Enhancing communication in radiology using a hybrid computer-human based system.

INTRODUCTION: Communication and physician burn out are major issues within Radiology. This study is designed to determine the utilization and cost benefit of a hybrid computer/human communication tool to aid in relay of clinically important imaging findings. MATERIAL AND METHODS: Analysis of the total number of tickets, (requests for assistance) placed, the type of ticket and the turn-around time was performed. Cost analysis of a hybrid computer/human communication tool over a one-year period was based on human costs as a multiple of the time to close the ticket. Additionally, we surveyed a cohort of radiologists to determine their use of and satisfaction with this system. RESULTS: 14,911 tickets were placed in the 6-month period, of which 11,401 (76.4%) were requests to "Get the Referring clinician on the phone." The mean time to resolution (TTR) of these tickets was 35.3 (±17.4) minutes. Ninety percent (72/80) of radiologists reported being able to interpret a new imaging study instead of waiting to communicate results for the earlier study, compared to 50% previously. 87.5% of radiologists reported being able to read more cases after this system was introduced. The cost analysis showed a cost savings of up to $101.12 per ticket based on the length of time that the ticket took to close and the total number of placed tickets. CONCLUSIONS: A computer/human communication tool can be translated to significant time savings and potentially increasing productivity of radiologists. Additionally, the system may have a cost savings by freeing the radiologist from tracking down referring clinicians prior to communicating findings.

Complex Rotation Quantum Dynamic Neural Networks (CRQDNN) using Complex Quantum Neuron (CQN): Applications to time series prediction.

Quantum Neural Networks (QNN) models have attracted great attention since it innovates a new neural computing manner based on quantum entanglement. However, the existing QNN models are mainly based on the real quantum operations, and the potential of quantum entanglement is not fully exploited. In this paper, we proposes a novel quantum neuron model called Complex Quantum Neuron (CQN) that realizes a deep quantum entanglement. Also, a novel hybrid networks model Complex Rotation Quantum Dynamic Neural Networks (CRQDNN) is proposed based on Complex Quantum Neuron (CQN). CRQDNN is a three layer model with both CQN and classical neurons. An infinite impulse response (IIR) filter is embedded in the Networks model to enable the memory function to process time series inputs. The Levenberg-Marquardt (LM) algorithm is used for fast parameter learning. The networks model is developed to conduct time series predictions. Two application studies are done in this paper, including the chaotic time series prediction and electronic remaining useful life (RUL) prediction.

A Spiking Neural Simulator Integrating Event-Driven and Time-Driven Computation Schemes Using Parallel CPU-GPU Co-Processing: A Case Study.

Time-driven simulation methods in traditional CPU architectures perform well and precisely when simulating small-scale spiking neural networks. Nevertheless, they still have drawbacks when simulating large-scale systems. Conversely, event-driven simulation methods in CPUs and time-driven simulation methods in graphic processing units (GPUs) can outperform CPU time-driven methods under certain conditions. With this performance improvement in mind, we have developed an event-and-time-driven spiking neural network simulator suitable for a hybrid CPU-GPU platform. Our neural simulator is able to efficiently simulate bio-inspired spiking neural networks consisting of different neural models, which can be distributed heterogeneously in both small layers and large layers or subsystems. For the sake of efficiency, the low-activity parts of the neural network can be simulated in CPU using event-driven methods while the high-activity subsystems can be simulated in either CPU (a few neurons) or GPU (thousands or millions of neurons) using time-driven methods. In this brief, we have undertaken a comparative study of these different simulation methods. For benchmarking the different simulation methods and platforms, we have used a cerebellar-inspired neural-network model consisting of a very dense granular layer and a Purkinje layer with a smaller number of cells (according to biological ratios). Thus, this cerebellar-like network includes a dense diverging neural layer (increasing the dimensionality of its internal representation and sparse coding) and a converging neural layer (integration) similar to many other biologically inspired and also artificial neural networks.

Exponential passivity of memristive neural networks with time delays.

Memristive neural networks are studied across many fields of science. To uncover their structural design principles, the paper introduces a general class of memristive neural networks with time delays. Passivity analysis is conducted by constructing suitable Lyapunov functional. The analysis in the paper employs the results from the theories of nonsmooth analysis and linear matrix inequalities. A numerical example is provided to illustrate the effectiveness and less conservatism of the proposed results.

Computer-based assessment of student-constructed responses.

