Adaptive Correlation Filtering for Real-Time Tumor Tracking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing radiotherapy treatments face challenges in accurately delivering radiation to the real-time location of a tumor due to variations in patient positioning and tumor movement during treatment sessions.
Innovation Solution
The use of an adaptive correlation filter (ACF) to process imaging data, such as PET and CT images, to determine a target anchor location and calculate radiation fluence, allowing for real-time adjustment and delivery of radiation to the tumor, with the option to update the filter using additional imaging data for improved accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If traditional fixed radiation delivery methods are used, then treatment planning is simpler, but radiation delivery precision deteriorates due to patient positioning variations and tumor movement
Solution Approach 1:
The system dynamically updates the adaptive correlation filter during treatment based on real-time imaging data, allowing the radiation delivery system to adapt to tumor movement and positioning variations. The filter parameters are adjusted iteratively to track the tumor's actual location, transforming a static delivery system into a dynamic one that responds to changing conditions.
Solution Approach 2:
The system implements a feedback loop where imaging data is continuously acquired during treatment, the adaptive correlation filter processes this data to determine tumor location, and the radiation delivery is adjusted based on this information. This closed-loop feedback mechanism enables real-time correction of positioning errors and maintains high delivery precision.
2Measurement precision
If real-time imaging data processing is implemented, then tumor location accuracy improves, but processing time and computational load increase
Solution Approach 1:
The adaptive correlation filter is pre-configured with expected tumor characteristics and parameters before treatment begins. This preliminary setup allows the filter to be ready for immediate processing of real-time imaging data without requiring extensive initialization during treatment, reducing processing delays.
Solution Approach 2:
The filter parameters are dynamically adjusted during treatment based on incoming imaging data, allowing the system to maintain high accuracy while adapting to changing tumor positions and characteristics. This dynamic adaptation enables efficient processing by focusing computational resources on relevant updates rather than complete reprocessing.
3Manufacturing precision
If adaptive filtering with continuous updates is used, then radiation delivery accuracy improves, but system complexity and data processing requirements increase
Solution Approach 1:
The adaptive correlation filter serves multiple functions: it tracks tumor position, determines localization accuracy, and guides radiation delivery adjustments. This multi-functionality reduces the need for separate systems for each task, managing complexity while maintaining high delivery accuracy through a unified processing framework.
Solution Approach 2:
Continuous feedback from imaging data enables the system to maintain accuracy without requiring overly complex predetermined protocols. The feedback loop allows the system to respond adaptively to actual conditions, simplifying the overall control structure compared to systems that require complex pre-programming for all possible scenarios.
Data Source
AI summary
Disclosed herein are systems and methods of applying a tracking filter, such as an adaptive correlation filter (ACF), to imaging data acquired during a radiotherapy session and using the filtered image to guide the delivery of radiation. The filtered image may provide information about the real-time location of the target anchor and the radiotherapy system may then calculate a radiation fluence using the target anchor location information. The methods described herein may be used with image-guided radiotherapy (such as IMRT/SBRT/SRS), as well as biology-guided radiotherapy (BgRT), which is a type of radiotherapy that converts biologically-related imaging data acquired on the day of treatment into radiation fluences for delivery.