Radiotherapy Trajectory Optimization via BEV Mesh Connectivity

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current trajectory optimization methods in radiotherapy fail to preserve the geometrical relationship of adjacent apertures, leading to suboptimal radiation delivery and increased MLC contention issues, which degrades the quality of radiation beam trajectories.

Innovation Solution

The TORUS approach maps the connectedness of target regions from the Beam's Eye View (BEV) throughout the delivery coordinate space, using a modified Dijkstra path optimization method to select beam trajectories that maximize angular spread and minimize trajectory interference, thereby improving the synchronization of dynamic delivery in radiotherapy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If current trajectory optimization methods are used, then computational simplicity is maintained, but geometrical relationship of adjacent apertures is not preserved leading to suboptimal radiation delivery

Engineering Contradiction:
Improvetrajectory optimization qualityVSAvoidoptimization method complexity
Core Design Contradiction:
Manufacturing precisionVSDevice complexity

Solution Approach 1:

The patent segments the delivery coordinate space into discrete vertices and edges, creating a mesh representation that preserves geometrical relationships of adjacent apertures. This segmentation allows the optimization method to maintain spatial connectivity information while managing computational complexity through structured discretization.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces a new dimension by representing the delivery coordinate space as a mesh with vertices connected by edges, adding topological structure to the optimization problem. This dimensional transformation enables preservation of geometrical relationships while maintaining computational tractability through graph-based representation.

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

2Manufacturing precision

If dynamic delivery capabilities are increased, then dose gradient formation is improved, but MLC contention issues increase degrading trajectory quality

Engineering Contradiction:
Improvedose gradient formationVSAvoidtrajectory delivery reliability
Core Design Contradiction:
Manufacturing precisionVSReliability

Solution Approach 1:

The patent incorporates feedback by evaluating trajectory quality metrics including MLC contention detection during the optimization process. The mesh-based representation provides feedback on geometrical relationships, allowing the system to adjust trajectories to reduce MLC contention while maintaining dose gradient formation quality.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The patent employs dynamic optimization by allowing trajectory parameters to be adjusted iteratively based on evaluated performance metrics. The mesh structure enables dynamic evaluation of adjacent aperture relationships, allowing real-time adjustments to reduce MLC contention while preserving dose distribution quality.

Inventive Principle:
Principle #15Dynamics

3Manufacturing precision

If beam angle optimization is performed, then plan quality is improved, but treatment delivery time increases

Engineering Contradiction:
Improveplan qualityVSAvoidtreatment delivery time
Core Design Contradiction:
Manufacturing precisionVSLoss of time

Solution Approach 1:

The patent performs preliminary optimization by pre-calculating and storing the mesh representation of the delivery coordinate space with vertices and edges. This preliminary structuring of spatial relationships enables faster subsequent trajectory optimizations, reducing treatment delivery time while maintaining plan quality through pre-established geometrical awareness.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS10792513B2Trajectory optimization in radiotherapy using sectioning
Publication Date: 2020.10.06 THE BOARD OF TRUSTEES OF THE LELAND STANFORD JUNIOR UNIV
  • US10792513B2 patent drawing
  • US10792513B2 patent drawing
  • US10792513B2 patent drawing

AI summary

A radiation therapy treatment method includes providing a patient model, dosimetric constraints, delivery motion constraints, and delivery coordinate space of a radiation delivery device, where the delivery coordinate space is represented as a mesh with vertices connected by edges, where the vertices correspond to directions of a beam eye view (BEV) of the radiation delivery device. BEV region connectivity manifolds are constructed from the patient model, the dosimetric constraints, the delivery coordinate space, and existing beam trajectories, wherein each of the BEV region connectivity manifolds represents connections between contiguous 2D target regions. Beam trajectories are selected based on region connectedness information in the BEV region connectivity manifolds, the dosimetric constraints, the delivery motion constraints, and the existing beam trajectories. Radiation is delivered using the radiation delivery device in accordance with the selected beam trajectories.