Systems and methods for predicting individual patient response to radiotherapy using a dynamic carrying capacity model
View Patent ↗Systems and methods for predicting outcome of radiation therapy is described herein. An example method includes receiving respective values for tumor volume of a target patients tumor at first and second time points, and calculating a change in tumor volume between the first and second time points. The method also includes estimating a patient-specific carrying capacity based on a logistic growth model and the change in tumor volume. Additionally, the method includes predicting a volume of the target patient's tumor at a future time point during radiation treatment based, at least in part, on a historical carrying capacity reduction fraction distribution and the patient-specific carrying capacity. The method further includes predicting a patient-specific outcome of radiation therapy for the target patient based, at least in part, on the predicted volume of the target patients tumor at the future time point.
1. A method, comprising:
receiving at least two images of a target patient's tumor including a first image captured at a first time point and a second image captured at a second time point;
deriving respective values for tumor volume of the target patient's tumor at the first time point and the second time point from the at least two images;
calculating a change in tumor volume between the first and second time points based on the respective values for tumor volume;
estimating a patient-specific carrying capacity based on a logistic growth model and the change in tumor volume between the first and second time points;
predicting a volume of the target patient's tumor at a future time point during radiation treatment based, at least in part, on a historical carrying capacity reduction fraction distribution and the patient-specific carrying capacity; and
predicting a patient-specific outcome of radiation therapy for the target patient based, at least in part, on the predicted volume of the target patient's tumor at the future time point.
2. The method of claim 1 , wherein the first point in time is prior to a beginning of radiation therapy.
3. The method of claim 1 , wherein the second point in time is at a beginning of radiation treatment.
4. The method of claim 1 , further comprising:
receiving a respective value for tumor volume of the target patient's tumor at a third time point;
calculating a change in tumor volume between the second and third time points based on the respective values for tumor volume;
estimating a patient-specific carrying capacity reduction fraction based on the logistic growth model and the change in tumor volume between the second and third time points; and
predicting the volume of the target patient's tumor at the future time point during radiation treatment based, at least in part, on the patient-specific carrying capacity reduction fraction and the change in tumor volume between the second and third time points, wherein the third time point is during administration of radiation treatment.
5. The method of claim 4 , wherein the third time point is at a second, third, fourth, or fifth week of radiation treatment.
6. The method of claim 4 , wherein the future time point is at a sixth week of radiation treatment.
7. The method of claim 4 , wherein the step of predicting the volume of the target patient's tumor at the future time point in radiation treatment based, at least in part, on the patient-specific carrying capacity reduction fraction and the change in tumor volume between the second and third time points comprises:
updating the historical carrying capacity reduction fraction distribution to include the patient-specific carrying capacity reduction fraction for the target patient;
randomly sampling from the updated historical carrying capacity reduction fraction distribution; and
simulating tumor volume dynamics during radiation treatment for the target patient.
8. The method of claim 4 , further comprising weighting the patient-specific carrying capacity reduction fraction for the target patient.
9. The method of claim 1 , wherein the patient-specific outcome is predicted by comparing a change in tumor volume at the future time point to a threshold.
10. The method of claim 1 , wherein the predicted patient-specific outcome is one of: i) a percentage chance of success of radiation therapy, ii) locoregional control (LRC), or iii) disease-free survival (DFS).
11. The method of claim 1 , further comprising at least one of: i) treating the target patient based on the predicted patient-specific outcome or ii) administering radiation treatment after the second time point.
12. A system, comprising:
a processor; and
a memory operably coupled to the processor, the memory having computer-executable instructions stored thereon that, when executed by the processor, cause the processor to:
receiving at least two images of a target patient's tumor including a first image captured at a first time point and a second image captured at a second time point;
derive respective values for tumor volume of the target patient's tumor at the first time point and the second time point;
calculate a change in tumor volume between the first and second time points based on the respective values for tumor volume;
estimate a patient-specific carrying capacity based on a logistic growth model and the change in tumor volume between the first and second time points;
predict a volume of the target patient's tumor at a future time point during radiation treatment based, at least in part, on a historical carrying capacity reduction fraction distribution and the patient-specific carrying capacity; and
predict a patient-specific outcome of radiation therapy for the target patient based, at least in part, on the predicted volume of the target patient's tumor at the future time point.
13. The system of claim 12 , wherein the memory has further computer-executable instructions stored thereon that, when executed by the processor, cause the processor to:
receive a respective value for tumor volume of the target patient's tumor at a third time point;
calculate a change in tumor volume between the second and third time points based on the respective values for tumor volume;
estimate a patient-specific carrying capacity reduction fraction based on the logistic growth model and the change in tumor volume between the second and third time points; and
predict the volume of the target patient's tumor at the future time point during radiation treatment based, at least in part, on the patient-specific carrying capacity reduction fraction and the change in tumor volume between the second and third time points, wherein the third time point is during administration of radiation treatment.
14. The system of claim 13 , wherein the third time point is at a second, third, fourth, or fifth week of radiation treatment.
15. The system of claim 13 , wherein the future time point is at a sixth week of radiation treatment.
16. The system of claim 13 , wherein the step of predicting the volume of the target patient's tumor at the future time point in radiation treatment based, at least in part, on the patient-specific carrying capacity reduction fraction and the change in tumor volume between the second and third time points comprises:
updating the historical carrying capacity reduction fraction distribution to include the patient-specific carrying capacity reduction fraction for the target patient;
randomly sampling from the updated historical carrying capacity reduction fraction distribution; and
simulating tumor volume dynamics during radiation treatment for the target patient.
17. The system of claim 13 , wherein the memory has further computer-executable instructions stored thereon that, when executed by the processor, cause the processor to weight the patient-specific carrying capacity reduction fraction for the target patient.
18. The system of claim 12 , wherein the at least two images are computed-tomography (CT) images or magnetic resonance images (MRI).