed. The spatial predictability of wind speed is found to be lower in summer than in winter due to more complex and weaker wind-topography relationships. The relevance of these relationships is studied using an adaptive version of the GRNN algorithm which allows to select the useful terrain features by eliminating the noisy ones. This research provides a framework for extending the low-dimensional interpolation models to high-dimensional spaces by integrating additional features accounting for the topographic conditions at multiple spatial scales. Copyright (c) 2012 Royal Meteorological Society.

Contribution of neural networks to Alzheimer disease's progression.

The neuropathology of Alzheimer disease is characterized by senile plaques, neurofibrillary tangles and cell death. These hallmarks develop according to the differential vulnerability of brain networks, senile plaques accumulating preferentially in the associative cortical areas and neurofibrillary tangles in the entorhinal cortex and the hippocampus. We suggest that the main aetiological hypotheses such as the beta-amyloid cascade hypothesis or its variant, the synaptic beta-amyloid hypothesis, will have to consider neural networks not just as targets of degenerative processes but also as contributors of the disease's progression and of its phenotype. Three domains of research are highlighted in this review. First, the cerebral reserve and the redundancy of the network's elements are related to brain vulnerability. Indeed, an enriched environment appears to increase the cerebral reserve as well as the threshold of disease's onset. Second, disease's progression and memory performance cannot be explained by synaptic or neuronal loss only, but also by the presence of compensatory mechanisms, such as synaptic scaling, at the microcircuit level. Third, some phenotypes of Alzheimer disease, such as hallucinations, appear to be related to progressive dysfunction of neural networks as a result, for instance, of a decreased signal to noise ratio, involving a diminished activity of the cholinergic system. Overall, converging results from studies of biological as well as artificial neural networks lead to the conclusion that changes in neural networks contribute strongly to Alzheimer disease's progression.

Qualitative grading of severity of lumbar spinal stenosis based on the morphology of the dural sac on magnetic resonance images.

STUDY DESIGN.: Retrospective radiologic study on a prospective patient cohort. OBJECTIVE.: To devise a qualitative grading of lumbar spinal stenosis (LSS), study its reliability and clinical relevance. SUMMARY OF BACKGROUND DATA.: Radiologic stenosis is assessed commonly by measuring dural sac cross-sectional area (DSCA). Great variation is observed though in surfaces recorded between symptomatic and asymptomatic individuals. METHODS.: We describe a 7-grade classification based on the morphology of the dural sac as observed on T2 axial magnetic resonance images based on the rootlet/cerebrospinal fluid ratio. Grades A and B show cerebrospinal fluid presence while grades C and D show none at all. The grading was applied to magnetic resonance images of 95 subjects divided in 3 groups as follows: 37 symptomatic LSS surgically treated patients; 31 symptomatic LSS conservatively treated patients (average follow-up, 2.5 and 3.1 years); and 27 low back pain (LBP) sufferers. DSCA was also digitally measured. We studied intra- and interobserver reliability, distribution of grades, relation between morphologic grading and DSCA, as well relation between grades, DSCA, and Oswestry Disability Index. RESULTS.: Average intra- and interobserver agreement was substantial and moderate, respectively (k = 0.65 and 0.44), whereas they were substantial for physicians working in the study originating unit. Surgical patients had the smallest DSCA. A larger proportion of C and D grades was observed in the surgical group. Surface measurementsresulted in overdiagnosis of stenosis in 35 patients and under diagnosis in 12. No relation could be found between stenosis grade or DSCA and baseline Oswestry Disability Index or surgical result. C and D grade patients were more likely to fail conservative treatment, whereas grades A and B were less likely to warrant surgery. CONCLUSION.: The grading defines stenosis in different subjects than surface measurements alone. Since it mainly considers impingement of neural tissue it might be a more appropriate clinical and research tool as well as carrying a prognostic value.

