Abstract: A method enables testing and evaluation of an expert human reviewer or an artificial intelligence (AI) error detection engine associated with a radiotherapy treatment planning process. Intentional errors are introduced into the output of a software module or AI engine that performs a certain step in the radiotherapy treatment planning process. The efficacy of the human or AI reviewer in detecting errors can then be evaluated or tested by determining whether the human or AI reviewer has detected the introduced error.

Abstract: A method enables testing and evaluation of an expert human reviewer or an artificial intelligence (AI) error detection engine associated with a radiotherapy treatment planning process. Intentional errors are introduced into the output of a software module or AI engine that performs a certain step in the radiotherapy treatment planning process. The efficacy of the human or AI reviewer in detecting errors can then be evaluated or tested by determining whether the human or AI reviewer has detected the introduced error.

Abstract: Radiation treatment planning includes accessing values of parameters such as a number of beams to be directed into sub-volumes in a target, beam directions, and beam energies. Information that specifies limits for the radiation treatment plan are accessed. The limits include a limit on irradiation time for each sub-volume outside the target. Other limits can include a limit on irradiation time for each sub-volume in the target, a limit on dose rate for each sub volume in the target, and a limit on dose rate for each sub-volume outside the target. The values of the parameters are adjusted until the irradiation time for each sub-volume outside the target satisfies the maximum limit on irradiation time.

Abstract: Example methods and systems for quality-aware continuous learning for radiotherapy treatment planning are provided. One example method may comprise: obtaining an artificial intelligence (AI) engine that is trained to perform a radiotherapy treatment planning task. The method may also comprise: based on input data associated with a patient, performing the radiotherapy treatment planning task using the AI engine to generate output data associated with the patient; and obtaining modified output data that includes one or more modifications made by a treatment planner to the output data. The method may further comprise: performing quality evaluation based on (a) first quality indicator data associated with the modified output data, and/or (b) second quality indicator data associated with the treatment planner. In response to a decision to accept, a modified AI engine may be generated by re-training the AI engine based on the modified output data.

Abstract: Radiation treatment planning includes accessing values of parameters such as a number of beams to be directed into sub-volumes in a target, beam directions, and beam energies. Information that specifies limits for the radiation treatment plan are accessed. The limits include a limit on irradiation time for each sub-volume outside the target. Other limits can include a limit on irradiation time for each sub-volume in the target, a limit on dose rate for each sub-volume in the target, and a limit on dose rate for each sub-volume outside the target. The values of the parameters are adjusted until the irradiation time for each sub-volume outside the target satisfies the maximum limit on irradiation time.

Abstract: Example methods and systems for radiotherapy treatment planning are provided. One example method may comprise obtaining image data associated with a patient; and processing the image data to generate a treatment plan for the patient using an inferential chain that includes multiple AI engines that are trained separately to perform respective multiple treatment planning steps. A first treatment planning step may be performed using a first AI engine to generate first output data based on at least one of: (i) the image data, and (ii) first input data generated based on the image data. A second treatment planning step may be performed using a second AI engine to generate the treatment plan based on at least one of: (i) the first output data, and (ii) second input data generated based on the first output data.

Abstract: Radiation treatment planning includes accessing values of parameters such as a number of beams to be directed into sub-volumes in a target, beam directions, and beam energies. Information that specifies limits for the radiation treatment plan are accessed. The limits include a limit on irradiation time for each sub-volume outside the target. Other limits can include a limit on irradiation time for each sub-volume in the target, a limit on dose rate for each sub-volume in the target, and a limit on dose rate for each sub-volume outside the target. The values of the parameters are adjusted until the irradiation time for each sub-volume outside the target satisfies the maximum limit on irradiation time.

Abstract: A method enables testing and evaluation of an expert human reviewer or an artificial intelligence (AI) error detection engine associated with a radiotherapy treatment planning process. Intentional errors are introduced into the output of a software module or AI engine that performs a certain step in the radiotherapy treatment planning process. The efficacy of the human or AI reviewer in detecting errors can then be evaluated or tested by determining whether the human or AI reviewer has detected the introduced error.

