Patient Volume Segmentation Using CT–DSA Fusion for 3D AVM Targets

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing radiation treatment plans face challenges in accurately segmenting complex patient volumes, such as arteriovenous malformations, due to the limitations of two-dimensional digital subtraction angiography in providing accurate three-dimensional target information, leading to significant overestimation and underestimation of treatment volumes.

Innovation Solution

Fusing planning computed tomography image information with two-dimensional digital subtraction angiography image information to generate accurate three-dimensional target volumes by projecting segmented three-dimensional contours onto two-dimensional angiography images, using registration techniques and interactive user displays to enhance segmentation accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If two-dimensional digital subtraction angiography is used for segmentation, then the segmentation process is simplified, but the measurement precision of three-dimensional target volumes deteriorates

Engineering Contradiction:

Improvesegmentation process complexityVSAvoidthree-dimensional target volume accuracy

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

The patent projects two-dimensional contours from digital subtraction angiography images onto a three-dimensional computed tomography volume, effectively transforming 2D information into 3D spatial context. This dimensional transition allows the segmentation to leverage the simplicity of 2D contour extraction while achieving accurate 3D target volume definition through spatial projection and intersection of multiple 2D contours.

Inventive Principle:

Principle #17Another dimension (Dimensionality change)

2Productivity

If automated segmentation is used, then productivity is improved, but measurement precision deteriorates for complex structures like arteriovenous malformations

Engineering Contradiction:

Improvesegmentation efficiencyVSAvoidtarget volume accuracy

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The patent divides the segmentation process into distinct components: automated extraction of 2D contours from angiography images, projection of these contours onto the 3D CT volume, and iterative refinement through user interaction. This segmented approach allows automated processing to handle routine contour extraction while human expertise focuses on the more challenging 3D reconstruction and validation, optimizing both efficiency and precision.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system incorporates iterative feedback loops where the projected 3D contours are displayed to users for validation and adjustment. Users can modify the segmented volume based on anatomical knowledge, and these modifications feed back into the segmentation model, progressively improving accuracy for complex structures like arteriovenous malformations while maintaining automated efficiency.

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS12453868B2Patient volume segmentation apparatus and method

Publication Date: 2025.10.28 VARIAN MEDICAL SYST PARTICLE THERAPY GMBH & CO KG

AI summary

By one approach, a control circuit accesses planning computed tomography image information for a particular patient. The control circuit also accesses two-dimensional digital subtraction angiography image information for the particular patient. The control circuit then fuses the planning computed tomography image information with the two-dimensional digital subtraction angiography image information to provide fused image information of the patient target volume.