Abstract: For cameras that capture several images in a burst mode, some embodiments of the invention provide a method that presents one or more of the captured images differently than the remaining captured images. The method identifies at least one captured image as dominant image and at least another captured image as a non-dominant image. The method then displays each dominant image different from each non-dominant image in a concurrent presentation of the images captured during the burst mode. The dominant images may appear larger than non-dominant images, and/or appear with a marking that indicates that the images are dominant.

Abstract: For cameras that capture several images in a burst mode, some embodiments of the invention provide a method that presents one or more of the captured images differently than the remaining captured images. The method identifies at least one captured image as dominant image and at least another captured image as a non-dominant image. The method then displays each dominant image different from each non-dominant image in a concurrent presentation of the images captured during the burst mode. The dominant images may appear larger than non-dominant images, and/or appear with a marking that indicates that the images are dominant.

Abstract: For cameras that capture several images in a burst mode, some embodiments of the invention provide a method that presents one or more of the captured images differently than the remaining captured images. The method identifies at least one captured image as dominant image and at least another captured image as a non-dominant image. The method then displays each dominant image different from each non-dominant image in a concurrent presentation of the images captured during the burst mode. The dominant images may appear larger than non-dominant images, and/or appear with a marking that indicates that the images are dominant.

Abstract: For cameras that capture several images in a burst mode, some embodiments of the invention provide a method that presents one or more of the captured images differently than the remaining captured images. The method identifies at least one captured image as dominant image and at least another captured image as a non-dominant image. The method then displays each dominant image different from each non-dominant image in a concurrent presentation of the images captured during the burst mode. The dominant images may appear larger than non-dominant images, and/or appear with a marking that indicates that the images are dominant.

Abstract: A method of computing global-to-local metrics for recognition. Based on training examples with feature representations, the method automatically computes a local metric that varies over the space of feature representations to optimize discrimination and the performance of recognition systems. Given a set of points in an arbitrary features space, local metrics are learned in a hierarchical manner that give low distances between points of same class and high distances between points of different classes. Rather than considering a global metric, a class-based metric or a point-based metric, the proposed invention applies successive clustering to the data and associates a metric to each one of the clusters.

Abstract: A method for automatically segmenting a liver in digital medical images includes providing a 3-dimensional (3D) digital image I and a set of N training shapes {?i}i=1, . . . , N for a liver trained from a set of manually segmented images, selecting a seed point to initialize the segmentation, representing a level set function ??(?x+h) of a liver boundary ? in the image as ? ? ? ( x ) = ? 0 + ? i = 1 n ? ? i ? V i ? ( x ) , ? where ? ? 0 ? ( x ) = 1 N ? ? i = 1 N ? ? i ? ( x ) is a mean shape, {Vi(x)}i=1, . . .

Abstract: A method of computing global-to-local metrics for recognition. Based on training examples with feature representations, the method automatically computes a local metric that varies over the space of feature representations to optimize discrimination and the performance of recognition systems. Given a set of points in an arbitrary features space, local metrics are learned in a hierarchical manner that give low distances between points of same class and high distances between points of different classes. Rather than considering a global metric, a class-based metric or a point-based metric, the proposed invention applies successive clustering to the data and associates a metric to each one of the clusters.

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 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: 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 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: 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: A method for four-dimensional (4D) image verification in respiratory gated radiation therapy, includes: acquiring 4D computed tomography (CT) images, each of the 4D CT images representing a breathing phase of a patient and tagged with a corresponding time point of a first surrogate signal; acquiring fluoroscopic images of the patient under free breathing, each of the fluoroscopic images tagged with a corresponding time point of a second surrogate signal; generating digitally reconstructed radiographs (DRRs) for each breathing phase represented by the 4D CT images; generating a similarity matrix to assess a degree of resemblance in a region of interest between the DRRs and the fluoroscopic images; computing a compounded similarity matrix by averaging values of the similarity matrix across different time points of the breathing phase during a breathing period of the patient; determining an optimal time point synchronization between the DRRs and the fluoroscopic images by using the compounded similarity matrix;

Abstract: A method for automatically segmenting a liver in digital medical images includes providing a 3-dimensional (3D) digital image I and a set of N training shapes {?i}i=1, . . . , N for a liver trained from a set of manually segmented images, selecting a seed point to initialize the segmentation, representing a level set function ??(?x+h) of a liver boundary ? in the image as ? ? ? ( x ) = ? 0 + ? i = 1 n ? ? i ? V i ? ( x ) , ? where ? ? 0 ? ( x ) = 1 N ? ? i = 1 N ? ? i ? ( x ) is a mean shape, {Vi(x)}i=1, . . .

Abstract: This invention relates to shape priors for level set representations. An embodiment of the invention comprises a first stage and a second stage. In the first stage, a shape model can be built directly on level set space using a collection of samples. The shape model can be constructed using a variational framework to create a non-stationary pixel-wise model that accounts for shape variabilities. Then, in the second stage, the shape model can be used as basis to introduce the shape prior in an energetic form. In terms of level set representations, the shape prior aims at minimizing non-stationary distance between the evolving interface and the shape model. An embodiment according to the present invention can be integrated with an existing, data-driven variational method to perform image segmentation for physically corrupted and incomplete data.

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: A method for four-dimensional (4D) image verification in respiratory gated radiation therapy, includes: acquiring 4D computed tomography (CT) images, each of the 4D CT images representing a breathing phase of a patient and tagged with a corresponding time point of a first surrogate signal; acquiring fluoroscopic images of the patient under free breathing, each of the fluoroscopic images tagged with a corresponding time point of a second surrogate signal; generating digitally reconstructed radiographs (DRRs) for each breathing phase represented by the 4D CT images; generating a similarity matrix to assess a degree of resemblance in a region of interest between the DRRs and the fluoroscopic images; computing a compounded similarity matrix by averaging values of the similarity matrix across different time points of the breathing phase during a breathing period of the patient; determining an optimal time point synchronization between the DRRs and the fluoroscopic images by using the compounded similarity matrix;

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: 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.