Feasibility and Accuracy of Measuring Carotid Plaque Volume (Burden) With Contrast-Enhanced Tomographic 3D Ultrasound and Ultrasound Image Fusion.

BACKGROUND: Stenosis severity has been the indication for carotid endarterectomy (CEA) for 4 decades, but the annual stroke risk in asymptomatic carotid stenosis >70% is under 2%. Atherosclerotic volume has emerged as a risk factor for future stroke, but needs to be measured noninvasively. Tomographic ultrasound (tUS) is a novel technology that assembles 3D images in seconds. We evaluated accuracy of measuring Carotid Plaque Volume (CPV) with tUS in patients undergoing CEA. METHOD: Consecutive patients were imaged immediately before CEA by tUS and contrast-enhanced tUS (CEtUS). CPV was measured using tUS, CEtUS, and a fused images incorporating both tUS and CEtUS by trained vascular scientists. Precise volume of the endarterectomy specimen was measured using Archimedes technique. RESULTS: Mean ± sd (range) CPV in 129 endarterectomy specimens was 0.75 ± 0.43 cm3 (0.10-2.47 cm3). Mean ± sd CPV measured by tUS (n = 114) was 0.87 ± 0.51 cm3, CEtUS (n = 104) was 0.75 ± 0.45 cm3 and with fusion (n = 95) was 0.83 ± 0.49 cm3. Differences between specimen volume and CPV measured by tUS (0.13 ± 0.24 cm3), CEtUS (-0.01 ± 0.21 cm3) or fusion (-0.08 ± 0.20) were clinically insignificant. Intra-/interobserver differences were minimal. CONCLUSIONS: tUS accurately measures CPV with excellent intra-/interobserver agreement. CEtUS improves accuracy if precise CPV measurement is needed for research but tUS alone would be sufficient for population screening.

Physiologically motivated image fusion for object detection using a pulse coupled neural network.

This paper presents the first physiologically motivated pulse coupled neural network (PCNN)-based image fusion network for object detection. Primate vision processing principles, such as expectation driven filtering, state dependent modulation, temporal synchronization, and multiple processing paths are applied to create a physiologically motivated image fusion network. PCNN's are used to fuse the results of several object detection techniques to improve object detection accuracy. Image processing techniques (wavelets, morphological, etc.) are used to extract target features and PCNN's are used to focus attention by segmenting and fusing the information. The object detection property of the resulting image fusion network is demonstrated on mammograms and Forward Looking Infrared Radar (FLIR) images. The network removed 94% of the false detections without removing any true detections in the FLIR images and removed 46% of the false detections while removing only 7% of the true detections in the mammograms. The model exceeded the accuracy obtained by any individual filtering methods or by logical ANDing the individual object detection technique results.

Methodology and feasibility of a home-based examination in disabled older women: the Women's Health and Aging Study.

BACKGROUND: To ascertain disease and functional capacity in community-resident disabled older women in the Women's Health and Aging Study (WHAS), a prospective investigation of the causes and course of disability, a home-based standardized physical examination and performance test battery were developed. Thirty-nine tests were administered, 9 by a lay interviewer and 30 by a nurse. This scope and intensity of testing had not been performed previously in a home environment or on such a functionally limited population. Thus, substantial developmental work was required. This report describes the administrative procedures and field experience for each exam component, highlighting innovations pertinent to home administration. METHODS: Exclusion criteria, safety issues, administration time, completion rates, and reasons for incomplete data are reported. Administration time is based on 30 exams conducted over a 3-week period 90% of the way through baseline data collection. Completion status was determined using all 1,002 participants and is categorized as follows: complete; partial; not done, health; not done, other; and refused. RESULTS: Seventy-two percent of the screened, eligible respondents completed the 30-min interviewer-administered physical assessment and the 2-hr, 10-min nurse examination. Classifiable data were obtained for 90% of participants on 36 examination items. Lower completion rates were obtained on the other three tests primarily due to exclusions for health-related conditions; environmental constraints and participant refusal were minimal. CONCLUSION: Extensive, research-oriented physical evaluation can be successfully and safely performed in a home setting. In future studies, home-based examination may be preferable, as participation in the WHAS examination substantially exceeded rates for clinic-based exams in similar populations.

