Various embodiments set forth systems and techniques for generating seams for a 3D model. The techniques include generating, based on the 3D model, one or more inputs for one or more trained machine learning models; providing the one or more inputs to the one or more trained machine learning models; receiving, from the one or more trained machine learning models, seam prediction data generated based on the one or more inputs; and placing one or more predicted seams on the 3D model based on the seam prediction data.

Methods are disclosed for the generation and editing of layer delineations within three-dimensional tomography scans. Cross sections of a subject are generated and presented to an operator, who has the ability to edit layer delineations within the cross section, or determine parameters used to generate new cross sections. By guiding an operator through a set of displayed cross sections, the methods can allow for a more rapid, efficient, and error-free segmentation of the subject. The cross sections can be nonplanar in shape or planar and non-axis-aligned. The cross sections can be restricted to exclude one or more user-defined regions of the subject, or to include only one or more user-defined regions of the subject. The cross sections can be localized to a point-of-interest. Iterative implementations of the methods can be used to arrive at a segmentation deemed satisfactory by the user.

An image processing apparatus according to an embodiment includes processing circuitry. The processing circuitry is configured to generate, from three-dimensional medical image data, a first cross-sectional image and a second cross-sectional image intersecting the first cross-sectional image and is configured to change display locations of the first cross-sectional image and the second cross-sectional image on a display, in conjunction with a change in an intersecting location of the first and the second cross-sectional images.

A medical image processing apparatus according to an embodiment includes processing circuitry. The processing circuitry extracts, based on a first area that is an area to which radiation is emitted and a second area that is an area affected by the radiation emitted, a cross-section that satisfies a certain condition and that passes through two points, the first area and the second area being specified by volume data and the two points being a first point included in the first area and a second point included in the second area. The processing circuitry causes a display to present an image of the cross-section.

A computer-based method for generating a context preserving mapping of tubular structures represented by a 3D dataset having the steps of projecting a skeleton of a 3D tubular structure on to a 2D plane, and adjusting the projected skeleton to correct projection imbued distortion in skeleton length. The 2D projected skeleton is processed to remove intersections, and a surface boundary around the 2D skeleton is determined for the map. The 3D surface of the skeleton is mapped to match the 3D boundary to create a 3D map of the tubular structure.

The invention relates to a device (10) for visualizing a 3D object, an X-ray imaging system (1) for visualizing a 3D object, a method for visualizing a 3D object, and a computer program element for controlling such device (10) and a computer readable medium having stored such computer program element. The device (10) for visualizing a 3D object comprises a processing unit (11). The processing unit (11) is configured to provide an image in a 2D projection plane (23). The processing unit (11) is configured to project an initial 3D object (22) from an initial plane (27) with an inverse projection transformation in the 2D projection plane (23) of the image to achieve an inverse 2D object (24). The inverse projection transformation is a projection transformation, wherein a vanishing point is at the other side of the 2D projection plane (23) than the initial object. The processing unit (11) is configured to point-mirror the inverse 2D object (24) to achieve a mirrored non-inverse 2D object (25). The processing unit (11) is configured to project the mirrored non-inverse 2D object (25) back to the initial plane (27) to provide a corrected 3D object (26). The processing unit (11) is configured to project the corrected 3D object (26) again to the 2D projection plane (23) of the image to provide a final 3D object (28) appearing to be non-inversely projected.

A method, apparatus, system, and computer program for generating clinical information. Information indicating at least one clinical aspect of an object is received. Clinical information of interest relating to the at least one clinical aspect is generated from a plurality of projection images.

A medical image processing apparatus includes a port, a processor and a display. The port acquires volume data. The processor sets a three-dimensional region in the volume data, acquires three vectors orthogonal to each other from the three-dimensional region, calculates three surfaces to which the vectors are normal lines, and generates three cross-sectional images of the volume data by setting the respective surfaces as cross-sections. The display shows the generated cross-sectional images. The processor shifts at least one surface in parallel along the corresponding normal line and regenerates a cross-sectional image in which the shifted surface is a cross-section.

Techniques for generating a hollow model from a medical image are disclosed herein. In an example, a hollow model may be created within a medical imaging visualization application through the generation of a mask of an interior space of a segmented anatomical structure, the extrusion of a shell mask from the mask of the interior space, and the generation of a visualization of the shell mask within the medical imaging visualization application. For example, the mask may be provided as a layer in the medical imaging visualization application, allowing a user to visualize the produced shell mask of the hollow model from the perspective of the medical imaging. In further examples, the hollow model generation techniques may be used with techniques for shell region modifications, variable shell thickness, multiple shell layer, and trimming of shell endpoints.

The present invention relates to a device for displaying image information, the device comprising: a detection unit (10), which is configured to identify a plurality of admissible display orientations of multiple data sets; a restriction unit (20), which is configured to restrict the plurality of admissible display orientations of at least one of the multiple data sets to a set of admissible display orientations in common for all the multiple data sets; and/or to restrict a plurality of admissible scrolling directions of at least one of the multiple data sets to a set of admissible scrolling directions that are normal to the restricted admissible display orientations; and a display unit (30), which is configured to display the multiple data sets using the set of the restricted display orientations and/or the set of restricted scrolling directions.