Radiation therapy treatment verification with electronic portal imaging device transit images

1. A method for implementation by at least one data processor for radiation therapy treatment verification, the method comprising:

acquiring treatment plan information from a radiation therapy system;

acquiring patient image data;

acquiring transit image data received from an electronic portal imaging device during radiation therapy;

dividing the treatment plan information into a plurality of segments;

determining predicted segment image data utilizing a predicted image calculation algorithm and at least the patient image data, and the treatment plan information;

determining a predicted integrated image through superposition of the predicted segment image data;

determining measured segment responses from the transit image data utilizing the predicted segment image data and the predicted integrated image;

converting the measured segment responses to measured segment doses; and

comparing a measured dose map comprising a sum of the measured segment doses to a planned dose map based on the treatment plan information to assess radiation treatment delivery.

2. The method of claim 1 , the comparing further comprising:

transmitting, to a recipient device, a difference between the measured dose map and the planned dose map.

3. The method of claim 1 , the converting comprising utilization of an effective field size calculator.

4. The method of claim 1 , the converting comprising utilization of a ray tracer algorithm.

5. The method of claim 2 , the comparing further comprising at least one of:

displaying, at an electronic display, a report comprising the difference; and

generating, at an electronic device, a warning based on the difference.

6. The method of claim 1 , the converting comprising:

accessing, from at least one database, a measurement of an output of a treatment beam, the patient image data, and a physical configuration of the radiation therapy system;

generating a conversion factor based on the accessed measurement, the patient image data, and the physical configuration corresponding to a segment; and

applying the conversion factor to the measured segment responses to generate the measured segment doses.

7. The method of claim 1 , wherein the patient image data comprises three-dimensional images of patient anatomy.

8. The method of claim 1 , wherein each of the plurality of segments correspond to a time window where the radiation treatment delivery of dose to a portion of a patient anatomy is substantially constant.

9. The method of claim 1 , the converting comprising:

executing a neural network to generate the predicted integrated image by weighting a predicted segment response contribution as part of an input layer of the neural network.

10. The method of claim 1 , wherein the comparison of the measured dose map to the planned dose map comprises the comparison of a first sum of the measured segment doses to a second sum of the desired doses.

11. The method of claim 1 , further comprising:

generating an electronic warning at a display device based on the comparing of the measured dose map to the planned dose map, when a dose is outside of a predetermined dose limit.

12. The method of claim 1 , the determining of the measured segment responses comprising:

extracting a predicted response contribution based on the predicted segment image data and the predicted integrated image; and

generating the measured segment response from the predicted response contribution and the transit data.

13. A computer program product comprising a non-transitory, machine-readable medium storing instructions which, when executed by at least one programmable processor, cause the at least one programmable processor to perform operations comprising:

acquiring treatment plan information from a radiation therapy system;

acquiring patient image data;

acquiring transit image data received from an electronic portal imaging device during radiation therapy;

dividing the treatment plan information into a plurality of segments; determining predicted segment image data utilizing a predicted image calculation algorithm and at least the patient image data, and the treatment plan information;

determining a predicted integrated image through superposition of the predicted segment image data;

determining measured segment responses from the transit image data utilizing the predicted segment image data and the predicted integrated image;

converting the measured segment responses to measured segment doses; and

comparing the measured segment doses to desired doses to assess radiation treatment delivery.

14. A system comprising:

a radiation therapy system comprising:

an electronic portal imaging device; and

a radiation source configured to generate a treatment beam that intersects the electronic portal imaging device;

at least one programmable processor; and

a non-transitory machine-readable medium storing instructions which, when executed by the at least one programmable processor, cause the at least one programmable processor to perform operations comprising:

acquiring treatment plan information from the radiation therapy system;

acquiring patient image data;

acquiring transit image data received from the electronic portal imaging device during radiation therapy;

dividing the treatment plan information into a plurality of segments;

determining predicted segment image data utilizing a predicted image calculation algorithm and at least the patient image data, and the treatment plan information;

determining a predicted integrated image through superposition of the predicted segment image data;

determining measured segment responses from the transit image data utilizing the predicted segment image data and the predicted integrated image;

converting the measured segment responses to measured segment doses; and

comparing the measured segment doses to desired doses to assess radiation treatment delivery.