Student-constructed responses, such as essays, short-answer questions, and think-aloud protocols, provide a valuable opportunity to gauge student learning outcomes and comprehension strategies. However, given the challenges of grading student-constructed responses, instructors may be hesitant to use them. There have been major advances in the application of natural language processing of student-constructed responses. This literature review focuses on two dimensions that need to be considered when developing new systems. The first is type of response provided by the student-namely, meaning-making responses (e.g., think-aloud protocols, tutorial dialogue) and products of comprehension (e.g., essays, open-ended questions). The second corresponds to considerations of the type of natural language processing systems used and how they are applied to analyze the student responses. We argue that the appropriateness of the assessment protocols is, in part, constrained by the type of response and researchers should use hybrid systems that rely on multiple, convergent natural language algorithms.

Experimental validation of a hybrid computational model for selective stimulation using transverse intrafascicular multichannel electrodes.

Recently a hybrid model based on the finite element method and on a compartmental biophysical representation of peripheral nerve fibers and intraneural electrodes was developed founded on experimental physiological and histological data. The model appeared to be robust when dealing with uncertainties in parameter selection. However, an experimental validation of the findings provided by the model is required to fully characterize the potential of this approach. The recruitment properties of selective nerve stimulation using transverse intrafascicular multichannel electrodes (TIME) were investigated in this work in experiments with rats and were compared to model predictions. Animal experiments were performed using the same stimulation protocol as in the computer simulations in order to rigorously validate the model predictions and understand its limitations. Two different selectivity indexes were used, and new indexes for measuring electrode performance are proposed. The model predictions are in decent agreement with experimental results both in terms of recruitment curves and selectivity values. Results show that these models can be used for extensive studies targeting electrode shape design, active sites shape, and multipolar stimulation paradigms. From a neurophysiological point of view, the topographic organization of the rat sciatic nerve, on which the model was based, has been confirmed.

Extracting medication information from clinical text.

The Third i2b2 Workshop on Natural Language Processing Challenges for Clinical Records focused on the identification of medications, their dosages, modes (routes) of administration, frequencies, durations, and reasons for administration in discharge summaries. This challenge is referred to as the medication challenge. For the medication challenge, i2b2 released detailed annotation guidelines along with a set of annotated discharge summaries. Twenty teams representing 23 organizations and nine countries participated in the medication challenge. The teams produced rule-based, machine learning, and hybrid systems targeted to the task. Although rule-based systems dominated the top 10, the best performing system was a hybrid. Of all medication-related fields, durations and reasons were the most difficult for all systems to detect. While medications themselves were identified with better than 0.75 F-measure by all of the top 10 systems, the best F-measure for durations and reasons were 0.525 and 0.459, respectively. State-of-the-art natural language processing systems go a long way toward extracting medication names, dosages, modes, and frequencies. However, they are limited in recognizing duration and reason fields and would benefit from future research.

Does a hybrid electronic-paper environment impact on health professional information seeking?

UNLABELLED: The purpose of this study was to investigate the effects of a hybrid electronic-paper patient record environment upon health professional information seeking (i.e. amount of information accessed, choice of key sources of information, type of information and use of information seeking tactics). A within group, laboratory, experimental study was conducted using two simulation environments (i.e. a paper patient record and a hybrid or electronic-paper environment). Thirty-five novice nurses participated in this within group, laboratory based study. Findings revealed significant differences between the paper and hybrid environments in terms of their effects upon information seeking. SUBJECTS: (1) accessed less data in the hybrid than the paper environment, (2) accessed more non-electronic sources than electronic sources of information in the hybrid environment, and (3) used more passive information seeking tactics in the hybrid than the paper environment. Findings from the cued recall data revealed subjects experienced increased cognitive load in the hybrid environment. Implications for the design of hybrid environments are discussed.

Hybrid SPECT-CT: integration of CT coronary artery calcium scoring and angiography with myocardial perfusion.

A natural extension of current imaging paradigms for diagnosing coronary artery disease may well be the integration of CT with myocardial perfusion single-photon CT (SPECT). Although there is a wealth of clinical information regarding the utility of SPECT, the value of CT in the cardiology arena has only recently been explored. CT has the advantage of detecting coronary atherosclerosis at its earliest stages, allowing initiation of appropriate therapeutic measures well before development of obstructive coronary artery disease. However, SPECT can clarify the anatomic findings of CT based on a functional assessment of myocardial blood flow, thereby guiding management decisions. Hybrid imaging with SPECT and CT angiography may prove important from a diagnostic and therapeutic view point in several clinical scenarios, and it is likely that over the next decade fusion imaging may more precisely tailor therapy, reduce healthcare costs, and improve patient outcome.

Simplest ever digital / analog neuron: "SEDAN-6".

The author continues with his series on artificial neuron construction. Using the smallest commercially available microcontroller, a 6-pin 8-bit unit, he has created several types of McCulloch-Pitts neurons and logic elements suitable for inclusion into various kinds of artificial neural networks. Additionally, by employing the on-chip analog comparator and simple off-chip stratagems, he has also implemented Hebb neurons and his android emotion emulator. These designs constitute the simplest artificial neurons which can be embodied using a microcontroller, and which are suitable for a wide variety of applications.

