Vascular Tracking Model for Post-Contrast Vessel Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vascular interventional surgeries face challenges in accurately tracking blood vessels due to the fast flow and toxicity of contrast agents, and movements caused by factors like respiration and heartbeat, which complicate prolonged visualization and require high doses of contrast agents.
Innovation Solution
A method and system for vascular tracking that determines vascular and background movements using a movement determination model based on reference and contrasted images, allowing prediction of vascular regions even after contrast agent dissipation, utilizing machine learning models for accurate tracking.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Illumination intensity
If contrast agent is injected to visualize blood vessels, then vascular visualization is improved, but contrast agent toxicity and rapid flow cause prolonged visualization to be unachievable
Solution Approach 1:
The system performs preliminary action by capturing multiple contrasted images during the brief period when contrast agent is present, extracting vascular movement information in advance. This allows the vascular tracking model to predict vessel locations after contrast dissipation without requiring continuous contrast injection, thus extending visualization duration while reducing toxicity exposure.
2Measurement precision
If high dose of contrast agent is used to maintain visualization, then vascular tracking accuracy is improved, but patient exposure to toxic substance increases
Solution Approach 1:
The system creates a virtual copy of the vascular structure through image processing and machine learning models. By training a vascular tracking model on contrasted images to predict vessel locations in non-contrasted images, the system replicates vascular visualization without requiring additional contrast agent, thus maintaining tracking accuracy while eliminating toxic exposure.
3Stability of the object's composition
If patient remains still during surgery, then vascular image stability is improved, but patient movement due to respiration and heartbeat cannot be prevented
Solution Approach 1:
The system applies dynamics by transitioning from static image analysis to dynamic temporal modeling. The vascular tracking model processes sequences of contrasted images over time, capturing the dynamic movement patterns of blood vessels caused by respiration and heartbeat. This enables the system to adapt to physiological movements and maintain accurate vascular localization despite patient immobility constraints.
Data Source
AI summary
Embodiments of the present disclosure provide a method and a system for vascular tracking. The method includes determining a plurality of first vascular movements and a plurality of first background movements of an object based on a reference image and a plurality of contrasted images of the object; determining structural parameters of a movement determination model based on the plurality of first vascular movements and the plurality of first background movements; and determining a predictive vascular region in a target image based on the movement determination model.