Motion Blur Probability Map for Diagnostic Images
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Diagnostic imaging faces challenges in detecting and reporting anatomical motion blur caused by patient movement and internal anatomy motion, which differs significantly from photographic imaging and existing blur compensation methods that can alter image contents or introduce artifacts.
Innovation Solution
A method for detecting motion blur in diagnostic images involves obtaining image data, identifying regions of interest, calculating motion-sensitive features, and reporting the probability of blur within these regions, using edge images and statistical measures to assess and correct for motion blur.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If conventional blur compensation methods (e.g., de-blur kernels) are applied to diagnostic images, then image sharpness is improved, but image contents are altered and artifacts are introduced
Solution Approach 1:
The patent creates a probability map that copies the structural information of motion blur detection without altering the original diagnostic image. The probability map indicates regions likely to contain motion blur through statistical features (edge density, gradient orientation) while preserving the original image contents intact, avoiding the artifact introduction problem of conventional de-blur methods
2Reliability
If motion blur detection is performed on entire anatomical regions, then detection coverage is improved, but diagnostic precision is reduced due to inability to identify specific blur locations
Solution Approach 1:
The patent segments the diagnostic image into multiple regions of interest (ROIs) based on anatomical structures and motion blur probability. Each ROI is independently analyzed using motion-sensitive features, allowing precise identification of specific blur locations while maintaining comprehensive coverage. The segmentation enables both high detection coverage and precise localization by processing manageable image portions separately
3Measurement precision
If statistical features are calculated for motion blur detection, then detection accuracy is improved, but processing time is increased
Solution Approach 1:
The patent applies partial action by calculating motion-sensitive statistical features (edge density, gradient orientation) only in regions where motion blur is suspected based on preliminary analysis. Rather than processing the entire image uniformly, the system identifies high-probability regions first and applies detailed statistical analysis only there, reducing overall processing time while maintaining high detection accuracy in critical areas
Data Source
AI summary
A method for detecting one or more motion effects in a diagnostic image obtains image data for the diagnostic image and identifies at least one region of interest in the diagnostic image. The probability of motion blur within the at least one region of interest is calculated according to a motion-sensitive feature of the at least one region of interest. The calculated probability for motion blur within the at least one region of interest is reported.