The present disclosure provides a radiation method for radiating a fluence map having a zero-fluence region under a movement of MLC (Multi-Leaf Collimator) includes a determining step of determining at least one basic fluence map from the fluence map. The basic fluence map includes a first non-zero fluence region and a second non-fluence region having the zero-fluence region therebetween. The radiation method includes a first radiating step including radiating the first non-zero fluence region, along with moving a first group of leaf pairs and moving a vertical jaw to shade the first group of leaf pairs, and a second radiating step including radiating the second non-zero fluence region, along with moving a second group of leaf pairs and withdrawing the vertical jaw to expose the second group of leaf pairs.

Generally speaking, pursuant to these various embodiments a memory stores prescribed treatment instructions for a particular patient radiation therapy. Those treatment instructions specify clinical metrics for goals pertaining to at least one treatment volume for the particular patient. Either directly or inferentially those clinical metrics are prioritized. A control circuit automatically converts those treatment instructions into resultant radiation treatment plan optimization objectives where the automatic conversion can compatibly comprise a non-convex optimization objective. The control circuit then automatically iteratively optimizes the radiation treatment plan for the particular patient radiation therapy as a function, at least in part, of the aforementioned resultant optimization objectives to thereby produce an optimized radiation treatment plan for the particular patient that a radiation treatment platform then utilizes to administer therapeutic radiation to the particular patient.

A system, medium, and method including obtaining a plurality of positions for multiple components defined by a plan; obtaining a set of constraints that express limitations for the multiple components at the plurality of positions, the constraints being applicable to a plan where the multiple components synchronously change their positions with time to traverse a prescribed sequence of the plurality of positions, at least one of the multiple components being further constrained to change its position over time by staying within a predefined tolerance to a predefined smooth function of position over time between different positions; determining a trajectory of position and a minimum duration in which the multiple components completely synchronously traverse the prescribed sequence of positions while satisfying the constraints for the multiple components; and generating a record of the determined trajectory of position and the minimum duration for the plurality of components.

Streamlined and partially automated methods of setting normal tissue objectives in radiation treatment planning are provided. These methods may be applied to multiple-target cases as well as single-target cases. The methods can impose one or more target-specific dose falloff constraints around each target, taking into account geometric characteristics of each target such as target volume and shape. In some embodiments, methods can also take into account a planner's preferences for target dose homogeneity. In some embodiments, methods can generate additional dose falloff constraints in locations between two targets where dose bridging is likely to occur.

Techniques for adjusting radiotherapy treatment for a patient in real-time are provided. The techniques include obtaining a training patient anatomy at a first time within a training radiotherapy treatment fraction after a training radiotherapy treatment dose has been delivered by a radiotherapy device; computing a deviation between the training patient anatomy at the first time and reference training patient anatomy during the training radiotherapy treatment fraction, wherein the reference training patient anatomy indicates a prescribed training dose parameter to be delivered within the training radiotherapy treatment fraction; applying the computed deviation to a machine learning model to estimate one or more intra-fraction radiotherapy treatment parameters of a function that provides a radiotherapy device parameter adjustment based on the one or more intra-fraction radiotherapy treatment parameters; and training the machine learning model to establish a relationship between the computed deviation and the one or more intra-fraction radiotherapy treatment parameters.

The present disclosure generally relates to a multi-leaf collimator. The multi-leaf collimator may include a set of leaves installed in a cavity, each leaf of the set of leaves having a length along a first direction. At least a portion of the set of leaves may extend beyond the cavity along the first direction. The set of leaves may be arranged along a second direction, the second direction being different from the first direction. A length of a target leaf of the set of leaves may be less than a length of a reference leaf of the set of leaves. The target leaf may be located in an end portion of the set of leaves along the second direction. The length of the set of leaves may conform to the shape of a maximum therapeutic radiation field.

A cost function is constructed so as to guide an optimization process to achieve similar coverage for all targets simultaneously in a concurrent radiation treatment of multiple targets, so that a single scaling factor may be used in a plan normalization to achieve the desired coverage for all the targets. The cost function includes a component that favors a solution that attains similar target coverages for all targets, as well as a component that favors a solution that approaches the desired target coverage value for each individual target. The cost function includes a max term relating to deficiencies of actual target coverages with respect to a desired target coverage, or alternatively a soft-max term relating to deviations of actual target coverages with respect to an average target coverage, as well as to deficiencies of actual target coverages with respect to a desired target coverage.

In radiation therapy, treatment objectives applicable to different identified structures in a patient's body (e.g., a target structure and an organ at risk (OAR)) may conflict due to overlap between the structures. Automated systems and methods can detect and resolve such conflicts. For example, a set of modified regions that do not overlap with each other can be defined, and a modified treatment objective for each modified region can be determined based on the original treatment objectives. The modified regions and modified treatment objectives can be used in treatment planning processes.

A control circuit optimizes a radiation treatment plan for a patient treatment volume using an automatically iterating optimization process that optimizes as a function, at least in part, of predetermined cost functions, wherein at least one of the cost functions favors apertures for the multi-leaf collimation system having local curvature that deviates only minimally from a reference curvature. By one approach the control circuit determines the reference curvature as a function, at least in part, of at least one of setting the reference curvature to a static minimal local curvature, a shape of a projective mapping of the treatment volume onto an isocenter plane, and/or a fluence map associated with an amount of radiation to be administered to the treatment volume from a particular direction. By one approach the control circuit dynamically determines when to employ one or more such cost functions.

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.