Masking Non-Bony Structures for 2D-3D Registration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current imaging modalities, such as CT and live X-ray, face challenges in registering image data from the visceral cavity due to cluttered views from tissue and contrast-enhanced vasculature, making it difficult to distinguish bony structures like the spine and ribcage, which hinders accurate registration.
Innovation Solution
An imaging device with a model provision unit generating a deformable cavity model, a processing unit that adapts this model to image data, and a registration unit that masks non-bony structures, allowing for enhanced visibility and selective rendering of bony landmarks for optimal registration between different imaging modalities.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If tissue and contrast-enhanced vasculature are visualized in the visceral cavity, then complete anatomical information is provided, but visibility of bony structures is reduced due to cluttered views
Solution Approach 1:
The patent extracts and removes non-bony structures (tissue and contrast-enhanced vasculature) from the visual field by masking them in the CT image data. This extraction allows bony structures to become clearly visible without the clutter of other anatomical features, directly resolving the contradiction between providing complete anatomical information and maintaining visibility of bony landmarks for registration.
2Productivity
If manual 2D-3D registration is performed using traditional methods, then registration can be completed, but time consumption is excessive due to difficult landmark distinction
Solution Approach 1:
The patent applies preliminary action by pre-processing the CT image data to mask non-bony structures before the registration process begins. This preparation creates optimized visual conditions with clearly visible bony landmarks, enabling physicians to perform registration much faster than with unprocessed images, thereby reducing time loss while maintaining registration accuracy.
3Measurement precision
If all anatomical structures are displayed during registration, then comprehensive anatomical context is available, but registration accuracy is reduced due to difficulty in distinguishing landmarks
Solution Approach 1:
The patent applies segmentation by separating bony structures from non-bony structures through masking. The CT image data is segmented to display only bony landmarks while hiding soft tissue and vasculature. This segmentation improves registration accuracy by making landmarks clearly distinguishable, while the automated masking process manages the complexity rather than increasing it.
Data Source
AI summary
The invention relates to an imaging device (10) for registration of different imaging modalities, an imaging system (1) for registration of different imaging modalities, a method for registration of different imaging modalities, a computer program element for controlling such device and a computer readable medium having stored such computer program element. The imaging system (1) for registration of different imaging modalities comprises a first imaging modality (2), a second imaging modality (3), and an imaging device (10) for registration of different imaging modalities. The imaging device (10) for registration of different imaging modalities comprises a model provision unit (11), a first image data provision unit (12), a processing unit (13), a second image data provision unit (14), and a registration unit (15). The model provision unit (11) provides a cavity model of a visceral cavity. The first image data provision unit (12) provides first image data showing a region of interest of a patient by the first imaging modality (2). The processing unit (13) registers the cavity model to the first image data and adapts the cavity model based on the first image data. The processing unit (13) differs between bony and non-bony structures and masks a non-bony structure in the first image data based on the adapted cavity model. The second image data provision unit (14) provides second image data showing the region of interest of a patient by the second imaging modality (3). The registration unit (15) registers the masked first image data and the second image data.