Abstract: A region-based push-relabel formulation is disclosed that removes the requirement that the entire graph should fit into the computer memory and yields an implementation that can reduce the required size and redundancy of accesses to the data memory, thus improving speed performance, while allowing for an efficient parallel processing implementation. The algorithm assigns all vertices that are not part of the sources or sinks with a value of 1. Sinks are assigned with zeros and sources are assigned a label equal to the number of their vertices. The preflow is then pushed from the sources to their neighbors, if any. When the preflow has all reached the boundaries, an adjacent region of the neighboring set is selected and preflow is pushed within this region. When the values of the preflow have been exhausted, region relabeling is done to update the label values. This is repeated within the region until all preflow has exited to the boundary of this region.

Abstract: A method for rendering a two-dimensional image comprising: (a) obtaining a first three-dimensional set of data for a relatively high quality image; (b) generating a second three-dimensional set of data for a relatively low quality image from the obtained three-dimensional set of data; (c) rendering a relatively low quality two-dimensional image from second three-dimensional set of data; (d) rendering a first portion of a relatively high quality two-dimensional image from a first portion of the first three-dimensional set of data; (e) blending the rendered low quality two-dimensional image with relatively high quality two-dimensional image; (f) rendering a second portion of a relatively high quality two-dimensional image from a different portion of the first three-dimensional set of data; and (g) blending the rendered low quality two-dimensional image from second three-dimensional set of data with relatively high quality two-dimensional image from the second portion of the first three-dimensional set of data.

Abstract: A method includes displaying a reference polar coordinate system on a display screen, and displaying a radiation pattern image on the display screen in juxtaposition with the displayed reference polar coordinate system. In another aspect, an angled line is drawn on a display screen to represent the proposed layout of a leaky coaxial cable. A point of interest is selected that is spaced from the proposed cable layout, and one of the segments of the cable is determined as likely to produce a dominant level of irradiation with respect to the point of interest.

Abstract: This invention describes an optimization and view dependency reduction method for multiplanar reformatting (MPR) of slice-based volume images. This method utilizes a traversal scheme that allows for efficient access of the computer memory layout of a sliced based volume, and therefore optimizes overall processing time. This method does not require changes to the volume memory layout or additional volume memory. Instead, efficient memory access is achieved by adaptive traversal patterns on the reformatting planes. The traversal pattern is adapted on-the-fly during rendering as the reformatting plane location and orientation is changed arbitrarily relative to the volume. In this way, the typical speed differences between various reformatting planes orientations caused by inefficient memory access is greatly reduced. Computer cache coherency, SIMD coherent implementation, and multiprocessing environments are also considered in the design of the traversal pattern.

Abstract: A method and system may operate to receive a first data from a sensor of a controlled device via a wireless network at a first time, transmit the first data to a controller system, receive a second data from the sensor of the controlled device via the wireless network at a second time, transmit the second data to the controller system, determine that a third data has not been received prior to a predetermined time period, or that the third data has been received prior to the predetermined time period and the third data is outside of a determined range of values, calculate a fourth data based on the first data and the second data, and transmit the fourth data to the controller system at a third time.

Abstract: A computer-implemented method is disclosed for comparing three dimensional (3D) digital medical images. The method uses a reference MPR to position subsequent MPRs in one or more other 3D digital medical images so their content matches the reference MPR. The matched MPRs may then be used by a medical professional to diagnose a patient condition. The ability to quickly and automatically position matching MPRs for multiple 3D images eases the medical staff workload and shortens diagnostics time. Matching MPRs provides an effective way to view the 3D volumes for anatomical changes over time and to monitor medical conditions such as stenosis and tumors.

Abstract: Myocardial tissue tracking techniques are used to project or guide a single manually-defined set of myocardial contours through time. Displacement encoding with stimulated echoes (DENSE), harmonic phase (HARP) and speckle tracking is used to encode tissue displacement into the phase of complex MRI images, providing a time series of these images, and facilitating the non-invasive study of myocardial kinematics. Epicardial and endocardial contours need to be defined at each frame on cine DENSE images for the quantification of regional displacement and strain as a function of time. The disclosed method presents a novel and effective two dimensional semi-automated segmentation technique that uses the encoded motion to project a manually defined region of interest through time. Contours can then easily be extracted for each cardiac phase.

Abstract: Multiplanar reformatting visualization is provided with multiple scrolling speeds. A plurality of buffers is provided. Each buffer stores composites of data from different planes. The amount of compositing to generate a total composite for a visualization may be less since the division into partial composites may reduce addition and subtraction or other compositing operations. One level of partial composite buffers may be used. The total is recomputed for each visualization. In other embodiments, a hierarchal buffer structure is used. For example, a total composite buffer is provided in addition to the partial composite buffers. By re-compositing the partial composites before and after adjustment for scrolling increment from the total composite buffer, the total composite is updated for scrolling. Two or more levels of buffers may be used.

