Search

Congenital Nystagmus (CN) is an ocular-motor disorder characterised by involuntary, conjugated ocular oscillations, and its pathogenesis is still unknown. The pathology is defined as “congenital” from the onset time of its arise which could be at birth or in the first months of life. Visual acuity in CN subjects is often diminished due to nystagmus continuous oscillations, mainly on the horizontal plane, which disturb image fixation on the retina. However, during short periods in which eye velocity slows down while the target image is placed onto the fovea (called foveation intervals) the image of a given target can still be stable, allowing a subject to reach a higher visual acuity. In CN subjects, visual acuity is usually assessed both using typical measurement techniques (e.g. Landolt C test) and with eye movement recording in different gaze positions. The offline study of eye movement recordings allows physicians to analyse nystagmus main features such as waveform shape, amplitude and frequency and to compute estimated visual acuity predictors. This analytical functions estimates the best corrected visual acuity using foveation time and foveation position variability, hence a reliable estimation of this two parameters is a fundamental factor in assessing visual acuity. This work aims to enhance the foveation time estimation in CN eye movement recording, computing a second order approximation of the slow phase components of nystag-mus oscillations. About 19 infrared-oculographic eye-movement recordings from 10 CN subjects were acquired and the visual acuity assessed with an acuity predictor was compared to the one measured in primary position. Results suggest that visual acuity measurements based on foveation time estimation obtained from interpolated data are closer to value obtained during Landolt C tests.

Congenital nystagmus is an ocular-motor disorder characterised by involuntary, conjugated and bilateral to and fro ocular oscillations. In this study a method to recognise automatically jerk waveform inside a congenital nystagmus recording and to compute foveation time and foveation position variability is presented. The recordings were performed with subjects looking at visual targets, presented in nine eye gaze positions; data were segmented into blocks corresponding to each gaze position. The nystagmus cycles were identified searching for local minima and maxima (SpEp sequence) in intervals centred on each slope change of the eye position signal (position criterion). The SpEp sequence was then refined using an adaptive threshold applied to the eye velocity signal; the outcome is a robust detection of each slow phase start point, fundamental to accurately compute some nystagmus parameters. A total of 1206 slow phases was used to compute the specificity in waveform recognition applying only the position criterion or adding the adaptive threshold; results showed an increase in negative predictive value of 25.1% using both features. The duration of each foveation window was measured on raw data or using an interpolating function of the congenital nystagmus slow phases; foveation time estimation less sensitive to noise was obtained in the second case.

Congenital nystagmus (CN) is an ocular-motor disorder characterised by involuntary, conjugated ocular oscillations and its pathogenesis is still under investigation. This kind of nystagmus is termed congenital (or infantile) since it could be present at birth or it can arise in the first months of life. Most of CN patients show a considerable decrease of their visual acuity: image fixation on the retina is disturbed by nystagmus continuous oscillations, mainly horizontal. However, the image of a given target can still be stable during short periods in which eye velocity slows down while the target image is placed onto the fovea (called foveation intervals). To quantify the extent of nystagmus, eye movement recording are routinely employed, allowing physicians to extract and analyse nystagmus main features such as waveform shape, amplitude and frequency. Using eye movement recording, it is also possible to compute estimated visual acuity predictors: analytical functions which estimates expected visual acuity using signal features such as foveation time and foveation position variability. Use of those functions extend the information from typical visual acuity measurement (e.g. Landolt C test) and could be a support for therapy planning or monitoring. This study focuses on detection of CN patients' waveform type and on foveation time measure. Specifically, it proposes a robust method to recognize cycles corresponding to the specific CN waveform in the eye movement pattern and, for those cycles, evaluate the exact signal tracts in which a subject foveates. About 40 eyemovement recordings, either infrared-oculographic or electrooculographic, were acquired from 16 CN subjects. Results suggest that the use of an adaptive threshold applied to the eye velocity signal could improve the estimation of slow phase start point. This can enhance foveation time computing and reduce influence of repositioning saccades and data noise on the waveform type identification.

