AI-ENABLED EARLY-PET ACQUISITION
    1.
    发明公开

    公开(公告)号:US20230230297A1

    公开(公告)日:2023-07-20

    申请号:US18011052

    申请日:2021-06-16

    CPC classification number: G06T11/003 G06T2210/41 G06T2211/424

    Abstract: Data processing systems (DPS) and related methods for nuclear medicine imaging. At an input interface (IN), first projection data (λ), or a first image (V) reconstructable from the first projection data, is received. The first projection data is associated with a first waiting period (ΔT*). The first waiting period indicates the time period from administration of a tracer agent to a start of acquisition by a nuclear medicine imaging apparatus (IA) of the projection date. A trained machine learning module (MLM) estimates, based on the first projection data (λ) or on the first image (V), a second projection data (λ′) or a second image (V′) associable with a second waiting period (ΔT), longer than the first waiting period (ΔT*). Nuclear imaging can thus be conducted quicker. Similar machine learning based data processing systems and related methods are also envisaged to reduce acquisition time periods or the time it takes to reconstruct imagery.

    AUTOMATED CORONARY ANGIOGRAPHY ANALYSIS

    公开(公告)号:US20220351369A1

    公开(公告)日:2022-11-03

    申请号:US17618445

    申请日:2020-06-29

    Abstract: A method and apparatus for analyzing diagnostic image data are provided in which a plurality of acquisition images of a vessel of interest having been acquired with a pre-defined acquisition method is received at a trained classifying device and classified, by the classifying device, to extract at least one quantitative feature of the vessel of interest from at least one acquisition image of the plurality of acquisition images. The at least one quantitative feature is then output associated with the at least one acquisition image while the acquisition of the diagnostic image data is still in progress and one or more adjustable image acquisition settings are adjusted based on the at least one quantitative feature to optimize the acquisition of the diagnostic image data.

    FRACTIONAL FLOW RESERVE DETERMINATION
    4.
    发明申请

    公开(公告)号:US20200337664A1

    公开(公告)日:2020-10-29

    申请号:US16922069

    申请日:2020-07-07

    Abstract: The present invention relates to a device (1) for fractional flow reserve determination. The device (1) comprises a model generator (10) configured to generate a three-dimensional model (3DM) of a portion of an imaged vascular vessel tree (VVT) surrounding a stenosed vessel segment (SVS), based on a partial segmentation of the imaged vascular vessel tree (VVT). Further, the device comprises an image processor (20) configured to calculate a blood flow (Q) through the stenosed vessel segment (SVS) based on an analysis of a time-series of X-ray images of the vascular vessel tree (VVT). Still further, the device comprises a fractional-flow-reserve determiner (30) configured to determine a fractional flow reserve (FFR) based on the three-dimensional model (3DM) and the calculated blood flow.

    CALIBRATION-FREE TOMOSYNTHESIS
    5.
    发明申请

    公开(公告)号:US20200315551A1

    公开(公告)日:2020-10-08

    申请号:US16305246

    申请日:2017-06-05

    Abstract: The present invention relates to tomosynthesis. In order to further facilitate and improve the generation of three-dimensional image data, an X-ray imaging system (10) for calibration-free tomosynthesis is provided. The system comprises an imaging arrangement (12) with an X-ray detector unit (14) and an X-ray unit (16) comprising a plurality of X-ray sources (18). The system also comprises an image processing unit (20), an object receiving space (22), and a moving unit (24) for providing a relative movement between the imaging arrangement and an object of interest arranged at least partially in the object receiving space. The X-ray sources are provided in a known spatial relationship; the X-ray detector unit and the X-ray unit are also provided in a known spatial detector-sources-relationship. The moving unit provides a relative movement between the object of interest and the imaging arrangement in order to provide a plurality of system-to-object positions. The X-ray unit is configured to provide X-ray radiation to the object of interest from a plurality of different directions for each system-to-object position in order to provide a plurality of subsets of views with different viewing directions. The processing unit is configured to determine positions of the object in relation to the imaging arrangement based on the subsets of views, and to calculate a three-dimensional geometric position for each view of the subsets of views, and also to calculate a three-dimensional tomosynthesis reconstruction volume from the plurality of subsets of views.

    INTRAVASCULAR FLOW DETERMINATION
    7.
    发明申请

    公开(公告)号:US20190298311A1

    公开(公告)日:2019-10-03

    申请号:US16339159

    申请日:2017-09-27

    Abstract: The present invention relates to intravascular flow determination. In order to provide a facilitated way to determine flow values with improved accuracy, an intravascular flow determination device (50) is provided that comprises an input unit (54), a data processing unit (52), and an output unit (56). The input unit is configured to provide a measured local flow velocity value of a fluid inside a vessel of an object, which local flow velocity value is measured at a local position of interest, and to provide local spatial data of the vessel and the local position of interest; wherein the local flow velocity value, and the local spatial data relate to the same in position in time; and to provide a model flow-profile. The data processing unit is configured to adapt the model flow-profile based on the local values and the spatial data of the vessel and fluid dynamic constraints to generate an adapted local flow-profile relating to a cross-section at the local position of interest; and to determine a local peak flow value of the fluid inside the vessel based on the generated adapted local flow-profile. The output unit is configured to provide the local peak flow value.

    DETERMINING AN OPTIMAL PLACEMENT OF A PEDICLE SCREW

    公开(公告)号:US20190133690A1

    公开(公告)日:2019-05-09

    申请号:US16096367

    申请日:2017-04-26

    Abstract: The present invention relates to a device (2) for determining an optimal placement of a pedicle screw (4), comprising a processing unit (14), wherein the processing unit is configured to receive a model data set representing a model surface (22) of a human vertebra model (18) and a pedicle screw model (30) being optimally placed in a span of a pedicle section (28) of the model surface, wherein the processing unit is configured to receive 5 image data representing a surface image (26) of at least one human vertebra (6), GO and wherein the processing unit is configured to adapt the model data set for each of a number of the at least one human vertebra, such that an adapted model data set representing a correspondingly adapted model surface (36), which fits to the surface image of the respective human vertebra, is provided for each of the number of the at least one human vertebra, wherein each of the 10 adapted model data sets also represents a correspondingly adapted pedicle screw model (38). The present invention further relates to a corresponding method, a corresponding computer program element and a corresponding computer readable medium.

    CONE BEAM COMPUTED TOMOGRAPHY PROJECTION VALUES PROVIDING SYSTEM AND METHOD

    公开(公告)号:US20190105003A1

    公开(公告)日:2019-04-11

    申请号:US15554439

    申请日:2017-01-19

    Abstract: The present invention relates to a projection values determination device (14) being adapted to determine a projection value for an x-ray of a cone beam (4) based on detection values generated by detection elements of a three-dimensional arrangement of detection elements, which have been traversed by the x-ray, and not based on a detection value generated by a detection element which has not been traversed by the x-ray. Hence, the projection values determination device does not determine a projection value for a respective x-ray based on a detection value generated by a detection element not traversed by the respective x-ray. In particular, also in the cone direction only detection values are considered for generating a projection value, which have been generated by detection elements which have really been traversed by the respective x-ray. This can lead to reduced cross talk and computed tomography images having an improved image quality.

Patent Agency Ranking