Interested in licensing this patent?
MTEC can help explore whether this patent might be available for licensing for your application.
Publication Number
US-10765888-B2
Publication Date
2020-09-08
Expiration Date
Abstract
The present disclosure relates to systems, methods, and computer-readable storage media for radiotherapy. Embodiments of the present disclosure may receive a plurality of training data and determine one or more predictive models based on the training data. The one or more predictive models may be determined based on at least one of a conditional probability density associated with a selected output characteristic given one or more selected input variables or a joint probability density. Embodiments of the present disclosure may also receive patient specific testing data. In addition, embodiments of the present disclosure may predict a probability density associated with a characteristic output based on the one or more predictive models and the patient specific testing data. Moreover, embodiments of the present disclosure may generate a new treatment plan based on the prediction and may use the new treatment plan to validate a previous treatment plan.
Core Innovation
The invention is a radiotherapy system configured to use training data associated with past treatment plans used to treat sample patients. The training data includes observations associated with conditions of the sample patients and derived from medical image data, and includes plan outcomes reflecting outcomes resulting from the past treatment plans, or plan parameters reflecting design parameters of the past treatment plans.
Using this training data, the processing device determines a joint probability density indicating a likelihood that both observations and plan outcomes or plan parameters are present in the training data. Based on the determined joint probability density, the system calculates a conditional probability indicating a likelihood that the plan outcome or plan parameter is present in the training data.
The system predicts a probability of a patient specific plan outcome or patient specific plan parameter based on the conditional probability and at least one patient specific observation associated with the target patient and derived from medical image data. The treatment plan is generated based on the prediction and the radiotherapy device is controlled to perform radiotherapy treatment according to the generated treatment plan.
The disclosed approach supports probabilistic estimation of joint and conditional relationships for radiotherapy planning, including predicting probabilities and probability distributions for patient specific outcomes and parameters. The document describes that plan outcomes and/or plan parameters may include radiotherapy-related probabilities, survival time, displacement, and coordinate mapping, and that predicted dose distributions can be used to derive DVHs for generating a treatment plan.
Claims Coverage
The document includes two independent claims that cover a radiotherapy system and a method for treating a target patient. Each independent claim is centered on determining joint probability density, calculating conditional probability, predicting a patient specific plan outcome or plan parameter, generating a treatment plan, and controlling a radiotherapy device to perform treatment.
Joint probability density from observations and outcomes/parameters
Determining a joint probability density indicating a likelihood that both at least one particular observation and at least one particular plan outcome of the one or more plan outcomes or plan parameter of the plan parameters are present in the training data.
Conditional probability based on the joint probability density
Calculating a conditional probability based upon the determined joint probability density, wherein the conditional probability indicates a likelihood that the at least one particular plan outcome or the plan parameter is present in the training data.
Predicting patient specific plan outcome/parameter using patient specific observations
Predicting a probability of a patient specific plan outcome or patient specific plan parameter based on the conditional probability and at least one patient specific observation associated with the target patient and derived from medical image data associated with the target patient.
Generating a treatment plan and controlling a radiotherapy device
Generating the treatment plan based on the prediction; and controlling a radiotherapy device to perform radiotherapy treatment according to the generated treatment plan.
Probabilistic treatment planning method using joint and conditional probability
Determining a joint probability density indicating a likelihood that both at least one particular observation and at least one particular plan outcome or plan parameter are present in the training data; calculating a conditional probability based upon the determined joint probability density; predicting a probability of a patient specific plan outcome or plan parameter based on the conditional probability and at least one patient specific observation associated with the target patient and derived from medical image data associated with the target patient; generating the treatment plan based on the prediction; and controlling a radiotherapy device to perform radiotherapy treatment according to the generated treatment plan.
Across the independent claims, the core coverage requires estimating a joint probability density from training observations and plan outcomes/parameters, deriving a conditional probability from that joint probability density, predicting patient-specific plan outcome/parameter probabilities from patient-specific observations derived from medical image data, generating a treatment plan from the prediction, and controlling a radiotherapy device to perform treatment.
Stated Advantages
Not explicitly described in patent.
Documented Applications
Not explicitly described in patent.
Interested in licensing this patent?