Blood Vessel Extraction in 2D Thermography with Local Maximality
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods struggle to accurately isolate blood vessels in thermographic images of the breast, particularly in the presence of hotspots and non-uniform heat distributions, which are crucial for early detection of breast cancer.
Innovation Solution
A method involving temperature-based and shape-based analysis to identify candidate vessel pixels, followed by a constraint of local maximality to eliminate spurious pixels, and classification using a classifier system based on tortuosity of vessel structures.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If temperature-based analysis alone is used to detect vessel pixels, then detection speed is improved, but measurement precision deteriorates due to hotspots and non-uniform heat distributions
Solution Approach 1:
The patent combines temperature-based analysis with shape-based analysis to detect vessel pixels. The temperature-based method provides rapid initial detection while the shape-based method refines accuracy by analyzing vessel morphology characteristics, thereby resolving the contradiction between detection speed and precision in the presence of hotspots and non-uniform heat distributions.
Solution Approach 2:
The patent introduces an intermediary constraint of local maximality that acts as a filter between the temperature-based detection and final vessel identification. This intermediary step eliminates spurious non-vessel pixels by requiring that detected pixels represent local temperature maxima, thereby improving measurement precision without significantly sacrificing detection speed.
2Measurement precision
If shape-based analysis is used to detect vessel-like structures, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The patent applies shape-based analysis selectively to candidate regions identified by temperature-based analysis, rather than processing the entire image with complex shape algorithms. This local quality approach improves measurement precision for vessel detection while minimizing the increase in device complexity by limiting complex processing to relevant areas only.
Solution Approach 2:
The patent segments the detection process into distinct stages: temperature-based preliminary detection, shape-based refinement of candidate regions, and final classification. This segmentation allows each stage to use appropriately complex methods for its specific task, improving overall precision without unnecessarily increasing overall device complexity.
3Measurement precision
If dual criterion analysis (temperature and shape) is performed, then measurement precision is improved, but loss of time increases due to additional processing steps
Solution Approach 1:
The patent performs preliminary temperature-based analysis to identify candidate vessel pixels before applying the more time-consuming shape-based analysis. This preliminary action filters the image data to only relevant regions, thereby improving measurement precision while minimizing the time loss associated with dual criterion analysis by avoiding unnecessary processing of non-vessel areas.
Solution Approach 2:
The patent applies shape-based analysis partially, only to candidate pixels identified by temperature-based analysis, rather than applying it to the entire image. This partial action approach maintains high measurement precision for vessel detection while significantly reducing the time loss that would result from exhaustive dual criterion analysis of all pixels.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Effectively extracts blood vessels in thermographic images, enabling accurate differentiation between malignant and non-malignant breast tissue by quantifying vascular and non-vascular features, enhancing early detection of breast cancer.
Implementation Method 1
Thermography is an emerging alternative non-radiation and non-contact screening method for breast cancer detection... Thermography can also be used for imaging other body parts and it accurately depicts the temperature distribution on the skin.
Implementation Method 2
A temperature-based analysis is performed on the image to detect vessel pixels
Implementation Method 3
A shape-based analysis is also performed to detect pixels of vessel-like structures
Data Source
Figure 1
Figure 2
Figure 3
AI summary
What is disclosed is a system and method for isolating blood vessels in a thermographic image of a patient's breast or any other muscular region of the body. A thermographic image of a patient is received. A temperature-based analysis is performed on the image to detect vessel pixels. An intensity-based method analysis is performed on the image. A shape-based analysis is also performed to detect pixels of vessel-like structures. Candidate pixels which satisfy one or more of intensity-based or temperature-based or shaped-based criterion are identified. A constraint of local maximallity is thereafter imposed on each candidate pixel that satisfies both criterion to eliminate spurious non-vessel pixels. Candidate pixels which satisfy both criterion are then marked with a different color such that the vessel structures in the breast tissue can be visually differentiated. The vessel structures are provided to a classifier system which classifies the tissue in the thermal image as malignant and non-malignant otherwise, based on a tortuosity of the vessel structures.