Abstract: The present invention relates to flexible sheath assemblies capable of being localized in three-dimensions (i.e., determining the location and orientation) in real-time based on two-dimensional x-ray images, and related systems and methods.

Abstract: A system comprising an adjustable mount arm, a bronchoscope coupled to the adjustable mount arm, an attachment coupled to the bronchoscope, and a steerable sheath coupled to the attachment and configured to be inserted through the bronchoscope. The system further includes a flexible probe configured to be inserted through the steerable sheath and the bronchoscope.

Abstract: The present invention relates to flexible sheath assemblies capable of being localized in three-dimensions (i.e., determining the location and orientation) in real-time based on two-dimensional x-ray images, and related systems and methods.

Abstract: 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.

Abstract: 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 (204). The framework then extracts a centerline of the volume of interest (206). In response to receiving one or more user-selected points along the centerline (208), the framework determines at least one blood dynamics measure associated with the one or more user-selected points (210), and generates a visualization based on the blood dynamics measure (212).

Abstract: 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.

Abstract: The invention relates to a tomography system (TA) comprising a first (QD1) and a second (QD2) beam source-detector pair for capturing one series (A1, A2) of projection image data sets (PB1, PB2) each from one projection angle (W1, W2) 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 (VW1) of the first pixel values (PW1) and/or while taking into account second confidence values (VW2) of the second pixel values (PW2). The confidence value (VW1, VW2) of a pixel value (PW1, PW2) depends on a pixel-specific traversing length (L) that a projection beam (PS1, PS2) traverses on a path through parts (Gi) of the vascular system (GS) from the first (Q1) or the second (Q2) beam source to a pixel-specific sensor element (S) of the associated first (D1) or second (D2) detector.

Abstract: 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 (204). The framework then extracts a centerline of the volume of interest (206). In response to receiving one or more user-selected points along the centerline (208), the framework determines at least one blood dynamics measure associated with the one or more user-selected points (210), and generates a visualization based on the blood dynamics measure (212).

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: The invention relates to a tomography system (TA) comprising a first (QD1) and a second (QD2) beam source-detector pair for capturing one series (A1, A2) of projection image data sets (PB1, PB2) each from one projection angle (W1, W2) 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 (VW1) of the first pixel values (PW1) and/or while taking into account second confidence values (VW2) of the second pixel values (PW2). The confidence value (VW1, VW2) of a pixel value (PW1, PW2) depends on a pixel-specific traversing length (L) that a projection beam (PS1, PS2) traverses on a path through parts (Gi) of the vascular system (GS) from the first (Q1) or the second (Q2) beam source to a pixel-specific sensor element (S) of the associated first (D1) or second (D2) detector.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.

Abstract: 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.