Abstract: According to an embodiment of the invention, signals coming from a number of pixels or sub-pixels are compared and those signals from pixels or sub-pixels, which are substantially brighter than the other pixels in the comparison, are excluded from contributing to the output signal, to suppress direct detection events in X-ray detectors. For this an X-ray detector apparatus (101) can comprise: —an array (102) of pixel arrangements (303), —each pixel arrangement (303) comprising at least one radiation collection device (311) for converting incident radiation into a collection device signal, —switching arrangements (313, 324, 314, 142; 313, 315, 314, 352, 142; 313, 315, 314; 361) for providing to respectively one output element (141) a signal derived from the collection device signals of a plurality of radiation collection devices (311) of at least one pixel arrangement (303).

Abstract: A method and a computing unit are disclosed for measuring and displaying the bone density of a patient. In at least one embodiment, separate projection data are used from a CT scan with at least two different x-ray energy regions; volume displays for bone material and at least one further material composition are generated; two DEXA projection recordings with different x-ray energy spectra are simulated from these volume displays; the two simulated DEXA projection recordings are used to determine the specific bone mass density according to the DEXA method; and at least one projection recording and at least one average specific bone mass density are output.

Abstract: A self-learning imaging method is particularly suited radiation imaging, such as for mammography. A plurality of training data sets are displayed on a display apparatus. A grayscale value setting is selected for each training data set. A feature set with at least one feature is assigned to each training data set. The feature set and the grayscale value setting are stored for each training data set. The grayscale value setting of an examination data set is selected according to the feature sets and the grayscale value setting of the training data sets.

Abstract: Each image in a first set of images includes respective exposures of an image capture device to a beam of radiation, each of a plurality of components of a radiation delivery system being at respective specified orientations with respect to a three-dimensional coordinate system during each of the exposures. Respective beam images are reconstructed from each of the exposures by drawing a line at a predetermined angle to the first image and through a center of a radiation beam shown on each first image. The reconstructed beam images are combined on a second image.

Abstract: In one aspect, there is disclosed a digital signal processor and method performed by the same for performing object detection, including facial detection, in a reduced number of clock cycles. The method comprises using Sobel edge detection to identify regions with many edges, and classifying those regions as foreground candidates. Foreground candidates are further checked for vertical or horizontal symmetry, and symmetrical windows are classified as face candidates. Viola-Jones type facial detection is then performed only on those windows identified as face candidates.

Abstract: Computer-implemented methods of reconstructing an image object for a measured object in object space from image data in data space cause a computer system to execute instructions for providing zonal information separating the object space into at least two zones, providing at least two zonal image objects, each zonal image object being associated with one of the at least two zones, performing a zonal smoothing operation on at least one of the zonal image objects, thereby generating at least one smoothed zonal image object, reconstructing the image object on the basis of the at least one smoothed zonal image object, and outputting the image object.

Abstract: An image processing apparatus includes a probability value calculator that calculates, based on color feature data of a pixel included in an image, respective probabilities that the pixel belongs to a specific area and a non-specific area; a weighted edge intensity calculator that calculates a weighted edge intensity between neighboring pixels based on pixel values and color feature data of the pixel included in the image and a neighboring pixel of the pixel; an energy function creator that uses the probabilities and the weighted edge intensity to create an energy function expressed by a result of an area determination of the pixel; and an area divider that divides the image into the plurality of areas based on the energy function.

Abstract: An apparatus for generating a diagnosis image includes a local contrast characteristic calculator configured to calculate local contrast characteristics of radiation image data of a low-energy sub-band from radiation image data generated by radiation having at least two energy bands passing through a subject; a local contrast characteristic applier configured to apply the calculated local contrast characteristics to radiation image data of a full-energy band generated by the radiation having at least two energy bands passing through the subject; and a diagnosis image generator configured to generate a diagnosis image of the subject based on the radiation image data of the full-energy band to which the local contrast characteristics have been applied.

Abstract: In a method for displaying mammography images, an identification of the mammography images is first inputted via a user interface of a computer system. A host is employed to receive the identification for activating the mammography images and reading a header of the mammography images. The host reads a plurality of displaying rules previously configured for comparing with the header of the mammography images. The host then automatically selects one of the plurality of displaying rules that is best conformed to the header of the mammography images. The host automatically classifies the mammography images according to the selected one displaying rule. Finally, a monitor displays the classified mammography images.

