脉冲耦合神经网络的并行加速优化算法研究

并行编程技术可以有效提高算法的执行效率。文中分别利用CPU的单指令多数据流扩展指令集（Streaming SIMD Extensions,SSE）技术和多核并行编程技术,对脉冲耦合神经网络（Pulse Coupled Neural Network,PCNN）分割算法进行并行编程优化,以减少算法的运行时间。实验结果表明,SSE技术以及多核并行编程技术大大加快了PCNN分割算法的运行速度,有效提高了算法的执行效率,在一定程度上解决了该方法计算量大、耗时多的问题,具有应用于医学图像处理的潜在价值。     

Biotechnological applications of image analysis: present and future prospects.

The current and potential biotechnological applications of image analysis and image processing systems are reviewed. Image analysis systems have proven to be highly versatile and efficient tools for assisting academic biotechnological research. It is expected that image analysis systems will allow more rapid and accurate quantification of numerous biotechnological analyses. There is, therefore, much scope for the implementation of image analysis/processing systems in a large variety of industrial and clinical applications.     

Using MATLAB software with Tomcat server and Java platform for remote image analysis in pathology

Background

The Matlab software is a one of the most advanced development tool for application in engineering practice. From our point of view the most important is the image processing toolbox, offering many built-in functions, including mathematical morphology, and implementation of a many artificial neural networks as AI. It is very popular platform for creation of the specialized program for image analysis, also in pathology. Based on the latest version of Matlab Builder Java toolbox, it is possible to create the software, serving as a remote system for image analysis in pathology via internet communication. The internet platform can be realized based on Java Servlet Pages with Tomcat server as servlet container.

Methods

In presented software implementation we propose remote image analysis realized by Matlab algorithms. These algorithms can be compiled to executable jar file with the help of Matlab Builder Java toolbox. The Matlab function must be declared with the set of input data, output structure with numerical results and Matlab web figure. Any function prepared in that manner can be used as a Java function in Java Servlet Pages (JSP). The graphical user interface providing the input data and displaying the results (also in graphical form) must be implemented in JSP. Additionally the data storage to database can be implemented within algorithm written in Matlab with the help of Matlab Database Toolbox directly with the image processing. The complete JSP page can be run by Tomcat server.

Results

The proposed tool for remote image analysis was tested on the Computerized Analysis of Medical Images (CAMI) software developed by author. The user provides image and case information (diagnosis, staining, image parameter etc.). When analysis is initialized, input data with image are sent to servlet on Tomcat. When analysis is done, client obtains the graphical results as an image with marked recognized cells and also the quantitative output. Additionally, the results are stored in a server database. The internet platform was tested on PC Intel Core2 Duo T9600 2.8GHz 4GB RAM server with 768x576 pixel size, 1.28Mb tiff format images reffering to meningioma tumour (x400, Ki-67/MIB-1). The time consumption was as following: at analysis by CAMI, locally on a server – 3.5 seconds, at remote analysis – 26 seconds, from which 22 seconds were used for data transfer via internet connection. At jpg format image (102 Kb) the consumption time was reduced to 14 seconds.

Conclusions

The results have confirmed that designed remote platform can be useful for pathology image analysis. The time consumption is depended mainly on the image size and speed of the internet connections. The presented implementation can be used for many types of analysis at different staining, tissue, morphometry approaches, etc. The significant problem is the implementation of the JSP page in the multithread form, that can be used parallelly by many users. The presented platform for image analysis in pathology can be especially useful for small laboratory without its own image analysis system.

