MR Motion Detection for Image-Guided Thermal Therapy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Image-guided thermal therapy is challenged by patient movement, which can lead to inaccurate temperature monitoring and potential damage to healthy anatomical features due to shifts in measured temperatures, as MRI thermometry is sensitive to small movements.
Innovation Solution
A computer system using trained machine-learning models to analyze MR images before and during therapy, determining the shape and position of thermal therapy applicators and anatomical features, and detecting movements exceeding a threshold to prevent damage by adjusting therapy delivery.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If MRI thermometry is used to monitor temperature during thermal therapy, then temperature monitoring capability is improved, but sensitivity to patient movement causes measurement accuracy to deteriorate
Solution Approach 1:
The patent introduces an intermediary object (the marker) that is insensitive to patient movement. This marker serves as a mediator between the imaging system and the thermal therapy monitoring system, providing stable reference points that are not affected by physiological movements, thereby resolving the contradiction between temperature monitoring accuracy and measurement reliability under movement
Solution Approach 2:
The patent creates a virtual copy of the physical space by placing markers at known positions within the target volume. These markers generate corresponding signals in the imaging data that serve as digital replicas or copies of physical reference points, enabling accurate tracking and motion compensation without being affected by patient movement
2Difficulty of detecting and measuring
If small patient movements are detected using traditional methods, then motion detection capability is improved, but detection accuracy deteriorates due to difficulty in detecting small movements
Solution Approach 1:
The patent uses markers as intermediary objects that amplify the detectability of small movements. Instead of directly detecting subtle anatomical displacements, the system tracks the positions of high-contrast markers that serve as mediators, making small movements much easier to detect and measure with high precision
Solution Approach 2:
The patent employs markers with distinct signal characteristics (analogous to color changes in visual detection) that create high-contrast features in the imaging data. These markers appear as bright or distinct signals against the background tissue, enabling easy and accurate detection of their positions even when movements are very small
3Object-affected harmful factors
If temperature safety limits are enforced during thermal therapy, then patient safety is improved, but treatment effectiveness deteriorates due to premature procedure termination
Solution Approach 1:
The patent implements a feedback mechanism where marker positions are continuously monitored and used to detect patient movement. This feedback loop allows the system to distinguish between temperature changes caused by therapy and those caused by movement, enabling accurate temperature monitoring without premature termination and maintaining both safety and treatment effectiveness
Solution Approach 2:
The patent replaces the mechanical/physical assumption that temperature changes always indicate therapeutic heating with a signal processing approach. By substituting direct temperature interpretation with marker-based motion detection and compensation, the system can accurately distinguish between therapeutic heating and movement artifacts, preventing premature termination
Data Source
AI summary
A reference shape of each target object is determined from one or more of reference MR images using one or more trained machine-learning (ML) models, each reference MR image captured at a respective spatial location in the target volume. A subsequent shape of each target object is determined from one or more of subsequent MR images using the trained ML model(s), each reference MR image captured at the same respective spatial location in the target volume as a corresponding reference MR image. A respective movement of each target object is calculated based, at least in part, on a comparison of each subsequent shape for each target object to a corresponding reference shape for a corresponding target object at the same respective spatial location in the target volume. When the respective movement is greater than a predetermined threshold, a movement notification is produced.