Evaluation of texture features in hepatic tissue characterization from non-enhanced CT images

Aim of this paper is to evaluate the diagnostic contribution of various types of texture features in discrimination of hepatic tissue in abdominal non-enhanced Computed Tomography (CT) images. Regions of Interest (ROIs) corresponding to the classes: normal liver, cyst, hemangioma, and hepatocellular carcinoma were drawn by an experienced radiologist. For each ROI, five distinct sets of texture features are extracted using First Order Statistics (FOS), Spatial Gray Level Dependence Matrix (SGLDM), Gray Level Difference Method (GLDM), Laws' Texture Energy Measures (TEM), and Fractal Dimension Measurements (FDM). In order to evaluate the ability of the texture features to discriminate the various types of hepatic tissue, each set of texture features, or its reduced version after genetic algorithm based feature selection, was fed to a feed-forward Neural Network (NN) classifier. For each NN, the area under Receiver Operating Characteristic (ROC) curves (Az) was calculated for all one-vs-all discriminations of hepatic tissue. Additionally, the total Az for the multi-class discrimination task was estimated. The results show that features derived from FOS perform better than other texture features (total Az: 0.802+/-0.083) in the discrimination of hepatic tissue.

Computer-aided diagnosis of carotid atherosclerosis based on ultrasound image statistics, laws' texture and neural networks

Quantitative characterisation of carotid atherosclerosis and classification into symptomatic or asymptomatic is crucial in planning optimal treatment of atheromatous plaque. The computer-aided diagnosis (CAD) system described in this paper can analyse ultrasound (US) images of carotid artery and classify them into symptomatic or asymptomatic based on their echogenicity characteristics. The CAD system consists of three modules: a) the feature extraction module, where first-order statistical (FOS) features and Laws' texture energy can be estimated, b) the dimensionality reduction module, where the number of features can be reduced using analysis of variance (ANOVA), and c) the classifier module consisting of a neural network (NN) trained by a novel hybrid method based on genetic algorithms (GAs) along with the back propagation algorithm. The hybrid method is able to select the most robust features, to adjust automatically the NN architecture and to optimise the classification performance. The performance is measured by the accuracy, sensitivity, specificity and the area under the receiver-operating characteristic (ROC) curve. The CAD design and development is based on images from 54 symptomatic and 54 asymptomatic plaques. This study demonstrates the ability of a CAD system based on US image analysis and a hybrid trained NN to identify atheromatous plaques at high risk of stroke.

The Role of Consciousness in Memory

Conscious events interact with memory systems in learning, rehearsal and retrieval (Ebbinghaus 1885/1964; Tulving 1985). Here we present hypotheses that arise from the IDA computional model (Franklin, Kelemen and McCauley 1998; Franklin 2001b) of global workspace theory (Baars 1988, 2002). Our primary tool for this exploration is a flexible cognitive cycle employed by the IDA computational model and hypothesized to be a basic element of human cognitive processing. Since cognitive cycles are hypothesized to occur five to ten times a second and include interaction between conscious contents and several of the memory systems, they provide the means for an exceptionally fine-grained analysis of various cognitive tasks. We apply this tool to the small effect size of subliminal learning compared to supraliminal learning, to process dissociation, to implicit learning, to recognition vs. recall, and to the availability heuristic in recall. The IDA model elucidates the role of consciousness in the updating of perceptual memory, transient episodic memory, and procedural memory. In most cases, memory is hypothesized to interact with conscious events for its normal functioning. The methodology of the paper is unusual in that the hypotheses and explanations presented are derived from an empirically based, but broad and qualitative computational model of human cognition.

Learning Paradigms Exemplified by Virtual Experiments with Honey Bees

Learning is based on rules that can be elucidated by behavioural experiments. This article focuses on virtual experiments, in which non-associative learning (habituation, sensitization) and principles of associative learning (contiguity, inhibitory learning, generalization, overshadowing, positive and negative patterning) can be examined using 'virtual' honey bees in PER (Proboscis Reaction Extension) conditioning experiments. Users can develop experimental designs, simulate and document the experiments and find explanations and suggestions for the analysis of the learning experiments. The virtual experiments are based on video sequences and data from actual learning experiments. The bees' responses are determined by probability-based learning profiles.

