Exploration of pareto-optimal radiotherapy plans

A non-transitory computer-readable storage medium comprising computer-readable instructions for radiotherapy treatment planning, wherein the instructions, when executed with a computing machine, cause the computing machine to:

• obtain a plurality of solutions, defined in a manifold space, of a radiotherapy problem for providing radiotherapy treatment, wherein the radiotherapy problem is a multicriteria optimization problem, and wherein each of the plurality of solutions has a plurality of weights used to adjust a plurality of criteria for the multicriteria optimization problem;
• explore the plurality of solutions for the multicriteria optimization problem to identify an additional solution in a submanifold space, the exploring comprising:
• establishing the submanifold space from the manifold space, the submanifold space representing the plurality of solutions in fewer dimensions than the plurality of weights;
• producing additional sets of weights in the submanifold space based on derivatives of first-order optimality conditions of the radiotherapy problem, the derivatives determined with respect to the plurality of weights;
• and
• performing navigation in the submanifold space to arrive at the additional solution, the additional solution corresponding to one of the additional sets of weights;
• and
• generate treatment plan parameters based on the additional solution, wherein the treatment plan parameters are used in a treatment plan for delivery of the radiotherapy treatment via a radiotherapy machine.

A computing system configured for radiotherapy treatment planning, the computing system comprising:

• one or more memory devices to store data of a radiotherapy problem for providing radiotherapy treatment to a human subject from a radiotherapy treatment machine;
• and
• one or more processors configured to perform operations to:
• obtain a plurality of solutions to the radiotherapy problem, defined in a manifold space, wherein the radiotherapy problem is a multicriteria optimization problem, and wherein each of the plurality of solutions has a plurality of weights used to adjust a plurality of criteria for the multicriteria optimization problem;
• explore the plurality of solutions for the multicriteria optimization problem to identify an additional solution in a submanifold space, with operations to:
• establish the submanifold space from the manifold space, the submanifold space representing the plurality of solutions in fewer dimensions than the plurality of weights;
• produce additional sets of weights in the submanifold space based on derivatives of first-order optimality conditions of the radiotherapy problem, the derivatives determined with respect to the plurality of weights;
• and
• perform navigation in the submanifold space to arrive at the additional solution, the additional solution corresponding to one of the additional sets of weights;
• and
• generate treatment plan parameters based on the additional solution, wherein the treatment plan parameters are used in a treatment plan for delivery of the radiotherapy treatment via a radiotherapy machine.