Lung CT Abnormal Tissue Segmentation via Wavefront Propagation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In computed tomography, the low contrast between abnormal tissue and blood vessels containing a contrast medium makes it difficult to identify abnormal tissue, especially when it is close to or on blood vessels, due to similar gray-scale values.
Innovation Solution
The method involves recording slice images of the lung using X-ray radiation, differentiating blood vessels and abnormal tissue by evaluating their diameters, and using a wave front propagation technique to determine the boundaries between them, allowing for the segmentation and display of abnormal tissue on an output device.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Illumination intensity
If contrast medium is injected into blood vessels to make them recognizable, then blood vessels become clearly visible in the X-ray image, but the contrast between abnormal tissue and blood vessels becomes low, making abnormal tissue difficult to identify
Solution Approach 1:
The patent applies segmentation by dividing the image analysis into distinct steps: first identifying blood vessels through contrast enhancement, then separately identifying abnormal tissue through texture analysis and shape characterization. This allows both blood vessels and abnormal tissue to be clearly identified despite their similar gray-scale values, as each is analyzed using specialized criteria appropriate to its characteristics.
Solution Approach 2:
The patent applies local quality by using different analysis methods for different regions and structures. Blood vessels are identified using contrast medium enhancement and tubular shape analysis, while abnormal tissue is identified using texture analysis and irregular shape characterization. Each structure is evaluated with locally optimized criteria that exploit its specific properties rather than using a uniform approach.
2Ease of manufacture
If gray-scale values are used to identify structures in the image, then simple thresholding can be applied, but abnormal tissue near blood vessels cannot be distinguished due to similar attenuation values
Solution Approach 1:
The patent transitions from one-dimensional gray-scale analysis to multi-dimensional analysis by incorporating texture features, shape characteristics, and spatial relationships. Instead of relying solely on intensity values, the system evaluates multiple attributes simultaneously, adding dimensions of analysis that enable differentiation of tissues with similar attenuation values while maintaining computational feasibility.
Solution Approach 2:
The patent changes the parameters used for tissue identification from simple gray-scale thresholds to multiple parameters including texture metrics, shape descriptors, and spatial distribution characteristics. By evaluating tissue regions based on this expanded parameter set rather than single intensity values, the system achieves precise differentiation of abnormal tissue from blood vessels even when their attenuation values are similar.
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
This approach enables the clear identification of abnormal tissue near blood vessels, simplifying the analysis by distinguishing blood vessels from abnormal tissue based on diameter differences and contrast values, thereby enhancing the visibility of abnormal tissue in computed tomography images.
Implementation Method 1
computer tomographs have gained increasingly in importance in recent years. In computed tomography, x-ray radiation is irradiated from a radiation source towards an object to be examined
Implementation Method 2
on the basis of the attenuation of the X-ray radiation after this has passed through the object to be examined, an image is produced on a monitor
Data Source
AI summary
An imaging method for identifying abnormal tissue in the lung is provided, comprising the recording of slice images of the lung by means of X-ray radiation, recording of blood vessels, differentiation of blood vessels and abnormal tissue, segmentation of the abnormal tissue and display of the segmented abnormal tissue on an output device. In addition, a computer tomograph for identifying abnormal tissue in the lung is provided, having a radiation source for recording slice images of the lung and blood vessels by means of X-ray radiation, a computer unit for differentiating the blood vessels from the abnormal tissue and for segmenting the abnormal tissue, as well as an output device for displaying the segmented abnormal tissue. Furthermore, a computer program is provided for controlling a computer tomograph for an identification of abnormal tissue in the lung by means of a radiation source, designed to record slice images of the lung and blood vessels by means of X-ray radiation, to differentiate the blood vessels from abnormal tissue, to segment the abnormal tissue and to control an output device for displaying the abnormal tissue.