     

Raman ChemLighter: Fiber optic Raman probe imaging in combination with augmented chemical reality

Raman spectroscopy using fiber optic probe combines non‐contacted and label‐free molecular fingerprinting with high mechanical flexibility for biomedical, clinical and industrial applications. Inherently, fiber optic Raman probes provide information from a single point only, and the acquisition of images is not straightforward. For many applications, it is highly crucial to determine the molecular distribution and provide imaging information of the sample. Here, we propose an approach for Raman imaging using a handheld fiber optic probe, which is built around computer vision–based assessment of positional information and simultaneous acquisition of spectroscopic information. By combining this implementation with real‐time data processing and analysis, it is possible to create not only fiber‐based Raman imaging but also an augmented chemical reality image of the molecular distribution of the sample surface in real‐time. We experimentally demonstrated that using our approach, it is possible to determine and to distinguish borders of different bimolecular compounds in a short time. Because the method can be transferred to other optical probes and other spectroscopic techniques, it is expected that the implementation will have a large impact for clinical, biomedical and industrial applications.      

Self-Contained Induction of Neurons from Human Embryonic Stem Cells

Background

Neurons and glial cells can be efficiently induced from mouse embryonic stem (ES) cells in a conditioned medium collected from rat primary-cultured astrocytes (P-ACM). However, the use of rodent primary cells for clinical applications may be hampered by limited supply and risk of contamination with xeno-proteins.

Methodology/Principal Findings

We have developed an alternative method for unimpeded production of human neurons under xeno-free conditions. Initially, neural stem cells in sphere-like clusters were induced from human ES (hES) cells after being cultured in P-ACM under free-floating conditions. The resultant neural stem cells could circumferentially proliferate under subsequent adhesive culture, and selectively differentiate into neurons or astrocytes by changing the medium to P-ACM or G5, respectively. These hES cell-derived neurons and astrocytes could procure functions similar to those of primary cells. Interestingly, a conditioned medium obtained from the hES cell-derived astrocytes (ES-ACM) could successfully be used to substitute P-ACM for induction of neurons. Neurons made by this method could survive in mice brain after xeno-transplantation.

Conclusion/Significance

By inducing astrocytes from hES cells in a chemically defined medium, we could produce human neurons without the use of P-ACM. This self-serving method provides an unlimited source of human neural cells and may facilitate clinical applications of hES cells for neurological diseases.     

Correcting distortions in panoramic images using constructive neural networks

This paper presents a novel approach to the correction of panoramic (wide-angle) image distortions. Unlike traditional methods that separate the distortion of the panoramic image into radial and tangential components and then concentrate on the correction of one type of distortion at a time, the method presented in this paper uses an integrated approach that simultaneously corrects all non-linear distortions of the panoramic image. The system uses data obtained from carefully constructed calibration patterns to automatically build and train a constructive neural network of suitable complexity to approximate the characteristic distortion of the panoramic image. The trained neural network is then used to correct the distortions represented by the sample data. It is demonstrated that by applying the distortion correction method presented in this paper to panoramic images representing real world scenes, perspective-corrected views of the real world scene that are usable in a wide variety of applications can be generated.     

Noise-invariant Neurons in the Avian Auditory Cortex: Hearing the Song in Noise

Given the extraordinary ability of humans and animals to recognize communication signals over a background of noise, describing noise invariant neural responses is critical not only to pinpoint the brain regions that are mediating our robust perceptions but also to understand the neural computations that are performing these tasks and the underlying circuitry. Although invariant neural responses, such as rotation-invariant face cells, are well described in the visual system, high-level auditory neurons that can represent the same behaviorally relevant signal in a range of listening conditions have yet to be discovered. Here we found neurons in a secondary area of the avian auditory cortex that exhibit noise-invariant responses in the sense that they responded with similar spike patterns to song stimuli presented in silence and over a background of naturalistic noise. By characterizing the neurons'' tuning in terms of their responses to modulations in the temporal and spectral envelope of the sound, we then show that noise invariance is partly achieved by selectively responding to long sounds with sharp spectral structure. Finally, to demonstrate that such computations could explain noise invariance, we designed a biologically inspired noise-filtering algorithm that can be used to separate song or speech from noise. This novel noise-filtering method performs as well as other state-of-the-art de-noising algorithms and could be used in clinical or consumer oriented applications. Our biologically inspired model also shows how high-level noise-invariant responses could be created from neural responses typically found in primary auditory cortex.     