Computer-aided breast cancer detection and diagnosis of masses using difference of Gaussians and derivative-based feature saliency.

A new model-based vision (MBV) algorithm is developed to find regions of interest (ROI's) corresponding to masses in digitized mammograms and to classify the masses as malignant/benign. The MBV algorithm is comprised of five modules to structurally identify suspicious ROI's, eliminate false positives, and classify the remaining as malignant or benign. The focus of attention module uses a difference of Gaussians (DoG) filter to highlight suspicious regions in the mammogram. The index module uses tests to reduce the number of nonmalignant regions from 8.39 to 2.36 per full breast image. Size, shape, contrast, and Laws texture features are used to develop the prediction module's mass models. Derivative-based feature saliency techniques are used to determine the best features for classification. Nine features are chosen to define the malignant/benign models. The feature extraction module obtains these features from all suspicious ROI's. The matching module classifies the regions using a multilayer perceptron neural network architecture to obtain an overall classification accuracy of 100% for the segmented malignant masses with a false-positive rate of 1.8 per full breast image. This system has a sensitivity of 92% for locating malignant ROI's. The database contains 272 images (12 b, 100 microm) with 36 malignant and 53 benign mass images. The results demonstrate that the MBV approach provides a structured order of integrating complex stages into a system for radiologists.

Integrated feature architecture selection.

In this paper, we present an integrated approach to feature and architecture selection for single hidden layer-feedforward neural networks trained via backpropagation. In our approach, we adopt a statistical model building perspective in which we analyze neural networks within a nonlinear regression framework. The algorithm presented in this paper employs a likelihood-ratio test statistic as a model selection criterion. This criterion is used in a sequential procedure aimed at selecting the best neural network given an initial architecture as determined by heuristic rules. Application results for an object recognition problem demonstrate the selection algorithm's effectiveness in identifying reduced neural networks with equivalent prediction accuracy.

Artificial neural networks for early detection and diagnosis of cancer.

Why use neural networks? The reasons commonly cited in the literature for using artificial neural networks for any problem are many and varied. They learn from experience. They work where other algorithms fail. They generalize from the training examples to perform well on independent test data. They reduce the number of false alarms without increasing significantly the number of false negatives. They are fast and are easier to use than conventional statistical techniques, especially when multiple prognostic factors are needed for a given problem. These factors have been overly promoted for the neural techniques. The common theme of this paper is that artificial neural networks have proven to be an interesting and useful alternate processing strategy. Artificial neural techniques, however, are not magical solutions with mystical abilities that work without good engineering. With good understanding of their capabilities and limitations they can be applied productively to problems in early detection and diagnosis of cancer. The specific cancer applications which will be used to demonstrate current work in artificial neural networks for cancer detection and diagnosis are breast cancer, liver cancer and lung cancer.

Optical wavelet transforms from computer-generated holography.

An optical implementation of a wavelet transform is presented. Optical Haar wavelets are created by the use of computer-generated holography. Two different holographic techniques are explored: (1) interferogram and (2) detour-phase. A discrete representation of a continuous wavelet transform is obtained by the optical correlation of an image with a Haar mother wavelet. Experimental results are compared with their digital simulations.

Spectral analysis of the electroencephalographic response to motion sickness.

Ten subjects participated in a laboratory experiment using cross-coupled angular stimulation to induce motion sickness symptoms. A 14-channel montage using subdermal electrodes was employed to record the electroencephalogram during a pre-Coriolis stimulation baseline through to imminent emesis. Spectral analyses of the EEG were performed upon the recorded data and individual band energies were quantified to attempt to characterize the cortical electrical response to motion sickness. Power spectral analysis was performed upon the temporo-frontal signals through the entire period over the delta, theta, and alpha EEG bands. The power in each of these bands was integrated and the baseline periods compared with that during frank sickness. Mean power spectral energy in the delta band during frank sickness increased by a factor of 13.7 over baseline. Mean theta band energy increased by a factor of 2.2. Mean alpha band energy was not significantly different. EEG power spectral levels in the delta and theta bands increased along with the level of motion sickness symptoms. These changes, particularly those in the delta band, suggest that intense low frequency oscillatory stimulation is being diffusely projected about the central nervous system. These EEG changes, similar to those sometimes seen in partial seizures, and the similarity of the symptom/sign complex in the two disorders, provide evidence that the pathophysiology and electrophysiology of motion sickness may be a variant of seizure activity.

