Binary Tracking of Anatomical Structures in Radiotherapy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current tracking solutions for anatomical structures in medical images, such as lung tumors during radiotherapy, face challenges with occlusions and modality differences between planning CT and real-time x-ray images, leading to unreliable tracking results.
Innovation Solution
A computer-implemented method that binarizes reference and planning images, generates a template for tracking structures, and adjusts the radiation treatment beam position based on the determined position of the tracking structure in real-time x-ray images, using image fusion and template matching to account for breathing motion and occlusions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If Template Matching is used on gray-scale images with rectangular templates, then the tracking structure can be located in the search image, but the tracking reliability deteriorates when the tracking structure is occluded or when the motion state differs from the reference image
Solution Approach 1:
The patent segments the template into multiple regions: a core region containing only the tracking structure and peripheral regions containing occluding structures. By assigning different weights to these regions (higher weight to core, lower weight to periphery), the method isolates the tracking structure from occlusions while maintaining the ability to locate it in the search image.
Solution Approach 2:
The patent applies local quality by creating a spatially varying weight distribution within the template, where the core region (tracking structure) has high weight and peripheral regions (occluding structures) have low weight. This local differentiation allows the template to be more sensitive to the tracking structure while being less sensitive to occluding structures that move differently.
2Ease of operation
If DRR tracking is used with planning CT as template, then the tracking can be performed on x-ray images, but the tracking accuracy deteriorates due to modality differences and outdated planning data
Solution Approach 1:
The patent transforms the template from a DRR-based approach (which suffers from modality differences and outdated data) to a binary image-based approach. By converting both the reference image and template to binary format and creating the template from actual reference image data, the method adapts to real-time imaging conditions and maintains high accuracy despite breathing motion and occlusions.
Data Source
AI summary
Disclosed is a computer-implemented method for determining a position of an anatomical tracking structure in a tracking image usable for controlling a radiation treatment such as at least one of radiotherapy or radio surgery of a patient, a corresponding computer program, a non-transitory program storage medium storing such a program and a computer for executing the program, as well as a system for the position of an anatomical tracking structure in a tracking image usable for controlling a radiation treatment such as at least one of radiotherapy or radio surgery of a patient, a system comprising an electronic data storage device and the aforementioned computer.