Abstract: Example methods and systems for quality-aware continuous learning for radiotherapy treatment planning are provided. One example method may comprise: obtaining an artificial intelligence (AI) engine that is trained to perform a radiotherapy treatment planning task. The method may also comprise: based on input data associated with a patient, performing the radiotherapy treatment planning task using the AI engine to generate output data associated with the patient; and obtaining modified output data that includes one or more modifications made by a treatment planner to the output data. The method may further comprise: performing quality evaluation based on (a) first quality indicator data associated with the modified output data, and/or (b) second quality indicator data associated with the treatment planner. In response to a decision to accept, a modified AI engine may be generated by re-training the AI engine based on the modified output data.

Abstract: Radiation treatment planning includes accessing values of parameters such as a number of beams to be directed into sub-volumes in a target, beam directions, and beam energies. Information that specifies limits for the radiation treatment plan are accessed. The limits include a limit on irradiation time for each sub-volume outside the target. Other limits can include a limit on irradiation time for each sub-volume in the target, a limit on dose rate for each sub-volume in the target, and a limit on dose rate for each sub-volume outside the target. The values of the parameters are adjusted until the irradiation time for each sub-volume outside the target satisfies the maximum limit on irradiation time.

Abstract: Example methods and systems for generating an aggregated artificial intelligence (AI) engine for radiotherapy treatment planning are provided. One example method may include obtaining multiple AI engines associated with respective multiple treatment planners; generating multiple sets of output data using the multiple AI engines associated with the respective multiple treatment planners: comparing the multiple AI engines associated with the respective multiple treatment planners based on the multiple sets of output data; and based on the comparison, aggregating at least some of the multiple AI engines to generate the aggregated AI engine for performing the particular treatment planning step. The multiple AI engines may be trained to perform a particular treatment planning step, and each of the multiple AI engines is trained to emulate one of the multiple treatment planners performing the particular treatment planning step.

Abstract: Example methods and systems for radiotherapy treatment planning are provided. One example method may comprise obtaining image data associated with a patient; and processing the image data to generate a treatment plan for the patient using an inferential chain that includes multiple AI engines that are trained separately to perform respective multiple treatment planning steps. A first treatment planning step may be performed using a first AI engine to generate first output data based on at least one of: (i) the image data, and (ii) first input data generated based on the image data. A second treatment planning step may be performed using a second AI engine to generate the treatment plan based on at least one of: (i) the first output data, and (ii) second input data generated based on the first output data.

Abstract: Radiation treatment planning includes accessing values of parameters such as a number of beams to be directed into sub-volumes in a target, beam directions, and beam energies. Information that specifies limits for the radiation treatment plan are accessed. The limits include a limit on irradiation time for each sub-volume outside the target. Other limits can include a limit on irradiation time for each sub-volume in the target, a limit on dose rate for each sub-volume in the target, and a limit on dose rate for each sub-volume outside the target. The values of the parameters are adjusted until the irradiation time for each sub-volume outside the target satisfies the maximum limit on irradiation time.

Abstract: Example methods and systems for generating an aggregated artificial intelligence (AI) engine for radiotherapy treatment planning are provided. One example method may include obtaining multiple AI engines associated with respective multiple treatment planners; generating multiple sets of output data using the multiple AI engines associated with the respective multiple treatment planners: comparing the multiple AI engines associated with the respective multiple treatment planners based on the multiple sets of output data; and based on the comparison, aggregating at least some of the multiple AI engines to generate the aggregated AI engine for performing the particular treatment planning step. The multiple AI engines may be trained to perform a particular treatment planning step, and each of the multiple AI engines is trained to emulate one of the multiple treatment planners performing the particular treatment planning step.

Abstract: Radiation treatment planning includes accessing values of parameters such as a number of beams to be directed into sub-volumes in a target, beam directions, and beam energies. Information that specifies limits for the radiation treatment plan are accessed. The limits include a limit on irradiation time for each sub-volume outside the target. Other limits can include a limit on irradiation time for each sub-volume in the target, a limit on dose rate for each sub-volume in the target, and a limit on dose rate for each sub-volume outside the target. The values of the parameters are adjusted until the irradiation time for each sub-volume outside the target satisfies the maximum limit on irradiation time.