Congenital nystagmus (CN) is an ocular-motor disorder characterised by involuntary, conjugated ocular oscillations, that can arise since the first months of life. Pathogenesis of congenital nystagmus is still under investigation. In general, CN patients show a considerable decrease of their visual acuity: image fixation on the retina is disturbed by nystagmus continuous oscillations, mainly horizontal. However, image stabilisation is still achieved during the short periods in which eye velocity slows down while the target image is placed onto the fovea (called foveation intervals). To quantify the extent of nystagmus, eye movement recording are routinely employed, allowing physicians to extract and analyse nystagmus main features such as shape, amplitude and frequency. Using eye movement recording, it is also possible to compute estimated visual acuity predictors: analytical functions which estimates expected visual acuity using signal features such as foveation time and foveation position variability. Use of those functions add information to typical visual acuity measurement (e.g. Landolt C test) and could be a support for therapy planning or monitoring. This study focus on robust detection of CN patients' foveations. Specifically, it proposes a method to recognize the exact signal tracts in which a subject foveates, This paper also analyses foveation sequences. About 50 eyemovement recordings, either infrared-oculographic or electrooculographic, from different CN subjects were acquired. Results suggest that an exponential interpolation for the slow phases of nystagmus could improve foveation time computing and reduce influence of breaking saccades and data noise. Moreover a concise description of foveation sequence variability can be achieved using non-fitting splines. © 2009 Springer Berlin Heidelberg.

Congenital nystagmus (CN) is an ocular-motor disorder that appears at birth or during the first few months of life; it is characterised by involuntary, conjugated, bilateral to and fro ocular oscillations. Pathogenesis of congenital nystagmus is still unknown. Eye movement recording allow to extract and analyse nystagmus main features such as shape, amplitude and frequency; depending on the morphology of the oscillations nystagmus can be classified in different categories (pendular, jerk, horizontal unidirectional, bidirectional). In general, CN patient show a considerable decrease of the visual acuity: image fixation on the retina is disturbed by nystagmus continuous oscillations; however, image stabilisation is still achieved during the short foveation periods in which eye velocity slows down while the target image is placed onto the fovea. Visual acuity was found to be mainly dependent on foveation periods duration, but cycle-to-cycle foveation repeatability and reduction of retinal image velocities also contribute in increasing visual acuity. This study concentrate on cycle-to-cycle image position variation onto fovea, trying to characterise the sequences of foveation positions. Eye-movement (infrared oculographic or electro oculographic) recordings, relative to different gaze positions and belonging to more than 30 CN patients, were analysed. Preliminary results suggest that sequences of foveations show a cyclic pattern with a dominant frequency (around 0.3 Hz on average) much lower than that of the nystagmus (about 3.3 Hz on average). Sequences of foveations reveals an horizontal ocular swing of more than 2 degree on average, which can explain the low visual acuity of the CN patient. Current CN therapies, pharmacological treatment or surgery of the ocular muscles, mainly aim to increase the patient's visual acuity. Hence, it is fundamental to have an objective parameter (expected visual acuity) for therapy planning. The information about sequences of foveations can improve estimation of patient visual acuity.

A classification system able to evaluate the performances of a transition radiation detector prototype for electrons/hadrons discrimination is presented. It is based both on a layered feed-forward neural network trained using back-propagation and a likehood ratio technique. The information fed into the classification system consists of the number of hits detected by each multiwires proportional chamber of the detector. The best results are obtained by the neural network approach that successfully identifies 4.0 GeV/ c electrons with an hadron contamination of about 4x10 -3 at 98% acceptance efficiency.

This study extends a previous research concerning intervertebral motion registration by means of 2D dynamic fluoroscopy to obtain a more comprehensive 3D description of vertebral kinematics. The problem of estimating the 3D rigid pose of a CT volume of a vertebra from its 2D X-ray fluoroscopy projection is addressed. 2D-3D registration is obtained maximising a measure of similarity between Digitally Reconstructed Radiographs (obtained from the CT volume) and real fluoroscopic projection. X-ray energy correction was performed. To assess the method a calibration model was realised a sheep dry vertebra was rigidly fixed to a frame of reference including metallic markers. Accurate measurement of 3D orientation was obtained via single-camera calibration of the markers and held as true 3D vertebra position; then, vertebra 3D pose was estimated and results compared. Error analysis revealed accuracy of the order of 0.1 degree for the rotation angles of about 1 mm for displacements parallel to the fluoroscopic plane, and of order of 10 mm for the orthogonal displacement.

