Continuum radiotherapy treatment planning
Systems and methods are disclosed for dynamic radiotherapy treatment planning in a continuous space of computation. Example operations for generating treatment plan data for a radiotherapy treatment include: obtaining data for a radiotherapy treatment of a human subject; generating a set of radiation controls from the data for the radiotherapy treatment, with at least one of the radiation controls being based on a mapping from a continuous (e.g., infinite dimensional) computational space; converting the generated set of radiation controls to a set of treatment delivery parameters, the set of treatment delivery parameters corresponding to capabilities of a radiotherapy treatment machine; and producing treatment plan data for the radiotherapy treatment based on the set of treatment delivery parameters.
1 . A computer-implemented method for radiotherapy treatment planning, the method comprising:
obtaining data for a radiotherapy treatment of a human subject;
generating a set of radiation controls from the data for the radiotherapy treatment, wherein at least one of the radiation controls is based on a mapping from a continuous computational space;
converting the generated set of radiation controls to a set of treatment delivery parameters, the set of treatment delivery parameters corresponding to capabilities of a radiotherapy treatment machine; and
producing treatment plan data for the radiotherapy treatment based on the set of treatment delivery parameters.
2 . The method of claim 1 , wherein generating the set of radiation controls comprises solving an optimization problem for the radiotherapy treatment.
3 . The method of claim 2 , wherein optimization variables of the optimization problem comprise a set of auxiliary variables related to at least one of the radiation controls, having a relation defined by a linear operator.
4 . The method of claim 2 , wherein an objective function of the optimization problem comprises a functional that maps the radiation controls, based on the continuous computational space, into a scalar value.
5 . The method of claim 1 , wherein generating the set of radiation controls comprises producing a simulation of a radiation dose distribution corresponding to a particular set of radiation controls.
6 . The method of claim 5 , wherein producing the simulation of the radiation dose distribution corresponding to the particular set of radiation controls comprises applying a transform to produce simulated dose calculations, wherein the transform is defined in the continuous computational space as a convolution.
7 . The method of claim 6 , wherein applying the transform comprises producing a convolution between a patient-specific dose deposition kernel or fluence deposition matrix and a radiation control corresponding to at least one of irradiation time or radiation intensity.
8 . The method of claim 7 , wherein each dose deposition kernel or fluence deposition matrix represents a dose rate from a particular sector, a particular collimator, and a particular isocenter, to a particular location in a patient to receive the radiotherapy treatment.
9 . The method of claim 6 , wherein applying the transform comprises applying a Fourier transform, and wherein the simulated dose calculations are represented as a multiplication in Fourier space.
10 . The method of claim 6 , wherein applying the transform comprises applying one of a: wavelet, Laplace, Hankel, Mellin, or Hilbert transform.
11 . The method of claim 1 , wherein converting the generated set of radiation controls to the set of treatment delivery parameters is based on minimizing a degradation of plan quality according to a clinically relevant objective.
12 . The method of claim 1 , further comprising:
collapsing the set of treatment delivery parameters to a path to perform the radiotherapy treatment, based on a type of the radiotherapy treatment machine.
13 . The method of claim 12 , wherein the collapsing of the set of treatment delivery parameters is performed using curvelets.
14 . The method of claim 1 , wherein converting the set of radiation controls to the set of treatment delivery parameters comprises discretizing at least a portion of the set of radiation controls into a set of finite-dimensional treatment delivery parameters.
15 . The method of claim 1 , wherein generating the set of the radiation controls that belongs to the continuous computational space comprises using a probabilistic language of random fields, performing computations using a finite subset of points, and using interpolation to determine properties of each infinite-dimensional radiation control.
16 . The method of claim 1 , wherein the data for the radiotherapy treatment comprises imaging data based on a defined two-dimensional or three-dimensional grid.
17 . The method of claim 1 , wherein the data for the radiotherapy treatment comprises a definition of one or more volumes to receive the radiotherapy treatment from the radiotherapy treatment machine.
18 . The method of claim 17 , wherein the definition of one or more volumes defines one or more organ at risk areas and one or more target areas.
19 . The method of claim 1 , wherein the set of radiation controls are based on modulation of radiation using at least one of: focus position, directionality, irradiation time, flux, fluence, energy, or collimation, for the radiation.
20 . The method of claim 1 , wherein the radiotherapy treatment is provided with a Gamma knife, and wherein the set of treatment delivery parameters comprises a set of isocenters used for delivery of the radiotherapy treatment.
21 . The method of claim 20 , wherein the set of treatment delivery parameters further comprises timing for delivery of the radiotherapy treatment and a sequence for the delivery of the radiotherapy treatment.
22 . The method of claim 1 , wherein the radiotherapy treatment is provided with a Volumetric-modulated arc therapy (VMAT) or Intensity modulated radiation therapy (IMRT) using a Linac radiotherapy machine, and wherein the set of treatment delivery parameters comprises a set of arc control points.
23 . 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 perform operations that:
obtain data for a radiotherapy treatment of a human subject;
generate a set of radiation controls from the data for the radiotherapy treatment, wherein at least one of the radiation controls is based on a mapping from a continuous computational space;
convert the generated set of radiation controls to a set of treatment delivery parameters, the set of treatment delivery parameters corresponding to capabilities of a radiotherapy treatment machine, and
produce treatment plan data for the radiotherapy treatment based on the set of treatment delivery parameters.
24 . A computing system for radiotherapy treatment planning, the computing system comprising:
one or more memory devices to store data for a radiotherapy treatment of a human subject; and
one or more processors configured to perform operations to:
generate a set of radiation controls from the data for the radiotherapy treatment, wherein at least one of the radiation controls is based on a mapping from a continuous computational space;
convert the generated set of radiation controls to a set of treatment delivery parameters, the set of treatment delivery parameters corresponding to capabilities of a radiotherapy treatment machine; and
produce treatment plan data for the radiotherapy treatment based on the set of treatment delivery parameters.