An example particle therapy system includes a particle accelerator to output a particle beam having a spot size; a scanning system for the particle accelerator to scan the particle beam in two dimensions across at least part of a treatment area of an irradiation target; and an adaptive aperture between the scanning system and the irradiation target. The adaptive aperture includes structures that are movable relative to the irradiation target to approximate a shape to trim part of the treatment area. The part of the treatment area has a size that is based on an area of the spot size.

A volumetric modulated arc therapy (VMAT) treatment plan may be optimized by obtaining a VMAT treatment plan and calculating a radiation dose matrix corresponding to each a plurality of beamlets, wherein each beamlet represents a change in field when an MLC leaf is moved a predetermined unit distance. The method includes defining an enhanced objective function (EOF) for achieving one or more clinical objectives and minimizing the EOF for proposed leaf positions iterating through each leaf of at least a subset of the leaves of the VMAT treatment plan (wherein the proposed leaf positions move each leaf into the field or out of the field by the predetermined unit distance and correspond to the addition or subtraction of the corresponding radiation dose matrix). The set of leaf positions of the VMAT treatment plan is updated according to the proposed leaf positions of the minimized EOF.

A method for determining a radiotherapy treatment plan can include: receiving anatomical data for a patient; generating, via a neural network analyzing the anatomical data, a plurality of fitness values for a plurality of candidate beam orientations; determining a selected beam orientation based on the plurality of fitness values; performing a fluence map optimization (FMO) process on the selected beam orientation; and determining a dose distribution for the patient based on the FMO process.

A memory has stored therein a fluence map that corresponds to a particular patient and a deep learning model. The deep learning model is trained to deduce a leaf sequence for a multi-leaf collimator from a fluence map. The deep learning model comprises a neural network model that was trained, at least in part, via a reinforcement learning method. A control circuit accesses the memory and is configured to iteratively optimize a radiation treatment plan to administer the therapeutic radiation to the patient by, at least in part, generating a leaf sequence as a function of the deep learning model and the fluence map by employing a plurality of agents to each separately use the deep learning model to each generate a leaf sequence for only a single leaf pair of the multi-leaf collimator.

A control circuit generates an optimized radiation treatment plan with respect to an adjustable collimation device and then automatically generates at least one quality assurance accuracy value corresponding to the optimized radiation treatment plan. By one approach, the aforementioned plan comprises a plurality of treatment fields. In such a case, automatically generating at least one quality assurance accuracy value can comprise, at least in part, automatically generating at least one quality assurance accuracy value for each of at least a substantial number (or all) of those treatment fields. By one approach, the aforementioned quality assurance accuracy value comprises a dimensionless metric. This dimensionless metric may represent, for example, dosimetric accuracy corresponding to the optimized radiation treatment plan.

Methods and apparatus are provided for planning and delivering radiation treatments by modalities which involve moving a radiation source along a trajectory relative to a subject while delivering radiation to the subject. In some embodiments the radiation source is moved continuously along the trajectory while in some embodiments the radiation source is moved intermittently. Some embodiments involve the optimization of the radiation delivery plan to meet various optimization goals while meeting a number of constraints. For each of a number of control points along a trajectory, a radiation delivery plan may comprise: a set of motion axes parameters, a set of beam shape parameters and a beam intensity.

Methods and apparatus are provided for planning and delivering radiation treatments by modalities which involve moving a radiation source along a trajectory relative to a subject while delivering radiation to the subject. In some embodiments the radiation source is moved continuously along the trajectory while in some embodiments the radiation source is moved intermittently. Some embodiments involve the optimization of the radiation delivery plan to meet various optimization goals while meeting a number of constraints. For each of a number of control points along a trajectory, a radiation delivery plan may comprise: a set of motion axes parameters, a set of beam shape parameters and a beam intensity.

Disclosed herein are systems and methods for guiding the delivery of therapeutic radiation using incomplete or partial images acquired during a treatment session. A partial image does not have enough information to determine the location of a target region due to, for example, poor or low contrast and/or low SNR. The radiation fluence calculation methods described herein do not require knowledge or calculation of the target location, and yet may help to provide real-time image guided radiation therapy using arbitrarily low SNR images.

Systems and methods for shuttle mode radiation delivery are described herein. One method for radiation delivery comprises moving the patient platform through the patient treatment region multiple times during a treatment session. This may be referred to as patient platform or couch shuttling (i.e., couch shuttle mode). Another method for radiation delivery comprises moving the therapeutic radiation source jaw across a range of positions during a treatment session. The jaw may move across the same range of positions multiple times during a treatment session. This may be referred to as jaw shuttling (i.e., jaw shuttle mode). Some methods combine couch shuttle mode and jaw shuttle mode. Methods of dynamic or pipelined normalization are also described.

A method includes detecting a potential setup error in a radiation treatment delivery session of a radiation treatment delivery system, wherein the setup error corresponds to a change in a current position of a treatment target relative to a prior position of the treatment target, and wherein the change includes a rotation relative to the prior position of the treatment target. The method further includes modifying, by a processing device, one or more planned leaf positions of a multileaf collimator (MLC) of a linear accelerator (LINAC) of the radiation treatment delivery system to compensate for the potential setup error corresponding to the rotation of the prior position of the treatment target.