Effects of Supplementing High or Low Quality Forages with Corn or Corn Processing Co-Products Upon Digestibility of Dry Matter and Energy by Steers

A digestibility trial, utilizing eight crossbred steers weighing initially 741 lbs. was conducted in an 8 x 8 Latin square design. High-fiber corn by-products were compared with corn as energy sources when fed in mixed diets with either lowor high-quality forage. Ground, dry corn stover and ground alfalfa hay were both fed alone or with corn grain, dried corn gluten feed (CGF), and dried corn distillers grains plus solubles (DDG) in a 1:1 ratio (dry basis). Total tract dry matter digestibility (DMD) was increased for both forages when fed with concentrates. Total tract DMD was similar in stover-based and alfalfa-based diets fed with CGF and DDG. However, stover+corn was lower in DMD than either stover+CGF and stover+DDG. Conversely, alfalfa+corn was higher in DMD than alfalfa+CGF or alfalfa+DDG. Feeding stover with corn tended to decrease digestibility of neutral detergent fiber (NDF), while feeding stover with CGF or DDG increased NDFD. There was no effect upon NDF digestion of alfalfa-based diets when fed with any of the concentrates. Feeding either forage with a concentrate increased digestible energy (DE). Stover+CGF and stover+DDG were similar in DE and were both higher in DE than stover+corn. Alfalfa+DDG tended to be higher than alfalfa+CGF and was similar to alfalfa+corn in DE. Alfalfa+CGF was lower in DE compared with alfalfa+corn. Results are interpreted to indicate that stover is more susceptible to negative feed interactions caused by corn grain than is alfalfa. Additionally, highfiber corn co-products fed with stover resulted in a positive associative effect but essentially had no associative effect when fed with alfalfa.

A distributed, semiotic-inductive and human-Oriented approach to web-scale knowledge retrieval

Web-scale knowledge retrieval can be enabled by distributed information retrieval, clustering Web clients to a large-scale computing infrastructure for knowledge discovery from Web documents. Based on this infrastructure, we propose to apply semiotic (i.e., sub-syntactical) and inductive (i.e., probabilistic) methods for inferring concept associations in human knowledge. These associations can be combined to form a fuzzy (i.e.,gradual) semantic net representing a map of the knowledge in the Web. Thus, we propose to provide interactive visualizations of these cognitive concept maps to end users, who can browse and search the Web in a human-oriented, visual, and associative interface.

Acquiring synaesthesia: insights from training studies

Synaesthesia denotes a condition of remarkable individual differences in experience characterized by specific additional experiences in response to normal sensory input. Synaesthesia seems to (i) run in families which suggests a genetic component, (ii) is associated with marked structural and functional neural differences, and (iii) is usually reported to exist from early childhood. Hence, synaesthesia is generally regarded as a congenital phenomenon. However, most synaesthetic experiences are triggered by cultural artifacts (e.g., letters, musical sounds). Evidence exists to suggest that synaesthetic experiences are triggered by the conceptual representation of their inducer stimuli. Cases were identified for which the specific synaesthetic associations are related to prior experiences and large scale studies show that grapheme-color associations in synaesthesia are not completely random. Hence, a learning component is inherently involved in the development of specific synaesthetic associations. Researchers have hypothesized that associative learning is the critical mechanism. Recently, it has become of scientific and public interest if synaesthetic experiences may be acquired by means of associative training procedures and whether the gains of these trainings are associated with similar cognitive benefits as genuine synaesthetic experiences. In order to shed light on these issues and inform synaesthesia researchers and the general interested public alike, we provide a comprehensive literature review on developmental aspects of synaesthesia and specific training procedures in non-synaesthetes. Under the light of a clear working definition of synaesthesia, we come to the conclusion that synaesthesia can potentially be learned by the appropriate training.

Sparse representation based action and gesture recognition

In this paper we present a solution to the problem of action and gesture recognition using sparse representations. The dictionary is modelled as a simple concatenation of features computed for each action or gesture class from the training data, and test data is classified by finding sparse representation of the test video features over this dictionary. Our method does not impose any explicit training procedure on the dictionary. We experiment our model with two kinds of features, by projecting (i) Gait Energy Images (GEIs) and (ii) Motion-descriptors, to a lower dimension using Random projection. Experiments have shown 100% recognition rate on standard datasets and are compared to the results obtained with widely used SVM classifier.

