XR Volume Measurement via 3D Mask Pixel Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for obtaining volume measurements from medical imagery are cumbersome, inefficient, and prone to user error, requiring manual tracing and combination of area measurements across multiple image slices.
Innovation Solution
The use of extended reality (XR) systems to determine volume by obtaining user input directed to a 3D representation of 2D images, selectively modifying mask pixels associated with selection masks to select corresponding voxels, and generating volume measurements based on the selected voxels.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual tracing and measurement of structures in each image slice is performed, then volume measurements can be obtained, but the process becomes cumbersome and time-consuming
Solution Approach 1:
The system automatically performs volume measurement by processing selection masks and associated image data without requiring manual tracing in each slice. The processor automatically identifies structures, retrieves corresponding image slices, and computes volume measurements, allowing the system to serve itself rather than requiring extensive manual intervention.
Solution Approach 2:
Selection masks are pre-generated and stored with anatomical structures before the measurement process. When a volume measurement is needed, the system retrieves the pre-prepared selection mask and processes it automatically, eliminating the need for manual tracing during measurement and significantly reducing time requirements.
2Measurement precision
If manual tracing of structures in multiple image slices is performed, then volume measurements can be obtained, but user error increases and efficiency decreases
Solution Approach 1:
The system automatically processes selection masks and computes volume measurements without requiring user tracing operations. The automated processing eliminates user error while maintaining measurement accuracy, and the interface requires only high-level user input rather than detailed manual tracing.
Solution Approach 2:
Selection masks serve as an intermediary representation that captures anatomical structures in a simplified format. Instead of requiring users to manually trace structures in each image slice, the selection mask acts as a mediator that encodes the structural information, allowing automated processing while maintaining measurement accuracy.
3Measurement precision
If conventional manual measurement methods are used, then volume can be measured from 2D images, but the process is complex and inefficient
Solution Approach 1:
The system performs automated volume measurement by processing selection masks and associated image data without requiring manual intervention in each measurement step. This self-service approach maintains measurement precision while dramatically improving productivity by eliminating repetitive manual tracing operations.
Solution Approach 2:
The patent replaces manual mechanical tracing operations with automated computational processing. Instead of requiring users to physically trace structures in each image slice, the system uses automated algorithms to process selection masks and compute volumes, substituting manual mechanical actions with automated digital processing for higher efficiency.
Data Source
AI summary
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.