Classification and fingerprinting of different berries based on biochemical profiling and antioxidant capacity

The objective of this work was to evaluate the biochemical composition of six berry types belonging to Fragaria, Rubus, Vaccinium and Ribes genus. Fruit samples were collected in triplicate (50 fruit each) from 18 different species or cultivars of the mentioned genera, during three years (2008 to 2010). Content of individual sugars, organic acids, flavonols, and phenolic acids were determined by high performance liquid chromatography (HPLC) analysis, while total phenolics (TPC) and total antioxidant capacity (TAC), by using spectrophotometry. Principal component analysis (PCA) and hierarchical cluster analysis (CA) were performed to evaluate the differences in fruit biochemical profile. The highest contents of bioactive components were found in Ribes nigrum and in Fragaria vesca, Rubus plicatus, and Vaccinium myrtillus. PCA and CA were able to partially discriminate between berries on the basis of their biochemical composition. Individual and total sugars, myricetin, ellagic acid, TPC and TAC showed the highest impact on biochemical composition of the berry fruits. CA separated blackberry, raspberry, and blueberry as isolate groups, while classification of strawberry, black and red currant in a specific group has not occurred. There is a large variability both between and within the different types of berries. Metabolite fingerprinting of the evaluated berries showed unique biochemical profiles and specific combination of bioactive compound contents.

Neural plasticity associated with recently versus often heard objects.

In natural settings the same sound source is often heard repeatedly, with variations in spectro-temporal and spatial characteristics. We investigated how such repetitions influence sound representations and in particular how auditory cortices keep track of recently vs. often heard objects. A set of 40 environmental sounds was presented twice, i.e. as prime and as repeat, while subjects categorized the corresponding sound sources as living vs. non-living. Electrical neuroimaging analyses were applied to auditory evoked potentials (AEPs) comparing primes vs. repeats (effect of presentation) and the four experimental sections. Dynamic analysis of distributed source estimations revealed i) a significant main effect of presentation within the left temporal convexity at 164-215ms post-stimulus onset; and ii) a significant main effect of section in the right temporo-parietal junction at 166-213ms. A 3-way repeated measures ANOVA (hemisphere×presentation×section) applied to neural activity of the above clusters during the common time window confirmed the specificity of the left hemisphere for the effect of presentation, but not that of the right hemisphere for the effect of section. In conclusion, spatio-temporal dynamics of neural activity encode the temporal history of exposure to sound objects. Rapidly occurring plastic changes within the semantic representations of the left hemisphere keep track of objects heard a few seconds before, independent of the more general sound exposure history. Progressively occurring and more long-lasting plastic changes occurring predominantly within right hemispheric networks, which are known to code for perceptual, semantic and spatial aspects of sound objects, keep track of multiple exposures.

Brain glucose sensing and neural regulation of insulin and glucagon secretion.

Glucose homeostasis requires the tight regulation of glucose utilization by liver, muscle and white or brown fat, and glucose production and release in the blood by liver. The major goal of maintaining glycemia at ∼ 5 mM is to ensure a sufficient flux of glucose to the brain, which depends mostly on this nutrient as a source of metabolic energy. This homeostatic process is controlled by hormones, mainly glucagon and insulin, and by autonomic nervous activities that control the metabolic state of liver, muscle and fat tissue but also the secretory activity of the endocrine pancreas. Activation or inhibition of the sympathetic or parasympathetic branches of the autonomic nervous systems are controlled by glucose-excited or glucose-inhibited neurons located at different anatomical sites, mainly in the brainstem and the hypothalamus. Activation of these neurons by hyper- or hypoglycemia represents a critical aspect of the control of glucose homeostasis, and loss of glucose sensing by these cells as well as by pancreatic β-cells is a hallmark of type 2 diabetes. In this article, aspects of the brain-endocrine pancreas axis are reviewed, highlighting the importance of central glucose sensing in the control of counterregulation to hypoglycemia but also mentioning the role of the neural control in β-cell mass and function. Overall, the conclusions of these studies is that impaired glucose homeostasis, such as associated with type 2 diabetes, but also defective counterregulation to hypoglycemia, may be caused by initial defects in glucose sensing.