Analysis of dynamic videofluoroscopic can provide spine kinematic data with an acceptable low X-ray dose. Estimation of the kinematics relies on accurate recognition of vertebrae positions and rotations on each radiological frame. In previous works we presented a procedure for automatic tracking of vertebra motion by smoothed gradient operators and template matching in fluoroscopic image sequences. A limitation to the accurate estimation of the kinematics by automatic tracking of vertebrae motion, independently by the specific methodology employed (e.g. manual marking, corner or edge automatic detection, etc.), is mainly due to noise: low-dose X-ray image sequences exhibit severe signal-dependent noise that should be reduced, while preserving anatomical edges and structures. Noise in low-dose X-ray images originates from various sources, however quantum noise is by far the more dominant noise in low-dose X-ray images and other sources can be neglected. Signal degraded by quantum noise is commonly modeled by a Poisson distribution, but it is possible to approximate it as additive zero-mean Gaussian noise with signal-dependent variance. In this work we propose a digital spatial filter for reducing noise in low-dose X-ray images. The proposed filter is based on averaging of only similar pixels (whose grey level is contained within ±3σ) instead of spatial averaging of all neighbouring pixels. The effectiveness of the filter performance was evaluated by fluoroscopic image sequence processing, comparing the results of the automatic vertebra tracking on filtered and unfiltered images.

We investigate the retrieval properties of fully connected saturated neural networks trained by the Edinburgh algorithm with correlated patterns {ξi}. We evaluate the effect of the correlation on the overlap between {ξi} and the network configuration after one time step and on the basins of attraction. We also show that the introduction of the thermal noise does not change the domains of attraction of the correlated memories.

The expected high volume imagery data from Nasa Mission to the Planet Earth is one of the target application areas for automated cloud retrieval, and more generally for automated image classification. We used the backpropagation (BP), the cascade-correlation (CC) and Kohonen self-organizing map (SOM) neural network architectures for cloud retrieval from satellite imagery. We have used a simple scene (a mixed scene containing only cloud and ocean). This simple scene allows us to evaluate the accuracy of the classification better than a complicated scene. Both BP and CC performed at the same accuracy level, while the SOM algorithm was slightly less accurate in performing unsupervised learning. This study shows that for simple scenes, which are abundant in global monitoring satellite imagery, a simple pixel-by-pixel or 3x3 window approaches provide high accuracy classification without using complicated contextual information.

A neural network based system for the localization and tracking of a moving target in space related scenes is described. The neural control system is used to "drive" the input sensor on the image plane by means of sequential moves, in order to overlap the final position of the moving sensor to the target.

Problems related to rapid transformation of land-use have reached a significant impact level. Photo interpretation by human experts has been the major data source for disasters' monitoring and urban planning applications. However, images collected from a sensor which combines reasonably good spectral and spatial resolution images acquired by IKONOS II satellite and a RGB-HIS transformation technique have been considered to merge spectral and spatial information. Then, textural information, which characterizes urban area, has been extracted with the use of an appropriate filter for edge extraction. An MLP classifier has been trained to produce a labeled image with great accuracy in test even if a limited training set has been used. For a photo interpreter, the results reveal a good feasibility of the classified image for monitoring the presence of changes in urban areas, useful for cartographic updating.

The authors present two artificial neural network architectures that perform offline segmentation of telerobotics tasks using force data. Two network architectures have been tested. The first one is based on turning temporal sequences into spatial patterns. The second architecture extends the first model by including the network's output in the input array. Experimental data are classified offline by a hidden Markov model providing the transition times and the corresponding segmentation for the training data. It was found that the first architecture needs a high number of iterations for learning the associations, whereas the latter has a high convergence speed. >

This paper describes a research activity devoted to verify the feasibility of a neural network approach for automatic detection of naval targets in radar imagery. The activity is part of a more ambitious industrial project concerning the use of advanced image processing techniques for improving the safety in maritime surveillance of harbour traffic. Having in mind this final application, the task of automatic target detection has to fulfil two main requirements: 1) quasi real time response, in the sense that each input radar image of about 1000 by 1000 pixels has to be analyzed in a time comparable with the sweep period of the acquisition system, i.e. three seconds; 2)very high accuracy, i.e. each ship in the scene must be surely detected: this means that the efficiency of the detection system should be not minus than 100%. These two applicative needs have to meet with the high degree of noise (clutter) characterizing the input radar data. In order to face up to the complexity of the exposed goal, the task has been decomposed in a set of sequential subtasks: noise elimination, preliminary object recognition and classified image reconstruction. Moreover, both neural and traditional tools have been used, designing a multi-modular hybrid system (a detailed discussion about the advantages of hybrid architecture can be found, for example, in (F. Folgelman Suolie, 1993)).

