Computer modeling for field geometry selection
Disclosed herein are systems and methods for identifying radiation therapy treatment data for different patients, such as field geometry. A central server collects patient data, radiation therapy treatment planning data, clinic-specific rules, and other pertinent treatment/medical data associated with a patient. The server then executes one or more machine-learning computer models to predict field geometry variables and weights associated with the patient's treatments. Using the predicted variables and weights, the server execute a clinic-specific set of logic to identify suggested field geometry, such as couch/gantry angles and/or arc attributes. The server then monitors whether end users (e.g., medical professionals) revise the suggested field geometry and trains the model accordingly.
1. A method comprising:
receiving, by a server, radiation therapy treatment planning data associated with treatment of a patient, the radiation therapy treatment planning data further comprising at least a patient identifier;
retrieving, by the server using the patient identifier, anatomy data associated with the patient; retrieving, by the server using a clinic identifier for a clinic implementing the treatment of the patient, a file comprising clinic-specific logic indicating clinic-specific rules with corresponding weights for identifying treatment attributes of a radiotherapy machine in accordance with at least one of radiation therapy treatment planning data or the anatomy data;
executing, by the server, one or more machine-learning models using the radiation therapy treatment planning data, anatomy data, and clinic-specific logic to identify one or more variables, wherein the one or more machine-learning models are trained based on previously performed radiation therapy treatments and previous patient data associated with the previously performed radiation therapy treatments and clinic-specific logic;
executing, by the server using the variables, a logical network computer model to identify one or more attributes of the radiotherapy machine to perform the treatment by ingesting the one or more variables generated via the machine-learning model, the logical network computer model configured to use the clinic-specific logic to determine the one or more attributes of the radiotherapy machine based on the one or more variables, anatomy data associated with the patient, and the clinic-specific logic with corresponding weights; and
displaying, by the server on a graphical user interface, the one or more attributes of the radiotherapy machine to perform the treatment.
2. The method of claim 1 , further comprising:
transmitting, by the server, an instruction to a radiotherapy machine to modify itself based on the identified one or more attributes.
3. The method of claim 1 , wherein the graphical user interface is displayed on the radiotherapy machine.
4. The method of claim 1 , wherein the graphical user interface is displayed on at least one of a physician device or an electronic device associated with a clinic conducting the treatment.
5. The method of claim 4 , wherein the server monitors whether a user interacts with at least one attribute displayed on the graphical user interface.
6. The method of claim 5 , wherein the server trains the one or more machine-learning models based on the interaction.
7. The method of claim 1 , wherein the identified attribute is angle associated with a couch or a gantry of the radiotherapy machine.
8. The method of claim 1 , wherein the identified attribute is a rotation or arc attribute of a gantry associated with the radiotherapy machine.
9. The method of claim 8 , wherein the rotation or arc attribute corresponds to whether a gantry of the radiotherapy machine conducting the treatment has a full or partial arc.
10. The method of claim 1 , further comprising:
comparing, by the server, the identified one or more attributes of a radiotherapy machine against one or more predetermined thresholds.
11. A system comprising:
a radiotherapy machine; and
a server in communication with the radiotherapy machine, the server configured to:
receive radiation therapy treatment planning data associated with treatment of a patient, the radiation therapy treatment planning data further comprising at least a patient identifier;
retrieve, using the patient identifier, anatomy data associated with the patient;
retrieve, using a clinic identifier for a clinic implementing the treatment of the patient, a file comprising clinic-specific logic indicating clinic-specific rules with corresponding weights for identifying treatment attributes of the radiotherapy machine in accordance with at least one of radiation therapy treatment planning data or anatomy data;
execute one or more machine-learning model using the radiation therapy treatment planning data, anatomy data, and clinic-specific logic to identify one or more variables, wherein one or more machine-learning models are trained based on previously performed radiation therapy treatments and previous patient data associated with the previously performed radiation therapy treatments and clinic-specific;
execute, using the variables, a logical network computer model to identify one or more attributes of the radiotherapy machine to perform the treatment by ingesting the one or more variables generated via the machine-learning model, the logical network computer model configured to use the clinic-specific logic to determine the one or more attributes of the radiotherapy machine based on the one or more variables, anatomy data associated with the patient, and the clinic-specific logic with corresponding weights; and
display, on a graphical user interface, the identified one or more attributes of a radiotherapy machine to perform the treatment.
12. The system of claim 11 , wherein the server is further configured to:
transmit an instruction to a radiotherapy machine to modify itself based on the identified one or more attributes.
13. The system of claim 11 , wherein the graphical user interface is displayed on the radiotherapy machine.
14. The system of claim 11 , wherein the graphical user interface is displayed on at least one of a physician device or an electronic device associated with the clinic.
15. The system of claim 14 , wherein the server monitors whether a user interacts with at least one attribute displayed on the graphical user interface.
16. The system of claim 15 , wherein the server trains the one or more machine-learning models based on the interaction.
17. The system of claim 11 , wherein the identified attribute is angle associated with a couch or a gantry of the radiotherapy machine.
18. The system of claim 11 , wherein the identified attribute is a rotation or arc attribute of a gantry associated with the radiotherapy machine.
19. The system of claim 18 , wherein the rotation or arc attribute corresponds to whether a gantry of the radiotherapy machine conducting the treatment has a full or partial arc.
20. The system of claim 11 , wherein the server is further configured to:
compare the identified one or more attributes of a radiotherapy machine against one or more predetermined thresholds.