3D Medical Image Visualization Through ROI Threshold Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing medical visualization systems for image-guided surgery struggle with noise and background clutter, particularly in displaying 3D models, which can obscure the relevant anatomical structures and surgical tools, leading to reduced accuracy and user experience.
Innovation Solution
A method and system that employs image segmentation to distinguish regions of interest from background, using multiple threshold values to enhance 3D model generation, reducing noise and focusing on relevant anatomical structures and surgical tools, and displaying these through a see-through augmented reality headset.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If 3D models are displayed with background features, then complete anatomical information is provided, but noise and background clutter increase reducing image quality
Solution Approach 1:
The patent applies segmentation by dividing the 3D medical image into multiple regions of interest (ROIs) and background regions. Different threshold values are applied to different regions: a first threshold for ROIs containing anatomical structures and a second, higher threshold for background regions. This selective thresholding segments the display content to show only relevant anatomical information while filtering out background noise and clutter, directly resolving the contradiction between information completeness and noise reduction.
Solution Approach 2:
The patent implements local quality by applying different display characteristics to different regions of the 3D model. Regions containing anatomical structures use one threshold value for high visibility, while background regions use a higher threshold value for suppression. This creates spatially varying display quality, enhancing relevant structures while maintaining noise reduction in background areas.
2Object-affected harmful factors
If multiple threshold values are applied to different regions, then image quality and relevance are enhanced, but system complexity increases
Solution Approach 1:
The segmentation approach divides the complex thresholding task into manageable regions. By first identifying ROIs versus background regions, then applying appropriate thresholds to each segment, the system manages complexity through structured division rather than attempting a single complex global thresholding operation.
Solution Approach 2:
The system performs preliminary region classification before applying thresholds. By pre-identifying which voxels belong to anatomical structures versus background, the system prepares the data structure in advance, making the subsequent threshold application more efficient and less complex than applying multiple thresholds simultaneously without region knowledge.
Data Source
AI summary
A computer-implemented method includes obtaining a three-dimensional (3D) image of a region of a body of a patient, the 3D image having feature values. The 3D image is segmented to define one or more regions of interest (ROIs). At least one region of interest (ROI) feature threshold is determined. A background feature threshold is determined. A 3D model is generated from the 3D image based on the determined at least one ROI feature threshold, the determined background feature threshold, and the segmentation. The 3D model is output for display to a user.