Abstract: Method of generating radiation images of an elongate body by applying different computer-implemented stitching methods to the same set of partial radiation images. A warning is generated in case of substantial deviation between the applied stitching methods.

Abstract: There are provided an image processing apparatus, line detection method and a computer-readable, non-transitory medium that can precisely detect boundaries of a document from a read image. The image processing apparatus includes an edge pixel extractor for extracting edge pixels from an input image, a line candidate detector for extracting a line candidate from the extracted edge pixels by using Hough transformation, and a line detector for detecting a line from edge pixels within a predetermined distance from the line candidate by using the least square method.

Abstract: An image processing apparatus and method. The image processing apparatus includes: a data acquisition device for acquiring image data of a subject including a target bone; and a data processor for acquiring binary image data by performing thresholding based on the image data, segmenting the binary image data into a plurality of segments by labeling, determining one of the plurality of segments as a target image based on image characteristics of the target bone, and measuring a length of the target bone based on the target image.

Abstract: A method, wireless system, and medium are provided for estimating capacity for a new communication session initiated by a wireless device. The wireless system includes a base station and wireless devices that wirelessly connect to the base station. The base station executes a wireless scheduler that coordinates wireless transmission over wireless networks. The base station also executes a bandwidth estimation component to estimate available bandwidth for a new communication session. The estimated available bandwidth is used in a quick configuration message communicated from the base station to a wireless device to notify the wireless device of the capacity available at the base station and of a transmission rate for the wireless device.

Abstract: In the CT imaging system, a one-direction condition improves noise uniformity in the denoised images and avoids over smoothing in the low noise regions in an image, assuming that the image originally has an unequal noise distribution. On the other hand, the discrete gradients of total variation (DTV) minimization results in an improved edge preserving effects in comparison to the conventional total variation (TV) minimization. Using DTV, the pixel values on an edge will not be substantially affected after a certain denoising treatment. The difference between the DTV minimization and the conventional TV minimization is substantially negligible for strong edges while the DTV minimization substantially improves in preserving the weak edges. DTV keeps the original values while TV slightly smoothes the values for the pixel near the bottom and top of edges.

Abstract: An edge graph in which a pixel of an image is set as a node and an edge is set between nodes is generated. The dissimilarity or similarity between nodes at the two ends of the edge is used as the feature amount of the edge, and the edge is classified into one of a plurality of classes based on the feature amount. The edge of interest is selected in ascending class order of the feature amount, and it is determined whether to merge determination target regions to which the nodes at the two ends of the edge of interest belong. Determination target regions determined to be able to be merged are merged, and a feature amount in the merged region is updated.

Abstract: A method of classifying, with a computer processor, at least one feature of cells from a low contrast, digital image. The method includes generating a contrast-enhanced image by applying a high-pass filter to the low contrast, digital image. The contrast-enhanced image is smoothed with a first low pass filter. A background image, generated from the low contrast, digital image, is subtracted from the smoothed, contrast-enhanced image to form an analysis image. The at least one feature is identified in analysis image.

Abstract: Methods for detecting structured artifacts in a video may begin by accepting a video frame at a video input and then generating a filtered frame from the video frame. After a differenced image is produced, groups of connected pixels (blobs) within the differenced frame are identified, and isolated blobs are removed to produce a cleaned image. A Fourier transform is performed on the cleaned image, and structured artifacts may be identified based on a comparison of magnitudes of the Fourier components of the cleaned image. Devices that detect and identify structured artifacts are also described.

Abstract: The present invention provides a method for brightness equalization of a plurality of images to equalize brightness when composing, into a single image, a plurality of images acquired from a plurality of cameras.

Abstract: A classifier (20) is trained by a feature matrix (18, 18?) made up of feature vectors (F11, . . . , Fkm). The feature vectors are generated by operating on each of a plurality (k) of training image data sets with each of a plurality (m) of image processing algorithms (121, . . . , 12m) to generate processed and segmented images. Features of the segmented regions are extracted (14) to generate the feature vectors. In this manner, the classifier is trained with data generated with a variety of image processing algorithms.

