Determining volume of a selectable region using extended reality
Inventors
ROZNICK, James S. • RUSSELL, Kyle Jordan
Assignees
Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-12277668-B2
Publication Date
2025-04-15
Expiration Date
Abstract
A system for determining volume of a selectable region is configurable to (i) obtain user input directed to a 3D representation of a set of 2D images and (ii) based on the user input, selectively modify one or more mask pixels of one or more respective selection masks. Each 2D image of the set of 2D images is associated with a respective selection mask. The 3D representation represents pixels of the set of 2D images with corresponding voxels. The user input selects one or more voxels of the 3D representation. The one or more mask pixels is associated with one or more pixels of the set of 2D images that correspond to the one or more voxels of the 3D representation selected via the user input.
Core Innovation
The invention presents a 3D representation of a set of 2D images within a 3D environment, where each 2D image is associated with a respective selection mask. In the 3D representation, pixels of the set of 2D images are represented with corresponding voxels within the 3D environment, and user input is directed to the 3D representation to select one or more voxels.
Based on the user input, the system selectively modifies one or more mask pixels of one or more of the respective selection masks. The one or more mask pixels are associated with one or more pixels of the set of 2D images that correspond to the one or more voxels selected via the user input, and a quantity of mask pixels that become selectively modified corresponds to a quantity of voxels selected.
The approach enables interactive selection and deselection by modifying mask pixels to store values indicating selection and deselection for a calculation of an output metric. The described flow includes obtaining 3D user input, modifying mask pixels on per-slice selection masks, computing an output metric from the selected mask pixels, and displaying the metric contemporaneously with the 3D selection. GPU shader reduction operations sum binary mask values into reduced selection masks at lower resolution using higher-bit reduced masks.
Claims Coverage
The independent claims are directed to a system and a method for presenting a 3D representation of 2D images with voxel-to-mask mapping and interactive user selection that selectively modifies corresponding mask pixels, and to a system that supports both selection and deselection via values stored in mask pixels for an output metric. Across the independent claims, the main inventive features include voxel-based selection driving per-slice selection-mask pixel modification and associating stored mask pixel values with calculation of an output metric.
3D representation of 2D images with voxel-to-mask mapping
Presenting a 3D representation of a set of 2D images within a 3D environment, each 2D image being associated with a respective selection mask, wherein the 3D representation represents pixels of the set of 2D images with corresponding voxels within the 3D environment.
User input selects voxels in the 3D representation
Obtaining user input directed to the 3D representation within the 3D environment, the user input selecting one or more voxels of the 3D representation.
Selective modification of corresponding selection-mask pixels
Based on the user input directed to the 3D representation within the 3D environment, selectively modifying one or more mask pixels of one or more of the respective selection masks, the one or more mask pixels being associated with one or more pixels of the set of 2D images that correspond to the one or more voxels of the 3D representation selected via the user input within the 3D environment, wherein a quantity of mask pixels that become selectively modified corresponds to a quantity of voxels selected via the user input directed to the 3D representation of the set of 2D images within the 3D environment.
Mask pixels store selection value for output-metric calculation
Selectively modifying one or more first mask pixels of one or more of the respective selection masks, wherein selectively modifying the one or more first mask pixels causes the one or more first mask pixels to store a first value indicating selection for a calculation of an output metric.
Deselection via stored deselection value for output-metric calculation
Based on the second user input directed to the 3D representation within the 3D environment, selectively modifying one or more second mask pixels of one or more of the respective selection masks, wherein selectively modifying the one or more second mask pixels causes the one or more second mask pixels to store a second value indicating deselection of the one or more second mask pixels or data associated therewith for the calculation of the output metric.
Overall, the independent claims cover interactive selection within a 3D environment that drives selective modification of corresponding per-slice selection-mask pixels, with selection and deselection represented by stored values used for calculation of an output metric.
Stated Advantages
Efficient real-time computation of output metrics using parallel GPU shader reduction operations to sum binary mask values into reduced selection masks at lower resolution.
Documented Applications
Facilitating image analysis by interactively selecting voxels in a 3D representation of a set of 2D images associated with selection masks, and computing an output metric from modified mask pixels.
Interested in licensing this patent?