The present disclosure is related to systems and methods for image processing. The method may include obtaining an image including at least one of a first type of artifact or a second type of artifact. The method may include determining, based on a trained machine learning model, at least one of first information associated with the first type of artifact or second information associated with the second type of artifact in the image. The trained machine learning model may include a first trained model and a second trained model. The first trained model may be configured to determine the first information. The second trained model may be configured to determine the second information. The method may include generating a target image based on at least part of the first information and the second information.

Nondestructive evaluation (NDE) of objects can elucidate impacts of various process parameters and qualification of the object. Computed tomography (CT) enables rapid NDE and characterization of objects. However, CT presents challenges because of artifacts produced by standard reconstruction algorithms. Beam-hardening artifacts especially complicate and adversely impact the process of detecting defects. By leveraging computer-aided design (CAD) models, CT simulations, and a deep-neutral network high-quality CT reconstructions that are affected by noise and beam-hardening can be simulated and used to improve reconstructions. The systems and methods of the present disclosure can significantly improve the reconstruction quality, thereby enabling better detection of defects compared with the state of the art.

A method and a system for providing calibration for a polychromatic photon counting detector forward counting model. Measurements with multiple materials and known path lengths are used to calibrate the photon counting detector counting response of the forward model. The flux independent weighted bin response function is estimated using the expectation maximization method, and then used to estimate the pileup correction terms at plural tube voltage settings for each detector pixel. The beam hardening corrections are then applied to the measured projection data sinogram, and the corrected sinogram is reconstructed to the counting image at the selected single energy.

The present invention relates to a method of metal artefact reduction in x-ray dental volume tomography, the method comprising: a step (S1) of obtaining two-dimensional x-ray images (1) or a sinogram (2) of at least part (v) of a patient jaw (3a), acquired through relatively rotating an x-ray source (4) and a detector (5) around the patient jaw (3a); the method being characterized by further comprising: a step (S2) of detecting metal objects (6) in the two-dimensional x-ray images (1) or the sinogram (2) by using at least a trained artificial intelligence algorithm to generate 2D masks (7) which represent the metal objects (6) in the two-dimensional x-ray images (1) or 3D masks which represent the metal objects (6) in the sinogram (2), respectively; and a step (S4; S5) of reconstructing a three dimensional tomographic image (8) respectively based on two-dimensional x-ray images (1) or the sinogram (2) and the 2D masks (7) or the 3D masks as generated.

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.1, 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.

A method for the reduction of streak artifacts in an image data set reconstructed from projection images of an X-ray device is provided. The method includes determining a first interim data set by applying a non-linear low-pass filter to pixels that satisfy a selection condition. A second non-linear, high-pass-filtered interim data set is determined by pixel-by-pixel subtraction of the first interim data set from the image data set. The second interim data set is Fourier transformed in order to obtain a spatial frequency data set. Frequency portions attributable to artifacts in the spatial frequency data set are removed, and the processed spatial frequency data set is inverse Fourier transformed, such that a third interim data set is obtained. An artifact-reduced result data set is determined by addition of the third interim data set and the first interim data set.

A method and a system for providing calibration for a polychromatic photon counting detector forward counting model. Measurements with multiple materials and known path lengths are used to calibrate the photon counting detector counting response of the forward model. The flux independent weighted bin response function is estimated using the expectation maximization method, and then used to estimate the pileup correction terms at plural tube voltage settings for each detector pixel. The beam hardening corrections are then applied to the measured projection data sinogram, and the corrected sinogram is reconstructed to the counting image at the selected single energy.

A deep-learning-based method for metal artifact reduction in CT images includes providing a dataset and a cGAN. The dataset includes CT image pairs, randomly partitioned into a training set, a validation set, and a testing set. Each Pre-CT and Post-CT image pairs is respectively acquired in a region before and after an implant is implanted. The Pre-CT and Post-CT images of each pair are artifact-free CT and artifact-affected CT images, respectively. The cGAN is conditioned on the Post-CT images, includes a generator and a discriminator that operably compete with each other, and is characterized with a training objective that is a sum of an adversarial loss and a reconstruction loss. The method also includes training the cGAN with the dataset; inputting the post-operatively acquired CT image to the trained cGAN; and generating an artifact-corrected image by the trained cGAN, where metal artifacts are removed in the artifact-corrected image.

A reconstructed volume of a region of patient anatomy is processed to reduce motion artifacts in the reconstructed volume. Autosegmentation of high-contrast structures present in an initial reconstructed volume is performed to generate a 3D representation of the high-contrast structures. 2D mask projections are generated by performing forward projection on the 3D representation, where each 2D mask projection includes location information indicating pixels that correspond to the high-contrast structures during the forward projection process. The acquired 2D projections are modified via in-painting to generate corrected 2D projections, where the acquired 2D projections are modified using information from the 2D mask projections. For example, pixels in the acquired 2D projections that are associated with high-contrast moving structures are replaced with low-contrast pixels. These corrected 2D projections are used to produce an improved reconstructed volume with fewer and/or less visually prominent motion artifacts.

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.