Abstract: An image processing device includes a tomographic image generating section that acquires generates tomographic images, a display processing section that displays a second radiographic image, and detection section. If a region of interest is specified on the second radiographic image, the detection section performs image analysis by comparing the region of interest with corresponding regions that are regions in the tomographic images corresponding to the region of interest, and detects a tomographic image including a corresponding region that is similar to the region of interest. If a position of interest is specified on the second radiographic image, the detection section performs image analysis by comparing the position of interest with corresponding positions that are positions in the tomographic images corresponding to the position of interest, and detects a tomographic image including a corresponding position that is similar to the position of interest.

Abstract: A method for generating a solid model of a heart in a predetermined phase of its periodic pumping movement is proposed. During a single C-arm rotation of a C-arm X-ray unit an electrocardiogram signal with consecutive RR intervals is observed by an EKG trigger. In each RR interval a digital X-ray image is generated by EKG triggering of the C-arm X-ray unit as soon as a time difference between the current phase and the predetermined phase is less than a predetermined value. For each of the X-ray images in addition a parameter influencing the geometry of the C-arm X-ray unit is ascertained. The solid model is generated from several of the X-ray images. At least one X-ray image is selected from each RR interval and for each of the selected X-ray images a projection data set for the calculation of the solid model is ascertained by the ascertained parameter.

Abstract: An image analysis apparatus that analyzes, based on a series of three-dimensional images of lungs at different time phases, a three-dimensional distribution of ventilation volume of the lungs, includes a lung region extraction unit that extracts a lung region from each of the three-dimensional images; an alignment unit that aligns the lung regions between the series of three-dimensional images and calculates a displacement vector field in the lung region; a function calculation unit that calculates a local ventilation volume function representing a temporal change in ventilation volume at each point in the displacement vector field in each of the three-dimensional images based on the displacement vector field; and a quantification unit that quantifies a difference between the local ventilation volume function and a benchmark ventilation volume function serving as a reference and calculates a quantitative value representing the difference.

Abstract: When displaying a stereo image of radiographic images, troublesome work for indicating an abnormal shadow with a three-dimensional cursor is reduced. An abnormal shadow detection unit 8c detects abnormal shadows from radiographic images for left and right eyes for displaying a stereo image. When a plurality of abnormal shadows are detected, an abnormal shadow specification unit 8d specifies abnormal shadows corresponding to each other in two radiographic images. A display control unit 8e gives a three-dimensional cursor to a predetermined abnormal shadow of the plurality of abnormal shadows, and displays a stereo image using the radiographic images for left and right eyes.

Abstract: In an apparatus configured to generate a report based on diagnosis target images, image characteristic conditions to identify a plurality of diagnosis target images specified by a user as a group are derived, search conditions of images similar to the diagnosis target images by using the obtained image characteristic conditions are determined, a database is searched for one or more similar images satisfying the search conditions; and image findings satisfying predetermined conditions is extracted from image findings attached to one or more obtained similar images.

Abstract: A method of image reconstruction is provided. When an object is not placed in a measurement space, first intensity images of an electromagnetic wave passing through the measurement space and corresponding to photon energy levels are measured. When the object is placed in the measurement space, second intensity images of the electromagnetic wave passing through the object and corresponding to photon energy levels are measured. In a database, data including an attenuation coefficient of each substance respectively having components irradiated by the electromagnetic wave corresponding to each photon energy level and a thickness of each substance in a transmission direction of the electromagnetic wave corresponding to each photon energy level are provided. Attenuation images of the object respectively corresponding to the components are calculated according to the data and the first and second intensity images. An image reconstruction system and a method and system of image construction are also provided.

Abstract: The inversion algorithm based on the maximum entropy method (MEM) removes unwanted effects in high energy imaging resulting from an uncollimated source interacting with a finitely thick scintillator. The algorithm takes as input the image from the thick scintillator (TS) and the radiography setup geometry. The algorithm then outputs a restored image which appears as if taken with an infinitesimally thin scintillator (ITS). Inversion is accomplished by numerically generating a probabilistic model relating the ITS image to the TS image and then inverting this model on the TS image through MEM. This reconstruction technique can reduce the exposure time or the required source intensity without undesirable object blurring on the image by allowing the use of both thicker scintillators with higher efficiencies and closer source-to-detector distances to maximize incident radiation flux.

