The present disclosure relates to systems and methods for image reconstruction. The systems and methods may obtain an initial image to be processed. The systems and methods may also generate a reconstructed image by performing a plurality of iteration steps on the initial image. At least one of the plurality of iteration steps may include a first optimization operation and a second optimization operation. The first optimization operation may include receiving an image to be processed in the iteration step and determining an updated image by preliminarily optimizing the image to be processed. The second optimization operation may include determining, using an optimizing model, an optimized image based on the updated image and designating the optimized image as a next image to be processed in a next iteration step or designating the optimized image as the reconstructed image.

The disclosure relates to systems and methods for iterative reconstruction. Raw data detected from a plurality of angles by an imaging device may be obtained. A first seed image may be generated by performing a filtered back projection on the raw data. A first air mask may be determined by performing a minimum value back projection (BP) on the raw data. One or more images may be reconstructed by performing an iterative reconstruction based on the first seed image, the first air mask, and the raw data.

Disclosed is a method for region-of-interest enhanced PET image reconstruction based on multi-task learning, which comprises the following steps: firstly, acquiring a backprojection image of the PET original data, and designing a main task of establishing a mapping between the backprojection image and a reconstructed PET image by using a three-dimensional deep convolution neural network. A new auxiliary task 1 is designed to predict a computerized tomography (CT) image with the same anatomical structures as the PET image reconstructed from the backprojection image, so as to reduce the noise in the reconstructed PET image by using the local smoothing information of the high-resolution CT image.

In a method to acquire a 3D image of a sample structure initially a first raw 2D set of 2D images of a sample structure is acquired at a limited number of raw sample planes. From this first raw 2D set a 3D image of the sample structure being represented by a 3D volumetric image data set is calculated and a measurement parameter is extracted from the 3D volumetric image data set. Such measurement parameter is assigned to the number of 2D image acquisitions recorded during the acquisition step. Then, a further interleaving 2D set of 2D images of the sample structure is required by recording a further number of interleaving 2D image acquisitions at a further number of interleaved sample planes which do not coincide with the previous acquisition sample planes. The steps “calculating,” “extracting” and “assigning” are repeated for the further interleaving 2D set. The actual and the last extracted measurement parameters are compared to check whether a convergence criterion is met. If not, the steps “acquiring,” “calculating,” “extracting,” “assigning” and “comparing” are repeated for a further interleaving 2D set including a further number of interleaving 2D image acquisitions at a further number of interleaved sample planes which do not coincide with the previous acquisition sample planes. This is done until the convergence criterion is met or until a given maximum number of 2D image acquisitions is recorded. The measurement parameter and a total number of recorded 2D image acquisitions are output. A projection system used for such method comprises a projection light source, a rotatable sample structure holder and a spatially resolving detector. Alternatively or in addition, such method can be used by a data processing system to acquire virtual tomographic images of a sample. With such method, a sample throughput is improved.

Among other things, one or more techniques and/or systems for generating a three-dimensional combined image is provided. A three-dimensional test image of a test item is combined with a three-dimensional article image of an article that is undergoing a radiation examination to generate the three-dimensional combined image. A first selection region of the three-dimensional article image is selected. The three-dimensional test image of the test item is inserted within the first selection region. Although the test item is not actually comprised within the article under examination, the three-dimensional combined image is intended to cause the test item to appear to be comprised within the article.

Methods and systems for PET image reconstruction are provided. A method may include obtaining an image sequence associated with a subject. The image sequence may include one or more images generated via scanning the subject at one or more consecutive time periods. The method may also include obtaining a target machine learning model. The method may further include generating at least one target image using the target machine learning model based on the image sequence. The at least one target image may present a dynamic parameter associated with the subject. The target machine learning model may provide a mapping between the image sequence and the at least one target image.

A system for monitored tomographic reconstruction, comprising: an x-ray generator configure to generate x-ray beams for scanning an object; detectors configured to capture a plurality of projections for each scan; at least one hardware processor; and one or more software modules that, when executed by the at least one hardware processor, receive the plurality of projections from the detectors and as each of the plurality of projections is received, generate a partial reconstruction, and make a stopping decision with respect to whether or not another projection should be obtained based on a stopping problem and that defines when a reconstructed image quality is sufficient with respect to the expended cost as determined by a stopping rule.

A system and method include training of an artificial neural network to generate an output three-dimensional image volume based on input two-dimensional projection images, the training based on a plurality of subsets of two-dimensional projection images of each of a plurality of sets of two-dimensional projection images and associated ones of three-dimensional image volumes reconstructed from each of the plurality of sets of two-dimensional projection images.

The present disclosure is directed to MRI techniques. The techniques include occupying a central region of a first k-space with full sampling along a Cartesian trajectory, occupying a peripheral region of the first k-space with undersampling along a non-Cartesian trajectory; acquiring sensitivity distribution information of receiving coils; based on a sensitivity distribution chart, merging the Cartesian data of the central region according to multiple channels to obtain a third k-space; based on the sensitivity distribution chart, applying parallel imaging and compressed sensing to the undersampled non-Cartesian trajectory to reconstruct an image, obtaining a second k-space by transformation, and when the second k-space and third k-space are synthesized, using a central region of the second k-space to replace the third k-space of a corresponding region to obtain a k-space suitable for image reconstruction.

An x-ray tomographic method for reconstructing an object, includes, on the basis of a plurality of images, each image in the plurality of images corresponding to a projection of the object, reconstructing the object using an iterative reconstruction method so as to produce a plurality of reconstructions x.sub.(m) of the object.