Intraluminal Image Processing for Abnormal Portion Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current image processing technologies for intraluminal images struggle to accurately detect abnormal portions such as lesions or bleeding sites without incorrectly identifying groove positions or contour portions as abnormalities, due to the inclusion of edges and bending boundaries within the closed regions.
Innovation Solution
An image processing apparatus that calculates gradient strength, extracts closed regions based on predetermined curvature and gradient strength conditions, and detects abnormal portions within these regions using energy calculations and weighted sums to transform and refine the initial closed regions, thereby excluding edges and bending contours.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If closed regions are extracted without considering curvature conditions, then the extraction process is simpler and faster, but edges and bending contours are incorrectly included as abnormal portions
Solution Approach 1:
The patent applies parameter changes by introducing curvature as a new parameter to characterize boundary regions. The curvature calculation unit computes curvature values for each boundary segment, and the extraction unit uses these values to identify and exclude high-curvature regions (edges and bending contours) from closed regions. This parameter-based approach enables precise differentiation between normal tissue boundaries and abnormal portions without overly complicating the overall extraction process.
2Measurement precision
If gradient strength thresholding is applied to exclude edges, then detection precision improves, but the processing time and computational load increase
Solution Approach 1:
The patent implements preliminary action by pre-calculating gradient strength for all pixels in the intraluminal image before performing closed region extraction. The gradient calculation unit computes gradient magnitude and direction for each pixel, storing these values for subsequent use. This preliminary computation allows the extraction unit to quickly identify and exclude edge regions using the pre-computed gradient information, avoiding repeated calculations during the region extraction and abnormal portion detection phases, thus reducing overall processing time.
Data Source
AI summary
An apparatus includes a calculating unit that calculates gradient strength of respective pixel values based on an intraluminal image, an extracting unit that extracts a closed region from the image, and a detecting unit that detects an abnormal portion of the closed region. The closed region satisfies conditions that the pixel of which gradient strength is a predetermined value or more is not included in the closed region and a boundary of the closed region does not bend with predetermined curvature or higher toward an inner side of the closed region. The extracting unit includes a setting unit that sets an initial closed region based on the gradient strength, an energy calculating unit that calculates values of types of energies based on an outer shape of the closed region and the gradient strength, and an energy weighted-sum calculating unit that calculates a weighted sum of the types of energy.