Multi-Modality Vessel Model Fusion for Diagnostic Accuracy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current vascular imaging modalities, such as X-ray Angiography, Computed Tomography Angiography, and intravascular imaging techniques, face challenges in accurately assessing artery diseases due to limitations like blooming artifacts, fore-shortening, and incomplete visualization of lesions, which hinders comprehensive diagnosis and treatment planning.
Innovation Solution
A system and method for jointly processing and analyzing vascular images from multiple imaging modalities, including XA, CTA, OCT, and IVUS, to fuse vessel models and generate a comprehensive fused model for improved diagnostic analysis, providing accurate vessel information and lesion characterization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Shape
If CTA is used for non-invasive 3D imaging, then vessel tree visualization is improved, but calcium deposit blooming artifacts worsen
Solution Approach 1:
The patent combines CTA 3D vessel tree model with XA 2D projection model and intravascular imaging models (OCT/IVUS) to create a fused multi-modality model. This merging allows the system to leverage the comprehensive vessel tree structure from CTA while compensating for its blooming artifacts using high-resolution intravascular imaging data from the same or different patients.
2Measurement precision
If XA is used for high-resolution 2D imaging, then lumen visualization is improved, but lesion visibility and 3D structure worsen
Solution Approach 1:
The patent projects 3D intravascular imaging data (OCT/IVUS cross-sectional slices) onto the 2D XA projection plane to create a synthesized 3D model. This dimensional transformation allows the system to recover 3D structural information and lesion details that were lost in the 2D XA projection, while maintaining the high-resolution lumen boundary information from XA.
3Measurement precision
If intravascular imaging is used for high-resolution cross-sectional imaging, then vessel wall detail is improved, but field of view and comprehensive lesion picture worsen
Solution Approach 1:
The patent segments the vessel into multiple cross-sectional slices from intravascular imaging data, then reconstructs a comprehensive 3D model by integrating these slices with the full-vessel-tree CTA model. This segmentation approach allows the system to achieve high-resolution vessel wall characterization in local regions while maintaining a complete field of view through the 3D reconstruction.
4Reliability
If multiple imaging modalities are used for comprehensive assessment, then diagnostic accuracy is improved, but system complexity worsens
Solution Approach 1:
The patent introduces a computational model fusion system as an intermediary that automatically integrates data from multiple imaging modalities. This intermediary layer handles the complexity of multi-modality data processing, registration, and fusion algorithms, presenting a unified simplified interface to users while maintaining high diagnostic accuracy through comprehensive multi-source information integration.
Data Source
AI summary
Embodiments of the disclosure provide methods and systems for multi-modality joint analysis of a plurality of vascular images. The exemplary system may include a communication interface configured to receive the plurality of vascular images acquired using a plurality of imaging modalities. The system may further include at least one processor, configured to extract a plurality of vessel models for a vessel of interest from the plurality of vascular images. The plurality of vessel models are associated with the plurality of imaging modalities, respectively. The at least one processor is also configured to fuse the plurality of vessel models associated with the plurality of imaging modalities to generate a fused model for the vessel of interest. The at least one processor is further configured to provide a diagnostic analysis result based on the fused model of the vessel of interest.