Abstract: A method for fusing a plurality of images. The method includes: acquiring the plurality of images from a plurality of different modalities, each one of the images having a different reference space; and fusing the plurality of images into a common reference space, such common reference space being different from the reference space of each one of the plurality of acquired images. Thus, with such method, a unified process is provided for handling fusion across multiple clinical interventional and/or surgery (i.e., intra-operative) procedures.

Abstract: A method for monitoring cardiac function of a patient during a magnetic resonance imaging (MRI) procedure, including: acquiring an MR image sequence of the patient's heart during a cardiac phase; segmenting a left ventricle of the patient's heart in the MR image sequence, wherein the segmentation produces endocardial and epicardial contours; representing at least one of the contours in polar or radial coordinates and computing its Fourier transform, wherein the Fourier transform produces Fourier descriptors for the contour; putting a vector of the Fourier descriptors into a classifier, wherein the classifier determines whether the contour reflects normal wall motion in the cardiac phase or whether the contour reflects abnormal wall motion in the cardiac phase; and alerting a medical practitioner when abnormal wall motion is detected.

Abstract: A method for guiding stent deployment during an endovascular procedure includes providing a virtual stent model of a real stent that specifies a length, diameter, shape, and placement of the real stent. The method further includes projecting the virtual stent model onto a 2-dimensional (2D) DSA image of a target lesion, manipulating a stent deployment mechanism to navigate the stent to the target lesion while simultaneously acquiring real-time 2D fluoroscopic images of the stent navigation, and overlaying each fluoroscopic image on the 2D DSA image having the projected virtual stent model image, where the 2D fluoroscopic images are acquired from a C-arm mounted X-ray apparatus, and updating the projection of the virtual stent model onto the fluoroscopic images whenever a new fluoroscopic image is acquired or whenever the C-arm is moved, where the stent is aligned with the virtual stent model by aligning stent end markers with virtual end markers.

Abstract: A method of determining a three-dimensional (3D) position of a catheter tip includes: compensating a 2D position of the tip of the catheter for respiratory motion to generate a compensated 2D catheter position, generating weighted sample points around the compensated 2D catheter position, determining correspondent points of the weighted sample points in a 3D image, computing a weighted mean and a weighted covariance of each correspondent point, and determining the 3D position of the catheter tip in the 3D image from a fusion of the weighted means and weighted covariances.

Abstract: A view represented by echocardiographic data is classified. A probabilistic boosting network is used to classify the view. The probabilistic boosting network may include multiple levels where each level has a multi-class local structure classifier and a plurality of local-structure detectors corresponding to the respective multiple classes. In each level, the local structure is classified as a particular view and then the local structure is detected to determine whether the currently selected local structure corresponds to the class. The view classification may be used to determine gate locations, such as a gate for spectral Doppler analysis.

Abstract: A method for eliminating errors in foreground object detection in digitized images comprises providing a reference camera and a secondary camera, vertically aligning each said camera with a baseline that is approximately perpendicular to a ground plane, wherein said reference camera is placed lower than said secondary camera, selecting a foreground pixel in a reference view of a first point in a foreground object, finding a conjugate pixel of the foreground pixel in a secondary view, using the foreground and conjugate pixels to determine an image base pixel of a base point in the reference view, wherein said base point is a point on the ground plane below the first point, and using the foreground and image base pixels to find a location where the ground plane is first visible.

Abstract: A method and system for registering a first image of, for example, a liver and a second image of the liver being contrast-enhanced comprises: deriving a statistical similarity measure between images; deriving a smooth divergence-free vector field derived from a gradient of the statistical similarity measure; and integrating the vector field for providing a fluid-based algorithm including a volume-preserving constraint for a transformation for registering the images.

Abstract: A system for creating physical simulations using hand-sketched three-dimensional (3D) objects, including: a memory device for storing a program; a processor in communication with the memory device, the processor operative with the program to enable: 3D objects to be hand-sketched and assigned physical descriptions; and behavior of the physical descriptions to be simulated in a physics environment.

Abstract: An architecture tangibly embodied on a computer readable medium, the architecture for creating a particle system to be used in a physical simulation, including: a plurality of particle generation modules, wherein a particle generation module generates particles in a particle system; a plurality of particle motion modules, wherein a particle motion module produces physical motion of particles in a particle system; a plurality of particle display modules, wherein a particle display module renders particles in a particle system; a plurality of target effect modules, wherein a target effect module modifies particles in a particle system to perform in a certain way when they collide with an object; and a plurality of particle data structures.

