General Electric Company

David Thomas Gering

Gopal Biligeri Avinash

Richard Scott Hinks

Sandeep Narendra Gupta

Kevin Matthew Koch

David Matthew Deaven

John David Hoford

A technique for selecting portions of a medical image data set to be stored and portions of the medical image data set to be discarded in order to reduce the overall amount of image data that is stored for each image data set. The selection is based on the clinical purpose for obtaining the medical image data. The clinical purpose for obtaining the medical image is used to select an atlas. The atlas is labeled with information that establishes the relative relevance of various regions of the atlas. The atlas is aligned to the image and the labeling information is transferred from the atlas to the medical image. Each region of the medical image is then processed based on the labeling information received from the atlas. The regions of greatest relevance are stored at their full resolution. Regions of lesser relevance are stored at less than the full resolution. Finally, regions of no relevance are discarded and not stored at all.

Atlas-based image compression

A technique for prioritizing portions of compressed multi-resolution medical image data to be processed. More relevant portions of medical image data are compressed at a higher resolution than less relevant portions of medical image data. A mask is created from the image data and used to assign data compression quality factors to corresponding image blocks in the image data. The image data in each region is compressed based on their assigned quality factor. During processing of the compressed image data, the compressed image data and the mask are accessed. The mask is used to direct the processing of the compressed image data.

Processing of content-based compressed images

A method for visualizing data includes the step of providing a virtual flight visualization of image data representing a non-landscape object.

Methods and apparatus for visualizing data

A technique for selecting portions of a multi-resolution medical image data set to be stored and the portions of the multi-resolution medical image data set to be discarded in order to reduce the overall amount of image data that is stored for each image data set. The selection is based on the clinical purpose for obtaining the medical image data. The clinical purpose for obtaining the medical image is used to select a segmentation algorithm to segment the image data into several regions based on their relevance to the purpose for obtaining the image data. A mask is created from the segmented data. The mask is used to assign data compression quality factors to corresponding regions in the image data. The image data in each region is compressed based on their assigned quality factor. The image data that is highly relevant is compressed with lossless data compression. The image data in regions of lesser relevance are compressed with lossy data compression. The image data that is of no relevance for the purpose that the image data was obtained is discarded.

Content-based image compression

A graphical user interface and method allows a user to interactively select an arterial input function. An anatomical image and time-course data corresponding to a selected region of interest are displayed simultaneously. The time-course data is displayed as an array of graphs, annotated with best-fit curves and parameters derived from fitting the time-course data. The region displayed in the graphs may be updated by panning and zooming with a mouse in the image. Time-course data corresponding to a graph is selected for use in deriving an arterial input function. The arterial input function is used to calculate maps of hemodynamic parameters.

Method, apparatus and user interface for determining an arterial input function used for calculating hemodynamic parameters

A technique for prioritizing portions of compressed multi-resolution medical image data to be processed. More relevant portions of medical image data are compressed at a higher resolution than less relevant portions of medical image data. A mask is created from the image data and used to assign data compression quality factors to corresponding image blocks in the image data. The image data in each region is compressed based on their assigned quality factor. During processing of the compressed image data, the compressed image data and the mask are accessed. The mask is used to direct the processing of the compressed image data. Depending upon the application, the mask can be used to direct that the image data for the regions of most relevance be processed before the image data for the regions of lesser relevance. However, the mask can be used to direct that the image data for the regions of lesser relevance be processed before the image data for the regions of most relevance.

Certain embodiments of the present invention provide methods and systems for selecting an application for processing an electronic image file based upon the content of the image file. Certain embodiments provide an image selector selecting an image from an image storage device, an identification module providing a label to the image based on the content of the image, an application selector choosing at least one application from a plurality of applications to process the image, and a learning unit maintaining a record of image labels and the applications presently and previously processing the images.

