3D Tumor Localization Using Adaptive MRI Slice Tracking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing radiation therapy techniques face challenges in accurately tracking and localizing tumors in three-dimensional space due to organ and tumor motion, particularly during radiotherapy, which complicates the creation of treatment plans and increases exposure to additional radiation through CT imaging.
Innovation Solution
A method and system using MRI-guided adaptive filter models to generate three-dimensional localization of tumors by processing 2D medical images, converting them into adaptive filters, and tracking tumor movement in real-time, thereby enhancing the accuracy of radiation therapy planning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If CT imaging is used for treatment planning, then accurate representation of patient geometry and electron densities is achieved, but patient is exposed to additional radiation dosage
Solution Approach 1:
The patent uses MRI imaging as an intermediary to obtain soft tissue contrast information without ionizing radiation, then integrates this with CT data or uses adaptive filter models to compensate for the lack of electron density information, thereby avoiding additional radiation exposure while maintaining planning accuracy
Solution Approach 2:
The patent replaces CT-based geometric representation with MRI-based soft tissue contrast representation, using magnetic resonance principles instead of ionizing radiation to achieve detailed anatomical visualization for treatment planning
2Object-affected harmful factors
If 2D MR slices are acquired at a particular location, then imaging is performed without ionizing radiation, but the tumor may not be included in the slice due to target organ or tumor motion
Solution Approach 1:
The patent transitions from static 2D slice acquisition to dynamic 3D volumetric imaging, using the temporal and spatial dimensions to track tumor motion and ensure the tumor remains within the imaging volume throughout the treatment process
Solution Approach 2:
The patent implements real-time or near-real-time image acquisition and processing to dynamically adapt to tumor motion, using adaptive filter models that can track and compensate for organ and tumor movement during the treatment session
3Reliability
If treatment planning is performed manually with trial-and-error optimization, then clinical acceptability is achieved, but the process is time-consuming and complex
Solution Approach 1:
The patent implements automated feedback loops where adaptive filter models continuously refine tumor localization and treatment plan optimization based on real-time imaging data, automatically adjusting parameters to meet clinical objectives without manual trial-and-error
Solution Approach 2:
The patent uses automated algorithms to dynamically adjust treatment planning parameters such as beam angles, intensities, and shapes based on real-time tumor position and motion patterns, optimizing the treatment plan automatically while maintaining clinical acceptability
Data Source
Figure 1
Figure 2
Figure 3
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 a target in a three-dimensional (3D) volume. For example, an image acquisition device may provide a 3D medical image containing a region of interest of the target. A processor may then extract a plurality of two-dimensional (2D) slices from the 3D image. The processor may also determine a 2D patch for each 2D slice, wherein the 2D patch corresponds to an area of the 2D slice associated with the target. The processor may also convert the 2D patch to an adaptive filter model for determining a location of the region of interest.