A method for visualizing a three-dimensional volume for use in a virtual reality environment is performed by uploading two-dimensional images for evaluation, creating planar depictions of the two-dimensional images, and using thresholds to determine if voxels should be drawn. A voxel volume is created from the planar depictions and voxels. A user defines a plane to be used for slicing the voxel volume, and sets values of the plane location and plane normal. The slice plane is placed within the voxel volume and defines a desired remaining portion of the volumetric plane to be displayed. All but the desired remaining portion of the voxel volume is not drawn and the remaining portion is displayed.

Rendering system combines point sampling and volume sampling operations to produce rendering outputs. For example, to determine color information for a surface location in a 3-D scene, one or more point sampling operations are conducted in a volume around the surface location, and one or more sampling operations of volumetric light transport data are performed farther from the surface location. A transition zone between point sampling and volume sampling can be provided, in which both point and volume sampling operations are conducted. Data obtained from point and volume sampling operations can be blended in determining color information for the surface location. For example, point samples are obtained by tracing a ray for each point sample, to identify an intersection between another surface and the ray, to be shaded, and volume samples are obtained from a nested 3-D grids of volume elements expressing light transport data at different levels of granularity.

The present disclosure provides computer-aided diagnosis systems and methods. The method may include obtaining multiple medical images of one or more bones; for at least one of the multiple medical images, detecting one or more bone fracture regions of the one or more bones in the medical image; causing a management list to be displayed for managing the one or more bones; receiving an instruction related to selecting at least one of the one or more bones, the instruction being generated through the management list; and upon receiving the instruction, causing the following to be displayed: at least one of one or more reconstructed bone images related to the at least one selected bone; or a marker of the one or more detected bone fracture regions related to the at least one selected bone.

The present disclosure provides computer-aided diagnosis systems and methods for detecting bone fracture. The method may include obtaining one or more medical images related to one or more bones. The method may also include obtaining a fracture detection model generated based on a machine learning model. The method may also include detecting, for at least one of the one or more medical images, one or more bone fracture regions of the one or more bones in the medical image using the fracture detection model.

A method and a system for determining an orthodontic treatment for a plurality of teeth of a subject are provided. The method comprises: receiving a 3D representation of a first tooth and a second tooth, adjacent thereto, of the subject, of a plurality of teeth of the subject; obtaining a tooth-gingiva segmentation loop; identifying an outer set of vertices positioned outside the tooth-gingiva segmentation loop and an inner set of vertices positioned inside the tooth-gingiva segmentation loop; generating a first interdental loop extending, along the 3D representation, through a given inner vertex and a given outer vertex, such that: the first interdental loop is at least partially indicative of an interdental boundary between the first tooth and the second tooth; and the first interdental loop intersects the tooth-gingiva segmentation loop; and generating the first tooth 3D representation based on the tooth-gingiva segmentation loop and the first interdental loop.

Rendering system combines point sampling and volume sampling operations to produce rendering outputs. For example, to determine color information for a surface location in a 3-D scene, one or more point sampling operations are conducted in a volume around the surface location, and one or more sampling operations of volumetric light transport data are performed farther from the surface location. A transition zone between point sampling and volume sampling can be provided, in which both point and volume sampling operations are conducted. Data obtained from point and volume sampling operations can be blended in determining color information for the surface location. For example, point samples are obtained by tracing a ray for each point sample, to identify an intersection between another surface and the ray, to be shaded, and volume samples are obtained from a nested 3-D grids of volume elements expressing light transport data at different levels of granularity.

Disclosed is a three-dimensional ultrasound image display method comprising the following steps: S1: obtaining a series of original two-dimensional images having spatial position and angle information by means of automatic or manual scanning; S2: performing image reconstruction on the basis of the original two-dimensional images to obtain three-dimensional volumetric images; S3: obtaining, from the three-dimensional volumetric images, one or more section images intersecting the original two-dimensional images, and obtaining one or more reconstructed two-dimensional images by means of image processing; S4: displaying together the one or more original two-dimensional images and the one or more section images in a three-dimensional space; and S5: selecting and displaying feature points, feature lines, and feature surfaces in the three-dimensional space on the basis of the original two-dimensional volumetric images. The present method provides an efficient and high-precision three-dimensional image display method, which can be widely applied to ultrasound and other three-dimensional imaging modes.

A cube map is used for determining the appearance of a surface by means of a precomputed texture image. Embodiments of the present invention are drawn computer systems and methods for rendering a spherical projection as a cube map that mitigates non-uniform pixel density near the edges of the cube map to avoid artifacts and increase rendering performance.

A method using a two-dimensional (2D) image representation of three-dimensional (3D) geometric objects in a machine learning framework has been developed. The method includes generating a single 2D geometry image corresponding to a 3D object model, and providing the single geometry image as input to a shape analysis task to enable shape analysis of the 3D object model based only on information encoded in the single 2D geometry image in the machine learning framework.

In an image generation apparatus, a virtual space generation section generates a virtual space in which an object and a virtual camera are arranged in accordance with input information acquired by an input information acquisition section. An intermediate image generation section draws the virtual space by a past technique. A curved surface generation section of a display image generation section generates, for each polygon of an object, a curved surface corresponding to the polygon. A pixel displacement acquisition section acquires a correspondence in pixel position between an image drawn with a planar polygon and a curved surface image. A drawing section determines color values of the pixels of the display image in accordance with the correspondence by referring to an original image. An output section outputs data of the display image generated as described above to a display apparatus.