In vitro analog of classical conditioning of feeding behavior in aplysia.

The feeding behavior of Aplysia californica can be classically conditioned using tactile stimulation of the lips as a conditioned stimulus (CS) and food as an unconditioned stimulus (US). Moreover, several neural correlates of classical conditioning have been identified. The present study extended previous work by developing an in vitro analog of classical conditioning and by investigating pairing-specific changes in neuronal and synaptic properties. The preparation consisted of the isolated cerebral and buccal ganglia. Electrical stimulation of a lip nerve (AT4) and a branch of the esophageal nerve (En2) served as the CS and US, respectively. Three protocols were used: paired, unpaired, and US alone. Only the paired protocol produced a significant increase in CS-evoked fictive feeding. At the cellular level, classical conditioning enhanced the magnitude of the CS-evoked synaptic input to pattern-initiating neuron B31/32. In addition, paired training enhanced both the magnitude of the CS-evoked synaptic input and the CS-evoked spike activity in command-like neuron CBI-2. The in vitro analog of classical conditioning reproduced all of the cellular changes that previously were identified following behavioral conditioning and has led to the identification of several new learning-related neural changes. In addition, the pairing-specific enhancement of the CS response in CBI-2 indicates that some aspects of associative plasticity may occur at the level of the cerebral sensory neurons.

Tracking the Flow of Information through the Hippocampal Formation in the Rat

The hippocampus receives input from upper levels of the association cortex and is implicated in many mnemonic processes, but the exact mechanisms by which it codes and stores information is an unresolved topic. This work examines the flow of information through the hippocampal formation while attempting to determine the computations that each of the hippocampal subfields performs in learning and memory. The formation, storage, and recall of hippocampal-dependent memories theoretically utilize an autoassociative attractor network that functions by implementing two competitive, yet complementary, processes. Pattern separation, hypothesized to occur in the dentate gyrus (DG), refers to the ability to decrease the similarity among incoming information by producing output patterns that overlap less than the inputs. In contrast, pattern completion, hypothesized to occur in the CA3 region, refers to the ability to reproduce a previously stored output pattern from a partial or degraded input pattern. Prior to addressing the functional role of the DG and CA3 subfields, the spatial firing properties of neurons in the dentate gyrus were examined. The principal cell of the dentate gyrus, the granule cell, has spatially selective place fields; however, the behavioral correlates of another excitatory cell, the mossy cell of the dentate polymorphic layer, are unknown. This report shows that putative mossy cells have spatially selective firing that consists of multiple fields similar to previously reported properties of granule cells. Other cells recorded from the DG had single place fields. Compared to cells with multiple fields, cells with single fields fired at a lower rate during sleep, were less likely to burst, and were more likely to be recorded simultaneously with a large population of neurons that were active during sleep and silent during behavior. These data suggest that single-field and multiple-field cells constitute at least two distinct cell classes in the DG. Based on these characteristics, we propose that putative mossy cells tend to fire in multiple, distinct locations in an environment, whereas putative granule cells tend to fire in single locations, similar to place fields of the CA1 and CA3 regions. Experimental evidence supporting the theories of pattern separation and pattern completion comes from both behavioral and electrophysiological tests. These studies specifically focused on the function of each subregion and made implicit assumptions about how environmental manipulations changed the representations encoded by the hippocampal inputs. However, the cell populations that provided these inputs were in most cases not directly examined. We conducted a series of studies to investigate the neural activity in the entorhinal cortex, dentate gyrus, and CA3 in the same experimental conditions, which allowed a direct comparison between the input and output representations. The results show that the dentate gyrus representation changes between the familiar and cue altered environments more than its input representations, whereas the CA3 representation changes less than its input representations. These findings are consistent with longstanding computational models proposing that (1) CA3 is an associative memory system performing pattern completion in order to recall previous memories from partial inputs, and (2) the dentate gyrus performs pattern separation to help store different memories in ways that reduce interference when the memories are subsequently recalled.

Molecular mechanisms underlying a cellular analog of operant reward learning.

