The present technology relates to an imaging system. The imaging system can comprise at least one processor configured to apply a projection precomputation algorithm and an x-ray tomography image reconstruction system. The projection precomputation algorithm can be configured to: generate a projection operator matrix that can be used to calculate a plurality of voxels from a plurality of projection measurements before the plurality of projection measurements is acquired and store the projection operator matrix in memory. The projection operator matrix can be at least one of: a compressed matrix, a multi-iteration projection operator matrix, and a combination thereof. The x-ray tomography image reconstruction system can be configured to apply the projection operator matrix to generate a reconstructed three-dimensional image of at least an internal portion of a selected object under a surface of the selected object when the plurality of projection measurements is acquired.

A guided pairing method includes generating a singles list by detecting a plurality of singles at a plurality of detector elements in a detector array, the plurality of singles falling within a plurality of detection windows; for each detection window of the plurality of detection windows in the singles list having exactly two singles of the plurality of singles, determining the line of responses (LORs) for each of the two singles of the plurality of singles; for each detection window of the plurality of detection windows in the singles list having more than two singles of the plurality of singles, determining all coincidences possible based on the more than two singles; generating a weight for said each coincidence of the coincidences based on the determined LORs for said each of the two singles of the plurality of singles; and pairing the more than two singles based on the generated weight for said each coincidence of the coincidences.

Techniques for generating a synthetic computed tomography (sCT) image from a cone-beam computed tomography (CBCT) image are provided. The techniques include receiving a CBCT image of a subject; generating, using a generative model, a sCT image corresponding to the CBCT image, the generative model trained based on one or more deformable offset layers in a generative adversarial network (GAN) to process the CBCT image as an input and provide the sCT image as an output; and generating a display of the sCT image for medical analysis of the subject.

A nuclear medicine diagnosis apparatus according to an embodiment includes a processing circuit. The processing circuit is configured: to obtain coincidence data including a direct incidence event to a gamma ray detector and a scattering event in a subject; to obtain an electron density function of the subject and geometric information of the gamma ray detector; to estimate a first probability value corresponding to the direct incidence event in the subject and a second probability value corresponding to the scattering event, based on one or both of the electron density function and the geometric information; and to reconstruct a Positron Emission Tomography (PET) image based on the first probability value, the second probability value, and the coincidence data. The processing circuit is configured to reconstruct the PET image based on a system matrix that is based on the first probability value and the second probability value.

Provided is a method for performing reconstruction and noise removal with high accuracy on various undersampling patterns including equidistant undersampling. An image processing unit that processes measurement data acquired by an MRI apparatus performs image reconstruction by using measurement data on respective channels measured in a predetermined undersampling pattern and sensitivity distributions of respective reception coils. At this time, denoising of a reconstructed image and a calculation for maintaining consistency between original measurement data and the measurement data on the respective channels created from denoised images are sequentially processed. Accordingly, image restoration and denoising with high accuracy are possible without depending on the undersampling pattern.

A method for image postprocessing includes steps as follows. A first reconstructed image is generated through a solving method according to the measuring data. The measuring data is measured by an image capturing device, and the image capturing device is selected from a group consisting of a magnetic induction tomography (MIT) device, a magnetoacoustic tomography with magnetic induction (MAT-MI) device, a magneto-acoustic-electrical tomography device, a ultrasound device, a positron emission tomography (PET) device, a computed tomography (CT) device, a magnetic resonance imaging (MRI) device, a microwave tomography device, a pressure tomography device, an optical coherence tomography device, a doppler ultrasonography device, a mammogram device and, an imaging photoplethysmogram (PPG) device, or the like. Then, the first reconstructed image is post-processed through a neural network algorithm to generate a second reconstructed image.

The present disclosure relates to methods, systems, and non-transitory computer readable mediums for reconstructing an image. Image data may be obtained, wherein the image data may include projection data and may be generated by an imaging device. An objective function associated with a target image may be determined based on the image data. The objective function may include a difference model, wherein the difference model may represent a difference between a projection of the target image and the image data. The difference model may be determined based on a weighting matrix, and the weighting matrix may be determined based on an extended Tam window. The target image may be reconstructed by performing a plurality of iterations based on the objective function.

An apparatus and method for obtaining a thick-slice image from tilted thin-slice computed-tomography (CT) projection data. Tilted CT projection data is obtained for a series of projection planes, wherein the projection planes are parallel for all scans, and the translation direction between CT scans is not orthogonal to the projection planes (i.e., the projection planes are tilted relative to the translation direction between CT scans). Thin-slice images are reconstructed from the respective CT scans, and then grouped into thick-slice groupings. An offset results among the thin-slice images within a thick-slice grouping due to the tilt of the projection planes. This offset is compensated by interpolating and resampling the thin-slice images onto non-offset pixel grids. The interpolated and resampled thin-slice images are then averaged pixel-by-pixel to obtain thick-slice images having the same tilt angle as the thin-slice images.

A method of reconstructing an image that may include in at least one example: determining coincidence events based on detection by a detector during a continuous incremental scanning; determining an axial position for each of the coincidence events; storing data for each of the coincidence events including the axial position in a list mode; sorting the data for each of the coincidence events according to a spatial order; and obtaining an image by performing iterative reconstruction with the sorted data for each of the coincidence events.

A method for movement compensation during CT reconstruction, comprises calculating slice images. The calculating slice images comprising: selecting an initial movement state; calculating a reference voxel position in relation to the initial movement state; calculating a column image position of a voxel; ascertaining a changed movement state of the voxel at the column image position; calculating a changed voxel position in relation to the changed movement state; calculating a changed image position of the voxel; and using an image value of the intermediate image at the changed image position for back projection to calculate the slice images.