Abstract: A method for obtaining a digital chest x-ray image of a patient. The method includes providing a default set of technique settings for the chest x-ray, wherein the default set is selectable by an operator command and includes using a peak kilovoltage exposure setting that is below 90 kVp with beam filtration of the x-ray, and applying a rib contrast suppression algorithm to the digital chest x-ray image data acquired from the exposure.

Abstract: A system for generating a reconstruction of an object of interest comprises a shape model generator (1) for generating a shape model representing a shape of the object in dependence on a plurality of projections of the object, and a reconstructor (2) for reconstructing the object, based on the projections, in dependence on the shape model to obtain the reconstruction of the object. The reconstructor (2) comprises a soft-tissue reconstructor (4) for generating a reconstruction favoring soft tissue, based on the plurality of projections, and a sparse reconstructor (5) for generating a reconstruction of sparse objects, based on the plurality of projections. The reconstructor (2) comprises a clipping subsystem (3) for clipping an outside of the object from the reconstruction, based on the shape model, or the reconstructor (2) is arranged for reconstructing only an inside and/or boundary of the object as defined by the shape model.

Abstract: Disclosed herein is a framework for facilitating fused-image visualization for surgery evaluation. In accordance with one aspect of the framework, at least one pre-operative image and at least one intra-operative image of an anatomical structure are received. A region of interest may be identified in the intra-operative image. The pre-operative image may be straightened, and a symmetric region may be identified in the straightened pre-operative image. The symmetric region is substantially symmetrical to a target region in the straightened pre-operative region. The target region corresponds to the region of interest in the intra-operative image. The symmetric region may be extracted and reflected to generate a reference image. The intra-operative image may be rigidly registered with the reference image to generate registered intra-operative image, which is overlaid on the target region in the straightened pre-operative image to generate a fused image.

Abstract: A medical image system includes: a storage unit which stores a first medical image; a selection unit which selects a medical image to be associated with a second medical image; a designation unit which designates an abnormal shadow candidate; a reception unit which receives the second medical image newly created; a determination unit which determines whether or not the first medical image selected is an image suited for association, and the abnormal shadow candidate designated and the second medical image received satisfy a predetermined condition; an association unit which stores the second medical image in association with the abnormal shadow candidate; and a monitoring unit which monitors the association, outputs a warning, and stores the abnormal shadow candidate or the second medical image in association with information indicating there is no second medical image or abnormal shadow candidate to be associated, respectively.

Abstract: Described embodiments include a system, method, and computer program product. In a described system, a receiver circuit receives at least two reference images of a patient body part. Each reference image includes a respective landmark subsurface feature of the patient body part, and each imaged landmark subsurface feature has a respective spatial relationship to a respective region of a surface of the patient body part imaged during a medical examination. A feature matching circuit determines a correspondence between (x) each atlas landmark subsurface feature of the patient body part included in a landmark subsurface feature atlas and (y) each respective imaged landmark subsurface feature. A reporting circuit generates informational data reporting a depiction of an area of the surface of the patient body part by at least two adjacent imaged regions of the surface of the patient body part. A communication circuit outputs the informational data.

Abstract: A statistical analysis is performed on pixel values of at least one region of interest in an image obtained by substantially uniform irradiation of an x-ray detector and deciding upon the presence of a source of x-ray beam in-homogeneity by comparing the results of the statistical analysis with at least one predetermined acceptance criterion.

Abstract: A correction information generation method and a correction information generation apparatus enabling easy Flat-Field Correction operation without special accessory equipment are provided. The correction information generation method for performing Flat-Field Correction of X-ray detection sensitivity on a pixel detector, includes the steps of: moving the relative position of a detector 130 with respect to an incident X-ray having a cross-sectional beam shape traversing a detection surface so that the whole of the detection surface is irradiated with the incident X-ray in total time and each of pixels arranged in the moving direction is uniformly irradiated; and generating information for correcting the sensitivity of a pixel based on an intensity value detected for a given energy band of the incident X-ray.