Operant conditioning is a ubiquitous but mechanistically poorly understood form of associative learning in which an animal learns the consequences of its behavior. Using a single-cell analog of operant conditioning in neuron B51 of Aplysia, we examined second-messenger pathways engaged by activity and reward and how they may provide a biochemical association underlying operant learning. Conditioning was blocked by Rp-cAMP, a peptide inhibitor of PKA, a PKC inhibitor, and by expressing a dominant-negative isoform of Ca2+-dependent PKC (apl-I). Thus, both PKA and PKC were necessary for operant conditioning. Injection of cAMP into B51 mimicked the effects of operant conditioning. Activation of PKC also mimicked conditioning but was dependent on both cAMP and PKA, suggesting that PKC acted at some point upstream of PKA activation. Our results demonstrate how these molecules can interact to mediate operant conditioning in an individual neuron important for the expression of the conditioned behavior.

Characterization of the interactions between two sites of plasticity engaged during eyelid conditioning

Here, we investigate the involvement of two sites of plasticity in the learning and expression of a simple associative motor behavior—the classically conditioned eyelid response. While previous studies clearly demonstrate that lesions of the anterior interpositus nucleus of the cerebellum abolish learned responses and prevent subsequent learning, studies investigating the effects of lesions of the cerebellar cortex on learning and retention have produced discrepant results. We complement ablative lesion studies of the cortex with the use of reversible, pharmacological blockade of cerebellar cortical transmission to investigate the role of the cerebellar cortex in eyelid conditioning. We demonstrate that both pharmacological blockade as well as focused ablative lesions of the cortex abolish timed responses and unmask responses with a fixed, short latency that are not displayed by the intact animal. Pharmacological blockade of cerebellar cortex output at various stages of acquisition and extinction reveals appropriate, learning dependent changes in the amplitude and probability of short latency responses during training. Acquisition of both short latency as well as timed responses is prevented by ablative lesions of the anterior lobe of the cerebellar cortex. These convergent results from technically distinct methods of removing the influence of the cerebellar cortex from conditioned behavior are consistent with the proposal that (1) eyelid conditioning engages two cerebellar sites of plasticity-one in the cortex and one in the anterior interpositus nucleus, (2) plasticity in the cerebellar cortex is necessary for proper response timing, (3) plasticity in the nucleus mediates the short latency responses unmasked by lesions of the cerebellar cortex, and (4) cerebellar cortical output is necessary for the induction of plasticity in the nucleus. ^

A Food Recognition System for Diabetic Patients based on an Optimized Bag of Features Model

Computer vision-based food recognition could be used to estimate a meal's carbohydrate content for diabetic patients. This study proposes a methodology for automatic food recognition, based on the Bag of Features (BoF) model. An extensive technical investigation was conducted for the identification and optimization of the best performing components involved in the BoF architecture, as well as the estimation of the corresponding parameters. For the design and evaluation of the prototype system, a visual dataset with nearly 5,000 food images was created and organized into 11 classes. The optimized system computes dense local features, using the scale-invariant feature transform on the HSV color space, builds a visual dictionary of 10,000 visual words by using the hierarchical k-means clustering and finally classifies the food images with a linear support vector machine classifier. The system achieved classification accuracy of the order of 78%, thus proving the feasibility of the proposed approach in a very challenging image dataset.

Sparse computation for large-scale binary classification

Well-known data mining algorithms rely on inputs in the form of pairwise similarities between objects. For large datasets it is computationally impossible to perform all pairwise comparisons. We therefore propose a novel approach that uses approximate Principal Component Analysis to efficiently identify groups of similar objects. The effectiveness of the approach is demonstrated in the context of binary classification using the supervised normalized cut as a classifier. For large datasets from the UCI repository, the approach significantly improves run times with minimal loss in accuracy.

Automated counting of bacterial colony forming units on agar plates.

Manual counting of bacterial colony forming units (CFUs) on agar plates is laborious and error-prone. We therefore implemented a colony counting system with a novel segmentation algorithm to discriminate bacterial colonies from blood and other agar plates.A colony counter hardware was designed and a novel segmentation algorithm was written in MATLAB. In brief, pre-processing with Top-Hat-filtering to obtain a uniform background was followed by the segmentation step, during which the colony images were extracted from the blood agar and individual colonies were separated. A Bayes classifier was then applied to count the final number of bacterial colonies as some of the colonies could still be concatenated to form larger groups. To assess accuracy and performance of the colony counter, we tested automated colony counting of different agar plates with known CFU numbers of S. pneumoniae, P. aeruginosa and M. catarrhalis and showed excellent performance.