MR Linac Tumor Gating With Real-Time Slice Registration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing radiation therapy treatment plans are challenged by changes in the position of target tumors during delivery, leading to misalignment and potential damage to surrounding healthy tissues due to the time-consuming and offline nature of current imaging and planning methods.
Innovation Solution
An adaptive image-guided therapy delivery system that utilizes real-time imaging and machine learning to rapidly acquire and register imaging slices, allowing for contemporaneous adjustments to the therapy protocol to align with the actual tumor position, incorporating deformable vector fields and machine learning models to determine and compensate for tumor movement.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If offline treatment planning and imaging methods are used, then treatment plan creation can be completed with sufficient detail, but the position of the target tumor changes during delivery leading to misalignment
Solution Approach 1:
The system transitions from static offline treatment planning to dynamic real-time adaptive planning. The treatment plan is continuously updated during radiation delivery based on real-time tumor position feedback from imaging, allowing the plan to adapt dynamically as the tumor moves throughout the treatment session.
Solution Approach 2:
The system performs preliminary imaging and treatment planning before radiation delivery, then uses this information to guide real-time adjustments. The offline plan serves as a preliminary framework that is subsequently refined based on actual tumor position observations during treatment.
2Measurement precision
If real-time imaging and adaptive planning are implemented, then tumor position accuracy is improved, but the complexity of the treatment delivery system increases
Solution Approach 1:
The system merges multiple functions into an integrated adaptive treatment delivery system. Imaging acquisition, real-time image processing, tumor position tracking, and treatment plan modification are combined into a unified system that operates seamlessly during radiation delivery, reducing the need for separate independent systems.
Solution Approach 2:
The system introduces an intermediary adaptive planning layer between the original treatment plan and actual beam delivery. This intermediary component processes real-time imaging data, calculates tumor position deviations, and generates corrected beam parameters, acting as a mediator that translates observed tumor position into appropriate treatment adjustments.
3Ease of operation
If traditional offline treatment planning is used, then the treatment process is simpler to execute, but surrounding healthy tissues may be damaged due to tumor movement
Solution Approach 1:
The system implements feedback control by continuously monitoring tumor position through real-time imaging and using this information to adjust treatment parameters. The feedback loop compares actual tumor position against the planned position and automatically modifies beam targeting to compensate for deviations, preventing healthy tissue damage while maintaining treatment simplicity.
Data Source
Figure 1A
Figure 1B
Figure 2
AI summary
Systems and methods are provided for registering images. The systems and methods perform operations comprising: receiving, at a first time point in a given radiation session, a first imaging slice corresponding to a first plane; encoding the first imaging slice to a lower dimensional representation; applying a trained machine learning model to the encoded first imaging slice to estimate an encoded version of a second imaging slice corresponding to a second plane at the first time point to provide a pair of imaging slices for the first time point; simultaneously spatially registering the pair of imaging slices to a volumetric image, received prior to the given radiation session, comprising a time-varying object to calculate displacement of the object; and generating an updated therapy protocol to control delivery of a therapy beam based on the calculated displacement of the object.