Siemens Healthcare Gmbh

Siemens Medical Solutions Usa, Inc.

Siemens Aktiengesellschaft

Kevin Royalty

Sebastian Schafer

Markus Kowarschik

Christopher Rohkohl

Sonja Gehrisch

Benno Heigl

Jurgen Endres

Klaus Klingenbeck

Olivier Pauly

Frederik Bender

Gunter Lauritsch

Sebastian Schafter

Described herein are technologies for facilitating reconstruction of flow data. In accordance with one aspect, the framework receives a four-dimensional projection image dataset and registers one or more pairs of temporally adjacent projection images in the image dataset. Two-dimensional flow maps may be determined based on the registered pairs. The framework may then sort the two-dimensional flow maps according to heart phases, and reconstruct a three-dimensional flow map based on the sorted two-dimensional flow maps.

Reconstruction of flow data

A framework for quantitative evaluation of time-varying data. In accordance with one aspect, the framework delineates a volume of interest in a four-dimensional (4D) Digital Subtraction Angiography (DSA) dataset (). The framework then extracts a centerline of the volume of interest (). In response to receiving one or more user-selected points along the centerline (), the framework determines at least one blood dynamics measure associated with the one or more user-selected points (), and generates a visualization based on the blood dynamics measure ().

Quantitative evaluation of time-varying data

A framework for defective pixel correction using adversarial networks. In accordance with one aspect, the framework receives first and second training image datasets. The framework performs adversarial training of a corrector and a classifier with the first and second training image datasets respectively. The corrector may be trained to correct a first input image and the classifier may be trained to recognize whether a second input image is real or generated by the corrector. The framework applies the trained corrector to a current image to correct any defective pixels and generate a corrected image. The corrected image may then be presented.

Defective pixel correction using adversarial networks

The invention relates to a tomography system (TA) comprising a first (QD) and a second (QD) beam source-detector pair for capturing one series (A, A) of projection image data sets (PB, PB) each from one projection angle (W, W) each and a volume image production system (VE) for producing a series (AV) of volume images (VB) of a vascular system (GS) while taking into account first confidence values (VW) of the first pixel values (PW) and/or while taking into account second confidence values (VW) of the second pixel values (PW). The confidence value (VW, VW) of a pixel value (PW, PW) depends on a pixel-specific traversing length (L) that a projection beam (PS, PS) traverses on a path through parts (Gi) of the vascular system (GS) from the first (Q) or the second (Q) beam source to a pixel-specific sensor element (S) of the associated first (D) or second (D) detector. The invention further relates to a corresponding method () for producing a series (AV) of volume images (VB) of a vascular system (GS).

Tomography system and method for producing a series of volume images of a vascular system

A framework for defective pixel identification is described herein. In accordance with one aspect, the framework performs a machine learning technique to train a classifier using a training image dataset. The trained classifier is applied to a current image to identify one or more defective pixels, which may then be corrected.

Defective pixel identification using machine learning

A method calculates a four-dimensional DSA dataset from x-ray datasets. Each of the x-ray datasets contains a two-dimensional x-ray projection of an examination volume in relation to a direction of projection and a recording time. A first three-dimensional DSA dataset of a first reconstruction volume is determined based on the x-ray datasets. The first reconstruction volume is a part of the examination volume. A second three-dimensional DSA dataset of a second reconstruction volume is determined based on the x-ray datasets. The second reconstruction volume is a part of the first reconstruction volume. The second three-dimensional DSA dataset is segmented. The x-ray datasets are normalized based on the first three-dimensional DSA dataset. A four-dimensional DSA dataset is calculated by back projection of the normalized x-ray datasets onto the segmented second three-dimensional DSA dataset. The four-dimensional DSA dataset contains a number of third three-dimensional DSA datasets and associated time information.

Calculating a four dimensional DSA dataset with variable spatial resolution

Systems and methods are provided for refined data reconstruction. In accordance with one aspect, the framework performs a first four-dimensional reconstruction of time-varying data to generate a four-dimensional Digital Subtraction Angiography (DSA) dataset of an object of interest. The framework extracts a volume of interest from the four-dimensional DSA dataset to generate a volume array. The volume of interest may be refined based on the volume array to generate a refined dataset. A second four-dimensional reconstruction may then be performed based on the refined dataset to generate a zoomed-in four-dimensional representation of the volume of interest.

Refined reconstruction of time-varying data

Systems and methods are provided for data reconstruction. In accordance with one aspect, data interpolation is performed on a time-varying three-dimensional (3D) image dataset of one or more vessel-like structures to generate at least one interpolated voxel value. The interpolated voxel value is used to correct at least one value of a vessel voxel representing the one or more vessel-like structures in the time-varying 3D dataset.

Reconstruction of time-varying data

Described herein are technologies for facilitating three-dimensional imaging based on prior image data. In accordance with one aspect, deformable registration is performed to align three-dimensional (3D) image data to a sparse set of two-dimensional (2D) projection image data of at least one structure of interest. An iterative reconstruction scheme may then be performed to minimize a difference between the aligned 3D image data and the 2D image data.

Prior image based three dimensional imaging

A framework for image-based reconstruction is provided herein. In accordance with one aspect, the framework receives three-dimensional projection image data of an aneurysm wall in a vascular structure of interest and electrocardiogram signal data, wherein the three-dimensional projection image data is correlated to phases of the electrocardiogram signal data. The framework may sort the three-dimensional projection image data into phase-binned image data according to the phases, and reconstruct three-dimensional layouts of the aneurysm wall in the vascular structure of interest using the phased-binned image data. The framework may then determine the motion of the aneurysm wall between the phases based on the reconstructed three-dimensional layouts.

Reconstruction of aneurysm wall motion

A method for providing a 3D image data record of a physiological object with a metal object therein is proposed. To enable an image of the metal object in the physiological object, for instance a biopsy needle in a human patient to be recorded as a 3D image in this patient, two 2D x-ray images of the patient are obtained with the needle with the aid of a biplane x-ray system, and back projection allows a 3D image data record to be generated, which is then subject to a filtering with a gray-scale value window. After filtering, information relating to the position and shape of the metal object in space is obtained. The thus obtained first 3D image data record can be combined with another 3D image data record, in particular with a 3D image data record of the patient without the metal object obtained with the same biplane x-ray system.

Growing community of inventors

Fitchburg, WI, United States of America

Kevin Royalty