Tumor Feeder Vessel Detection via Morphological Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for detecting feeder vessels associated with tumors are not effective or accurate, leading to potential damage to healthy tissues during embolization procedures.
Innovation Solution
A method and device utilizing medical images, such as CT angiography or MRI, to identify and characterize blood vessels through segmentation and machine learning models, determining feeder vessels based on morphological characteristics like diameter, branching, and tortuosity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If physician-based visual inspection is used to identify feeder vessels, then the method is simple and requires no additional equipment, but the accuracy and reliability of tumor identification is poor leading to damage of healthy tissues
Solution Approach 1:
The patent segments the blood vessel network into individual vessels and analyzes their morphological characteristics (diameter, branching patterns, tortuosity) to distinguish tumor feeder vessels from normal vessels. This segmentation enables automated, objective identification based on quantitative features rather than subjective visual inspection.
Solution Approach 2:
The patent replaces the mechanical/visual inspection method with a computational system that processes medical images through algorithms. The system automatically extracts vascular characteristics and classifies vessels based on their morphological properties, eliminating the need for physician expertise in visual differentiation.
2Measurement precision
If automated detection systems are implemented to improve accuracy, then the reliability of tumor identification improves, but the device complexity and cost increase
Solution Approach 1:
The patent changes the parameters for vessel identification from subjective visual criteria to objective morphological measurements including diameter variations, branching angles, and tortuosity values. These quantitative parameters enable precise automated detection of tumor-associated vascular changes.
Solution Approach 2:
The patent employs a multi-functional imaging system that performs CT angiography, skeletonization, and machine learning classification within a single integrated workflow. The system handles multiple processing stages (image acquisition, vessel extraction, characteristic measurement, and classification) using coordinated algorithms rather than separate devices.
Data Source
AI summary
A method and a device for determining a presence of tumor are provided. The method includes receiving a medical image associated with a patient. The medical image includes a region of interest associated with the patient. The method includes identifying one or more blood vessels associated with the region of interest in the medical image. The method includes determining a set of characteristics associated with the one or more blood vessels using a trained machine learning model. The method also includes determining whether the one or more blood vessels are feeder vessels associated with the tumor based on the set of characteristics associated with the one or more blood vessels. The method includes detecting a tumor region in the region of interest based on the feeder vessels, when the one or more blood vessels are the feeder vessels associated with the tumor.