Systems and methods for radiotherapy planning

1 . A system for radiotherapy planning, comprising:

at least one storage device including a set of instructions; and

at least one processor configured to communicate with the at least one storage device, wherein when executing the set of instructions, the at least one processor is configured to perform operations including:

obtaining planning information relating to at least one beam to be delivered to a subject in a treatment of the subject;

generating, based on the planning information, an input of a fluence map generation model; and

for each of the at least one beam, generating, based on the input of the fluence map generation model, at least one deliverable fluence map relating to a plurality of segments of each of the at least one beam.

2 . The system of claim 1 , wherein the planning information comprises:

segmentation information of one or more regions of interest (ROIs) of the subject to which the at least one beam is to be delivered; and

a beam angle of each of the at least one beam.

3 . The system of claim 2 , wherein the planning information further comprises a reference image of the subject.

4 . The system of claim 1 , wherein the planning information comprises an optimized fluence map of each of the at least one beam.

5 . The system of claim 4 , wherein the obtaining planning information relating to at least one beam to be delivered to a subject in a treatment of the subject comprises:

for each of the at least one beam,

obtaining a preliminary fluence map of each of the at least one beam; and

generating the optimized fluence map of each of the at least one beam by optimizing the preliminary fluence map.

6 . The system of claim 1 , wherein the at least one processor is further configured to generate the fluence map generation model according to a training process including:

obtaining at least one training sample, each of which includes sample planning information and at least one ground truth deliverable fluence map, the sample planning information relating to at least one sample beam to be delivered to a sample subject, and the at least one ground truth deliverable fluence map relating to at least one sample segment of each of the at least one sample beam; and

generating the fluence map generation model by training a preliminary model using the at least one training sample.

7 . The system of claim 6 , wherein the at least one processor is further configured to obtain each of the at least one training sample by:

for each of the at least one sample beam corresponding to each of the at least one training sample,

obtaining a sample preliminary fluence map of each of the at least one sample beam;

generating a sample optimized fluence map of each of the at least one sample beam by optimizing the sample preliminary fluence map;

converting the sample optimized fluence map into at least one sample preliminary segment fluence map of the at least one sample segment of each of the at least one sample beam; and

generating, based on the at least one sample preliminary segment fluence map, the at least one ground truth deliverable fluence map relating to the at least one sample segment of each of the at least one sample beam.

8 . The system of claim 1 , wherein the fluence map generation model includes at least one of a convolutional neural network (CNN) or a generative adversarial network (GAN).

9 . The system of claim 1 , wherein the at least one deliverable fluence map comprises at least one of:

a composite fluence map of the plurality of segments; or

a plurality of segment fluence maps, each of which corresponds to one of the plurality of segments.

10 . A method implemented on a computing device having at least one processor and at least one computer-readable storage medium for radiotherapy planning, the method comprising:

obtaining planning information relating to at least one beam to be delivered to a subject in a treatment of the subject;

generating, based on the planning information, an input of a fluence map generation model; and

for each of the at least one beam, generating, based on the input of the fluence map generation model, at least one deliverable fluence map relating to a plurality of segments of each of the at least one beam.

11 . The method of claim 10 , wherein the planning information comprises:

segmentation information of one or more regions of interest (ROIs) of the subject to which the at least one beam is to be delivered; and

a beam angle of each of the at least one beam.

12 . The method of claim 11 , wherein the planning information further comprises a reference image of the subject.

13 . The method of claim 10 , wherein the planning information comprises an optimized fluence map of each of the at least one beam.

14 . The method of claim 13 , wherein the obtaining planning information relating to at least one beam to be delivered to a subject in a treatment of the subject comprises:

for each of the at least one beam,

obtaining a preliminary fluence map of each of the at least one beam; and

generating the optimized fluence map of each of the at least one beam by optimizing the preliminary fluence map.

15 . The method of claim 10 , wherein the fluence map generation model is generated according to a training process including:

obtaining at least one training sample, each of which includes sample planning information and at least one ground truth deliverable fluence map, the sample planning information relating to at least one sample beam to be delivered to a sample subject, and the at least one ground truth deliverable fluence map relating to at least one sample segment of each of the at least one sample beam; and

generating the fluence map generation model by training a preliminary model using the at least one training sample.

16 . The method of claim 15 , wherein each of the at least one training sample is obtained by:

for each of the at least one sample beam corresponding to each of the at least one training sample,

obtaining a sample preliminary fluence map of each of the at least one sample beam;

generating a sample optimized fluence map of each of the at least one sample beam by optimizing the sample preliminary fluence map;

converting the sample optimized fluence map into at least one sample preliminary segment fluence map of the at least one sample segment of each of the at least one sample beam; and

generating, based on the at least one sample preliminary segment fluence map, the at least one ground truth deliverable fluence map relating to the at least one sample segment of each of the at least one sample beam.

17 . The method of claim 10 , wherein the fluence map generation model includes at least one of a convolutional neural network (CNN) or a generative adversarial network (GAN).

18 . The method of claim 10 , wherein the at least one deliverable fluence map comprises at least one of:

a composite fluence map of the plurality of segments; or

a plurality of segment fluence maps, each of which corresponds to one of the plurality of segments.

19 . A non-transitory computer readable medium, comprising a set of instructions for radiotherapy planning, wherein when executed by at least one processor, the set of instructions direct the at least one processor to effectuate a method, the method comprising:

obtaining planning information relating to at least one beam to be delivered to a subject in a treatment of the subject;

generating, based on the planning information, an input of a fluence map generation model; and

for each of the at least one beam, generating, based on the input of the fluence map generation model, at least one deliverable fluence map relating to a plurality of segments of each of the at least one beam.

20 . The non-transitory computer readable medium of claim 19 , wherein the at least one deliverable fluence map comprises at least one of:

a composite fluence map of the plurality of segments; or

a plurality of segment fluence maps, each of which corresponds to one of the plurality of segments.