Artificial intelligence modeling for radiation therapy dose distribution analysis
Disclosed herein are methods and systems to optimize a radiation therapy treatment plan using dose distribution values predicted via a trained artificial intelligence model. A server trains the AI model using a training dataset comprising data associated with a plurality of previously implemented radiation therapy treatments on a plurality of previous patients and dose distributions associated with one or more organs of each previous patient. The server then executes the trained AI model to predict dose distribution for a patient. The server then displays a heat map illustrating the predicted values, transmits the predicted values to a plan optimizer to generate an optimized treatment plan for the patient, and/or transmits an alert when a treatment plan generated by a plan optimizer deviates from rules and thresholds indicated within the patient's plan objectives.
1. A method comprising:
retrieving, by a processor, a radiation therapy treatment plan for a patient comprising a plan dose distribution value associated with the patient;
executing, by the processor using the radiation therapy treatment plan, an artificial intelligence model to predict a predicted dose distribution value for an anatomical region of the patient based at least in part on the plan dose distribution value, the artificial intelligence model trained using a training dataset comprising data associated with a plurality of previously implemented radiation therapy treatments on a plurality of previous patients and dose distributions associated with one or more organs of each previous patient; and
transmitting, by the processor, a notification when the predicted dose distribution value exceeds a threshold corresponding to a criterion to identify a first region indicating a hot spot or a second region indicating a cold spot.
2. The method of claim 1 , wherein the threshold is retrieved from a plan objective associated with the patient.
3. The method of claim 1 , wherein the threshold corresponds to at least one dose distribution value within an existing treatment plan generated by a plan optimizer software solution.
4. The method of claim 1 , wherein the radiation therapy treatment plan is generated by a plan optimizer application and further comprising:
transmitting, by the processor, data associated with the at least one dose distribution value predicted by the artificial intelligence model to the plan optimizer application.
5. The method of claim 1 , wherein the artificial intelligence model is trained using dose-volume histograms of previous patients and their corresponding first and second thresholds.
6. The method of claim 1 , wherein the artificial intelligence model is trained using a set of medical images associated with previous patients.
7. The method of claim 6 , wherein the processor revises at least one medical image from the set of medical images that includes a particular object.
8. The method of claim 1 , wherein the notification comprises a heat map having a set of segments where each segment corresponds to a first coordinate and a second coordinate of the anatomical region of the patient, wherein a visual attribute of each segment corresponds to a calculated dose distribution value.
9. A computer system comprising:
a server comprising a processor and a non-transitory computer-readable medium containing instructions that when executed by the processor causes the processor to perform operations comprising:
retrieve a radiation therapy treatment plan for a patient comprising a plan dose distribution value associated with the patient;
execute, using the radiation therapy treatment plan, an artificial intelligence model to predict a predicted dose distribution value for an anatomical region of the patient based at least in part on the plan dose distribution value, the artificial intelligence model trained using a training dataset comprising data associated with a plurality of previously implemented radiation therapy treatments on a plurality of previous patients and dose distributions associated with one or more organs of each previous patient; and
transmit a notification when the predicted dose distribution value exceeds a threshold corresponding to a criterion to identify a first region indicating a hot spot or a second region indicating a cold spot.
10. The computer system of claim 9 , wherein the threshold is retrieved from a plan objective associated with the patient.
11. The computer system of claim 9 , wherein the threshold corresponds to at least one dose distribution value within an existing treatment plan generated by a plan optimizer software solution.
12. The computer system of claim 9 , wherein the radiation therapy treatment plan is generated by a plan optimizer application and the instructions further cause the processor to:
transmit the at least one dose distribution value predicted by the artificial intelligence model to the plan optimizer application.
13. The computer system of claim 9 , wherein the artificial intelligence model is trained using dose-volume histograms of previous patients and their corresponding first and second thresholds.
14. The computer system of claim 9 , wherein the artificial intelligence model is trained using a set of medical images associated with previous patients.
15. The computer system of claim 14 , wherein the instructions are configured to further cause the processor to revise at least one medical image from the set of medical images that includes a particular object.
16. The computer system of claim 9 , wherein the notification comprises a heat map having a set of segments where each segment corresponds to a first coordinate and a second coordinate of the anatomical region of the patient, wherein a visual attribute of each segment corresponds to a calculated dose distribution value.
17. A computer system comprising:
a processor in communication with an artificial intelligence model and an electronic device, the processor configured to:
retrieve a radiation therapy treatment plan for a patient comprising a plan dose distribution value associated with the patient;
execute, using the radiation therapy treatment plan, the artificial intelligence model to predict a predicted dose distribution value for an anatomical region of the patient based at least in part on the plan dose distribution value, the artificial intelligence model trained using a training dataset comprising data associated with a plurality of previously implemented radiation therapy treatments on a plurality of previous patients and dose distributions associated with one or more organs of each previous patient; and
transmit a notification, to the electronic device, when the predicted dose distribution value exceeds a threshold corresponding to a criterion to identify a first region indicating a hot spot or a second region indicating a cold spot.
18. The computer system of claim 17 , wherein the threshold is retrieved from a plan objective associated with the patient.