Automated Shutter Edge Detection in X-Ray Imaging
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In medical x-ray examinations, the presence of shutter edges, which are opaque materials used to shield body parts from radiation, creates bright regions in images that are diagnostically useless and can distract radiologists, impairing diagnosis due to glare and dominating the intensity histogram.
Innovation Solution
A method and system for detecting and removing unwanted information in medical images by processing edge information, generating candidate edges, evaluating them using a predetermined rule set, and removing unwanted information based on their location, utilizing techniques like down-sampling, gradient operators, and Canny edge detection to identify and eliminate shutter areas.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If shutters are used to shield body parts from radiation, then radiation protection is improved, but image quality deteriorates due to bright regions and glare that distract radiologists
Solution Approach 1:
The patent extracts and removes the shutter regions from the medical image through automated detection and removal processes. The system identifies shutter edges and extracts the unwanted bright regions, leaving only the diagnostically useful portions of the image, thereby eliminating the distracting glare while preserving the protective function of shutters during image acquisition
2Area of stationary object
If shutter areas are included in the image, then complete coverage is achieved, but diagnostic usefulness deteriorates due to domination of intensity histogram by non-informative bright regions
Solution Approach 1:
The system extracts only the diagnostically useful regions from the image by detecting shutter edges and removing the associated bright regions. This extraction process eliminates the non-informative areas that dominate the intensity histogram while preserving the complete diagnostic information from the uncovered body parts
Solution Approach 2:
The patent applies different processing qualities to different regions of the image: shutter regions are completely removed or suppressed, while non-shutter regions are preserved with their original diagnostic quality. This local differentiation ensures that diagnostic areas maintain their information content while shutter areas contribute no harmful glare
Data Source
AI summary
A method for removing shutter areas in an image, in particular an x-ray image is provided. Edges are examined in a multi-resolution image pyramid and evaluated to determine potential shutter blade candidates defining the shutter areas. Heuristic rules and/or an automatic classifier such as a Neuronal Network, are applied to distinguish true shutter blades from false positives. The rule set and the classifier are based on a set of features extracted from the potential shutter blade candidates as well as predetermined knowledge of the expected placement of the shutter, human anatomy. Up to four shutter blades are expected to be detected and based on these blades, the bright areas in the image that occur due to the shutters are removed.