Abstract: A method relates to the use of deep learning techniques, which may be implemented using trained neural networks (50), to estimate various types of missing projection or other unreconstructed data. Similarly, the method may also be employed to replace or correct corrupted or erroneous projection data as opposed to estimating missing projection data.

Abstract: Disclosed aspects relate to the acquisition and processing of projection data using temporal characteristics of the imaged volume, such as the uptake and clearance of a contrast agent within the volume. Such temporal aspects may be used in the acquisition process, such as to differentially acquire images based on the propagation of the contrast agent. In addition, such temporal aspects may be used in the processing of projection data to generate differential projections (e.g., first or second order subtraction projections), compound projections synthesized using the absolute or relative maximum opacity values observed over time for a region of interest, or interpolated projections synthesized using observed opacity values at known or fixed time intervals and a derived peak opacity time.

Abstract: In accordance with the present disclosure, the present technique finds a diagnostic scan timing for a non-static object (e.g., a heart or other dynamic object undergoing motion) from raw scan data, as opposed to reconstructed image data. To find the scan timing, a monitoring scan of a patient's heart is performed. In the monitoring scan, the patient dose may be limited or minimized. As the projection data is acquired during such a monitoring scan, the projection data may be subjected to sinogram analysis in a concurrent or real-time manner to determine when to start (or trigger) the diagnostic scan.

Abstract: In accordance with the present disclosure, the present technique finds a diagnostic scan timing for a non-static object (e.g., a heart or other dynamic object undergoing motion) from raw scan data, as opposed to reconstructed image data. To find the scan timing, a monitoring scan of a patient's heart is performed. In the monitoring scan, the patient dose may be limited or minimized. As the projection data is acquired during such a monitoring scan, the projection data may be subjected to sinogram analysis in a concurrent or real-time manner to determine when to start (or trigger) the diagnostic scan.

Abstract: A method relates to the use of deep learning techniques, which may be implemented using trained neural networks (50), to estimate various types of missing projection or other unreconstructed data. Similarly, the method may also be employed to replace or correct corrupted or erroneous projection data as opposed to estimating missing projection data.

Abstract: A method of breast image reconstruction includes positioning a breast on an imaging system support plate, compressing the breast with a flexible paddle, obtaining imaging data, estimating a breast thickness profile by at least one of placing markers on the breast, performing an image-based analysis of the obtained data, using an auxiliary system, and performing a model-based computation. The three-dimensional (3D) reconstruction including using a thickness profile of the breast surface in at least one of an iterative reconstruction, a filtered back-projection reconstruction, and a joint reconstruction performed using information obtained from an ultrasound scan. A non-transitory medium having executable instructions to cause a processor to perform the method is also disclosed.

Abstract: A method for imaging a target region in a subject is presented. The method includes selecting one or more tomographic angle sequences, acquiring one or more image sequences corresponding to the one or more tomographic angle sequences, where each image sequence has a corresponding tomographic angle sequence, deriving geometric information corresponding to one or more structures of interest in at least one of the image sequences, identifying visualization information, generating one or more displacement maps based on the geometric information, the visualization information, at least a subset of at least one of the one or more tomographic angle sequences, or combinations thereof, transforming at least a subset of images in the one or more image sequences based on corresponding displacement maps to create one or more transformed/stabilized image sequences, and visualizing on a display the one or more transformed/stabilized image sequences to provide a stabilized presentation of the target region.

Abstract: A method of breast image reconstruction includes positioning a breast on an imaging system support plate, compressing the breast with a flexible paddle, obtaining imaging data, estimating a breast thickness profile by at least one of placing markers on the breast, performing an image-based analysis of the obtained data, using an auxiliary system, and performing a model-based computation. The three-dimensional (3D) reconstruction including using a thickness profile of the breast surface in at least one of an iterative reconstruction, a filtered back-projection reconstruction, and a joint reconstruction performed using information obtained from an ultrasound scan. A non-transitory medium having executable instructions to cause a processor to perform the method is also disclosed.

Abstract: A method of breast image reconstruction includes positioning a breast on an imaging system support plate, compressing the breast with a flexible paddle, obtaining imaging data, estimating a breast thickness profile by at least one of placing markers on the breast, performing an image-based analysis of the obtained data, using an auxiliary system, and performing a model-based computation. The three dimensional reconstruction including using a thickness profile of the breast surface in at least one of an iterative reconstruction, a filtered back-projection reconstruction, and a joint reconstruction performed using information obtained from an ultrasound scan. A non-transitory medium having executable instructions to cause a processor to perform the method is also disclosed.

Abstract: The present disclosure relates various approaches by which mask and contrast projection data may be acquired using a continuous projection acquisition process, without an interruption in acquisition or resetting of the system between the acquisition of the mask projection data and the contrast projection data. In certain implementations, the approaches described herein may be employed with a single-plane or multi-plane tomosynthesis system.