A computational neural model of orientation detection based on multiple guesses: comparison of geometrical and algebraic models

The implementation of Hubel-Wiesel hypothesis that orientation selectivity of a simple cell is based on ordered arrangement of its afferent cells has some difficulties. It requires the receptive fields (RFs) of those ganglion cells (GCs) and LGN cells to be similar in size and sub-structure and highly arranged in a perfect order. It also requires an adequate number of regularly distributed simple cells to match ubiquitous edges. However, the anatomical and electrophysiological evidence is not strong enough to support this geometry-based model. These strict regularities also make the model very uneconomical in both evolution and neural computation. We propose a new neural model based on an algebraic method to estimate orientations. This approach synthesizes the guesses made by multiple GCs or LGN cells and calculates local orientation information subject to a group of constraints. This algebraic model need not obey the constraints of Hubel-Wiesel hypothesis, and is easily implemented with a neural network. By using the idea of a satisfiability problem with constraints, we also prove that the precision and efficiency of this model are mathematically practicable. The proposed model makes clear several major questions which Hubel-Wiesel model does not account for. Image-rebuilding experiments are conducted to check whether this model misses any important boundary in the visual field because of the estimation strategy. This study is significant in terms of explaining the neural mechanism of orientation detection, and finding the circuit structure and computational route in neural networks. For engineering applications, our model can be used in orientation detection and as a simulation platform for cell-to-cell communications to develop bio-inspired eye chips.     

A general-purpose system for the rapid acquisition and computer processing of optical and scanning electron microscope images—II. Software

The design and implementation of software for the operation of a general-purpose optical and electron microscope image processing system is described. The software is a group of programs, controlled by a command-line interpreter called IPR (Image PRocessing). The interpreter may be used interactively, or groups of commands may be issued indirectly after placing them in files. Programs for specialized image processing applications may obtain the services of the system's memory-resident programs, through the same interprogram communication methods that are used by the command-line interpreter.     

A model for integrating elementary neural functions into delayed-response behavior

It is well established that various cortical regions can implement a wide array of neural processes, yet the mechanisms which integrate these processes into behavior-producing, brain-scale activity remain elusive. We propose that an important role in this respect might be played by executive structures controlling the traffic of information between the cortical regions involved. To illustrate this hypothesis, we present a neural network model comprising a set of interconnected structures harboring stimulus-related activity (visual representation, working memory, and planning), and a group of executive units with task-related activity patterns that manage the information flowing between them. The resulting dynamics allows the network to perform the dual task of either retaining an image during a delay (delayed-matching to sample task), or recalling from this image another one that has been associated with it during training (delayed-pair association task). The model reproduces behavioral and electrophysiological data gathered on the inferior temporal and prefrontal cortices of primates performing these same tasks. It also makes predictions on how neural activity coding for the recall of the image associated with the sample emerges and becomes prospective during the training phase. The network dynamics proves to be very stable against perturbations, and it exhibits signs of scale-invariant organization and cooperativity. The present network represents a possible neural implementation for active, top-down, prospective memory retrieval in primates. The model suggests that brain activity leading to performance of cognitive tasks might be organized in modular fashion, simple neural functions becoming integrated into more complex behavior by executive structures harbored in prefrontal cortex and/or basal ganglia.     

Oil cakes and their biotechnological applications--a review

Oil cakes have been in use for feed applications to poultry, fish and swine industry. Being rich in protein, some of these have also been considered ideal for food supplementation. However, with increasing emphasis on cost reduction of industrial processes and value addition to agro-industrial residues, oil cakes could be ideal source of proteinaceous nutrients and as support matrix for various biotechnological processes. Several oil cakes, in particular edible oil cakes offer potential benefits when utilized as substrate for bioprocesses. These have been utilized for fermentative production of enzymes, antibiotics, mushrooms, etc. Biotechnological applications of oil cakes also include their usages for vitamins and antioxidants production. This review discusses various applications of oil cakes in fermentation and biotechnological processes, their value addition by implementation in feed and energy source (for the production of biogas, bio-oil) as well.     

