Adaptive Filter Model for 3D Tumor Tracking in Radiation Therapy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current radiation therapy techniques face challenges in accurately tracking and localizing moving tumors in three-dimensional space during treatment, particularly due to limitations in two-dimensional imaging and the complexity of sparing surrounding healthy tissues, which can lead to inefficiencies and increased radiation exposure.
Innovation Solution
A method and system utilizing adaptive filter models based on MRI images to track a moving three-dimensional target in real-time, by receiving and processing two-dimensional slices, applying offset values, and generating confidence scores to determine the target's location and predict its future position, enabling precise localization and tracking during radiation therapy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If 2D imaging is used to track tumors, then device complexity is reduced, but measurement precision of tumor location in 3D space deteriorates
Solution Approach 1:
The patent applies dimensionality change by using multiple 2D MRI slices acquired at different angles and positions to reconstruct and track 3D tumor location. The system acquires 2D slices in different orientations (axial, coronal, sagittal) and uses image registration algorithms to integrate this multi-planar information into accurate 3D tumor localization, thereby achieving 3D measurement precision through 2D imaging components.
Solution Approach 2:
The patent segments the 3D imaging problem into multiple 2D slice acquisitions. Instead of using a single complex 3D imaging system, the approach divides the volume into multiple 2D slices that are acquired separately and then computationally integrated. This segmentation allows the use of simpler 2D imaging components while achieving 3D tracking capability through image fusion and registration techniques.
2Object-affected harmful factors
If treatment planning complexity increases to spare more organs at risk, then radiation safety to healthy tissues improves, but treatment planning time deteriorates
Solution Approach 1:
The patent implements real-time feedback through continuous tumor tracking during radiation delivery. The system acquires 2D MRI slices during treatment, updates tumor location in real-time, and provides feedback to the treatment delivery system. This allows dynamic adjustment of beam positioning and intensity to maintain precise tumor targeting while minimizing exposure to moving organs at risk, thereby improving radiation safety without requiring excessively complex pre-planning.
Solution Approach 2:
The patent transitions from static treatment planning to dynamic adaptive radiation therapy. The system continuously updates tumor location and organ-at-risk positions during treatment delivery using real-time 2D MRI imaging. Treatment parameters such as beam position, intensity, and shape are dynamically adjusted based on current anatomical positions, allowing the plan to adapt to patient motion and anatomical changes without requiring complete re-planning.
3Manufacturing precision
If real-time tumor tracking is implemented, then radiation delivery precision improves, but system complexity and processing time deteriorate
Solution Approach 1:
The patent extracts only the essential information needed for tumor tracking from full 3D MRI volumes by using selective 2D slice acquisition. Instead of processing complete volumetric data in real-time, the system acquires and processes only specific 2D slices that contain the tumor, reducing computational complexity while maintaining tracking precision. This extraction approach focuses computational resources on relevant regions and moments.
Solution Approach 2:
The patent replaces complex mechanical 3D imaging systems with a computational approach using 2D MRI slice acquisition and digital image registration. Instead of using mechanically complex volumetric imaging hardware, the system uses software-based image fusion and registration algorithms to reconstruct 3D tumor position from 2D slices, substituting mechanical complexity with computational processing.
Data Source
AI summary
The present disclosure relates to systems, methods, and computer-readable storage media for segmenting medical image. Embodiments of the present disclosure may locate and track a moving, three-dimensional (3D) target in a patient undergoing image-guided radiation therapy. For example, an adaptive filter model for a region of interest in the patient may be received, wherein the adaptive filter model is based on the target to be tracked. An image acquisition device may obtain a two-dimensional (2D) slice of a region of interest in the patient. A processor may then apply the adaptive filter model to the 2D slice, wherein the adaptive filter model includes an offset value. The processor may also determine a location of the target in the 2D slice based on the adaptive filter model. The processor may also estimate a potential location of the target based on the offset value. The processor may then repeat one or more of the above steps to track the moving target during image-guided radiation therapy of the patient.