摘要:
A method and system for left ventricle (LV) detection in 2D magnetic resonance imaging (MRI) images is disclosed. In order to detect the LV in a 2D MRI image, a plurality of LV candidates are detected, for example using marginal space learning (MSL) based detection. Candidates for distinctive anatomic landmarks associated with the LV are then detected in the 2D MRI image. In particular, apex candidates and base candidates are detected in the 2D MRI image. One of the LV candidates is selected as a final LV detection result by ranking the LV candidates based on the LV candidates, the apex candidates, and the base candidates using a trained ranking model.
摘要:
In a method and magnetic resonance (MR) apparatus for determination of movement of an examination subject during the acquisition of (MR) measurement data using at least two antenna elements that exhibit respectively different spatial positions, after each radiated excitation pulse a navigator signal is acquired in the measurement data and movement of the examination subject between two excitation pulses during the acquisition of the measurement data is determined from a change of the signal strength of the navigator signal in the at least two antenna elements and based on the respective spatial positions of the antenna elements.
摘要:
In a method for evaluation of two images of an organ system acquired at different points in time to establish a pathological variation, the organ system exhibits a first region and a second region that are present in and that are differentiated in each of the images, with the second region of the pathological variation being acquired more strongly than the first region. A registration is determined that causes the respective first region in two images to be in registration with each other. Imaging system-dependent differences, in particular deformations, are determined and compensated between the two images. After an extension of the registration such that the second region is encompassed as well by the extended registration, via a transformation one of the two images to the other can be made, presented and/or stored that includes the second region, using the extended registration. A medical imaging system with a computer can implement the method.
摘要:
A method for identifying a region of interest within a time sequence of images includes acquiring a time sequence of images comprising a plurality of image frames. Image segmentation is performed to segment a region of interest (ROI) from within each of the plurality of image frames of the time sequence of images. Manual edits are received for the ROI within one or more of the plurality of image frames. The manual edits are propagated to other image frames of the plurality of images. An extent to which each of the manual edits are propagated to other image frames is dependent upon a transformation function or deformation field used to propagate the manual edits and a weighing factor that is influenced by a distance in time between the other image frames and the frames that have been manually edited.
摘要:
In a method to determine an inversion time value for contrast improvement between different tissue in a contrast agent-supported magnetic resonance imaging, a series of magnetic resonance images of an imaging area is acquired using an inversion recovery sequence with different inversion times. A structure in the magnetic resonance images is segmented and a time response of the signal intensity of image elements corresponding to one another in the magnetic resonance images of the segmented structure is automatically determined. Minima of the signal intensity in the segmented structure are determined automatically and associated with the associated inversion time values. The optimal inversion time value for contrast improvement is automatically determined from the inversion time values that have been associated with the minima of the signal intensity in the segmented structure.
摘要:
In a method to determine an inversion time value for contrast improvement between different tissue in a contrast agent-supported magnetic resonance imaging, a series of magnetic resonance images of an imaging area is acquired using an inversion recovery sequence with different inversion times. A structure in the magnetic resonance images is segmented and a time response of the signal intensity of image elements corresponding to one another in the magnetic resonance images of the segmented structure is automatically determined. Minima of the signal intensity in the segmented structure are determined automatically and associated with the associated inversion time values. The optimal inversion time value for contrast improvement is automatically determined from the inversion time values that have been associated with the minima of the signal intensity in the segmented structure.
摘要:
In a method and magnetic resonance (MR) apparatus for determination of movement of an examination subject during the acquisition of (MR) measurement data using at least two antenna elements that exhibit respectively different spatial positions, after each radiated excitation pulse a navigator signal is acquired in the measurement data and movement of the examination subject between two excitation pulses during the acquisition of the measurement data is determined from a change of the signal strength of the navigator signal in the at least two antenna elements and based on the respective spatial positions of the antenna elements.
摘要:
A method including receiving an image sequence, wherein the image sequence includes a plurality of two-dimensional (2D) image frames of an organ arranged in a time sequence; constructing a three-dimensional (3D) volume by stacking a plurality of the 2D image frames in time order; detecting a best bounding box for a target of interest in the 3D volume, wherein the best bounding box is specified by a plurality of parameters including spatial and temporal information contained in the 3D volume; and determining the target of interest from the best bounding box.
摘要:
A method and system for left ventricle (LV) detection in 2D magnetic resonance imaging (MRI) images is disclosed. In order to detect the LV in a 2D MRI image, a plurality of LV candidates are detected, for example using marginal space learning (MSL) based detection. Candidates for distinctive anatomic landmarks associated with the LV are then detected in the 2D MRI image. In particular, apex candidates and base candidates are detected in the 2D MRI image. One of the LV candidates is selected as a final LV detection result by ranking the LV candidates based on the LV candidates, the apex candidates, and the base candidates using a trained ranking model.
摘要:
A method for identifying a region of interest within a time sequence of images includes acquiring a time sequence of images comprising a plurality of image frames. Image segmentation is performed to segment a region of interest (ROI) from within each of the plurality of image frames of the time sequence of images. Manual edits are received for the ROI within one or more of the plurality of image frames. The manual edits are propagated to other image frames of the plurality of images. An extent to which each of the manual edits are propagated to other image frames is dependent upon a transformation function or deformation field used to propagate the manual edits and a weighing factor that is influenced by a distance in time between the other image frames and the frames that have been manually edited.