Abstract: Systems and methods are disclosed for evaluating cardiovascular treatment options for a patient. One method includes creating a three-dimensional model representing a portion of the patient's heart based on patient-specific data regarding a geometry of the patient's heart or vasculature; and for a plurality of treatment options for the patient's heart or vasculature, modifying at least one of the three-dimensional model and a reduced order model based on the three-dimensional model. The method also includes determining, for each of the plurality of treatment options, a value of a blood flow characteristic, by solving at least one of the modified three-dimensional model and the modified reduced order model; and identifying one of the plurality of treatment options that solves a function of at least one of: the determined blood flow characteristics of the patient's heart or vasculature, and one or more costs of each of the plurality of treatment options.

Abstract: A system and/or method automatically identifies one or more vascular regions in a medical image or set of medical images. For example, the system/method may automatically identify vascular structures as belonging to the left carotid, right carotid, and/or basilar vascular regions in the head. The system/method takes as input the medical image(s) and automatically identifies one or more vascular regions. The system/method may also automatically generate MIP renderings of the identified region or regions.

Abstract: A method, apparatus, article of manufacture, and computer program product display multiple slices of a three-dimensional body in a computer drawing application. A first view of a 3D body is displayed. One or more slice sketches are defined on the first view. A single slice view of the three dimensional body is displayed. The single slice view simultaneously depicts all of the slices with a zero-depth representation of each slice.

Abstract: According to one embodiment, an X-ray diagnostic apparatus includes a data acquiring unit and a data processing unit. The data acquiring unit acquires X-ray projection data corresponding to plural directions from an object in which a stent having markers has been inserted by exposing X-rays to the object from the plural directions. The data processing unit obtains a spatial position corresponding to at least one marker out of the markers based on first three dimensional image data generated by first image reconstruction processing of the X-ray projection data to generate second three dimensional image data by second image reconstruction processing of the X-ray projection data with a correction using a shift amount obtained based on the X-ray projection data and projected data of the one marker on a projected plane of the X-ray projection data.

Abstract: A 3D-originated cardiac roadmapping device and method include providing 3D+t image data of a vascular structure of an object; acquiring 2D image data of the object that includes the vascular structure, where the 2D image data includes at least one 2D image. The method further includes projecting the vascular structure, thereby generating mask images based on the 3D+t image data; and registering the at least one 2D image with one of the mask images. The registration includes finding the maximum of a similarity factor between the mask images and the at least one 2D image. The method further includes generating a combination of the at least one 2D image and a projection of the vascular structure based on the 3D+t image data according to the registration; and displaying the combination as a guiding vessel tree projection.

Abstract: A method and system for acquiring, processing, storing, and displaying x-ray mammograms Mp tomosynthesis images Tr representative of breast slices, and x-ray tomosynthesis projection images Tp taken at different angles to a breast, where the Tr images are reconstructed from Tp images.

Abstract: A method and an apparatus for providing panoramic image data by reconstructing frame images captured by a panoramic imaging apparatus, are disclosed. In reconstruction of images with multiple image layers, sizes of images reconstructed with an image layer or images to be used for a reconstruction are scaled. An image is selected by analyzing sharpness. A panoramic image is provided by combining selected image. According to the present invention, parts having unclear focal planes may be completely removed in a panoramic image and it is possible to provide an image including only with focused regions.

Abstract: An imaging method includes calculating a derivative back projection (DBP) result value using a DBP method with respect to a projection image of a field of view (FOV) inside an object, and reconstructing an image of the FOV by applying a regulation function to the FOV while reconstructing the image of the FOV using the DBP result value.

Abstract: In one aspect, a method for determining a value for at least one parameter of a configuration of a model, the model associated with structure of which view data has been obtained from at least one x-ray scanning device capable of producing x-ray radiation, the view data being obtained, at least in part, by scanning at least a portion of the structure, wherein the view data is attenuation data of the x-ray radiation attenuated by the structure as a function of view angle about the structure is provided. The method comprises acts of operating on the view data to detect at least one feature in the view data, and determining the value for the at least one parameter of the configuration of the model based, at least in part, on the at least one feature.

