MRI-Guided Radiotherapy Marker Detection via Signal Void Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current radiation therapy treatment planning systems for organs like the prostate require improved image processing, especially in MRI-only or MRI-assisted treatments, as they struggle with accurate delineation and dynamic shape tracking of markers within magnetic resonance images, which are challenging due to varying contrasts and deformations.
Innovation Solution
A magnetic resonance imaging (MRI) guided radiation therapy apparatus that acquires and processes 3D and 2D image data to identify signal voids, calculate their likelihood of being part of a predefined marker, and control irradiation based on updated marker shapes, potentially avoiding the need for additional CT image acquisitions and reconstructions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual delineation of marker shape is performed in MRI images, then radiation therapy planning can be conducted, but the process is time-consuming and prone to errors
Solution Approach 1:
The system enables automatic self-delineation of the marker by having the marker itself generate identifiable signal characteristics (signal voids or signal enhancements) that the processing system can automatically detect and track, eliminating the need for manual operator intervention in marker outlining while maintaining high precision
Solution Approach 2:
The manual mechanical process of operator delineation is replaced by an automated image processing system that uses signal processing algorithms to automatically identify and track marker boundaries based on characteristic MRI signal patterns, significantly reducing time while maintaining or improving accuracy
2Measurement precision
If additional CT image acquisitions are performed for radiotherapy planning, then accurate density information is obtained, but the complexity and resource requirements increase
Solution Approach 1:
The MRI system is made multi-functional by enabling it to provide both anatomical imaging and density information previously requiring separate CT scans. The processing system extracts density-related information from MRI signal characteristics, allowing a single imaging modality to fulfill multiple planning requirements
Solution Approach 2:
The patent combines the functions of anatomical imaging and density measurement into a single MRI-based workflow. By merging these previously separate functions into one imaging modality and processing pipeline, the system reduces overall complexity while maintaining the necessary information quality for radiotherapy planning
3Device complexity
If marker shape is assumed static in treatment planning, then planning is simplified, but accuracy decreases when marker deforms during treatment
Solution Approach 1:
The system transitions from static to dynamic marker tracking by continuously monitoring the marker's signal characteristics across multiple imaging time points. The processing system adapts to marker shape changes by recalculating marker boundaries based on updated signal patterns, ensuring accurate positioning even when the marker deforms during treatment
Solution Approach 2:
The system implements feedback by using detected marker signal characteristics to continuously update and refine the treatment plan. When marker position or shape changes are detected through signal void or enhancement patterns, the system provides feedback to adjust radiation delivery parameters, maintaining accuracy throughout the treatment process
Data Source
AI summary
The present disclosure relates to a method for controlling a magnetic resonance imaging guided radiation therapy apparatus (100) comprising a magnetic resonance imaging system (106). The method comprises: acquiring magnetic resonance data using the magnetic resonance imaging system from an organ (146), the organ being marked by a predefined marker; the magnetic resonance data comprising 3D image data; identifying in a reconstructed 2D image of the magnetic resonance data at least one signal void candidate of the marker; processing the 3D image data and the identified signal void for calculating a likelihood that the identified signal void candidate is part of the marker; outputting an indication of the calculated likelihood; in response to the outputting, receiving a user input specifying performing a radio therapy; and controlling the irradiation of the organ using the radiation therapy.