Automated Blood Vessel Status Evaluation Using Deep Learning Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for evaluating blood vessel status, such as SYNTAX scoring, are complex and time-consuming, requiring manual analysis of angiography images by medical professionals, which can lead to inefficiencies in assessing cardiovascular occlusion and guiding treatments like stent placement or bypass surgery.
Innovation Solution
A blood vessel status evaluation method utilizing a multi-layer deep learning model system that analyzes angiography images to select target images, determine blood vessel types, divide patterns into scoring segments, and assess vessel status, thereby automating the evaluation process and increasing efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual analysis of angiography images is used to evaluate blood vessel status, then measurement precision can be maintained, but productivity is significantly reduced due to the complex and time-consuming nature of the evaluation process
Solution Approach 1:
The patent replaces the manual mechanical analysis process with an automated image processing system that uses computer algorithms to analyze angiography images, extract blood vessel features, and calculate SYNTAX scores automatically, thereby substituting human manual work with computational processing
Solution Approach 2:
The patent divides the complex blood vessel pattern recognition task into multiple processing stages: image preprocessing, blood vessel extraction, pattern segmentation into scoring segments, and automated scoring calculation. This segmentation allows each stage to be handled by specialized processing modules, improving overall system efficiency
2Reliability
If manual SYNTAX scoring procedure is executed, then reliable blood vessel status assessment can be obtained, but loss of time increases due to the extremely complicated scoring mechanism
Solution Approach 1:
The patent performs preliminary processing of angiography images including noise reduction, contrast enhancement, and blood vessel extraction before the actual scoring process. This preliminary action prepares the data in advance, making the subsequent SYNTAX scoring calculation faster and more reliable
Solution Approach 2:
The patent creates a digital representation (copy) of the blood vessel patterns from the angiography images, allowing the scoring process to be performed on this digital copy rather than requiring direct manual analysis of the original complex images, thereby reducing time loss
3Productivity
If automated image processing is implemented, then productivity is improved through faster analysis, but device complexity increases due to the need for multiple deep learning models
Solution Approach 1:
The patent employs multiple deep learning models that serve different functions within the same system: one model for image preprocessing, another for blood vessel extraction, and a third for pattern recognition. This multi-functionality allows a single integrated system to handle multiple processing tasks, improving productivity while managing complexity through functional specialization
Data Source
AI summary
A blood vessel status evaluation method and a blood vessel status evaluation device are provided. The method includes: obtaining at least one angiography image corresponding to a target user; analyzing the angiography image by a first deep learning model to select a target image from the angiography image; analyzing the target image by at least one second deep learning model to determine a blood vessel type of the target user and divide a target blood vessel pattern in the target image into a plurality of scoring segments; and analyzing an output of the second deep learning model by a third deep learning model to obtain a blood vessel status of the target user.