摘要:
A system and method are provided for contrast-invariant registration of images, the system including a processor, an imaging adapter or a communications adapter for receiving an image data sequence, a user interface adapter for selecting a reference frame from the image sequence or cropping a region of interest (ROI) from the reference frame, a tracking unit for tracking the ROI across the image sequence, and an estimation unit for segmenting the ROI in the reference frame or performing an affine registration for the ROI; and the method including receiving an image sequence, selecting a reference frame from the image sequence, cropping a region of interest (ROI) from the reference frame, tracking the ROI across the image sequence, segmenting the ROI in the reference frame, and performing an affine registration for the ROI.
摘要:
A method and system for retrospective image combination for free-breathing magnetic resonance (MR) images is disclose. A free-breathing cardiac MR image acquisition including a plurality of frames is received. A key frame is selected of the plurality of frames. A deformation field for each frame to register each frame with the key frame. A weight is determined for each pixel in each frame based on the deformation field for each frame under a minimum total deformation constraint. A combination image is then generated as a weighted average of the frames using the weight determined for each pixel in each frame.
摘要:
Magnetic resonance reconstruction includes motion compensation. Inverse-consistent non-rigid registration is used to determine motion between shots. The motion is incorporated into reconstruction. The incorporation compensates for the motion resulting from the period over which the MR data is acquired.
摘要:
A method for processing an object in image data includes the steps of drawing a contour on a pre-segmentation of an object in image data, generating at least one seed point on the pre-segmentation from an intersection of the contour and the pre-segmentation, providing a weighting factor between the seed points and the pre-segmentation, and segmenting the pre-segmentation using the seed points and the weighting factor to generate a new pre-segmentation.
摘要:
The present invention relates to a system of modeling a three dimensional target object which is represented by a plurality of cross-sectional images in order to provide a representative corresponding three dimensional model. The invention selects an initial model from a plurality of available initial models. This selection involves identifying an initial model based on physical similarity to the target object and then superimposing an initial model upon the target object, for each of the plurality of cross-sectional images. A determination is then made of an intersection contour of the initial model and a cross-sectional image of the target object and the determined intersection contour is refined in order to more closely delineate the target object. By sub-sampling points which represent the refined determined intersection contour, the invention obtains a sub-sampled contour dataset. The initial model is then adjusted towards the sub-samples contour to obtain a representative three dimensional model of the target object.
摘要:
A technique of tracking an object of interest in a sequence of images using active polyline contours. An image processor converts a sequence of images into digital image data related to light intensity at the pixels of each image. A computer stores the digital image data and forms an initial polyline that substantially outlines an edge of the object in a first image. The computer forms input polylines for each of the subsequent images which substantially outline the edge in the corresponding images and are derived from the optimal polyline of each previous such image. The computer processes the digital image data, performing a graph exploration procedure that starts with the initial polyline in the first image and the input polylines in the subsequent images. The graph exploration procedure searches polylines in a predefined search space to find the corresponding optimal polylines. The computer evaluates edge strength of the different polylines with respect to the light intensity of its underlying pixels to obtain corresponding contour costs. The polyline with the smallest contour cost is selected as the optimal contour for each of the images. The set of optimal contours are used to track the object of interest.
摘要:
The aorta and left atrium are localized from magnetic resonance data. The locations of the aorta and left atrium are detected jointly. The aorta and the left atrium are, at least in part, treated as one object. The detection may be from data representing a two-dimensional region. The two-dimensional region may be determined by first detecting the left ventricle from data representing a volume.
摘要:
A boundary in a medical image is segmented. To increase reproducibility, a multi-level segmentation approach is used. A boundary is detected based on a seed point. The boundary is used to construct a banded graph. Local segmentation is performed using the banded graph. Based on the local segmentation, a new seed point is found. The local segmentation identifies a consistent location for the seed point. The boundary detection is performed again using the new seed point.
摘要:
A method and system for propagation of myocardial infarction from delayed enhanced magnetic resonance imaging (DE-MRI) to cine MRI is disclosed. A reference frame is selected in a cine MRI sequence. Deformation fields are calculated within the cine MRI sequence to register the frames of the cine MRI sequence to the reference frame. A DE-MRI image having an infarction region is registered to the reference frame of the cine MRI sequence. The DE-MRI image may be registered to the infarction region using a hybrid registration algorithm that unifies both intensity and feature points into a single cost function. Infarction information in the DE-MRI image is then propagated cardiac phases of the frames in the cine MRI sequence based on the registration of the DE-MRI image to the reference frame and the plurality of deformation fields calculated within the cine MRI sequence.
摘要:
A method for segmenting an object of interest from an image of a patient having such object. Each one of a plurality of training shapes is distorted to overlay a reference shape with a parameter Θi being a measure of the amount of distortion required to effect the overlay. A vector of the parameters Θi is obtained for every one of the training shapes through the minimization of a cost function along with an estimate of uncertainty for every one of the obtained vectors of parameters Θi, such uncertainty being quantified as a covariance matrix Σi. A statistical model represented as {circumflex over (f)}H (Θ,Σ) is generated with the sum of kernels having a mean Θi and covariance Σi. The desired object of interest in the image of the patient is identified by positioning of the reference shape on the image and distorting the reference shape to overlay the obtained image with a parameter Θ being a measure of the amount of distortion required to effect the overlay. An uncertainty is quantified as a covariance matrix Σ and an energy function E=Eshape+Eimage is computed to obtain the probability of the current shape in the statistical shape model Eshape(Θ,Σ)=−log({circumflex over (f)}H) and the fit in the image Eimage.