3D Tumor Localization Using Adaptive MRI Slice Tracking

Resolve Bottlenecks,
Find Innovative Solutions
Generate 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

VSEngineering 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

Engineering Contradiction:
Improvepatient geometry representationVSAvoidradiation dosage
Core Design Contradiction:
Measurement precisionVSObject-affected harmful factors

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

Inventive Principle:
Principle #24Intermediary (Mediator)

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

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

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

Engineering Contradiction:
Improveionizing radiation exposureVSAvoidtumor localization accuracy
Core Design Contradiction:
Object-affected harmful factorsVSMeasurement precision

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

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

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

Inventive Principle:
Principle #15Dynamics

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

Engineering Contradiction:
Improveclinical acceptabilityVSAvoidtreatment planning time
Core Design Contradiction:
ReliabilityVSLoss of time

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

Inventive Principle:
Principle #23Feedback

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

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentEP3251089B1Three dimensional localization of a moving target for adaptive radiation therapy
Publication Date: 2025.11.12 ELEKTA AB
  • EP3251089B1 patent drawingFigure 1
  • EP3251089B1 patent drawingFigure 2
  • EP3251089B1 patent drawingFigure 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.