Automated 3D Image Distortion Correction Using Artificial Bone Landmarks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Comparing multiple in vivo images of subjects over time is challenging due to variations in pose and position, leading to distortions and orientation differences that hinder meaningful analysis and comparison, particularly in monitoring diseases like pulmonary diseases.
Innovation Solution
The automated generation of artificial landmarks along the bones in images allows for distortion correction and co-registration of images, using these landmarks to apply transformations that align and standardize image representations, facilitating comparison and analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multiple in vivo images are captured over time to monitor disease progression, then the ability to track changes improves, but variations in pose and position cause distortions and orientation differences that hinder meaningful comparison
Solution Approach 1:
The patent introduces artificial landmarks as intermediary reference points placed on bony structures that serve as mediators between multiple images. These landmarks provide stable, identifiable reference points that facilitate accurate alignment and comparison across images taken at different times, resolving the alignment precision problem while maintaining reliable disease monitoring
Solution Approach 2:
The patent creates a standardized reference copy of the anatomical structure by placing artificial landmarks according to a consistent protocol across multiple images. This copying approach ensures that the same reference framework is applied to each image, enabling precise comparison while accounting for pose and position variations
2Productivity
If automated image processing is used to identify regions of interest, then analysis efficiency improves, but extensive image segmentation is required which increases processing complexity
Solution Approach 1:
The patent performs preliminary action by placing artificial landmarks on bony structures before the actual disease monitoring analysis. These pre-placed landmarks serve as ready-made reference points that simplify subsequent image registration and region identification, reducing the complexity of extensive segmentation while maintaining high analysis efficiency
Solution Approach 2:
The patent extracts the bony structures with artificial landmarks as a separate reference framework from the full complex image data. By isolating these stable anatomical features, the system reduces processing complexity for the remaining soft tissue analysis while maintaining productivity through automated landmark-based registration
Data Source
AI summary
Presented herein are systems and methods for registering one or more images of one or more subjects based on the automated generation of artificial landmarks. An artificial landmark is a point within an image that is associated with a specific physical location of the imaged region. The artificial landmarks are generated in an automated and robust fashion along the bones of a subject's skeleton that are represented in the image (e.g. graphically). The automatically generated artificial landmarks are used to correct distortion in a single image or to correct distortion in and/or co-register multiple images of a series of images (e.g. recorded at different time points). The artificial landmark generation approach described herein thereby facilitates analysis of images used, for example, for monitoring the progression of diseases such as pulmonary diseases.