Neural network payload estimation for adaptive robot control.

A concept is proposed for utilizing artificial neural networks to enhance the high-speed tracking accuracy of robotic manipulators. Tracking accuracy is a function of the controller's ability to compensate for disturbances produced by dynamical interactions between the links. A model-based control algorithm uses a nominal model of those dynamical interactions to reduce the disturbances. The problem is how to provide accurate dynamics information to the controller in the presence of payload uncertainty and modeling error. Neural network payload estimation uses a series of artificial neural networks to recognize the payload variation associated with a degradation in tracking performance. The network outputs are combined with a knowledge of nominal dynamics to produce a computationally efficient direct form of adaptive control. The concept is validated through experimentation and analysis on the first three links of a PUMA-560 manipulator. A multilayer perceptron architecture with two hidden layers is used. Integration of the principles of neural network pattern recognition and model-based control produces a tracking algorithm with enhanced robustness to incomplete dynamic information. Tracking efficacy and applicability to robust control algorithms are discussed.

The multilayer perceptron as an approximation to a Bayes optimal discriminant function.

The multilayer perceptron, when trained as a classifier using backpropagation, is shown to approximate the Bayes optimal discriminant function. The result is demonstrated for both the two-class problem and multiple classes. It is shown that the outputs of the multilayer perceptron approximate the a posteriori probability functions of the classes being trained. The proof applies to any number of layers and any type of unit activation function, linear or nonlinear.

Herpes simplex virus neurovirulence and productive infection of neural cells is associated with a function which maps between 0.82 and 0.832 map units on the HSV genome.

A herpes simplex virus (HSV) intertypic recombinant (RE6) has been shown to be completely and specifically non-neurovirulent in mice. Direct intracranial inoculation of 10(8) PFU of RE6 does not result in a lethal encephalitis. Neurovirulent recombinant viruses were generated by cotransfection of RE6 DNA with DNA fragments cloned from the pathogenic HSV-1 strain 17 syn+. It was found that a 1.6-kb fragment mapping between 0.82-0.832 m.u. could restore the neurovirulent phenotype. Recombinants which incorporated at least part of this fragment were at least 100,000-fold more neurovirulent than RE6. The recombinants displayed a greatly enhanced capacity to replicate in mouse brain in vivo, but did not display enhanced replication over that of RE6 in cultured mouse cells at 38.5 degrees. Immunohistochemical analysis of infected mouse brain tissue revealed that the permissive host cell range of the recombinants was dramatically altered from that of RE6. While antigen positive cells were extremely rare in mouse brain tissue infected with RE6, the neurovirulent recombinants produced antigens in many cell types including neurons. Thus, wild-type HSV-1 sequences mapping between 0.82-0.832 m.u. can donate a highly neurovirulent phenotype to RE6.

Sidelobe reduction via multiaperture optical systems.

The impulse responses of multiaperture optical systems can generate large sidelobe irradiances. The purpose of this research was to design multiaperture systems with impulse responses that exhibit sidelobe irradiances less than that of the Airy pattern and central lobe widths no greater than that of a single large aperture of an equivalent diameter. Multiaperture systems composed of 19, 37, 61, and 91 apertures satisfy these performance criteria. However, the amount of energy in the central lobes of the multiaperture systems was less than that of a single large aperture.

Two-wave mixing in Ta-doped KNbO(3).

This Communication describes preliminary experimental two-wave mixing results with a new electrooptic material, 1% tantalum (Ta)-doped potassium niobate, KNbO(3).

Optical preprocessing using liquid crystal televisions.

The suitability of a low-cost liquid crystal TV to function as a spatial light modulator in an optical preprocessor for an electronic pattern recognition system is investigated. The application presented is optical edge enhancement. The liquid crystal TV performs reasonably well where high-quality images are not required. Three optical edge enhancement methods are presented: spatial filtering; image cancellation; and phase cancellation. The phase cancellation method was discovered during the course of this research.