IMRT Treatment Planning With Hybrid Quantum-Classical Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current computational methods for developing radiation treatment plans in External Beam Radiotherapy are time-consuming and resource-intensive, often resulting in only a low percentage of patients receiving high-quality plans due to the complexity of combinatorial optimization problems involving radiation intensity, beamlet angles, and 3-dimensional body tissue imaging.
Innovation Solution
A hybrid quantum-classical method is employed to solve optimization problems by iteratively processing data using classical search algorithms and quantum computing resources, reformulating optimization tasks into quadratic unconstrained binary optimization (QUBO) problems to efficiently search for optimal solutions, particularly for intensity-modulated radiation therapy (IMRT) treatment planning.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If classical computational methods are used to solve combinatorial optimization problems for radiation treatment planning, then solution quality can be achieved, but computation time and resource requirements increase significantly
Solution Approach 1:
The patent segments the complex combinatorial optimization problem into multiple smaller sub-problems that can be processed in parallel by quantum computing resources. The treatment planning problem is divided into discrete optimization tasks that can be solved independently and then combined, reducing overall computation time while maintaining solution quality.
Solution Approach 2:
The patent introduces quantum computing resources as an intermediary between the optimization problem definition and the solution generation. The quantum computer acts as a mediator that processes the segmented sub-problems using quantum algorithms, providing faster computation compared to classical methods while preserving the accuracy required for clinical decision-making.
2Measurement precision
If complex combinatorial optimization problems with many variables are solved using classical methods, then high quality treatment plans can be produced, but resource scarcity limits the percentage of patients receiving such plans
Solution Approach 1:
By segmenting the optimization problem into smaller sub-problems, the computational burden is reduced, allowing the system to process more patient cases simultaneously or in sequence. This segmentation enables the quantum computing resources to handle multiple optimization tasks that would be infeasible for classical systems, thereby increasing the number of patients who receive high-quality treatment plans.
Solution Approach 2:
The patent changes the computational parameters by transitioning from classical to quantum computing resources. This parameter change fundamentally alters the computational capacity and speed, enabling the system to process a larger volume of treatment planning cases with the same physical resources, thus improving productivity and access to quality care.
3Productivity
If iterative quantum-classical processing is used to solve optimization problems, then solution efficiency improves, but system complexity increases
Solution Approach 1:
The iterative quantum-classical processing system is segmented into distinct modules: a classical control system that prepares and processes data, and a quantum computing system that performs specific optimization calculations. This segmentation allows each component to be optimized independently and simplifies the overall system architecture by clearly defining interfaces and responsibilities between classical and quantum components.
Data Source
AI summary
Methods, systems, and apparatus for generating intensity modulated radiation therapy treatment plans. In one aspect, a method includes receiving data representing an optimization problem; iteratively processing, until termination criteria are met, the received data representing the optimization problem to obtain data representing a solution to the optimization problem, comprising, for each iteration: performing a classical search algorithm on an input for the iteration to determine a first solution; providing data representing the first solution to a quantum computing resource, wherein the data representing the first solution comprises a quadratic unconstrained binary optimization formulation of the optimization problem in a local region around the first solution; obtaining data representing a second solution from the quantum computing resource; and providing the data representing the second solution as input to a subsequent iteration; and initiating an action based on the data representing a solution to the optimization problem.