Apparatus and methods are described including, using a computer processor (28), automatically identifying whether a given pixel (111) within an image corresponds to a portion of an object. A set of concentric circles (132a-c) that are disposed around the pixel are sampled, and a first function is applied to each of the circles such that the circles are defined by a first set of rotationally invariant descriptors. A second function is applied to the set of circles to generate a second set of descriptors, each of which represents a difference between respective pairs of the circles. A third function is applied such that the second set of descriptors becomes rotationally invariant. The processor identifies whether the given pixel corresponds to the portion of the object, based upon the first and second sets of rotationally invariant descriptors. Other applications are also described.

A method and apparatus for Cone-Beam Computerized Tomography, (CBCT) is configured to increase the maximum Field-Of-View (FOV) through a composite scanning protocol and includes acquisition and reconstruction of multiple volumes related to partially overlapping different anatomic areas, and the subsequent stitching of those volumes, thereby obtaining, as a final result, a single final volume having dimensions larger than those otherwise provided by the geometry of the acquisition system.

A three-dimensional cardiac image segmentation method and apparatus are provided according to examples of the present disclosure. The method includes: searching from layers of cardiac computerized tomography CT images to obtain a layer of cardiac CT image located between a heart bottom portion and a heart upper portion as a first key layer; searching on the first key layer to obtain a boundary of the heart as a contour of the heart bottom portion, and generating a curved surface model based on the contour of the heart bottom portion and a lowest point of the heart bottom portion as a heart bottom model; searching layers of cardiac CT images above the first key layer to obtain boundaries of the heart as a contour of the heart upper portion, and generating a curved surface model based on the contour of the heart upper portion as a heart upper model.

The present invention relates to image contrast enhancement. In order to provide improved and stable contrast enhancement for each acquired image, a device (10) for image contrast enhancement of an X-ray image of a vascular structure is provided. The device (10) comprises an input unit (12) and a processing unit (14). The input unit is configured to provide an acquired X-ray image of a vascular structure with a contrast injection. The contrast injection is performed with a current contrast injection setting having at least one contrast injection parameter. The input unit is further configured to provide a generic vascular structure. The input unit is also configured to provide the current contrast injection setting. The processing unit is configured to determine an assessed contrast parameter for the generic vascular structure based on the current contrast injection setting. The processing unit is further configured to determine an adapted image contrast enhancement for the generic vascular structure based on the assessed contrast parameter. The processing unit is also configured to apply the adapted image contrast enhancement to the acquired X-ray image in order to generate a contrast-enhanced X-ray image.

An apparatus for generating corrected X-ray projection data from target X-ray projection data obtained by performing an X-ray scan with a detector having an anti-scatter grid, and a method for creating a lookup table and generating corrected X-ray projection data. The apparatus includes a detector configured to detect incident X-rays, an anti-scatter grid configured to suppress scattered radiation incident on the detector, and an X-ray source configured to irradiate the target with X-rays. Processing circuitry is configured to cause the X-ray source to scan, using a peak kilovoltage (kVp), the target to produce the target projection data, determine a patient-to-detector distance (PDD) and an area irradiated (FS), transform the target projection data into a spatial frequency domain, determine scatter values by accessing the lookup table using the kVp, PDD, and FS values, and subtract the scatter values from the frequency components to obtain the corrected X-ray projection data.

Provided is a preview image generating section configured to generate preview image during radiography for the purpose of providing a radiation tomography apparatus that allows suppression of unnecessary imaging time by displaying a condition of an image during the radiography in the process of diagnosis. An operator can recognize from the preview image how a subject appears in the image in a radiation tomography apparatus also during the radiography. This allows stopping the radiography before a diagnostic image having a suitable level of clearness for diagnosis is generated. As a result, a shorter imaging time is achieved, and burden to the subject can be suppressed.

A positioning apparatus and a positioning method has a control element and function 40 includes a radiograph acquisition element 41 that acquires radiograph data detected by two radiography systems selected from a group consisting of a flat panel detector, a DRR (Digital Reconstructed Radiograph) generation element 42 that generates DRR in two different directions by virtually performing fluoroscopic projection relative to the 3-dimensional CT data obtained through the network 17, a positioning element 43 that positions a CT to the X-ray fluoroscopic radiograph obtained from two radiography systems, and a displacement distance calculation element 44 that calculates a displacement distance of the tabletop 31 based on the gap between radiographs for improved positioning. The positioning element 43 has a multidimensional optimization element 45 and a 1-dimensional optimization element 46 that optimize parameters relative to rotation and translation of the fluoroscopic projection to maximize an evaluation function that evaluates a matching degree between the DRR and the X-ray fluoroscopic radiograph.

Systems and methods are provided for an X-ray imaging system. An X-ray source is configured to provide X-ray radiation and has an associated focal spot. A detector is configured to generate a digital image representing attenuation of the X-ray radiation as it passes through a subject. An image enhancement component is configured to apply a separable deconvolution kernel, derived from an estimate of a point spread function associated with the focal spot as a vector function applied to the rows and subsequently to the columns of the digital image.

Disclosed is an X-ray image forming device is disclosed. The device includes an X-ray imaging unit including a rotating member rotatable about a rotating shaft and linearly movable, and an X-ray source and an X-ray sensor disposed at opposite ends of the rotating member to face each other with a region of interest therebetween, a penetration data acquisition unit configured to acquire X-ray penetration data from multiple directions crossing through an image layer in the region of interest by controlling the X-ray imaging unit and an image reconstructor configured to generate projection data in a predetermined angle range at each section of the image layer from the X-ray penetration data, and reconstruct a two-dimensional X-ray panoramic image of the image layer based on the projection data.

A method, apparatus, system, and computer program for generating clinical information. Information indicating at least one clinical aspect of an object is received. Clinical information of interest relating to the at least one clinical aspect is generated from a plurality of projection images.