Whole Body Vibration training is more and more utilized in sport medicine to enhance athletic performance and training; recently, vibration treatment is being also used for therapy and rehabilitation for patients affected by different pathologies. It is also worth mention that excessive vibrations can be hazardous. The treatment is based on the hypothesis that under some circumstances vibration loads induce specific responses from the neuromuscular system; some clinical evidences suggest mechanical and metabolic reaction. Usually, vibrations are transmitted by means of a platform oscillating at different frequencies (10-80Hz) to patient body; mainly, limb muscles are involved. Many studies about the subject employ surface EMG recordings to evaluate muscle activity during vibration training. On electrodes, this condition generates large motion artifact at the vibration frequency. To get rid of such artifact an adaptive filter was designed: accelerometers placed onto platform or directly on muscles provide an error signal shape to be cancelled from the raw EMG. In particular, surface EMG have been recorded from leg quadriceps muscles of volunteers during whole body vibration therapy sessions at different oscillating frequency. A standard RLS adaptive filter have been used to cancel the motion artifact from EMG in real-time. Results show the effective cancellations of the vibration frequency from the raw EMG; the RMS value of the cleaned EMG results lower than that unprocessed in some cases up to 50%.

Many works in the field of image processing stress the utility of using Artificial Intelligence tools to obtain enhanced performances in the scene understanding task. Feigenbaum (1977) states that “..the power of an expert system derives from the knowledge it possesses not from the particular formalism and inference schemas it employs…”. In our opinion this assertion can be extended to all complex cognitive problems (such as natural language and automatic image understanding) in which human reasoning capabilities are required. “From this point of view a theory for the vision problem resolution must necessarily contain elements of a more general theory of thinking (Minsky, 1974)”. In order to translate these philosophical statements into action, we have to understand what kind of knowledge is useful for the vision problem resolution and how to represent it. Looking at the image understanding problem as a perception problem it is possible to individuate two different knowledge sources. The first one descends from the perceptual grouping laws of visible entities; the other derives directly from an explicit description of the objects to be recognized in the image describing a real scene. Normally these two knowledges are used in a hierarchical fashion with a special emphasis on one source at the expenses of the other. Moreover in many of these applications a low level processing attached to the image extracts features and a high level step tries to match the previously selected features with the model descriptions. A drawback of this approach is that an intelligent matching can be applied to an essentially non intelligent image partition.

Congenital nystagmus (CN) is a disturbance of the oculomotor centers which develops at birth or in the first months of life. Nystagmus consists essentially in involuntary, conjugated, horizontal rhythmic movements of the eye. Its pathogenesis is still unknown. Current therapies for CN aim to increase the patient’s visual acuity by means of refraction defects correction, drug delivery and ocular muscle surgery. Eye movement recording supports for accurate diagnosis, for patient follow-up and for therapy evaluation. In general, CN patients show a considerable decrease of visual acuity (image fixation on the retina is obstructed by nystagmus continuous oscillations) and severe postural alterations such as the anomalous head position, searched by patient to obtain a better fixation of the target image onto the retina. Often CN presents ‘neutral zones’ corresponding to particular gaze angles, in which nystagmus amplitude minimizes allowing a longer foveation time and a more stable repositioning of foveations, increasing visual acuity. Selected patients’ eye movements were recorded by using EOG or infrared oculography devices. Visual stimulation was delivered by means of an arched LED bar covering a visual field of –30 +30 degrees with respect to the central position. Computation of CN concise parameters allows in-dept analysis of foveations and estimation of visual acuity at different gaze angles. Preliminary results show a maximum of visual acuity at a specific gaze angle; this angle is mostly located at the patient’s right side for the analyzed group.