Methods and systems for radiotherapy treatment planning
Example methods for radiotherapy treatment planning are provided. One example method may include obtaining training data that includes multiple treatment plans associated with respective multiple past patients; and processing the training data to determine, from each of the multiple treatment plans, at least one of the following: first data associated with a particular past patient or a radiotherapy system for delivering radiotherapy treatment to the particular past patient, second data associated with treatment planning trade-off selected for the particular past patient and third data associated with radiation dose for delivery to the particular past patient. The method may also comprise: based on at least one of the first data, the second data and the third data, identifying one or more sub-optimal characteristics associated with the training data, obtaining improved training data and generating a dose estimation model based on the improved training data.
1. A method for a computer system to perform radiotherapy treatment planning, wherein the method comprises:
obtaining training data that includes multiple treatment plans associated with respective multiple past patients;
processing the training data to determine, from each of the multiple treatment plans, at least one of the following: first data associated with a particular past patient or a radiotherapy system for delivering radiotherapy treatment to the particular past patient, second data associated with a treatment planning trade-off selected for the particular past patient and third data associated with radiation dose for delivery to the particular past patient;
based on at least one of the first data, the second data and the third data, identifying one or more sub-optimal characteristics associated with the training data;
obtaining improved training data that is generated to reduce or eliminate the identified one or more sub-optimal characteristics associated with the training data;
generating a dose estimation model based on the improved training data;
obtaining first input data associated with patient geometry of a new patient; and
generating a treatment plan for the new patient using the dose estimation model based on the first input data.
2. The method of claim 1 , wherein identifying the one or more sub-optimal characteristics comprises one or more of the following:
identifying a first sub-optimal characteristic in the form of a gap associated with the first data, the second data, or a combination of the first data and the second data; and
identifying a second sub-optimal characteristic in the form of a particular treatment plan that requires a re-planning, or includes a particular treatment planning trade-off.
3. The method of claim 2 , wherein identifying the first sub-optimal characteristic comprises:
identifying the gap based on multiple data clusters associated with the first data, the second data, or the combination of the first data and the second data.
4. The method of claim 2 , wherein identifying the second sub-optimal characteristic comprises:
comparing the third data identified from the particular treatment plan with estimated lower radiation dose data and estimated upper radiation dose data, wherein the third data includes mean radiation dose data associated with multiple organs-at-risk (OARs).
5. The method of claim 4 , wherein identifying the second sub-optimal characteristic comprises one of the following:
in response to determination that the mean radiation dose data is higher than the estimated lower radiation dose data for all of the multiple OARs, and higher than the estimated upper radiation dose data for some of the multiple OARs, determining that the particular treatment plan requires the re-planning; and
in response to determination that the mean radiation dose data is lower than the estimated lower radiation dose data for some of the multiple OARs, and lower than the estimated upper radiation dose data for some of the multiple OARs, determining that the particular treatment plan includes the particular treatment planning trade-off.
6. The method of claim 2 , wherein the method further comprises one or more of the following:
based on the first sub-optimal characteristic, generating the improved training data by including at least one alternative or additional treatment plan in the training data to reduce or eliminate the gap; and
based on the second sub-optimal characteristic, generating the improved training data by performing the required re-planning on the particular treatment plan.
7. The method of claim 1 , wherein processing the training data comprises one or more of the following:
determining, from each of the multiple treatment plans, the first data that includes one or more of the following geometrical features associated with the particular past patient: target volume, OAR volume, relative overlap volume and relative out-of-field volume;
determining, from each of the multiple treatment plans, the first data that includes one or more of the following non-geometrical features: number of fields, directionality of the fields, prescription to the particular past patient and photon energy;
determining, from each of the multiple treatment plans, the third data that includes one or more of the following features associated with radiation dose: dose volume histogram (DVH) and dose distribution; and
determining, from each of the multiple treatment plans, the second data that is associated with one of the following treatment planning trade-offs:
trade-off between a first objective associated with an organ-at-risk (OAR) and a second objective associated with a target;
trade-off between a first objective associated with a first OAR and a second objective associated with a second OAR;
trade-off between a first objective associated with a target and a second objective associated with multiple OARs;
trade-off between a first objective associated with a first feature that is non-dosimetrical and a second objective associated with one or more second features; and
trade-off between a first objective associated with a first group of features and a second objective associated with a second group of features.
