Abstract: An iterative Kalman Filter method was developed to address the need for estimating randomly moving targets during cancer radiotherapy on a standard equipped linear accelerator. Extensive evaluation of this method using different treatment scenarios shows sub-mm accuracy and precision. In addition, the system and method allows the target (or surrogates of the target) to be monitored without the need of a learning arc, reducing additional imaging dose to the patient. In addition, the method and system performs robustly against imaging and segmentation noise.

Abstract: Methods, apparatuses and systems are disclosed for dose-based optimization related to multi-leaf collimator (“MLC”) tracking during radiation therapy. In an example, a method includes calculating a planned radiation dose using an MLC plan in an unshifted dose volume, acquiring, using a radiation machine, a target position through motion tracking, and shifting the dose volume by the target position. The method also includes integrating a three-dimensional dose into a two-dimensional beam’s eye view grid and fitting, using the radiation machine for each leaf track, an MLC aperture by minimizing a cost function. The method further includes calculating and accumulating a delivered dose based on the fitted leaf positions of the MLC and updating a gantry position and MLC leaves to update a next planned dose.

Abstract: There is disclosed a method for estimating the position of a target in a body of a subject. The method includes, receiving an external signal that is related with motion of the target; and using a model of a correlation between the external signal and the motion of the target to estimate the position of the target, wherein said position estimation includes an estimate of three dimensional location and orientation of the target. The method further includes periodically receiving a 2-dimensional projection of the target; and updating the model of correlation between the external signal and the motion of the target based on a comparison of the estimated position of the target and the 2-dimensional projection of the target. The method is used in guided radiation therapy.

Abstract: The present invention is concerned with a method and system for guiding a radiation therapy system. The method comprises: capturing an image of a target area to which radiation is to be delivered; analysing the image with a trained convolutional neural network to determine the position of one or more objects of interest present in the target area; and outputting the determined position/s to the radiation therapy system.

Abstract: There is disclosed a method for estimating the position of a target in a body of a subject. The method includes, receiving an external signal that is related with motion of the target; and using a model of a correlation between the external signal and the motion of the target to estimate the position of the target, wherein said position estimation includes an estimate of three dimensional location and orientation of the target. The method further includes periodically receiving a 2-dimensional projection of the target; and updating the model of correlation between the external signal and the motion of the target based on a comparison of the estimated position of the target and the 2-dimensional projection of the target. The method is used in guided radiation therapy.