System and method for identifying target regions prior to organs at risk segmentation

1. A method for generating a three dimensional (3D) bounding box of a region of interest (ROI) of a patient, comprising:

receiving, by a device, a two dimensional (2D) maximum intensity projection (MIP) image that is a first view of the patient;

receiving, by the device, a 2D MIP image that is a second view of the patient;

detecting, by the device, a first 2D bounding box of the ROI of the patient using the 2D MIP image that is the first view of the patient;

detecting, by the device, a second 2D bounding box of the ROI of the patient using the 2D MIP image that is the second view of the patient;

receiving, by the device, a 3D MIP image of the patient;

generating, by the device, the 3D bounding box of the ROI of the patient using only the first 2D bounding box, the second 2D bounding box, and the 3D MIP image of the patient; and

providing, by the device, the 3D MIP image including the 3D bounding box of the ROI of the patient.

2. The method of claim 1 , further comprising:

removing, by the device, data of the 3D MIP image that is not within the 3D bounding box; and

providing, by the device, the 3D MIP image from which the data has been removed.

3. The method of claim 1 , further comprising:

inputting, by the device, the 2D MIP image that is the first view of the patient, and the 2D MIP image that is the second view of the patient into a region based convolutional neural network (RCNN); and

detecting, by the device, the first 2D bounding box and the second 2D bounding box based on an output of the RCNN.

4. The method of claim 1 , further comprising:

identifying, by the device, a first minimum horizontal value, a first maximum horizontal value, a first minimum vertical value, and a first maximum vertical value of the first 2D bounding box of the ROI.

5. The method of claim 4 , further comprising:

identifying, by the device, a second minimum horizontal value and a second maximum horizontal value of the second 2D bounding box of the ROI.

6. The method of claim 5 , further comprising:

generating, by the device, the 3D bounding box of the ROI using the first minimum horizontal value, the first maximum horizontal value, the first minimum vertical value, and the first maximum vertical value of the first 2D bounding box of the ROI, and using the second minimum horizontal value and the second maximum horizontal value of the second 2D bounding box of the ROI.

7. The method of claim 1 , wherein the ROI is a head of the patient.

8. A device for generating a three dimensional (3D) bounding box of a region of interest (ROI) of a patient, comprising:

at least one memory configured to store program code;

at least one processor configured to read the program code and operate as instructed by the program code, the program code including:

receiving code that is configured to cause the at least one processor to receive a two dimensional (2D) maximum intensity projection (MIP) image that is a first view of the patient, receive a 2D MIP image that is a second view of the patient, and receive a 3D MIP image of the patient;

detecting code that is configured to cause the at least one processor to detect a first 2D bounding box of the ROI of the patient using the 2D MIP image that is the first view of the patient, and detect a second 2D bounding box of the ROI of the patient using the 2D MIP image that is the second view of the patient;

generating code that is configured to cause the at least one processor to generate the 3D bounding box of the ROI of the patient using only the first 2D bounding box, the second 2D bounding box, and the 3D MIP image of the patient; and

providing code that is configured to cause the at least one processor to provide the 3D MIP image including the 3D bounding box of the ROI of the patient.

9. The device of claim 8 , further comprising:

removing code that is configured to cause the at least one processor to remove data of the 3D MIP image that is not within the 3D bounding box, and

wherein the providing code is further configured to cause the at least one processor to provide the 3D MIP image from which the data has been removed.

10. The device of claim 8 , further comprising:

inputting code that is configured to cause the at least one processor to input the 2D MIP image that is the first view of the patient, and the 2D MIP image that is the second view of the patient into a region based convolutional neural network (RCNN), and

wherein the detecting code is further configured to cause the at least one processor to detect the first 2D bounding box and the second 2D bounding box based on an output of the RCNN.

11. The device of claim 8 , further comprising:

identifying code that is further configured to cause the at least one processor to identify a first minimum horizontal value, a first maximum horizontal value, a first minimum vertical value, and a first maximum vertical value of the first 2D bounding box of the ROI.

12. The device of claim 11 , wherein the identifying code is further configured to cause the at least one processor to identify a second minimum horizontal value and a second maximum horizontal value of the second 2D bounding box of the ROI.

13. The device of claim 12 , wherein the generating code is further configured to cause the at least one processor to generate the 3D bounding box of the ROI using the first minimum horizontal value, the first maximum horizontal value, the first minimum vertical value, and the first maximum vertical value of the first 2D bounding box of the ROI, and using the second minimum horizontal value and the second maximum horizontal value of the second 2D bounding box of the ROI.

14. The device of claim 8 , wherein the ROI is a head of the patient.

15. A non-transitory computer-readable medium storing instructions, the instructions comprising: one or more instructions that, when executed by one or more processors of a device for generating a three dimensional (3D) bounding box of a region of interest (ROI) of a patient, cause the one or more processors to:

receive a two dimensional (2D) maximum intensity projection (MIP) image that is a first view of the patient;

receive a 2D MIP image that is a second view of the patient;

detect a first 2D bounding box of the ROI of the patient using the 2D MIP image that is the first view of the patient;

detect a second 2D bounding box of the ROI of the patient using the 2D MIP image that is the second view of the patient;

receive a 3D MIP image of the patient;

generate the 3D bounding box of the ROI of the patient using only the first 2D bounding box, the second 2D bounding box, and the 3D MIP image of the patient; and

provide the 3D MIP image including the 3D bounding box of the ROI of the patient.

16. The non-transitory computer-readable medium of claim 15 , wherein the one or more instructions cause the one or more processors to:

remove data of the 3D MIP image that is not within the 3D bounding box; and

provide the 3D MIP image from which the data has been removed.

17. The non-transitory computer-readable medium of claim 15 , wherein the one or more instructions cause the one or more processors to:

input the 2D MIP image that is the first view of the patient, and the 2D MIP image that is the second view of the patient into a region based convolutional neural network (RCNN); and

detect the first 2D bounding box and the second 2D bounding box based on an output of the RCNN.

18. The non-transitory computer-readable medium of claim 15 , wherein the one or more instructions cause the one or more processors to:

identify a first minimum horizontal value, a first maximum horizontal value, a first minimum vertical value, and a first maximum vertical value of the first 2D bounding box of the ROI.

19. The non-transitory computer-readable medium of claim 18 , wherein the one or more instructions cause the one or more processors to:

identify a second minimum horizontal value and a second maximum horizontal value of the second 2D bounding box of the ROI.

20. The non-transitory computer-readable medium of claim 19 , wherein the one or more instructions cause the one or more processors to:

generate the 3D bounding box of the ROI using the first minimum horizontal value, the first maximum horizontal value, the first minimum vertical value, and the first maximum vertical value of the first 2D bounding box of the ROI, and using the second minimum horizontal value and the second maximum horizontal value of the second 2D bounding box of the ROI.