Volume Rendering Label Layout for Real-Time Visibility Optimization

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Creating globally optimal and temporally coherent annotation layouts for labels in images without manual intervention is an NP-hard problem, and existing algorithms like genetic algorithms based on Darwinian evolution are inefficient for large images or image animations.

Innovation Solution

Optimizing label placement in images based on visibility measures, using iterative numerical optimization and visibility criteria, such as occlusion and proximity relationships, with techniques like gradient descent and simulated annealing, to enhance the visibility of regions of interest and landmarks.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If genetic algorithms are used for automated label placement, then the layout optimization can handle complex scenarios, but the computation time becomes too long for real-time use

Engineering Contradiction:

Improvelayout optimization qualityVSAvoidcomputation time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The patent pre-calculates visibility information for all possible label positions before performing layout optimization. This preliminary computation of visibility measures allows the optimization algorithm to quickly evaluate candidate positions without performing complex visibility calculations during the optimization process, thereby reducing computation time while maintaining optimization quality

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent employs dynamic programming with iterative optimization to adaptively adjust label positions based on visibility feedback. The algorithm dynamically recalculates optimal positions in real-time during the optimization process, allowing it to converge to high-quality solutions faster than static genetic algorithms

Inventive Principle:

Principle #15Dynamics

2Loss of information

If more labels are added to annotate more regions of interest, then more semantic information is provided, but occlusion of other labels and regions increases

Engineering Contradiction:

Improvesemantic information completenessVSAvoidocclusion

Core Design Contradiction:

Loss of informationVSObject-affected harmful factors

Solution Approach 1:

The patent optimizes label positions individually for each label based on local visibility conditions at its specific location. By calculating visibility measures for each label-position pair and adjusting positions to maximize local visibility, the system ensures that each label is placed where it will be most visible without necessarily occluding other labels or regions

Inventive Principle:

Principle #3Local quality

Solution Approach 2:

The patent implements an iterative optimization process that uses visibility feedback to continuously adjust label positions. The algorithm evaluates the visibility impact of each label placement and refines positions based on this feedback, allowing it to find configurations that maximize information display while minimizing occlusion through repeated evaluation and adjustment

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS12493953B2Dynamic layout optimization of annotation labels in volume rendering

Publication Date: 2025.12.09 SIEMENS HEALTHINEERS AG

AI summary

A layout of labels for annotating a rendered image is optimized. A rendered image is obtained, and locations of a plurality of regions of interest in the rendered image are determined. Semantic information associated with the plurality of regions of interest is obtained. Based on the semantic information and the locations of the plurality of regions of interest, and, taking into account a visibility of the labels and a further visibility of the regions of interest in the rendered image, the layout of the labels for annotating the plurality of regions of interest in the rendered image is determined.