ROI-Masked Image Registration for Moving Organ Interference
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Image registration in radiation therapy is challenged by interference features such as moving organs or tissues, which affect registration accuracy and subsequent treatment and clinical diagnosis.
Innovation Solution
A system and method for image registration that involves determining a registration mask associated with a region of interest (ROI) by removing or excluding interference structures, using an auxiliary mask to enhance registration accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If image registration is performed on the entire reference image and target image including all anatomical structures, then the registration process covers the complete field of view, but moving organs or tissues interfere with the registration accuracy of the target volume
Solution Approach 1:
The patent applies segmentation by dividing the image registration process into two distinct parts: a registration mask that identifies the target volume region, and the actual registration computation. The mask is generated by processing the reference image to isolate the target volume and exclude moving organs or tissues. This segmentation allows the registration to focus only on relevant anatomical structures, preventing interference from moving structures while maintaining complete field of view coverage.
Solution Approach 2:
The patent extracts the target volume information from the complete reference image by generating a registration mask that contains only the relevant anatomical structures. This extraction process removes interfering moving organs or tissues from the registration calculation while preserving the complete field of view in the original images for display and review purposes.
2Measurement precision
If a registration mask is generated to exclude moving organs or tissues, then registration accuracy is improved, but additional image processing steps are required
Solution Approach 1:
The patent applies preliminary action by generating the registration mask before performing the actual image registration. The mask creation process includes loading the reference image, segmenting the target volume, and excluding moving structures in advance. This preliminary processing prepares the data in an optimized state, allowing the subsequent registration step to proceed efficiently with pre-filtered information, reducing the complexity of the main registration algorithm.
Data Source
AI summary
Systems and methods for image registration are provided. The method may include obtaining a reference image of an object (510); the object includes a target volume; determining a registration mask associated with a region of interest (ROI) based on the reference image (520), the ROI includes at least a portion of the target volume; obtaining a target image of the object (530); and performing an image registration on the reference image and the target image based on the registration mask (540).