Object and scene analysis by saccadic eye-movements: an investigation with higher-order statistics

Based on an information theoretical approach, we investigate feature selection processes in saccadic object and scene analysis. Saccadic eye movements of human observers are recorded for a variety of natural and artificial test images. These experimental data are used for a statistical evaluation of the fixated image regions. Analysis of second-order statistics indicates that regions with higher spatial variance have a higher probability to be fixated, but no significant differences beyond these variance effects could be found at the level of power spectra. By contrast, an investigation with higher-order statistics, as reflected in the bispectral density, yielded clear structural differences between the image regions selected by saccadic eye movements as opposed to regions selected by a random process. These results indicate that nonredundant, intrinsically two-dimensional image features like curved lines and edges, occlusions, isolated spots, etc. play an important role in the saccadic selection process which must be integrated with top-down knowledge to fully predict object and scene analysis by human observers.     

Face recognition from a single image per person using deep architecture neural networks

Implementing an accurate face recognition system requires images in different variations, and if our database is large, we suffer from problems such as storing cost and low speed in recognition algorithms. On the other hand, in some applications there is only one image available per person for training recognition model. In this article, we propose a neural network model inspired of bidirectional analysis and synthesis brain network which can learn nonlinear mapping between image space and components space. Using a deep neural network model, we have tried to separate pose components from person ones. After setting apart these components, we can use them to synthesis virtual images of test data in different pose and lighting conditions. These virtual images are used to train neural network classifier. The results showed that training neural classifier with virtual images gives better performance than training classifier with frontal view images.     

High-resolution digital brain atlases: a Hubble telescope for the brain

We describe implementation of a method for digitizing at microscopic resolution brain tissue sections containing normal and experimental data and for making the content readily accessible online. Web-accessible brain atlases and virtual microscopes for online examination can be developed using existing computer and internet technologies. Resulting databases, made up of hierarchically organized, multiresolution images, enable rapid, seamless navigation through the vast image datasets generated by high-resolution scanning. Tools for visualization and annotation of virtual microscope slides enable remote and universal data sharing. Interactive visualization of a complete series of brain sections digitized at subneuronal levels of resolution offers fine grain and large-scale localization and quantification of many aspects of neural organization and structure. The method is straightforward and replicable; it can increase accessibility and facilitate sharing of neuroanatomical data. It provides an opportunity for capturing and preserving irreplaceable, archival neurohistological collections and making them available to all scientists in perpetuity, if resources could be obtained from hitherto uninterested agencies of scientific support.     

What electrical microstimulation has revealed about the neural basis of cognition

Neurophysiologists have shown repeatedly that neural activity in different brain structures can be correlated with specific perceptual and cognitive functions, but the causal efficacy of the observed activity has generally been a matter of conjecture. By contrast, electrical microstimulation, which allows the experimenter to manipulate the activity of small groups of neurons with spatial and temporal precision, can now be used to demonstrate causal links between neural activity and specific cognitive functions. Here, we review this growing literature, including applications to the study of attention, visual and somatosensory perception, 'read-out' mechanisms for interpreting sensory maps, and contextual effects on perception. We also discuss potential applications of microstimulation to studies of higher cognitive functions such as decision-making and subjective experience.     

Object-Oriented Design of QoS Multicast Communications

Multicast (group) communications have been widely recognized by current research and industry. Multicast is very useful for various network applications such as distributed (replicated) database, video/audio conference, information distribution and server locations, etc. But design and implementation of such multicast communication systems in networks are complicated tasks, especially when quality of services (QoS) of applications such as real-time and reliability are desired. To quick design and implement multicast communication, good tools are crucial and must be facilitated. This paper presents a novel object-oriented (O-O) QoS driven approach for the quick design and prototyping of multicast communication systems under certain QoS requirements for multicast message transmission and receptions such as real-time, total ordering, atomicity and fault-tolerance, etc.     

