Abstract: A method and apparatus for guiding image reading for colon screening, includes calculating a centerline for a colon; scrolling through a succession of two dimensional (2D) cross-sectional images of a colon in respective image planes, such that a current image plane includes a respective current focus point formed by an intersection of the centerline with the current image plane. The method further includes performing a three-dimensional (3D) region growing process for growing a region of a suitable given thickness around a current seed point in a current image plane, the current seed point being at the respective current focus point in the current image plane, such that the region growing “floods” folds within a prescribed distance from the current seed point such that part of the region intersects the current image plane.

Abstract: A method for combining at image data sets to generate a composite image. The method divides each of the data sets into a plurality of bricks along three mutually orthogonal axes. The method includes (a) building a hierarchical structure for each one of the at least two data sets, each structure comprising higher level blocks of voxels and lower level blocks of voxels, the higher level blocks having a larger number of voxels than the lower level blocks; (b) expanding boundaries of each one of the structures into corresponding expanded hierarchical structures, such boundary expanding comprising adding additional virtual processing bricks to the initial processing bricks, such virtual processing bricks comprising semi-unbounded blocks to provide the expanded boundaries of the expanded hierarchical structures; and (c) rendering each one of the bricks in each one of the expanded hierarchical structures into a two dimension image.

Abstract: A multi-camera system that collects images and videos of moving objects in dynamic and crowded scenes, subject to task constraints is disclosed. The system constructs “task visibility intervals” comprising information about what can be sensed in future time intervals. Methods for constructing these intervals applying prediction of future object motion and including consideration of factors such as object occlusion and camera control parameters are also disclosed. Using a plane-sweep algorithm, these atomic intervals can be combined in a method to form multi-task intervals, during which a single camera can collect videos suitable for multiple tasks simultaneously. Methods for fast camera scheduling that yield solutions within a small constant factor of an optimal solution are also disclosed.

Abstract: A method for reconstructing an image generated from radial trajectory data in frequency or k-space using a GPU. The method includes using a vertex shader of the GPU to transform coordinates of a window aligned with the radial trajectory data and using a pixel shader of the GPU to combine data along the radial trajectory with the coordinate transformed widow to distribute the data along the radial trajectory fed to the pixel shader into cells of a Cartesian coordinate system.

Abstract: A memory manager interfaces between a rendering application and the driver controlling one or more memories. A multi-level brick cache system caches bricks in a memory hierarchy to accelerate the rendering. One example memory hierarchy may include system memory, AGP memory, and graphics memory. The memory manager allows control of brick overwriting based on current or past rendering. Since different memories are typically available, one or more memory managers may control storage of bricks into different memories to optimize rendering. Management of different memory levels, overwriting based on current or previous rendering, and an interfacing memory manager may each be used alone or in any possible combination.

Abstract: A method for reducing B0 inhomogeneous effects in magnetic resonance imaging (MRI). The method includes: obtaining a high-resolution volumetric MR image of the patient, such high-resolution volumetric MR image having B0 inhomogeneous effects; calculating distortion within obtained the high-resolution volumetric MR image of the patient; and correcting the B0 inhomogeneous effects in the obtained high-resolution volumetric image using the calculated distortion.

Abstract: A manifold learning technique is applied to the problem of discriminating an object boundary between neighboring pixels/voxels in an image. The manifold learning technique is referred to as locality preserving projections. The application is for multi-channel images, which may include registered images/volumes, a time series of images/volumes, images obtained using different pulse sequences or contrast factors, radar and color photographs.

Abstract: Disclosed is robust click-point linking, defined as estimating a single point-wise correspondence between data domains given a user-specified point in one domain or as an interactive localized registration of a monomodal data pair. To link visually dissimilar local regions, Geometric Configuration Context (GCC) is introduced. GCC represents the spatial likelihood of the point corresponding to the click-point in the other domain. A set of scale-invariant saliency features are pre-computed for both data. GCC is modeled by a Gaussian mixture whose component mean and width are determined as a function of the neighboring saliency features and their correspondences. This allows correspondence of dissimilar parts using only geometrical relations without comparing the local appearances. GCC models are derived for three transformation classes: pure translation, scaling and translation, and similarity transformation.

Abstract: The present invention relates to a method for visually detecting and tracking an object through a space. The method chooses modules for a restricting a search function within the space to regions with a high probability of significant change, the search function operating on images supplied by a camera. The method also derives statistical models for errors, including quantifying an indexing step performed by an indexing module, and tuning system parameters. Further the method applies a likelihood model for candidate hypothesis evaluation and object parameters estimation for locating the object.

Abstract: A method and apparatus of visually depicting an organ, having the steps of choosing a predefined set features for analysis, the predefined set of features having distinguishing weak learners for an algorithm, wherein the predefined set of features and the weak learners chosen distinguish features of the organ desired to be represented, developing a strong classifier for the algorithm for the organ desired to be represented based upon the weak learners for the organ, one of conducing a body scan to produce a body scan data set and obtaining a body scan data set of information for a patient, applying the strong classifier and the algorithm to the body scan data set to develop a result of a representation of the organ and outputting the result of the step of applying of the strong classifier and the algorithm to the body scan data set to represent the organ.