Methods and systems for selecting an image application based on image content

A technique for selecting portions of a dynamic medical image data set to be stored and portions of the medical image data set to be discarded or processed differently in order to reduce the overall amount of image data that is stored for each image data set. The dynamic image data is segmented and registered. The segmentation and registration enables changes in intensity based on patient motion to be distinguished from changes in intensity due to anatomical function. In general, the regions with changes in intensity due to anatomical function are more relevant than regions with changes in intensity due to patient motion. The regions of greatest relevance are stored at their full resolution. Regions of lesser relevance are stored at less than the full resolution. Regions of no relevance are discarded and not stored at all.

Registration and compression of dynamic images

A method for generating an image of a region of interest of a subject includes obtaining a set of magnetic resonance (MR) data for the region of interest. In addition, photographic data for at least one surface of the region of interest is obtained, for example, from a database or by using a camera for photographing the region of interest. An image is generated by using the set of MR data to generate a depiction of at least one structure of the region of interest and by using the photographic data to generate a depiction of at least one surface of the region of interest.

Method and apparatus for generating an image using MRI and photography

System and method for incorporating user input on the fly during an otherwise automatic registration process. During rigid registration, user input adjusts the current computed pose or transformation that relates the two images being aligned. During warping, user input adjusts the flow field locally, and is gradually smoothed into the surrounding flow field. During multi-scale registration where images are first aligned at a course resolution, and subsequently at progressively finer resolutions, user input is applied at the current scale. User input is detected during the automated process either by interrupts or polling. Between user inputs the registration results are re-rendered.

Systems and methods for interactive image registration

Systems and methods are provided for accessing three dimensional representation of an anatomical surface and flattening the anatomical surface so as to produce a two dimensional representation of an anatomical surface. The two dimensional surface can be augmented with computed properties such as thickness, curvature, thickness and curvature, or user defined properties. The rendered two dimensional representation of an anatomical surface can be interacted by user so as to deriving quantitative measurements such as diameter, area, volume, and number of voxels.

System and method for flattened anatomy for interactive segmentation and measurement

Methods and system for segmenting image data are provided. The method includes fitting a topological atlas to acquired image data and generating spatially varying priors based on the fitted topological atlas. The method further includes segmenting the acquired image data based on the spatially varying priors.

Method and system for segmenting image data

A computer-aided detection system for evaluating tissue based on a series of timed images acquired both before and after a contrast agent is administered performs a temporal analysis of the tissue and then a spatial analysis in which the tissue is categorized. After the temporal and spatial analysis is performed, the results can be displayed. The displayed results can include both tissue characterization results, underlying curves used to determine the characterization, and confidence data regarding how good the characterization is expected to be. The confidence data can be provided, for example, by using variations in color schemes, displaying numerical confidence levels, or providing graphical features such as piecewise linear models.

Computer-aided detection system utilizing temporal analysis as a precursor to spatial analysis

A technique for reconstructing a corrected MR image from MR images distorted by foreign object induced magnetic fields includes locating a foreign object in a subject and defining a localized area of a field of view about the foreign object where a magnetic field distortion adversely affects a first magnetic distortion correction technique. The first magnetic distortion correction technique is applied to the field of view other than in the localized area. A second magnetic distortion correction technique is applied to the localized area and the results of the application of the first and second magnetic distortion correction techniques are combined. An image is reconstructed based on the results of the application of the first and second magnetic distortion correction techniques.

Method and apparatus for correcting distortion in MR images caused by metallic implants

A method and system are provided for controlling a motor to rapidly accelerate and synchronize with an external synchronization pulse. First, the motor is accelerated to only half of the desired speed. At this point, the phase error with the sync pulse is calculated, and the motor continues 'cruising' at half speed until the phase discrepancy diminishes. Then the motor rises to the full desired speed at the optimal time such that it is in phase with the sync pulse just as it reaches full speed. The acceleration is performed at a constant, yet slow enough, rate to receive at least three speed feedbacks. Then the instantaneous speed can be accurately measured and the next (and final) speed command during acceleration is interpolated between the ideal command for rising and the ideal command for cruising at the desired speed. The amount of phase discrepancy that diminishes while rising, as well as the ideal motor commands for cruising and rising, at both half and full speeds are adaptively learned and stored for the next run.

Growing community of inventors

Waukesha, WI, United States of America

David Thomas Gering