Abstract: The present disclosure presents systems and methods for correcting image artifacts on an x-ray image. X-ray images are obtained and processed with a correction algorithm that generates corrected pixel lines having pixels with corrected pixel values. The corrected pixel lines can then be processed with a filtering algorithm that generates filtered pixel line having pixels with a filtered pixel value. The bad pixel lines are replaced by the filtered pixel lines to generate corrected x-ray images.

Abstract: In a method for displaying mammography images, an identification of the mammography images is first inputted via a user interface of a computer system. A host is employed to receive the identification for activating the mammography images and reading a header of the mammography images. The host reads a plurality of displaying rules previously configured for comparing with the header of the mammography images. The host then automatically selects one of the plurality of displaying rules that is best conformed to the header of the mammography images. The host automatically classifies the mammography images according to the selected one displaying rule. Finally, a monitor displays the classified mammography images.

Abstract: A method and system for volumetric quantification of local bone changes includes the steps of loading at least a first and second (cone-beam) computed tomography three dimensional image, registering the first three dimensional image and second three dimensional image to one coordinate system, selecting a region of interest in one of the first three dimensional image or the second three dimensional image.

Abstract: A 2D or 3D velocity field is reconstructed from a cross-correlation analysis of image pairs of a sample, without first reconstructing images of the sample spatial structure. The method can be implemented via computer tomographic X-ray particle image velocimetry, using multiple projection angles, with phase contrast images forming dynamic speckle patterns. Estimated cross-correlations may be generated via convolution of a measured autocorrelation function with a velocity probability density function, and the velocity coefficients iteratively optimized to minimize the error between the estimated cross-correlations and the measured cross-correlations. The method may be applied to measure blood flow, and the motion of tissue and organs such as heart and lungs.

Abstract: A magnetic resonance system includes a magnetic resonance scanner having a multi-channel transmit coil or coil system and a magnetic resonance receive element; and a digital processor configured to perform an imaging process. The image process includes shimming the multi-channel transmit coil or coil system, acquiring a coil sensitivity map for the magnetic resonance receive element using the multi-channel transmit coil or coil system, acquiring a magnetic resonance image using the magnetic resonance receive element and the shimmed multi-channel transmit coil or coil system, and performing an intensity level correction on the acquired magnetic resonance image using the coil sensitivity map to generate a corrected magnetic resonance image.

Abstract: Overview images that represent the overview of a structure (e.g., the large intestine) are generated based on volume data, and displayed on a screen. Points within the overview images and points corresponding thereto in the volume data are set as target points. A target volume that includes the target points and line of sight vectors within the volume data having the target points as endpoints and a movable viewpoint as a starting point are set within the volume data. The directions of the line of sight vectors are changed by moving the viewpoint, and the target volumes are projected onto projection planes perpendicular to the directions of the line of sight vectors to generate detailed images that represent details of the structure in the vicinity of the target points. The detailed images are displayed on the screen.

Abstract: There is provided a method of reducing noise in a medical image while maintaining structure characteristics within the medical image. The method of reducing noise in the medical image includes: a step of estimating the amount of noise at each pixel by using a look-up table that previously stores physical properties of an image capturing device; a step of calculating a structure direction and a signal coherence at each pixel; a step of performing anisotropic smoothing by using an anisotropic smoothing filter kernel that reflects the structure direction and the signal coherence; and a step of obtaining a structure direction and a signal coherence from an image on which the anisotropic smoothing is performed, obtaining an anisotropic smoothing filter kernel that reflects the obtained structure direction and the signal coherence, and performing filtering that reflects statistical properties of the estimated amount of noise.

Abstract: A method for co-registration of angiography and intravascular images is described in which intravascular images are in the form of a sequence of images obtained from an intravascular imaging device which is pulled back through a vessel. The method includes generating a three-dimensional reconstruction of the trajectory of the intravascular device within the vessel from two or more bi-dimensional angiography images of such vessel which have been obtained from different perspectives. The method also includes determining a first position of an element of the device within the 3D reconstruction of the trajectory and correlating the position of such element with a correspondent point in the reconstructed trajectory during pull back. Further, the method includes correlating each intravascular image of the sequence with a corresponding spatial position within at least one of the bi-dimensional angiography images. A corresponding system and computer program are also described.