Automating chest radiograph imaging quality control

PurposeTo automate diagnostic chest radiograph imaging quality control (lung inclusion at all four edges, patient rotation, and correct inspiration) using convolutional neural network models.MethodsThe data comprised of 2589 postero-anterior chest radiographs imaged in a standing position, which were divided into train, validation, and test sets. We increased the number of images for the inclusion by cropping appropriate images, and for the inclusion and the rotation by flipping the images horizontally. The image histograms were equalized, and the images were resized to a 512 × 512 resolution. We trained six convolutional neural networks models to detect the image quality features using manual image annotations as training targets. Additionally, we studied the inter-observer variability of the image annotation.ResultsThe convolutional neural networks’ areas under the receiver operating characteristic curve were >0.88 for the inclusions, and >0.70 and >0.79 for the rotation and the inspiration, respectively. The inter-observer agreement between two human annotators for the assessed image-quality features were: 92%, 90%, 82%, and 88% for the inclusion at patient’s left, patient’s right, cranial, and caudal edges, and 78% and 89% for the rotation and inspiration, respectively. Higher inter-observer agreement was related to a smaller variance in the network confidence.ConclusionsThe developed models provide automated tools for the quality control in a radiological department. Additionally, the convolutional neural networks could be used to obtain immediate feedback of the chest radiograph image quality, which could serve as an educational instrument.     

Signal flow graphs and neural networks

The application of signal flow graphs to the learning process of neural networks is presented. By introducing the so-called adjoint graph, new insight into the mechanism of learning phenomena of the weights in neural networks has been obtained. The derived updating formulas are valid for both feedforward and recurrent neural networks and are especially useful from the hardware implementation point of view of the self-learning networks. The presented numerical experiments confirmed the usefulness of the presented approach. Received: 24 February 1993/Accepted in revised form: 28 July 1993     

Physical models of neural networks

The state of art in computer modelling of neural networks with associative memory is reviewed. The available experimental data are considered on learning and memory of small neural systems, on isolated synapses and on molecular level. Computer simulations demonstrate that realistic models of neural ensembles exhibit properties which can be interpreted as image recognition, categorization, learning, prototype forming, etc. A bilayer model of associative neural network is proposed. One layer corresponds to the short-term memory, the other one to the long-term memory. Patterns are stored in terms of the synaptic strength matrix. We have studied the relaxational dynamics of neurons firing and suppression within the short-term memory layer under the influence of the long-term memory layer. The interaction among the layers has found to create a number of novel stable states which are not the learning patterns. These synthetic patterns may consist of elements belonging to different non-intersecting learning patterns. Within the framework of a hypothesis of selective and definite coding of images in brain one can interpret the observed effect as the "idea? generating" process.     

On Optical Detection of Densely Labeled Synapses in Neuropil and Mapping Connectivity with Combinatorially Multiplexed Fluorescent Synaptic Markers

We propose a new method for mapping neural connectivity optically, by utilizing Cre/Lox system Brainbow to tag synapses of different neurons with random mixtures of different fluorophores, such as GFP, YFP, etc., and then detecting patterns of fluorophores at different synapses using light microscopy (LM). Such patterns will immediately report the pre- and post-synaptic cells at each synaptic connection, without tracing neural projections from individual synapses to corresponding cell bodies. We simulate fluorescence from a population of densely labeled synapses in a block of hippocampal neuropil, completely reconstructed from electron microscopy data, and show that high-end LM is able to detect such patterns with over 95% accuracy. We conclude, therefore, that with the described approach neural connectivity in macroscopically large neural circuits can be mapped with great accuracy, in scalable manner, using fast optical tools, and straightforward image processing. Relying on an electron microscopy dataset, we also derive and explicitly enumerate the conditions that should be met to allow synaptic connectivity studies with high-resolution optical tools.