Fuzzy Principal Components Analysis

Due to the large number of characteristics, there is a need to extract the most relevant characteristicsfrom the input data, so that the amount of information lost in this way is minimal, and the classification realized with the projected data set is relevant with respect to the original data. In order to achieve this feature extraction, different statistical techniques, as well as the principal components analysis (PCA) may be used. This thesis describes an extension of principal components analysis (PCA) allowing the extraction ofa finite number of relevant features from high-dimensional fuzzy data and noisy data. PCA finds linear combinations of the original measurement variables that describe the significant variation in the data. The comparisonof the two proposed methods was produced by using postoperative patient data. Experiment results demonstrate the ability of using the proposed two methods in complex data. Fuzzy PCA was used in the classificationproblem. The classification was applied by using the similarity classifier algorithm where total similarity measures weights are optimized with differential evolution algorithm. This thesis presents the comparison of the classification results based on the obtained data from the fuzzy PCA.

Forecasting tourism demand to Catalonia: neural networks vs. time series models

The increasing interest aroused by more advanced forecasting techniques, together with the requirement for more accurate forecasts of tourismdemand at the destination level due to the constant growth of world tourism, has lead us to evaluate the forecasting performance of neural modelling relative to that of time seriesmethods at a regional level. Seasonality and volatility are important features of tourism data, which makes it a particularly favourable context in which to compare the forecasting performance of linear models to that of nonlinear alternative approaches. Pre-processed official statistical data of overnight stays and tourist arrivals fromall the different countries of origin to Catalonia from 2001 to 2009 is used in the study. When comparing the forecasting accuracy of the different techniques for different time horizons, autoregressive integrated moving average models outperform self-exciting threshold autoregressions and artificial neural network models, especially for shorter horizons. These results suggest that the there is a trade-off between the degree of pre-processing and the accuracy of the forecasts obtained with neural networks, which are more suitable in the presence of nonlinearity in the data. In spite of the significant differences between countries, which can be explained by different patterns of consumer behaviour,we also find that forecasts of tourist arrivals aremore accurate than forecasts of overnight stays.

The neural basis for writing from dictation in the temporoparietal cortex.

Cortical electrical stimulation mapping was used to study neural substrates of the function of writing in the temporoparietal cortex. We identified the sites involved in oral language (sentence reading and naming) and writing from dictation, in order to spare these areas during removal of brain tumours in 30 patients (23 in the left, and 7 in the right hemisphere). Electrostimulation of the cortex impaired writing ability in 62 restricted cortical areas (.25 cm2). These were found in left temporoparietal lobes and were mostly located along the superior temporal gyrus (Brodmann's areas 22 and 42). Stimulation of right temporoparietal lobes in right-handed patients produced no writing impairments. However there was a high variability of location between individuals. Stimulation resulted in combined symptoms (affecting oral language and writing) in fourteen patients, whereas in eight other patients, stimulation-induced pure agraphia symptoms with no oral language disturbance in twelve of the identified areas. Each detected area affected writing in a different way. We detected the various different stages of the auditory-to-motor pathway of writing from dictation: either through comprehension of the dictated sentences (word deafness areas), lexico-semantic retrieval, or phonologic processing. In group analysis, barycentres of all different types of writing interferences reveal a hierarchical functional organization along the superior temporal gyrus from initial word recognition to lexico-semantic and phonologic processes along the ventral and the dorsal comprehension pathways, supporting the previously described auditory-to-motor process. The left posterior Sylvian region supports different aspects of writing function that are extremely specialized and localized, sometimes being segregated in a way that could account for the occurrence of pure agraphia that has long-been described in cases of damage to this region.