Siemens Healthineers International Ag

Varian Medical Systems, Inc.

Varian Medical Systems International Ag

Todd Arlin Wareing

Josh Star-Lack

Adam James Wang

Santtu Ollila

John Morton McGhee

Alexander Enrique Maslowski

Douglas Allen Barnett, Jr

Alexander Maslowski

Douglas Allen Barnett

Mingshan Sun

Adam Shar Wang

Alexander E Maslowski

Embodiments described herein provide for training an artificial intelligence model to boost dose depositions. The artificial intelligence model receives medical images and a dose deposition determined according to a first dose deposition model. The artificial intelligence model modifies the received dose deposition determined according to the first dose deposition model such that the dose deposition simulates a dose deposition determined by a second dose deposition model.

Artificial intelligence boosting dose calculations

A method of trajectory optimization for radiotherapy treatment includes providing a patient model having one or more regions of interest (ROIs), defining a delivery coordinate space (DCS), for each ROI, solving an adjoint transport to obtain an adjoint solution field from the ROI, for each vertex in the DCS, evaluating an adjoint photon fluence by performing ray tracing of the adjoint solution field, evaluating a dose of the ROI using the adjoint photon fluence, for each vertex in the DCS, evaluating a respective beam's eye view (BEV) score of each pixel of a BEV plane using the doses of the one or more ROIs, determining one or more BEV regions in the BEV plane based on the BEV scores, determining a BEV region connectivity manifold based on the BEV regions, and determining one or more optimal treatment trajectories based on the BEV region connectivity manifold.

Adjoint transport for dose in treatment trajectory optimization for external beam radiation therapy

Embodiments described herein provide for coupling Monte Carlo source modeling with deterministic dose calculations. An internal volumetric first scatter distributed source of a patient is determined using Monte Carlo simulations and ingested into one or more dosing algorithms. The dosing algorithms use the source model to determine a dose deposition.

Driving deterministic dose depositions with monte carlo source modeling

A method of beam angle optimization for an IMRT radiotherapy treatment includes providing a patient model having one or more regions of interest (ROIs), defining a delivery coordinate space (DCS), for each ROI, solving an adjoint transport to obtain an adjoint solution field from the ROI, for each vertex in the DCS, evaluating an adjoint photon fluence by performing ray tracing of the adjoint solution field, evaluating a dose of the ROI using the adjoint photon fluence, for each vertex in the DCS, evaluating a respective beam's eye view (BEV) score of each pixel of a BEV plane using the doses of the one or more ROIs, determining one or more BEV regions in the BEV plane based on the BEV scores, determining a BEV region connectivity manifold based on the BEV regions, and determining a set of IMRT fields based on the BEV region connectivity manifold.

Adjoint transport for dose in beam angle optimization for external beam radiation therapy

In accordance with at least some embodiments of the present disclosure, a process to estimate scattered radiation contained in x-ray projections for computed tomography (CT) reconstruction is provided. The process may construct an object model based on a plurality of projection images generated by CT scanning of an object using an x-ray radiation source and a detector panel. The process may construct a virtual radiation source based on the x-ray radiation source, and a virtual detector panel based on the detector panel. The process may perform a simulated CT scanning of the object model by simulating macroscopic behavior of particles being emitted from the virtual radiation source, passing through the object model, and being detected by the virtual detector panel. And the process may generate a simulated scatter image based on a first subset of particles scattered during the simulated CT scanning of the object model.

Automatic estimating and reducing scattering in computed tomography scans

Growing community of inventors

Blackfoot, ID, United States of America

Todd Arlin Wareing