Machine-learning modeling to generate virtual bolus attributes
Disclosed herein are methods and systems for predicting a virtual bolus in order to generate a radiation therapy treatment plan comprising training, by a processor, a machine-learning model using a training dataset comprising a set of medical images corresponding to a set of previously performed radiation therapy treatments, each medical image comprising at least one planning target volume and a non-anatomical region added to the medical image; and executing, by the processor, the machine-learning model using a medical image not included within the training dataset, the machine-learning model predicting an attribute of a non-anatomical region for the medical image not included in the training dataset.
1. A method comprising:
executing, by a processor, a machine-learning model using a medical image not used to train the machine-learning model to predict an attribute of a non-anatomical region for the medical image, the non-anatomical region being located on an outer surface of a patient,
wherein the machine-learning model has been trained using a set of medical images corresponding to a set of previously performed radiation therapy treatments, each medical image comprising at least one planning target volume and an added non-anatomical region for its respective radiation therapy treatment.
2. The method of claim 1 , wherein the non-anatomical region corresponds to material configured to reduce or increase radiation emitted towards the planning target volume.
3. The method of claim 1 , wherein the non-anatomical region has an electron density value or a mass density value corresponding to human flesh.
4. The method of claim 1 , wherein the attribute of the non-anatomical region corresponds to a thickness of the non-anatomical region.
5. The method of claim 1 , wherein the attribute of the non-anatomical region corresponds to a position of the non-anatomical region in relation to the planning target volume.
6. The method of claim 1 , wherein the attribute of the non-anatomical region corresponds to a position of the non-anatomical region compared to an organ of the patient.
7. The method of claim 1 , wherein each medical image within the set of medical images comprises an indication of whether its corresponding non-anatomical region is acceptable.
8. The method of claim 1 , further comprising:
instructing, by the processor, a radiation therapy machine to adjust at least one of its attributes in accordance with the attribute of the non-anatomical region.
9. The method of claim 1 , further comprising:
transmitting, by the processor, the attribute of the non-anatomical region to a computing device to be displayed on a graphical user interface.
10. The method of claim 1 , further comprising:
transmitting, by the processor, a revised medical image that comprises the medical image not used for training the machine-learning model and a depiction of the non-anatomical region predicted by the machine-learning model.
11. A 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:
executing a machine-learning model using a medical image not used to train the machine-learning model to predict an attribute of a non-anatomical region for the medical image, the non-anatomical region being located on an outer surface of a patient, wherein the machine-learning model has been trained using a set of medical images corresponding to a set of previously performed radiation therapy treatments, each medical image comprising at least one planning target volume and an added non-anatomical region for its respective radiation therapy treatment.
12. The system of claim 11 , wherein the non-anatomical region corresponds to material configured to reduce or increase radiation emitted towards the planning target volume.
13. The system of claim 11 , wherein the non-anatomical region has an electron density value or a mass density value corresponding to human flesh.
14. The system of claim 11 , wherein the attribute of the non-anatomical region corresponds to a thickness of the non-anatomical region.
15. The system of claim 11 , wherein the attribute of the non-anatomical region corresponds to a position of the non-anatomical region in relation to the planning target volume.
16. The system of claim 11 , wherein the attribute of the non-anatomical region corresponds to a position of the non-anatomical region compared to an organ of the patient.
17. The system of claim 11 , wherein each medical image within the set of medical images comprises an indication of whether its corresponding non-anatomical region is acceptable.
18. The system of claim 11 , wherein the instructions further cause the processor to instruct a radiation therapy machine to adjust at least one of its attributes in accordance with the attribute of the non-anatomical region.
19. The system of claim 11 , wherein the instructions further cause the processor to transmit the attribute of the non-anatomical region to a computing device to be displayed on a graphical user interface.
20. The system of claim 11 , wherein the instructions further cause the processor to transmit a revised medical image that comprises the medical not used for training the machine-learning model and a depiction of the non-anatomical region predicted by the machine-learning model.