8. A non-transitory computer-readable storage medium that includes a set of instructions which, in response to execution by a processor of a computer system, cause the processor to perform a method of radiotherapy treatment planning, the method comprising:
obtaining training data that includes multiple treatment plans associated with respective multiple past patients;
processing the training data to determine, from each of the multiple treatment plans, at least one of the following: first data associated with a particular past patient or a radiotherapy system for delivering radiotherapy treatment to the particular past patient, second data associated with a treatment planning trade-off selected for the particular past patient and third data associated with radiation dose for delivery to the particular past patient;
based on at least one of the first data, the second data and the third data, identifying one or more sub-optimal characteristics associated with the training data;
obtaining improved training data that is generated to reduce or eliminate the identified one or more sub-optimal characteristics associated with the training data;
generating a dose estimation model based on the improved training data;
obtaining first input data associated with patient geometry of a new patient; and
generating a treatment plan for the new patient using the dose estimation model based on the first input data.
9. The non-transitory computer-readable storage medium of claim 8 , wherein identifying the one or more sub-optimal characteristics comprises one or more of the following:
identifying a first sub-optimal characteristic in the form of a gap associated with the first data, the second data, or a combination of the first data and the second data; and
identifying a second sub-optimal characteristic in the form of a particular treatment plan that requires a re-planning, or includes a particular treatment planning trade-off.
10. The non-transitory computer-readable storage medium of claim 9 , wherein identifying the first sub-optimal characteristic comprises:
identifying the gap based on multiple data clusters associated with the first data, the second data, or the combination of the first data and the second data.
11. The non-transitory computer-readable storage medium of claim 9 , wherein identifying the second sub-optimal characteristic comprises:
comparing the third data identified from the particular treatment plan with estimated lower radiation dose data and estimated upper radiation dose data, wherein the third data includes mean radiation dose data associated with multiple organs-at-risk (OARs).
12. The non-transitory computer-readable storage medium of claim 11 , wherein identifying the second sub-optimal characteristic comprises one of the following:
in response to determination that the mean radiation dose data is higher than the estimated lower radiation dose data for all of the multiple OARs, and higher than the estimated upper radiation dose data for some of the multiple OARs, determining that the particular treatment plan requires the re-planning; and
in response to determination that the mean radiation dose data is lower than the estimated lower radiation dose data for some of the multiple OARs, and lower than the estimated upper radiation dose data for some of the multiple OARs, determining that the particular treatment plan includes the particular treatment planning trade-off.
13. The non-transitory computer-readable storage medium of claim 9 , wherein the method further comprises one or more of the following:
based on the first sub-optimal characteristic, generating the improved training data by including at least one alternative or additional treatment plan in the training data to reduce or eliminate the gap; and
based on the second sub-optimal characteristic, generating the improved training data by performing the required re-planning on the particular treatment plan.
14. The non-transitory computer-readable storage medium of claim 8 , wherein processing the training data comprises one or more of the following:
determining, from each of the multiple treatment plans, the first data that includes one or more of the following geometrical features associated with the particular past patient: target volume, OAR volume, relative overlap volume and relative out-of-field volume;
determining, from each of the multiple treatment plans, the first data that includes one or more of the following non-geometrical features: number of fields, directionality of the fields, prescription to the particular past patient and photon energy;
determining, from each of the multiple treatment plans, the third data that includes one or more of the following features associated with radiation dose: dose volume histogram (DVH) and dose distribution; and
determining, from each of the multiple treatment plans, the second data that is associated with one of the following treatment planning trade-offs:
trade-off between a first objective associated with an organ-at-risk (OAR) and a second objective associated with a target;
trade-off between a first objective associated with a first OAR and a second objective associated with a second OAR;
trade-off between a first objective associated with a target and a second objective associated with multiple OARs;
trade-off between a first objective associated with a first feature that is non-dosimetrical and a second objective associated with one or more second features; and
trade-off between a first objective associated with a first group of features and a second objective associated with a second group of features.
