Abstract: An image may be processed to normalize and/or remove noise from the image. The processing of the image may involve decomposition of the image into multiple components and subsequent gray scale registration across multiple scales.

Abstract: A technique for segmenting a ribcage, e.g., in a chest radiograph, may involve determining whether or not the top of the image cuts through the lungs. The process may then proceed to segment the top and the sides of the ribcage. A dynamic programming technique may be used to perform the segmentation.

Abstract: A method of obtaining one or more components from an image may include normalizing and pre-processing the image to obtain a processed image. Features may be extracted from the processed image. Neural-network-based regression may then be performed on the set of extracted features to predict the one or more components. These techniques may be applied, for example, to the problem of extracting and removing bone components from radiographic images, which may be thoracic (lung) images.

Abstract: Computer-aided diagnosis techniques may be combined with techniques to obtain derived images from radiographic images to provide enhanced computer-aided diagnosis of, for example, lung nodules.

Abstract: A method is disclosed, in a diagnostic medical environment, that enhances workflow while using a computer-aided-detection (or diagnosis) (CAD) system in the environment. The method comprises generating image data with a diagnostic medical imaging acquisition system. The image data is transmitted from the diagnostic medical imaging acquisition system to a computer-aided-detection (or diagnosis) (CAD) system and an archive/review station. Detection results are generated by processing the image data, using the CAD system, while storing and viewing the image data on the archive/review station. The detection results are transmitted from the CAD system to the archive/review station. The detection results are integrated with the image data by the archive/review station to form composite image data. The composite image data is displayed by the archive/review system.

Abstract: Computer-aided diagnosis techniques may be combined with techniques to obtain derived images from radiographic images to provide enhanced computer-aided diagnosis of, for example, lung nodules.

Abstract: Computer-aided diagnosis techniques may be combined with dual-energy radiography techniques to provide enhanced computer-aided diagnosis of, for example, lung nodules.

Abstract: Images may be registered by performing a number of operations that may include coarse alignment, coarse registration, and fine registration. The finely-registered images may be subtracted to obtain a residual image.

Abstract: An image may be processed to normalize and/or remove noise from the image. The processing of the image may involve decomposition of the image into multiple components and subsequent gray scale registration across multiple scales.

Abstract: A technique for registering multiple image representations relating to a common region of interest may involve producing multiple displacements from the image representations for a key point. A final displacement for the key point may be determined from correlations of the multiple displacements.

Abstract: A technique for segmenting a ribcage, e.g., in a chest radiograph, may involve determining whether or not the top of the image cuts through the lungs. The process may then proceed to segment the top and the sides of the ribcage. A dynamic programming technique may be used to perform the segmentation.

Abstract: A method of obtaining one or more components from an image may include normalizing and pre-processing the image to obtain a processed image. Features may be extracted from the processed image. Neural-network-based regression may then be performed on the set of extracted features to predict the one or more components. These techniques may be applied, for example, to the problem of extracting and removing bone components from radiographic images, which may be thoracic (lung) images.

Abstract: A user may be provided with identified regions of interest superimposed on a larger image, which may permit the user to individually examine the regions of interest. The regions of interest may be independently windowed and/or leveled and/or magnified according to parameters associated with the region of interest, which parameters may be generated by a computer-aided detection algorithm.

Abstract: Embodiments of the invention may process an input image using phase symmetry methods and use the resulting processing results to determine an object in the image. The object may be suppressed, if desired.

Abstract: Using identification of their sizes and positions, objects may be attenuated or removed from images. This may involve the use of various filtering operations and may further include coordinate transformations prior to and/or after the filtering. The filtered objects may then be subtracted from the image.

Abstract: An object in an image may be segmented by determining local pixel costs based on the image and using the local costs to determined cumulative pixel costs. A contour may then be determined based on the cumulative pixel costs.

Abstract: Computer-aided diagnosis techniques may be combined with dual-energy radiography techniques to provide enhanced computer-aided diagnosis of, for example, lung nodules.

Abstract: A user interface for facilitating a computer-aided diagnosis (CAD) includes an image input device that receives and scans the multiple images, and a film feeder that transports films from a film developer to the scanner. A multi-image identification input device uses bar code reading, numeric keypad, keyboard, network, and/or mouse to enter multiple image identification prior to image scanning. A display includes an image identification area, case processing status area, and a CAD detection and user modification area. The user can edit CAD results—accept, remove—and can add new diagnosis results to create a new composite diagnosis result.