Metal artifacts are reduced in x-ray computed tomography (CT) images using a suitably trained neural network, such as a convolutional neural network (CNN). Virtual metal DATA objects are inserted to either the raw projection data or CT image data (e.g., from pre-procedural CT scans) to generate sets of matching artifact-corrupted and artifact-uncorrupted images, and a CNN, or other neural network, is trained to separate the contribution to each image pixel due to patient anatomy, metal object, or metal object-induced artifact. The contributions from metal object-induced artifacts can then be removed to generate a final, artifact-reduced image.

A method of training a neural network is described that includes receiving an image of an anatomical portion of a subject, receiving a CAD model of a surgical implant, generating a first simulated image based on the image and the CAD model, the first simulated image depicting the surgical implant and the anatomical portion of the subject, modifying the simulated image to include simulated artifacts from metal, beam hardening, and scatter, to yield a second simulated image corresponding to the first simulated image, and providing the second simulated image to a neural network as an example input and the first simulated image to the neural network as an example output.

Selected artifacts, which may be based on distortions or selected attenuation features, may be reduced or removed from a reconstructed image. Various artifacts may occur due to the presence of a metal object in a field of view. The metal object may be identified and removed from a data that is used to generate a reconstruction.

A computer-implemented method is for artifact correction during a reconstruction of at least one slice image from at least one projection image. The at least one projection image includes a plurality of pixels, each pixel including a pixel value. The method includes determining at least one corrected projection image based on the at least one projection image via a computing circuit; reconstructing the at least one slice image based on the at least one corrected projection image; and providing the at least one slice image. The determining includes determining an average pixel value in at least one subarea of the at least one projection image, a correction value by multiplying the average pixel value by a scatter factor, and a plurality of corrected pixel values by subtracting the correction value from the plurality of pixel values. The corrected projection image includes pixels including the plurality of corrected pixel values.

The present disclosure provides systems and methods for medical imaging. The system may obtain a scout image of a subject lying on a scanning table. The scanning table may include N portions corresponding to N bed positions of a target scan, and an i.sup.th portion of the N portions may correspond to an i.sup.th bed position of the N bed positions. For the i.sup.th bed position, the system may determine one or more body parts of the subject located at the i.sup.th portion of the scanning table based on the scout image; and determine at least one scanning parameter or reconstruction parameter corresponding to the i.sup.th bed position based on the one or more body parts of the subject.

A correction apparatus reduces calculation costs for correcting artifacts due to a beam hardening effect in reconstructing a CT image by correcting an artifact due to a beam hardening effect caused in reconstructing a CT image. The correction apparatus includes processing circuitry configured to acquire an incident X-ray distribution, acquire a linear absorption coefficient model representing an energy dependency of a linear absorption coefficient by a scale factor including a parameter, acquire a projection image, and correct the projection image using the incident X-ray distribution and the linear absorption coefficient model.

Disclosed herein are methods for reducing beam-hardening artifacts in CT imaging using a mapping operator that comprises a hybrid spectral model that incorporates air scan X-ray intensity data acquired at two different effective mean energies. In one variation, the air scan X-ray intensity data acquired during a calibration session is combined with an ideal spectral model for each X-ray detector to derive the hybrid spectral mode. A mapping operator based on the hybrid spectral model is used to correct beam-hardening artifacts in the acquired CT projection data. In some variations, the mapping operator is a lookup table of monochromatic (corrected) projection values, and the acquired CT projection data is used to calculate the index of the lookup table entry that contains the corrected projection value that corresponds with the acquired CT projection data.

Systems and methods include segmentation of a first image of a subject to identify locations of anatomical structures of the subject, determination of a region of interest of the subject based on the locations of anatomical structures, determination of a coil-mixing matrix based on the region of interest, control of an MR scanner to acquire radial trajectory k-space data of the subject from each of a plurality of RF coils of the MR scanner, application of the coil-mixing matrix to the radial trajectory k-space data of the subject acquired from each of the plurality of RF coils to generate first radial trajectory k-space data, reconstruction of a second image of the subject based on the first radial trajectory k-space data, and display of the second image.

A method for reducing metal artifacts in a volume radiographic image acquires a first set of projection images of an object on a radiographic detector at different acquisition angles. An initial estimate of the volume that includes the object using the acquired projection images is generated. The estimated volume is updated by one or more iterations of generating a second set of scatter-corrected projection images using the acquired first set of projection images and the estimated volume; generating a third set of estimated projection images using forward ray-tracing through the estimated volume; and reconstructing the estimated volume according to a signal quality factor obtained from analysis of the detector signal and used in a comparison of the second set of scatter-corrected projection images with the third set of estimated projection images. One or more images rendered from the updated estimated volume are displayed.

A method for artifact correction in computed tomography, the method comprising: (1) acquiring a plurality of data sets associated with different X-ray energies (i.e., D.sub.1, D.sub.2, D.sub.3 . . . D.sub.n); (2) generating a plurality of preliminary images from the different energy data sets acquired in Step (1) (i.e., I.sub.I, I.sub.2, I.sub.3 . . . I.sub.n); (3) using a mathematical function to operate on the preliminary images generated in Step (2) to identify the sources of the image artifact (i.e., the artifact source image, or ASI, where ASI=f(I.sub.1, I.sub.2, I.sub.3 . . . I.sub.n)); (4) forward projecting the ASI to produce ASD=fp(ASI); (5) selecting and combining the original data sets D.sub.1, D.sub.2, D.sub.3 . . . D.sub.n in order to produce a new subset of the data associated with the artifact, whereby to produce the artifact reduced data, or ARD, where ARD=f(ASD, D.sub.1, D.sub.2, D.sub.3 . . . D.sub.n); (6) generating a repaired data set (RpD) to keep low-energy data in artifact-free data and introduce high-energy data in regions impacted by the artifact, where RpD=f(ARD, D.sub.1, D.sub.2, D.sub.3 . . . D.sub.n); and (7) generating a final reduced artifact image (RAI) from the repaired data, RAI=bp(RpD), where the function bp is any function which generates an image from data.