15. A computer system configured to perform radiotherapy treatment planning, the computer system comprising: a processor and a non-transitory computer-readable medium having stored thereon instructions that, when executed by the processor, cause the processor to:
obtain training data that includes multiple treatment plans associated with respective multiple past patients;
process the training data to determine, from each of the multiple treatment plans, at least one of the following: first data associated with a particular past patient or a radiotherapy system for delivering radiotherapy treatment to the particular past patient, second data associated with a treatment planning trade-off selected for the particular past patient and third data associated with radiation dose for delivery to the particular past patient;
based on at least one of the first data, the second data and the third data, identify one or more sub-optimal characteristics associated with the training data;
obtain improved training data that is generated to reduce or eliminate the identified one or more sub-optimal characteristics associated with the training data;
generate a dose estimation model based on the improved training data;
obtain first input data associated with patient geometry of a new patient; and
generate a treatment plan for the new patient using the dose estimation model based on the first input data.
16. The computer system of claim 15 , wherein the instructions for identifying the one or more sub-optimal characteristics cause the processor to perform one or more of the following:
identify a first sub-optimal characteristic in the form of a gap associated with the first data, the second data, or a combination of the first data and the second data; and
identify a second sub-optimal characteristic in the form of a particular treatment plan that requires a re-planning, or includes a particular treatment planning trade-off.
17. The computer system of claim 16 , wherein the instructions for identifying the first sub-optimal characteristic cause the processor to:
identify the gap based on multiple data clusters associated with the first data, the second data, or the combination of the first data and the second data.
18. The computer system of claim 16 , wherein the instructions for identifying the second sub-optimal characteristic cause the processor to:
compare the third data identified from the particular treatment plan with estimated lower radiation dose data and estimated upper radiation dose data, wherein the third data includes mean radiation dose data associated with multiple organs-at-risk (OARs).
19. The computer system of claim 18 , wherein the instructions for identifying the second sub-optimal characteristic cause the processor to perform one of the following:
in response to determination that the mean radiation dose data is higher than the estimated lower radiation dose data for all of the multiple OARs, and higher than the estimated upper radiation dose data for some of the multiple OARs, determine that the particular treatment plan requires the re-planning; and
in response to determination that the mean radiation dose data is lower than the estimated lower radiation dose data for some of the multiple OARs, and lower than the estimated upper radiation dose data for some of the multiple OARs, determine that the particular treatment plan includes the particular treatment planning trade-off.
20. The computer system of claim 16 , wherein the instructions further cause the processor to perform one or more of the following:
based on the first sub-optimal characteristic, generate the improved training data by including at least one alternative or additional treatment plan in the training data to reduce or eliminate the gap; and
based on the second sub-optimal characteristic, generate the improved training data by performing the required re-planning on the particular treatment plan.
21. The computer system of claim 15 , wherein the instructions for processing the training data cause the processor to perform one or more of the following:
determine, from each of the multiple treatment plans, the first data that includes one or more of the following geometrical features associated with the particular past patient: target volume, OAR volume, relative overlap volume and relative out-of-field volume;
determine, from each of the multiple treatment plans, the first data that includes one or more of the following non-geometrical features: number of fields, directionality of the fields, prescription to the particular past patient and photon energy;
determine, from each of the multiple treatment plans, the third data that includes one or more of the following features associated with radiation dose: dose volume histogram (DVH) and dose distribution; and
determine, from each of the multiple treatment plans, the second data that is associated with one of the following treatment planning trade-offs:
trade-off between a first objective associated with an organ-at-risk (OAR) and a second objective associated with a target;
trade-off between a first objective associated with a first OAR and a second objective associated with a second OAR;
trade-off between a first objective associated with a target and a second objective associated with multiple OARs;
trade-off between a first objective associated with a first feature that is non-dosimetrical and a second objective associated with one or more second features; and
trade-off between a first objective associated with a first group of features and a second objective associated with a second group of features.