Radiation beam alignment for a LINAC including (1) for each beam alignment parameter value of a set: (a) with a beam alignment parameter of a LINAC set to the beam alignment parameter value, using a gantry to generate a radiation beam; (b) using an imaging device to acquire a radiation transmission image indicative of a radiation field of the radiation beam after passing by a radiation opaque marker; (c) determining a location of a beam axis of the radiation beam and a center of a shadow of the marker based on the radiation transmission image; and (d) determining a target-to-beam-axis distance between the location of the beam axis and the center of the shadow of the radiation opaque marker; and (2) determining an optimum beam alignment parameter value based on the beam alignment parameter values and the target-to-beam-axis distances determined with the LINAC set to the beam alignment parameter values.

A method of sequential monoscopic tracking is described. The method includes generating a plurality of projections of an internal target region within a body of a patient, the plurality of projections comprising projection data about a position of an internal target region of the patient. The method further includes generating external positional data about external motion of the body of the patient using one or more external sensors. The method further includes generating, by a processing device, a correlation model between the projection data and the external positional data by fitting the plurality of projections of the internal target region to the external positional data. The method further includes estimating the position of the internal target region at a later time using the correlation model.

Systems and techniques may be used to estimate a real-time patient state during a radiotherapy treatment using a magnetic resonance linear accelerator (MR-Linac). For example, a method may include generating a dictionary of expanded potential patient measurements and corresponding potential patient states using a preliminary motion model. The method may include training, using a machine learning technique, a correspondence motion model relating an input patient measurement to an output patient state using the dictionary. The method may include estimating, using a processor, the patient state corresponding to a 2D MR image using the correspondence motion model. The method may include directing radiation therapy, using the MR-Linac, to a target according to the patient state.

A multi-leaf collimator is provided. The multi-leaf collimator may include a plurality of leaves configured to shield radiation beams. At least two leaves of the plurality of leaves may be movable in a direction parallel to each another. Each leaf of at least some of the plurality of leaves may be configured to be movable between at least two positions. At least one of the at least two positions may be adjustable.

To provide a radiation treatment system which enables wide irradiation range of radiation to a patient without increasing a load on a structure body. A radiation treatment system includes: a couch that carries a treatment target; a radiation source; a rotation mechanism configured to support the radiation source and to rotate the radiation source around the couch; a sensor configured to detect radiation transmitted through the treatment target; and a control unit configured to control the radiation source and the rotation mechanism, and the control unit sets an irradiation plan in which an irradiation range of first irradiation and an irradiation range of second irradiation are partially overlapped, and controls a radiation dose for an overlapping portion based on a detection result obtained by the sensor.

A computer-implemented method of performing a radiation therapy process includes: while a patient is disposed in a first position and maintains a first inspiration level, acquiring a set of projection images of a target volume associated with the patient; based on a treatment planning digital volume associated with the radiation therapy process and the set of projection images, generating a synthetic digital volume that includes the target volume; based on a treatment plan associated with the treatment planning digital volume and on the synthetic digital volume, generating a modified treatment fraction; and while the patient remains in the first position and maintains at least the first inspiration level, performing the modified treatment fraction.

A computer-implemented method of segmenting a reconstructed volume of a region of patient anatomy includes: determining an anatomical region associated with the reconstructed volume; detecting one or more metal objects disposed in an initial 3D metal object mask associated with the reconstructed volume; for each of the one or more metal objects disposed in the initial 3D metal object mask, determining a volume associated with the metal object; determining a value for at least one segmentation parameter based on the anatomical region and on the volume associated with the one or more metal objects; and generating a final 3D metal object mask associated with the reconstructed digital volume using the value for the segmentation parameter.

Provided is a method controlling a dose. The method includes: acquiring a therapy plan; dividing each of the plurality of dose control points in the therapy plan into a plurality of refined control points, wherein each of the plurality of refined control points corresponds to a target dose; performing the therapy plan, and performing a real-time statistical collection on an actual dose; and adjusting, based on a target dose and the actual dose at a refined control point that is executed, a target dose at a refined control point that is not executed in real time.

Systems and methods are disclosed for monitoring anatomic position of a human subject and modifying a radiotherapy treatment based on anatomic position changes, as determined with a regression model trained to estimate movement of a region of interest. Example operations for movement monitoring and therapy control include: obtaining 3D image data for a subject, which provides a reference volume and at least one defined region of interest; obtaining real-time 2D image data corresponding to the subject, captured during the radiotherapy treatment session; extracting features from the 2D image data; producing a relative motion estimation of a region of interest with a machine learning regression model, the model trained to estimate a spatial transformation from the 2D image data based on training from the reference volume; and controlling a radiotherapy beam of a radiotherapy machine used in the radiotherapy session, based on the relative motion estimation.

A radiation system is provided. The radiation system may include a bore accommodating an object, a rotary ring, a first radiation source and a second radiation source mounted on the rotary ring and a processor. The first radiation source may be configured to emit a first cone beam toward a first region of the object. The second radiation source may be configured to emit a second beam toward a second region of the object, the second region including at least a part of the first region. The processor may be configured to obtain a treatment plan of the object, the treatment plan including parameters associated with radiation segments. The processor may be further configured to control an emission of the first cone beam and/or the second beam based on the parameters associated with the radiation segments to perform a treatment and a 3-D imaging simultaneously.