Does computation provide a model for creativity? An epistemological perspective in neuroscience.

In 1939 Alan Turing, a major scholar in the field of mechanical computation, described a system whose computational power was beyond that of a discrete, finite state machine (Turing Machine). The composition of this system was likely the first example of what is now called an hybrid computational system. Since then, development of neural networks and brain automata has made aware that forms of computation might exist that are likely to go beyond Turing's limits. Natural systems, like the central nervous system in Mammals and man, are likely to use such a type of computation, especially to perform highly integrating activities, like feedback controls and mental creative processes. The latter are usually understood as processes that involve infinitary procedures, ending up in a complex information network, the computational maps, in which both digital, Turing-like computation and continuous, analog forms of calculus are expected to occur. Pictorial representation may be a fruitful example, mostly metaphorical, to analyze the use of this hybrid forms of computation by higher order computational maps, and the possible role of these types of computational processes in painting creativity is briefly analyzed in comparing 15th vs 16th century Renaissance Art. An open challenge for neuroscience in the 21st century is to clarify whether a hybrid neural learning network might represent a reasonable clue to scientifically interpret the theme of "creativity".

Neural networks: models and neurons show hybrid vigor in real time.

Hybrid networks in which living neurons interact with digital or analog model neurons are providing insights into the role of neural and synaptic properties in shaping neural network activity.

Three-dimensional human airway segmentation methods for clinical virtual bronchoscopy.

RATIONALE AND OBJECTIVES: The segmentation of airways from CT images is a critical first step for numerous virtual bronchoscopic (VB) applications. Automatic or semiautomatic methods are necessary, since manual segmentation is prohibitively time consuming. The methods must be robust and operate within a reasonable time frame to be useful for clinical VB use. The authors developed an integrated airway segmentation system and demonstrated its effectiveness on a series of human images. MATERIALS AND METHODS: The authors' airway segmentation system draws on two segmentation algorithms: (a) an adaptive region-growing algorithm and (b) a new hybrid algorithm that uses both region growing and mathematical morphology. Images from an ongoing VB study were segmented by means of both the adaptive region-growing and the new hybrid methods. The segmentation volume, branch number estimate, and segmentation quality were determined for each case. RESULTS: The results demonstrate the need for an integrated segmentation system, since no single method is superior for all clinically relevant cases. The region-growing algorithm is the fastest and provides acceptable segmentations for most VB applications, but the hybrid method provides superior airway edge localization, making it better suited for quantitative applications. In addition, the authors show that prefiltering the image data before airway segmentation increases the robustness of both region-growing and hybrid methods. CONCLUSION: The combination of these two algorithms with the prefiltering options allowed the successful segmentation of all test images. The times required for all segmentations were acceptable, and the results were suitable for the authors' VB application needs.

Scalable hybrid computation with spikes.

We outline a hybrid analog-digital scheme for computing with three important features that enable it to scale to systems of large complexity: First, like digital computation, which uses several one-bit precise logical units to collectively compute a precise answer to a computation, the hybrid scheme uses several moderate-precision analog units to collectively compute a precise answer to a computation. Second, frequent discrete signal restoration of the analog information prevents analog noise and offset from degrading the computation. And, third, a state machine enables complex computations to be created using a sequence of elementary computations. A natural choice for implementing this hybrid scheme is one based on spikes because spike-count codes are digital, while spike-time codes are analog. We illustrate how spikes afford easy ways to implement all three components of scalable hybrid computation. First, as an important example of distributed analog computation, we show how spikes can create a distributed modular representation of an analog number by implementing digital carry interactions between spiking analog neurons. Second, we show how signal restoration may be performed by recursive spike-count quantization of spike-time codes. And, third, we use spikes from an analog dynamical system to trigger state transitions in a digital dynamical system, which reconfigures the analog dynamical system using a binary control vector; such feedback interactions between analog and digital dynamical systems create a hybrid state machine (HSM). The HSM extends and expands the concept of a digital finite-state-machine to the hybrid domain. We present experimental data from a two-neuron HSM on a chip that implements error-correcting analog-to-digital conversion with the concurrent use of spike-time and spike-count codes. We also present experimental data from silicon circuits that implement HSM-based pattern recognition using spike-time synchrony. We outline how HSMs may be used to perform learning, vector quantization, spike pattern recognition and generation, and how they may be reconfigured.

An automatic microcalcification detection system based on a hybrid neural network classifier.

