Duke University

The University of North Carolina at Charlotte

Wake Forest University

Other

Varian Medical Systems, Inc.

Fang-Fang Yin

Yaorong Ge

Qingrong Jackie Wu

Lulin Yuan

Yang Sheng

Mark Oldham

Justus Adamson

James Talmage Dobbins, Iii

Chunhao Wang

Devon James Godfrey

Qiuwen Wu

Wentao Wang

William Giles

Xiaofeng Zhu

Obed Laryea

Taoran Li

Xinyi Li

A radiation treatment planning system can include a machine learning system that receives patient data, including an image scan (e.g., CT scan) and contour(s), a physician prescription, including planning target and dose, and device (radiation beam) data and outputs predicted fluence maps. The machine learning system includes at least two stages, where a stage of the at least two stages includes converting image scans from the patient data to projection images. A treatment planning system can receive the predicted fluence maps and generates treatment plans without performing inverse optimization.

Fluence map prediction and treatment plan generation for automatic radiation treatment planning

According to an aspect, a method includes receiving data about a patient, computing geometric characterization of one or more organs at risk proximate to a target volume of a patient or vice versa, and selecting relevant treatment knowledge and experience. The method also includes generating, based on the received data, computed geometric characterization, and available knowledge and experience, a first set of radiation treatment planning parameters that will lead to a high quality plan for the patient. Further, the method includes model-based prediction, based on the data, a second set or more of radiation treatment planning parameters that will lead to alternative achievable plans with different organ sparing objectives for treating the patient. The multiple sets for parameters can be used separately or in conjunction to generate treatment plans.

Systems and methods for specifying treatment criteria and treatment parameters for patient specific radiation therapy planning

Systems and methods for efficient and automatic determination of radiation beam configurations for patient-specific radiation therapy planning are disclosed. According to an aspect, a method includes receiving data based on patient information and geometric characterization of one or more organs at risk proximate to a target volume of a patient. The method includes determining automatically one or more radiation treatment beam configuration sets. Further, the method includes presenting the determined one or more radiation beam configuration sets via a user interface.

Automatic determination of radiation beam configurations for patient-specific radiation therapy planning

Systems and methods are provided for single isocenter radiotherapy of multiple targets. Conformal arc information may be used in a Conformal Arc Informed Volumetric Modulated Arc Therapy (CAVMAT) method that includes single isocenter radiotherapy of multiple targets where conformal multi-leaf collimator (MLC) trajectories may be used as the starting point for limited inverse optimization. Single isocenter radiotherapy of multiple targets may provide flexibility with less complex MLC trajectories, and fully block between targets with the MLC.

Systems and methods for single isocenter radiotherapy of multiple targets

Systems and methods for automatic, customized radiation treatment plan generation for cancer are disclosed. According to an aspect, a method includes receiving data indicating anatomy information of a patient and radiation beam characteristics of a radiation therapy system. Further, the method includes determining energy levels for application of radiation beams to the patient.

Systems and methods for automatic, customized radiation treatment plan generation for cancer

Disclosed herein are systems and methods for specifying treatment criteria and treatment planning parameters for patient specific radiation therapy planning. According to an aspect, a method includes receiving data about a patient, computing geometric characterization of one or more organs at risk proximate to a target volume of a patient or vice versa, and selecting relevant treatment knowledge and experience. The method also includes generating, based on the received data, computed geometric characterization, and available knowledge and experience, a first set of radiation treatment planning parameters that will lead to a high quality plan for the patient. Further, the method includes model-based prediction, based on the data, a second set or more of radiation treatment planning parameters that will lead to alternative achievable plans with different organ sparing objectives for treating the patient. The multiple sets for parameters can be used separately or in conjunction to generate treatment plans.

An apparatus and method for automatically generating radiation treatment planning parameters are disclosed. In accordance with the illustrative embodiment, a database is constructed that stores: (i) patient data and past treatment plans by expert human planners for these patients, and (ii) optimal treatment plans that are generated using multi-objective optimization and Pareto front search and that represent the best tradeoff opportunities of the patient case, and a predictive model (e.g., a neural network, a decision tree, a support vector machine [SVM], etc.) is then trained via a learning algorithm on a plurality of input/output mappings derived from the contents of the database. During training, the predictive model is trained to identify and infer patterns in the treatment plan data through a process of generalization. Once trained, the predictive model can then be used to automatically generate radiation treatment planning parameters for new patients.

Automatic generation of patient-specific radiation therapy planning parameters

Systems and methods include coordinated (KV) and megaelectronvolt (MV) computerized tomography (CT) imaging. KV and MV data are combined using a normalization process in order to generate CT images. The resulting CT images can include an improved signal to noise ratio in comparison to CT images generated using either KV or MV imaging alone. The coordinated KV and MV imaging process may be accomplished in significantly less time than using KV or MV imaging alone. This time savings has advantages in treatment verification. The MV projections are optionally generated using MV x-rays configured for x-ray treatment. In these cases the combined projections will reflect the treatment volume.

Computerized tomography image reconstruction

Systems and methods for localizing a target for radiotherapy based on digital tomosynthesis are provided. According to one method, DTS verification image data of a target located within or on a patient is generated. The DTS verification image data is compared with DTS reference image data of the target. Radiotherapy positioning information is determined based on the comparison of the DTS verification and reference image data.

Growing community of inventors

Durham, NC, United States of America

Fang-Fang Yin