Cyclic Motion Prediction for Latency-Compensated Radiation Therapy

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing radiation therapy systems struggle to accurately predict and compensate for quasiperiodic motion, such as respiratory motion, which affects the alignment of the therapy beam with the target locus, leading to potential damage to healthy tissues due to latency in image acquisition and processing.

Innovation Solution

A computer-implemented method that uses a cyclic motion model to predict future positions of anatomical structures based on historical physiologic signal data, updating the control protocol of medical devices to adaptively adjust the therapy delivery in real-time, including adjustments to the position of the patient, collimators, and therapy beam direction.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If real-time image guidance is used to track moving targets, then treatment accuracy is improved, but system complexity and computational requirements increase

Engineering Contradiction:

Improvetarget tracking accuracyVSAvoidsystem complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The system performs preliminary actions by pre-calculating motion vectors and predicting future target positions before treatment delivery. The therapy controller computes motion compensation parameters in advance based on measured motion, allowing the therapy beam to be proactively adjusted to anticipated target positions rather than reactively correcting after motion occurs.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system implements dynamic adaptation by continuously updating motion models and prediction parameters during treatment. The therapy controller dynamically adjusts the therapy beam parameters in real-time based on measured motion and predicted target positions, allowing the system to adapt to changing motion patterns while maintaining treatment accuracy.

Inventive Principle:

Principle #15Dynamics

2Measurement precision

If motion compensation is applied during therapy delivery, then treatment accuracy is improved, but computation time and processing delay increase

Engineering Contradiction:

Improvetherapy delivery accuracyVSAvoidcomputation delay

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system rushes through the computation process by using simplified predictive models and pre-computed motion parameters. Instead of performing complex real-time calculations for every motion update, the system uses efficient prediction algorithms that quickly estimate target positions based on measured motion trends, reducing computation time while maintaining adequate accuracy.

Inventive Principle:

Principle #21Skipping (Rushing through)

3Measurement precision

If continuous motion measurement is performed, then target tracking precision is improved, but data processing load and system resource consumption increase

Engineering Contradiction:

Improvemotion tracking precisionVSAvoidcomputational resource consumption

Core Design Contradiction:

Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The system applies partial action by selectively processing motion data at optimized intervals rather than continuously analyzing every motion parameter. The therapy controller processes essential motion parameters at reduced frequency while maintaining adequate tracking precision, avoiding the excessive computational burden of analyzing all motion data at maximum resolution.

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentEP4257049B1Motion prediction based on cyclic motion model

Publication Date: 2026.04.29 ELEKTA AB

Figure 1A
Figure 1B
Figure 1C

AI summary

An image-guided therapy delivery system includes a therapy generator configured to generate a therapy beam directed to a time-varying therapy locus within a therapy recipient, an imaging input configured to receive imaging information about a time-varying target locus within the therapy recipient, and a therapy controller. The therapy generator includes a therapy output configured to direct the therapy beam according to a therapy protocol. The therapy controller is configured to automatically generate a predicted target locus using information indicative of an earlier target locus extracted from the imaging information, a cyclic motion model, and a specified latency, and automatically generate an updated therapy protocol to align the time-varying therapy locus with the predicted target locus.