A hybrid intelligent system is presented for the identification of microcalcification clusters in digital mammograms. The proposed method is based on a three-step procedure: (a) preprocessing and segmentation, (b) regions of interest (ROI) specification, and (c) feature extraction and classification. The reduction of false positive cases is performed using an intelligent system containing two sub-systems: a rule-based and a neural network sub-system. In the first step of the classification schema 22 features are automatically computed which refer either to individual microcalcifications or to groups of them. Further reduction in the number of features is achieved through principal component analysis (PCA). The proposed methodology is tested using the Nijmegen and the Mammographic Image Analysis Society (MIAS) mammographic databases. Results are presented as the receiver operating characteristic (ROC) performance and are quantified by the area under the ROC curve (A(z)). In particular, the A(z) value for the Nijmegen dataset is 0.91 and for the MIAS is 0.92. The detection specificity of the two sets is 1.80 and 1.15 false positive clusters per image, at the sensitivity level higher than 0.90, respectively.

Adaptive hybrid interpolation techniques for direct Haptic rendering of isosurfaces.

Direct Haptic rendering of voxels from an anatomical dataset provides patient specific haptic feedback vital for diagnosis and surgical planning. Our algorithm uses zero sets of scalar trivariate function for polynomial interpolation with sixty-four neighborhood points to generate isosurfaces on the fly for haptic rendering. This approach gives continuity in surfaces as well as better capture of isosurface features of the medical dataset. The detailed algorithm is presented along with the description of results from haptically rendering medical datasets.

A hybrid on-line ECG segmenting system for long-term monitoring.

This paper introduces a new hybrid ECG beat segmenting system, which can be applied in the processing unit of single-channel, long-term ECG monitors for the on-line segmentation of the ECG signal. Numerous ECG segmentation techniques are already existing and applied, however sufficiently robust and reliable methods currently require more than one ECG signal channel and quite complex computations, which are practically not feasible in stand-alone, low-cost monitors. Our new system approach presents a time domain segmentation technique based on a priori physiological and morphological information of the ECG beat. The segmentation is carried out after classifying the ECG beat, using the linear approximation of the filtered ECG signal and considering the pathophysiological properties as well. The proposed algorithms require moderate computational power, allowing the practical realization in battery powered stand-alone long-term cardiac monitors or small-sized cardiac defibrillators. The prototype version of the system was implemented in Matlab. The test and evaluation of the system was carried out with the help of reference signal databases.

Analog circuits for modeling biological neural networks: design and applications.

Computational neuroscience is emerging as a new approach in biological neural networks studies. In an attempt to contribute to this field, we present here a modeling work based on the implementation of biological neurons using specific analog integrated circuits. We first describe the mathematical basis of such models, then present analog emulations of different neurons. Each model is compared to its biological real counterpart as well as its numerical computation. Finally, we demonstrate the possible use of these analog models to interact dynamically with real cells through artificial synapses within hybrid networks. This method is currently used to explore neural networks dynamics.

A hybrid technique for spectroscopic imaging with reduced truncation artifact.

Traditionally, Fourier spectroscopic imaging is associated with a small k-space coverage which leads to truncation artifacts such as "bleeding" and ringing in the resultant image. Because substantial truncation artifacts mainly arise from regions having intense signals, such as the subcutaneous lipid in the head, effective reduction of truncation artifacts can be achieved by obtaining an extended k-space coverage for these regions. In this paper, a hybrid technique which employs phase-encoded spectroscopic imaging (SI) to cover the central portion of the k-space and echo-planar spectroscopic imaging (EPSI) to measure the peripheral portion of the k-space is developed. EPSI, despite its inherently low SNR characteristics, provides a sufficient SNR for outer high-spatial frequency components of the aforementioned high signal regions and supplies an extended k-space coverage of these regions for the reduction of truncation artifacts. The data processing includes steps designed to remove inconsistency between the two types of data and a previously described technique for selectively retaining only outer k-space information for the high signal regions during the reconstruction. Experimental studies, in both phantoms and normal volunteers, demonstrate that the hybrid technique provides significant reduction in truncation artifacts.

Improved option pricing using artificial neural networks and bootstrap methods.

A hybrid neural network is used to predict the difference between the conventional option-pricing model and observed intraday option prices for stock index option futures. Confidence intervals derived with bootstrap methods are used in a trading strategy that only allows trades outside the estimated range of spurious model fits to be executed. Whilst hybrid neural network option pricing models can improve predictions they have bias. The hybrid option-pricing bias can be reduced with bootstrap methods. A modified bootstrap predictor is indexed by a parameter that allows the predictor to range from a pure bootstrap predictor, to a hybrid predictor, and finally the bagging predictor. The modified bootstrap predictor outperforms the hybrid and bagging predictors. Greatly improved performance was observed on the boundary of the training set and where only sparse training data exists. Finally, bootstrap bias estimates were studied.