System and methods for image segmentation using convolutional neural network

1. A computer-implemented method for segmenting a three-dimensional medical image, the method comprising:

receiving the three-dimensional medical image to be segmented;

creating a first stack of two-dimensional images from a first plane of the three-dimensional medical image;

segmenting, by a processor, the first stack of two-dimensional images using a first neural network model; and

determining, by the processor, a label map for the three-dimensional medical image by aggregating segmentation results of the first stack of two-dimensional images, the label map associating anatomic structure with elements of the three-dimensional medical image.

2. The method of claim 1 , further comprising:

creating a second stack of two-dimensional images from a second plane of the three-dimensional image; and

segmenting the second stack of two-dimensional images using a second neural network model.

3. The method of claim 2 , further comprising:

creating a third stack of two-dimensional images from a third plane of the three-dimensional image; and

segmenting the third stack of two-dimensional images using a third neural network model.

4. The method of claim 3 , further comprising determining the label map by fusing the aggregated segmentation results for the first plane, the second plane, and the third plane.

5. The method of claim 1 , further comprising:

creating a second stack of two-dimensional images from a second plane of the three-dimensional image;

combining the first stack of two-dimensional image and the second stack of two-dimensional images; and

segmenting the combined stack of two-dimensional images using the first neural network model.

6. The method of claim 1 , wherein a plane of the three-dimensional image is one of an axial plane, a sagittal plane, or a coronal plane.

7. The method of claim 1 , wherein the first stack of two-dimensional images is a stack of three-dimensional image patches, the central pixels of which substantially constitute an entire two-dimensional image.

8. The method of claim 1 , wherein the first neural network model comprises a deep convolutional neural network model.

9. The method of claim 1 , further comprising training the first neural network model using at least one three-dimensional training image.

10. A non-transitory computer-readable medium containing instructions that, when executable by at least one processor, cause the at least one processor to perform a method for segmenting a three-dimensional image, the method comprising:

receiving the three-dimensional medical image to be segmented;

creating a first stack of two-dimensional images from a first plane of the three-dimensional medical image;

segmenting the first stack of two-dimensional images using a first neural network model; and

determining a label map for the three-dimensional medical image by aggregating segmentation results of the first stack of two-dimensional images, the label map associating anatomic structure with elements of the three-dimensional medical image.

11. The non-transitory computer-readable medium of claim 10 , further comprising:

creating a second stack of two-dimensional images from a second plane of the three-dimensional image; and

segmenting the second stack of two-dimensional images using a second neural network model.

12. The non-transitory computer-readable medium of claim 11 , further comprising:

creating a third stack of two-dimensional images from a third plane of the three-dimensional image; and

segmenting the third stack of two-dimensional images using a third neural network model.

13. The non-transitory computer-readable medium of claim 12 , further comprising determining the label map by fusing the aggregated segmentation results for the first plane, the second plane, and the third plane.

14. The non-transitory computer-readable medium of claim 10 , further comprising

creating a second stack of two-dimensional images from a second plane of the three-dimensional image;

combining the first stack of two-dimensional images and the second stack of two-dimensional images; and

segmenting the combined stack of two-dimensional images using the first neural network model.

15. The non-transitory computer-readable medium of claim 10 , wherein a plane of the three-dimensional image is one of an axial plane, a sagittal plane, or a coronal plane.

16. The non-transitory computer-readable medium of claim 10 , wherein the first stack of two-dimensional images is a stack of three-dimensional image patches, the central pixels of which substantially constitute an entire two-dimensional image.

17. The non-transitory computer-readable medium of claim 10 , wherein the first neural network model comprises a deep convolutional neural network model.

18. The non-transitory computer-readable medium of claim 10 , further comprising training the first neural network model using at least one three-dimensional training image.

19. An image-guided radio therapy system, the system comprising:

an imaging device for obtaining a three-dimensional image to be segmented;

at least one storage device configured to store the three-dimensional image; and

an image processor configured to:

receive the three-dimensional medical image;

create a first stack of two-dimensional images from a first plane of the three-dimensional medical image;

segment the first stack of two-dimensional images using a first neural network model; and

determine a label map for the three-dimensional medical image by aggregating segmentation results of the first stack of two-dimensional images, the label map associating anatomic structure with elements of the three-dimensional medical image.

20. The image-guided radio therapy system of claim 10 , wherein the first neural network model comprises a deep convolutional neural network model.