Abstract: Methods for maximum scene surface temperature estimation for blades with reflective surface properties in advanced stationary gas turbines are disclosed. The approach utilizes high speed infrared imagery provided by an online monitor system using a focal plan array (FPA) for near-infrared monitoring during engine runtime up to base load. The one waveband method for temperature estimation is assumed as starting point. A lower surface emissivity and higher surface reflectance of thermal barrier coating (TBC) in near-infrared can cause systematic estimation errors. Methods using the one wave band method, with the purpose to reduce estimation errors for maximum temperatures are also disclosed. Theoretical results, data from numerical simulations, and real data from engine test are provided. A system for performing temperature estimation methods is also disclosed.

Abstract: A fast and robust segmentation model for piecewise smooth images is provided. Local statistics in an energy formulation are provided as a functional. The shape gradient of this new functional gives a contour evolution controlled by local averaging of image intensities inside and outside the contour. Fast computation is realized by expressing terms as the result of convolutions implemented via recursive filters. Results are similar to the general Mumford-Shah model but realized faster without having to solve a Poisson partial differential equation at each iteration. Examples are provided. A system to implement segmentation methods is also provided.

Abstract: An improved method of graph-based segmentation of objects in images uses the property of rectilinear shape classes which optimize the ratio of specific metrics, that can be expressed as Laplacian matrices applied to indicator vectors. A relaxation of the binary formulation of this problem allows a solution via generalized eigenvectors. This segmentation algorithm incorporating shape information requires no initialization, is non -iterative and finds a steady-state (i.e., global optimum) solution. The method is generally applicable to segmentation of rectilinear shapes.

Abstract: A method and system for displaying unseen areas in guided two dimensional (2D) colon screening, includes calculating segmentation and colon surface for a colon; calculating a centerline for the colon; designating as a current focus point a current point of intersection of a current portion of the centerline and a current cross-sectional image of a colon in a current image plane; and extracting a colon surface portion in a connected colon component containing the current focus point; and marking voxels of the colon surface portion as a “seen” area. Unseen areas of the colon surface are calculated by subtracting seen areas from the total colon area of observation. The unseen areas may then be displayed.

Abstract: A method for histogram calculation using a graphics processing unit (GPU), comprises storing image data in a two-dimensional (2D) texture domain; subdividing the domain into independent regions or tiles; calculating in parallel, in a GPU, a plurality of tile histograms, one for each tile; and summing up in parallel, in the GPU, the tile histograms so as to derive a final image histogram.

Abstract: A method for detecting and tracking a deformable object having a sequentially changing behavior, comprising: developing a temporal statistical shape model of the oscillatory behavior of the embedding function representing the object from prior motion; and then applying the model against future, sequential motion of the object in the presence of unwanted phenomena by maximizing the probability that the developed statistical shape model matches the sequential motion of the object in the presence of unwanted phenomena.

Abstract: A patient positioning system for positioning a patient relative to radiographic equipment. The system includes: a 3D optical imaging system for optically scanning the patient, such 3D optical imaging system having a focal plane and providing, for each position on the object, data representative of the intensity of reflected energy received by the system from such position and data representative of distance from such position on the object to the focal plane; a table apparatus for supporting the patient and for moving the table relative to the radiographic equipment in response to positioning signals; and a processor responsive to data from the radiographic equipment and the data from the a 3D optical imaging system for producing the positioning signals. The system enables a method for displaying temporal changes in a patient positioned with a bore of radiographic equipment.

Abstract: The performance of template matching is characterized by deriving the distribution of warp parameter estimate as a function of the ideal template, the ideal warp parameters and a given perturbation or noise model. An expression for the Probability Mass Function of the parameter estimate is provided. The optimal template size for template matching is the one that provides the best matching performance which is calculated from the minimum entropy of the parameter estimate.

Abstract: A method for producing three-dimensional images of a blood vessel. A first set of seed points is placed along a first estimate of a centerline of the vessel. A cyclic graph is constructed around a first one of the seed points in a plane passing through the seed points. The graph comprises a plurality of nodes, with edges connecting the nodes. The nodes are disposed at equally spaced intervals about each one of a circumference of plurality of concentric circles centered at the seed point The method applies filtering such as multi-scale mean shift intensity detection orthogonal to the edges of the cyclic graph to thereby estimate a boundary of the vessel. A new center of the estimated boundary is determined to thereby generate a new seed point. The process is repeated using the new seed point to thereby generate a final boundary of the vessel in the plane.

Abstract: A tunable representation for tracking that simultaneously encodes appearance and geometry in a manner that enables the use of mean-shift iterations for tracking is provided. The solution to the tracking problem is articulated into a method that encodes the spatial configuration of features along with their density and yet retains robustness to spatial deformations and feature density variations. The method of encoding of spatial configuration is provided using a set of kernels whose parameters can be optimized for a given class of objects off-line. The method enables the use of mean-shift iterations and runs in real-time. Better tracking results by the novel tracking method as compared to the original mean-shift tracker are demonstrated.