Temporal Angiogram Tagging for Multi-Region Visualization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
During endovascular interventions, navigating angiograms to identify and visualize multiple anatomical regions of interest spread far apart is challenging due to poor visibility of the vasculature, requiring multiple frame selections and inefficient contrast agent administration.
Innovation Solution
An image processing apparatus that registers frames with contrast agent propagation through regions of interest (ROIs) to a pre-op reference image, identifying main frames with high contrast agent concentration and associating them with user-selectable ROIs, enabling temporal navigation and retrieval of relevant frames for improved visualization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If multiple frames are selected to cover all target regions spread far apart, then complete coverage of anatomical regions is improved, but navigation complexity and time required increase
Solution Approach 1:
The system performs preliminary registration of all angiogram frames with the pre-operative reference image dataset before the intervention procedure. This advance preparation creates an associative data structure that links each ROI with its corresponding main frame, enabling rapid retrieval during the procedure without requiring time-consuming manual frame selection
Solution Approach 2:
The system creates a virtual copy of the anatomical navigation experience by registering fluoroscopic frames with pre-operative reference images. This allows the operator to navigate through a registered dataset during the procedure, effectively copying the planning phase anatomy into the intervention phase without requiring physical repositioning or multiple frame acquisitions
2Illumination intensity
If contrast agent is administered to reach distant target regions, then visualization of target anatomy is improved, but contrast agent volume and procedure time increase
Solution Approach 1:
The system identifies and stores the main frame for each ROI in advance by analyzing contrast agent concentration in the registered dataset. This preliminary identification allows the operator to directly retrieve pre-selected optimal frames showing each anatomical region at its best contrast, eliminating the need to wait for contrast to propagate to distant regions during the procedure
Solution Approach 2:
The system introduces a computational intermediary (the image processing apparatus with registration and identification functions) that mediates between the raw angiogram stream and the operator. This intermediary automatically analyzes contrast concentration, identifies main frames, and presents optimized views, replacing the manual process of waiting for contrast propagation and manually selecting frames
3Adaptability or versatility
If manual frame selection is used to navigate angiograms, then flexibility in viewing specific regions is improved, but operator workload and complexity increase
Solution Approach 1:
The system performs self-service by automatically analyzing the angiogram stream, identifying contrast-filled regions, and selecting main frames for each ROI without operator intervention. The image processing apparatus autonomously navigates through the temporal sequence, identifies when each ROI is optimally visualized, and presents the results in an interactive interface that maintains flexibility while eliminating manual frame-by-frame review
Solution Approach 2:
The system replaces the manual mechanical process of frame selection with an automated computational system. Instead of the operator manually reviewing frames and selecting those showing desired regions, an image processing apparatus with registration, identification, and association functions automatically performs the selection based on contrast agent concentration analysis, significantly reducing operator workload
Data Source
Figure 1
Figure 2
Figure 3
AI summary
An image processing apparatus and method take as input a pre-op reference image (OP) and a stream (A) of angiographic images (A1-A3). Based on a plurality of predefined regions of interest (ROIa-c) in said reference image (PO), the angiographic image best showing when displayed a respective one of the regions of interest (ROIa-c) is detected from among the steam (A) of angiographic images (A1-A3). The detected angiographic image is associated with said region of interest to form an associative data structure (DS). A graphical user interface (GUI) is generated that allows based on said associative data structure (DS) to retrieve the associated angiography upon a user selecting any one of the regions of interest (ROIa-c) on said graphical user interface (GUI).