Abstract: The invention relates to an image generation apparatus (1) for generating an image of an object. A reconstruction unit (10) reconstructs the image based on provided measured projection values such that costs defined by a cost function are reduced, wherein the cost function depends on differences between calculated projection values, which have been determined by simulating a forward projection through the image, and the provided measured projection values, and wherein a degree of dependence of the cost function on a respective difference depends on the respective difference. This can allow for a consideration of a degree of disturbance of the measured projection values by motion and/or by an incomplete illumination of the object during the reconstruction process, which can lead to a reconstruction of an image having an improved image quality.

Abstract: A method and related apparatus (116) for iterative reconstruction of a volume. A regularization parameter (?) of an iterative update function is spatially adapted and normalized in respect to a region of interest ROI in the volume. The method allows achieving essentially uniform noise distribution across the reconstructed volume.

Abstract: A method and related apparatus (116) for iterative reconstruction of a volume. A regularization parameter (?) of an iterative update function is spatially adapted and normalized in respect to a region of interest ROI in the volume. The method allows achieving essentially uniform noise distribution across the reconstructed volume.

Abstract: A method includes re-sampling current image data representing a reference motion state into a plurality of different groups, each group corresponding to a different motion state of moving tissue of interest, forward projecting each of the plurality of groups, generating a plurality of groups of forward projected data, each group of forward projected data corresponding to a group of the re-sampled current image data, determining update projection data based on a comparison between the forward projected data and the measured projection data, grouping the update projection data into a plurality of groups, each group corresponding to a different motion state of the moving tissue of interest, back projecting each of the plurality of groups, generating a plurality of groups of update image data, re-sampling each group of update image data to the reference motion state of the current image, and generating new current image data based on the current image data and the re-sampled update image data.

Abstract: Image processing methods and related apparatuses (SEG,UV). The apparatuses (SEG,UV) operate to utilize noise signal information in images (IM). According to one aspect, apparatus (SEG) uses the noise information (FX) to control a model based segmentation. According to a further aspect, apparatus (UV) operates, based on the noise information (FX), to visualize the uncertainty of image information that resides at edge portions of the or an image (IM).

Abstract: A method includes reconstructing measured projection data using an iterative statistical reconstruction algorithm that reduces image artifact caused by differences in variances in projections of the measured projection data used to update a voxel of the image for one or more voxels of the image. A reconstructor includes a processor that reconstructs measured projection data using an iterative statistical reconstruction algorithm that reduces or mitigates image artifact caused by differences in variances in projections used to update a voxel of the image for one or more voxels of the image. A computer readable storage medium encoded with computer executable instructions, which, when executed by a processor of a computer, cause the processor to: reduce image artifact caused by differences in variances in projections used to update a voxel of an image for one or more voxels of the image using an iterative statistical reconstruction algorithm.

Abstract: The invention relates to a forward projection apparatus for performing a forward projection through an image (22), wherein at least one of a number of rays (20, 21) for performing the forward projection, a ray spacing between the rays and a kernel width of an interpolation kernel for calculating interpolated values located on the rays is varied depending on the ray width relative to an effective image element spacing between image elements (24) of the image. This allows reducing artifacts in simulated projection data and, thus, in an image, which is iteratively reconstructed by using the simulated projection data. For example, if the number of provided rays and/or the ray spacing between the provided rays is varied, aliasing artifacts can be reduced. Moreover, if the ray spacing between the provided rays and/or the kernel width of the interpolation kernel is varied, artifacts caused by varying effective kernel widths may be reduced.

Abstract: A patient (14), at rest, is injected with a first isotope tracer. After a first uptake period, the patient is stressed and injected with a second isotope tracer. After a second isotope tracer uptake period, first and second isotope imaging data are concurrently detected by data acquiring devices (16). The first and second isotope imaging data are reconstructed into a first or rest state image, a second or stressed state image, and optionally a combined first and second isotope image. The image with the better image statistics is segmented to generate segmentation parameters, which segmentation parameters are applied to both the first or rest and second or stressed state images. In this manner, an image whose image statistics may be too weak for accurate segmentation is accurately segmented by generating two inherently aligned images and applying the same segmentation parameters to both.

Abstract: A method includes reconstructing measured projection data using an iterative statistical reconstruction algorithm that reduces image artifact caused by differences in variances in projections of the measured projection data used to update a voxel of the image for one or more voxels of the image. A reconstructor includes a processor that reconstructs measured projection data using an iterative statistical reconstruction algorithm that reduces or mitigates image artifact caused by differences in variances in projections used to update a voxel of the image for one or more voxels of the image. A computer readable storage medium encoded with computer executable instructions, which, when executed by a processor of a computer, cause the processor to: reduce image artifact caused by differences in variances in projections used to update a voxel of an image for one or more voxels of the image using an iterative statistical reconstruction algorithm.

Abstract: The invention relates to a forward projection apparatus for performing a forward projection through an image (22), wherein at least one of a number of rays (20, 21) for performing the forward projection, a ray spacing between the rays and a kernel width of an interpolation kernel for calculating interpolated values located on the rays is varied depending on the ray width relative to an effective image element spacing between image elements (24) of the image. This allows reducing artifacts in simulated projection data and, thus, in an image, which is iteratively reconstructed by using the simulated projection data. For example, if the number of provided rays and/or the ray spacing between the provided rays is varied, aliasing artifacts can be reduced. Moreover, if the ray spacing between the provided rays and/or the kernel width of the interpolation kernel is varied, artifacts caused by varying effective kernel widths may be reduced.

Abstract: The invention describes a method and a system for generating training data (DT) for an automatic speech recogniser (2) for operating at a particular first sampling frequency (fH), comprising steps of deriving spectral characteristics (SL) from audio data (DL) sampled at a second frequency (fL) lower than the first sampling frequency (fH), extending the bandwidth of the spectral characteristics (SL) by retrieving bandwidth extending informationOBE) from a codebook (6), and processing the bandwidth extended spectral characteristics (SLE) to give the required training data (DT). Moreover a method and a system (5) for generating a codebook (6) for extending the bandwidth of spectral characteristics (SL) for audio data (DL) sampled at a second sampling frequency (fL) to spectral characteristics (SH) for a first sampling frequency (fH) higher than the second sampling frequency (fL) are described.

Abstract: A patient (14), at rest, is injected with a first isotope tracer. After a first uptake period, the patient is stressed and injected with a second isotope tracer. After a second isotope tracer uptake period, first and second isotope imaging data are concurrently detected by data acquiring devices (16). The first and second isotope imaging data are reconstructed into a first or rest state image, a second or stressed state image, and optionally a combined first and second isotope image. The image with the better image statistics is segmented to generate segmentation parameters, which segmentation parameters are applied to both the first or rest and second or stressed state images. In this manner, an image whose image statistics may be too weak for accurate segmentation is accurately segmented by generating two inherently aligned images and applying the same segmentation parameters to both.

Abstract: The invention describes a method and a system for generating training data (DT) for an automatic speech recogniser (2) for operating at a particular first sampling frequency (fH), comprising steps of deriving spectral characteristics (SL) from audio data (DL) sampled at a second frequency (fL) lower than the first sampling frequency (fH), extending the bandwidth of the spectral characteristics (SL) by retrieving bandwidth extending informationOBE) from a codebook (6), and processing the bandwidth extended spectral characteristics (SLE) to give the required training data (DT). Moreover a method and a system (5) for generating a codebook (6) for extending the bandwidth of spectral characteristics (SL) for audio data (DL) sampled at a second sampling frequency (fL) to spectral characteristics (SH) for a first sampling frequency (fH) higher than the second sampling frequency (fL) are described.