Abstract: A general framework to enhance performance of automatic segmentation of a plurality of structures in medical imaging applications incorporates inter-structure spatial dependencies in to existing segmentation algorithms. Ranking the structures according to their dependencies allows a hierarchical approach to automatically segmenting multiple structures that improves each individual segmentation and provides automatic initializations.

Abstract: A system, method, apparatus, means, and computer program code for providing a delay guarantee for a wireless network is provided.

Abstract: A segmentation of the esophagus from image data by specifying only the two end points is disclosed. Surrounding structures are used as high-level constraints to construct shape and appearance models. Prior shape information is integrated for the segmentation of a new esophagus using a Bayesian formulation. This permits to automatically select the proper models. Given the end points, a shortest path algorithm provides the optimal esophagus according to the Bayesian formulation.

Abstract: Methods and systems for image segmentation are disclosed. A nonlinear statistical shape model of an image is integrated with a non-parametric intensity model to estimate characteristics of an image and create segmentations of an image based on Bayesian inference from characteristics of prior learned images based on the same models.

Abstract: Rendering with a punching mask is performed without voxelization. A plurality of sub-volumes are identified as a function of the punching mask. The sub-volumes are generally layered in range. Each sub-volume is rendered separately or independently. The renderings from multiple passes or sub-volumes are composited together.

Abstract: An apparatus and method for video object generation and selective encoding is provided. The apparatus includes a detection module for detecting a first object in at least one image frame of a series of image frames; a tracking module for tracking the first object in successive image frames and segmenting the first object from a background, the background being a second object; and an encoder for encoding the first and second objects to be transmitted to a receiver, wherein the first object is compressed at a high compression rate and the second object is compressed at a low compression rate. The receiver merges the first and second object to form a composite image frame. The method provides for detecting, tracking and segmenting one or more objects, such as a face, from a background to be encoded at the same or different compression rates to conserve bandwidth.

Abstract: A method for analyzing a medical image. The process: establishes a predetermined criteria; obtains data in a plane traverse the anatomical object; identifies a point disposed on the object in the plane; detects contour points of the object in the plane from the identified point; analyzes the obtained contour points to predict a subsequent point on the object and a tracing direction, such tracing direction being along the length of the object; determines a subsequent plane transverse the object, such predicted point being in the subsequent plane; repeats the process until the predetermined criterion is satisfied.

Abstract: Presegmentation or prior, pre-existing segmentation of an object obtained through other means will be presented for interactive editing of a segmented object in an image or volume. Prior segmentation will be seamlessly combined with graph cuts or the random walker methods. Editing of the presegmentation is possible, while maintaining the important property of both methods that an arbitrary segmentation may be achieved with enough interaction.

Abstract: A method for segmentation of an image interactively with a user utilizes level set segmentation and includes selecting by user input respective areas of object and of background; initializing an embedding function implementing a segmentation boundary according to the selecting; computing intensity distributions and for the respective areas of object and of background; and performing repeatedly the steps below until convergence is reached: (a) evolving the embedding function, (b) recomputing the intensity distributions, and (c) checking for new user input and, if so: (d) updating labeling of the areas of object and background.

Abstract: Traditional graph cuts provides a powerful method for producing semi-automatic image/volume segmentation, but often exceed available computer power. Multi-level methods for coarsening images/volumes are disclosed that allow for faster processing and creation of graph cuts segmentation without sacrificing quality of image. The disclosed graph cuts methods can be used at interactive speeds.

Abstract: Adaptive vision-based vehicle detection methods, taking into account the lighting context of the images are disclosed. The methods categorize the scenes according to their lighting conditions and switch between specialized classifiers for different scene contexts. Four categories of lighting conditions have been identified using a clustering algorithm in the space of image histograms: Daylight, Low Light, Night, and Saturation. Trained classifiers are used for both Daylight and Low Light categories, and a tail-light detector is used for the Night category. Improved detection performance by using the provided context-adaptive methods is demonstrated. A night time detector is also disclosed.

Abstract: A new measure to compare histogram-based descriptors, a diffusion distance, is disclosed. The difference between two histograms is defined to be a temperature field. The relationship between histogram similarity and diffusion process is discussed and it is shown how the diffusion handles deformation as well as quantization effects. As a result, the diffusion distance is derived as the sum of dissimilarities over scales. Being a cross-bin histogram distance, the diffusion distance is robust to deformation, lighting change and noise in histogram-based local descriptors. In addition, it enjoys linear computational complexity which significantly improves previously proposed cross-bin distances with quadratic complexity or higher The proposed approach is tested on both shape recognition and interest point matching tasks using several multi-dimensional histogram-based descriptors including shape context, SIFT and spin images.