A method includes generating a real-time ultrasound image of anatomy of interest. At least a sub-portion of the anatomy of interest is deformed from an initial location to a different location by pressure applied by an external force. The method further includes obtaining a 2-D slice, which corresponds to a same plane as the real-time ultrasound image, from 3-D reference image data, wherein a corresponding sub-portion is at the initial location. The method further includes determining displacement fields for the sub-portion from the sub-portion, the corresponding sub-portion and other anatomy not-deformed in the real-time ultrasound image and the 3-D reference image data. The method further includes deforming the 3-D reference image data using the displacement fields, which creates deformed 3-D reference image data based on the different location.

Disclosed are a bone age estimation method and a bone age estimation apparatus. The bone age estimation method may comprise the steps of: extracting a region of interest including a cervical spine region from a lateral cephalometric radiographic image obtained by imaging a subject's cervical spine, by using a first deep learning model; extracting landmarks from the extracted region of interest by using a second deep learning model; calculating a landmark numerical value on the basis of the extracted landmarks; and providing maturity information of a maturation stage of the cervical spine on the basis of the calculated landmark numerical value.

Disclosed are a bone age estimation method and a bone age estimation apparatus. The bone age estimation method may comprise the steps of: extracting a region of interest including a cervical spine region from a lateral cephalometric radiographic image obtained by imaging a subject's cervical spine, by using a first deep learning model; extracting landmarks from the extracted region of interest by using a second deep learning model; calculating a landmark numerical value on the basis of the extracted landmarks; and providing maturity information of a maturation stage of the cervical spine on the basis of the calculated landmark numerical value.

Provided are methods for estimating a Reserve Strength Ratio in a segment of a blood vessel or a lymphatic vessel. In some embodiments, the methods include providing a multiphase Digital Imaging and Communications in Medicine (DICOM) stack of computed tomography (CT) or magnetic resonance (MR) images of a blood vessel or a lymphatic vessel to software, wherein the stack of DICOM images is organized by phase; providing the output from the software to a Model Segmentation procedure in which the first phase of the DICOM stack (1st phase) is segmented to create the Geometric Model and finite element mesh of the 1st phase and a map of Local Thickness Measure; uploading a mesh created for the first phase onto the DICOM image volume; mapping each voxel position of the mesh for the first phase to all the subsequent meshes using an optical flow (OF) algorithm; creating deformed meshes at all phases from the maps of displaced nodes; estimating local curvature at each node location for all the phases using a finite difference method; evaluating the local deformation at each phase from the meshes corresponding to all the phases using an element approach; calculating local thickness at each node for all the phases using the deformation calculation at each phase and the thickness measured at the first phase and using the assumption of incompressibility for the aortic wall; and calculating the local principal stresses for each element from an extension of Laplace's equation applied to the local principal directions of curvatures, whereby the Reserve Strength Ratio in a segment of a blood vessel or a lymphatic vessel is estimated. Also provided are methods for predicting an increased risk of rupture of a blood vessel or a lymphatic vessel, methods for identifying subjects as being at risk for rupture of a blood vessel or a lymphatic vessel, and computer program products with computer executable instructions embodied in computer readable medium for performing the methods disclosed herein.

A citrus identification method comprises: performing first-time image acquisition processing on a target citrus tree to obtain a first image; inputting the first image into a first citrus fruit identification model to be processed to obtain a first identification result sequence; performing area interception processing on the first image to obtain a citrus fruit area; obtaining roundness integrity numerical values; selecting an appointed roundness integrity numerical value, and acquiring a defect position of an appointed citrus fruit in the first image; determining a first spatial range and a second spatial range; performing both first spray injection treatment and second spray injection treatment; performing second-time image acquisition processing to obtain a second image; inputting the second image into a second citrus fruit identification model to be processed to obtain a second identification result; and generating a citrus fruit identification result.

Methods and systems for constructing a three-dimensional (3D) model of a user in a virtual environment for full body virtual reality (VR) applications are described. The method includes receiving an image of the user captured using an RGB camera; detecting a body bounding box associated with the user using a first trained neural network; determining a segmentation map of the user, based on the body bounding box; determining a two-dimensional (2D) contour of the user from the segmentation map; forming a 3D extrusion model by extruding the 2D contour; and constructing the 3D model of the user in the virtual environment by applying a geometric transformation to the 3D extrusion model. Applications of full body VR include physical training and fitness sessions, games, control of computing devices, manipulation and display of data, interactive social media with VR, and the like.

Methods and systems for constructing a three-dimensional (3D) model of a user in a virtual environment for full body virtual reality (VR) applications are described. The method includes receiving an image of the user captured using an RGB camera; detecting a body bounding box associated with the user using a first trained neural network; determining a segmentation map of the user, based on the body bounding box; determining a two-dimensional (2D) contour of the user from the segmentation map; forming a 3D extrusion model by extruding the 2D contour; and constructing the 3D model of the user in the virtual environment by applying a geometric transformation to the 3D extrusion model. Applications of full body VR include physical training and fitness sessions, games, control of computing devices, manipulation and display of data, interactive social media with VR, and the like.

A method includes capturing a video of a plurality of drops being jetted through a nozzle of a printer. The method also includes measuring a signal proximate to the nozzle based at least partially upon the video. The method also includes determining one or more metrics that characterize a behavior of the drops based at least partially upon the signal.

A method for inspecting and post-processing a workpiece having a laser-cut, closed inner contour, in which method a gripper moves a workpiece picked up in a defined manner, between a previously stored pre-defined pick-up position AP and a pre-defined first gripper position GP1, delivering the workpiece to an inspection unit, and if post-processing is required, a pre-defined second gripper position GP2, delivering the workpiece to an ejector unit.

A method for inspecting and post-processing a workpiece having a laser-cut, closed inner contour, in which method a gripper moves a workpiece picked up in a defined manner, between a previously stored pre-defined pick-up position AP and a pre-defined first gripper position GP1, delivering the workpiece to an inspection unit, and if post-processing is required, a pre-defined second gripper position GP2, delivering the workpiece to an ejector unit.