Abstract: A system and method for providing decision support to a physician during a medical examination is disclosed. Data is received from a sensor representing a particular medical measurement. The received data includes image data. The received data and context data is analyzed with respect to one or more sets of training models. Probability values for the particular medical measurement and other measurements to be taken are derived based on the analysis and based on identified classes. The received image data is compared with training images. Distance values are determined between the received image data and the training images, and the training images are associated with the identified classes. Absolute value feature sensitivity scores are derived for the particular medical measurement and other measurements to be taken based on the analysis. The probability values, distance values and absolute value feature sensitivity scores are outputted to the user.

Abstract: A system and method for detecting an occupant and head pose using stereo detectors is disclosed. In the training stage, pairs of images taken simultaneously from a pair of stereo cameras are received and components in each pair of images are identified. Features are associated with each component and a value is associated with each feature. Among them, a subset of features with best discriminative capabilities is selected and forms a strong classifier for a given component in a pair of images. In the detection stage, the strong classifiers are used in the incoming image pairs to detect components. Identified components are used to detect occupants and head pose of the occupants. Stereo detection is combined with stereo matching in a systematic way to improve occupant detection and localization.

Abstract: A plane position for a standard view is detected from three-dimensional echocardiographic data. The position of the plane within the volume is defined by translation, orientation (rotation), and/or scale. Possible positions are detected and other possible positions are ruled out. The classification of the possible positions occurs sequentially by translation, then orientation, and then scale. The sequential process may limit calculations required to identify the plane position for a desired view.

Abstract: A method for deformable registration of 2 digital images includes providing a pair of digital images, including a fixed image and a moving image, extracting a set of edge images from each image of the pair of images, each edge set being extracted at a different resolution, selecting a pair of edge images with a lowest resolution, determining a mapping from edge points of the fixed image to edge points of moving image using a geodesic thin plate spline interpolation, applying the mapping to a next higher resolution edge point image of the moving image, selecting a pair of edge images at a next higher resolution, where a moving edge image is the moving edge image to which the mapping has been applied, repeating the steps at a next higher resolution for all edge images in the set of edge images, and applying the mapping to an entire moving image.

Abstract: Methods for segmentation of an object from a background in an image are disclosed. Segmentation is achieved by an adapted Random Walker segmentation method using directed edges in a graph. The segmentation applies the minimization of an approximation of an energy function. A minimizer of the approximated energy function can be found by using iterative steps. Weights are assigned to an edge between two nodes. The weights are dependent on the direction of an edge. A system for segmentation of an object from a background is also disclosed.

Abstract: A system and method for illumination invariant change detection are provided, the system including a processor, an energy ranking unit in signal communication with the processor for extracting block coefficients for the first and second images and computing an energy difference responsive to the coefficients for a frequency energy between the first and second images, and a change detection unit in signal communication with the processor for analyzing the energy difference and detecting a scene change if the energy difference is indicative of change; and the method including receiving first and second images, extracting block coefficients corresponding to frequency energies for the first and second images, computing an energy difference for at least one of the frequency energies between the first and second images, analyzing the at least one energy difference, and detecting a scene change if the energy difference is indicative of change.

Abstract: A method for deformable registration including determining a vector field from a two-dimensional matching of a volume of an object of interest and a two-dimensional image of the object of interest, providing a deformation profile, and finding a volume deformation that maps to a state of the two-dimensional image, wherein the deformation is parameterized by the vector field and control points of the deformation profile to find a control point configuration of the volume deformation.

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 for automatic virtual endoscopy navigation, including: (a) using a fisheye camera to generate an endoscopic image and a depth image from a current position of the camera in lumen computed tomographic (CT) data; (b) segmenting a first region and a second region from the depth image, wherein the first region identifies a view direction of the camera and the second region is an area through which the camera can be moved without touching an inner surface of the lumen; (c) moving the camera from the current position, while pointing the camera in the view direction, to a next position in the second region; and (d) repeating steps (a-c) in sequence using the next position in step (c) as the current position in step (a).

Abstract: Feature processing is provided for lung nodules in computer-assisted diagnosis. A feature that may better distinguish nodules from background is extracted using a Hough transform. Rather than relying on a specific boundary shape, the Hough transform accumulates evidence associated with a region, such as a ring region. The accumulated evidence provides a feature score without requiring a nodule to fit a specific shape. In another approach, a background level is determined from extracted features. Rather than attempting to normalize an image prior to extraction, the features are normalized. The feature normalization and generalized Hough transform extraction may be used together or alone.

Abstract: A method for view classification includes providing a frame of an object of interest, detecting a region of interest within the object of interest for each of a plurality of detectors (e.g., binary classifiers), wherein each binary classifier corresponds to a different view, performing a global view classification using a multiview classifier for each view, outputting a classification for each view, fusing outputs of the multiview classifiers, and determining and outputting a classification of the frame based on a fused output of the multiview classifiers.