Abstract: A method of breast image reconstruction includes positioning a breast on an imaging system support plate, compressing the breast with a flexible paddle, obtaining imaging data, estimating a breast thickness profile by at least one of placing markers on the breast, performing an image-based analysis of the obtained data, using an auxiliary system, and performing a model-based computation. The three dimensional reconstruction including using a thickness profile of the breast surface in at least one of an iterative reconstruction, a filtered back-projection reconstruction, and a joint reconstruction performed using information obtained from an ultrasound scan. A non-transitory medium having executable instructions to cause a processor to perform the method is also disclosed.

Abstract: The present disclosure relates to the iterative reconstruction of projection data. In certain embodiments, the iterative reconstruction is a multi-stage iterative reconstruction in which different feature are selectively emphasized at different stages. Selective emphasis at different stages may be accomplished by differentially handling two or more decompositions of an input image at certain iterations and/or by differently processing certain features with respect to each stage.

Abstract: Some embodiments are associated with generation of a volumetric image representing an imaged object associated with a patient. According to some embodiments, tomosynthesis projection data may be acquired. A computer processor may then automatically generate the volumetric image based on the acquired tomosynthesis projection data. Moreover, distances between voxels in the volumetric image may be spatially varied.

Abstract: A method for imaging a target region in a subject is presented. The method includes selecting one or more tomographic angle sequences, acquiring one or more image sequences corresponding to the one or more tomographic angle sequences, where each image sequence has a corresponding tomographic angle sequence, deriving geometric information corresponding to one or more structures of interest in at least one of the image sequences, identifying visualization information, generating one or more displacement maps based on the geometric information, the visualization information, at least a subset of at least one of the one or more tomographic angle sequences, or combinations thereof, transforming at least a subset of images in the one or more image sequences based on corresponding displacement maps to create one or more transformed/stabilized image sequences, and visualizing on a display the one or more transformed/stabilized image sequences to provide a stabilized presentation of the target region.

Abstract: In accordance with embodiments of the present, a method for acquiring an image is provided. The method comprises acquiring initial image data, identifying one or more regions of interest in at least one of the initial image data or in a first image generated from the initial image data. The method further comprises automatically deriving one or more scan parameters based upon the regions of interest, and acquiring second image data using the scan parameters.

Abstract: Disclosed aspects relate to the acquisition and processing of projection data using temporal characteristics of the imaged volume, such as the uptake and clearance of a contrast agent within the volume. Such temporal aspects may be used in the acquisition process, such as to differentially acquire images based on the propagation of the contrast agent. In addition, such temporal aspects may be used in the processing of projection data to generate differential projections (e.g., first or second order subtraction projections), compound projections synthesized using the absolute or relative maximum opacity values observed over time for a region of interest, or interpolated projections synthesized using observed opacity values at known or fixed time intervals and a derived peak opacity time.

Abstract: C-arm systems and method for making and using continuous C-arm spin acquisition trajectories for dynamic imaging and improved image quality are described. In such systems and methods, a C-arm gantry, coupled to a C-arm support assembly, is adapted to retain an x-ray source and an x-ray detector. The C-arm gantry is selectively rotatable relative to the C-arm support assembly about both a C-arm axis and a pivot-axis to displace the x-ray source and the x-ray detector along a continuous C-arm spin trajectory. The C-arm system is adapted for continuous three-dimensional acquisition of data along the continuous C-arm spin trajectory including a plurality of shorts arcs and a plurality of long arcs. The C-arm system is adapted for continuous three-dimensional acquisition of data along the continuous C-arm spin trajectory to provide continuous three-dimensional imaging of dynamic processes.

Abstract: Systems, methods and non-transitory computer readable media for imaging. The system includes one or more radiation sources and detectors configured to transmit x-ray radiation towards a subject for imaging a dynamic process in a ROI of the subject and to acquire projection data corresponding to the ROI, respectively. The system also includes a computing device operatively coupled to one or more of the radiation sources and the detectors. The computing device is configured to provide control signals for performing one or more reference scans for acquiring reference data from a plurality of angular positions around the subject and for performing one or more tomosynthesis scans using one or more tomosynthesis trajectories for acquiring tomosynthesis data following the onset of the dynamic process. Additionally, the computing device is configured to reconstruct one or more images representative of the dynamic process using the reference data and/or the tomosynthesis data.

Abstract: The present disclosure relates to the acquisition of image data over an extended field of view using an interventional tomosynthesis system. In one embodiment, the interventional tomosynthesis system has a base offset from the longitudinal axis of a patient table, such that movement of the table relative to the imager may be performed during tomosynthesis projection acquisition. One or both of the imager and the table may move to accomplish such relative motion.

Abstract: The present disclosure relates to the identification and tracking of a navigational instrument (e.g., a needle) in three-dimensions, with substantially real-time image updates of the instrument and updates of the tissue at an equal or lower rate. In certain embodiments, the images are acquired using a C-arm tomosynthesis system configured to move the X-ray source and detector in respective planes above and below the patient.