Systems and methods for anatomic structure segmentation in image analysis
Systems and methods are disclosed for anatomic structure segmentation in image analysis, using a computer system. One method includes: receiving an annotation and a plurality of keypoints for an anatomic structure in one or more images; computing distances from the plurality of keypoints to a boundary of the anatomic structure; training a model, using data in the one or more images and the computed distances, for predicting a boundary in the anatomic structure in an image of a patient's anatomy; receiving the image of the patient's anatomy including the anatomic structure; estimating a segmentation boundary in the anatomic structure in the image of the patient's anatomy; and predicting, using the trained model, a boundary location in the anatomic structure in the image of the patient's anatomy by generating a regression of distances from keypoints in the anatomic structure in the image of the patient's anatomy to the estimated boundary.
1. A computer-implemented method of machine-learning based anatomic structure segmentation in image analysis, the method comprising:
receiving image data of an anatomic structure of a patient;
obtaining an annotation of the anatomic structure;
determining, based on the annotation, one or more keypoints;
determining a respective distance between each keypoint and a boundary of the anatomic structure;
determining respective intensities along a respective ray associated with each keypoint;
training a patient-specific Convolutional Neural Network (CNN), based on the respective distance and the respective intensities of each keypoint, to predict sub-pixel or sub-voxel locations of the boundary of the anatomic structure; and
generating, using the trained patient-specific CNN a sub-pixel or sub-voxel boundary of the anatomic structure.
2. The computer-implemented method of claim 1 , wherein the generated sub-pixel or sub-voxel boundary of the anatomic structure is a continuous boundary.
3. The computer-implemented method of claim 1 , wherein the image data includes a plurality of successive frames that are orthogonal to a centerline of the anatomic structure.
4. The computer-implemented method of claim 3 , wherein generating the sub-pixel or sub-voxel boundary of the anatomic structure includes generating a respective boundary portion for each frame of the plurality of successive frames.
5. The computer-implemented method of claim 4 , wherein generating the sub-pixel or sub-voxel boundary of the anatomic structure further includes generating a continuous three-dimensional surface of the anatomic structure based on the respective boundary portions.
6. The computer-implemented method of claim 3 , wherein the annotation includes an identification, in each frame of the plurality of successive frames, of the centerline of the anatomic structure.
7. The computer-implemented method of claim 1 , wherein the anatomic structure includes a blood vessel.
8. A system for performing machine-learning based anatomic structure segmentation in image analysis, comprising:
at least one memory storing instructions and a Convolutional Neural Network (CNN); and
at least one processor operatively connected to the at least one memory and configured to execute the instructions to perform operations, including:
receiving image data of an anatomic structure of a patient;
obtaining an annotation of the anatomic structure;
determining, based on the annotation, one or more keypoints;
determining a respective distance between each keypoint and a boundary of the anatomic structure;
determining respective intensities along a respective ray associated with each keypoint;
training the CNN, based on the respective distance and the respective intensities of each keypoint, to be patient-specific and to predict sub-pixel or sub-voxel locations of the boundary of the anatomic structure; and
generating, using the trained patient-specific CNN a sub-pixel or sub-voxel boundary of the anatomic structure.
9. The system of claim 8 , wherein the generated sub-pixel or sub-voxel boundary of the anatomic structure is a continuous boundary.
10. The system of claim 8 , wherein the image data includes a plurality of successive frames that are orthogonal to a centerline of the anatomic structure.
11. The system of claim 10 , wherein generating the sub-pixel or sub-voxel boundary of the anatomic structure includes generating a respective boundary portion for each frame of the plurality of successive frames.
12. The system of claim 11 , wherein generating the sub-pixel or sub-voxel boundary of the anatomic structure further includes generating a continuous three-dimensional surface of the anatomic structure based on the respective boundary portions.
13. The system of claim 10 , wherein the annotation includes an identification, in each frame of the plurality of successive frames, of the centerline of the anatomic structure.
14. The system of claim 8 , wherein the anatomic structure includes a blood vessel.
15. A non-transitory computer-readable medium comprising instructions for machine-learning based anatomic structure segmentation in image analysis, the instructions executable by one or more processors to perform operations, including:
receiving image data of an anatomic structure of a patient;
obtaining an annotation of the anatomic structure;
determining, based on the annotation, one or more keypoints;
determining a respective distance between each keypoint and a boundary of the anatomic structure;
determining respective intensities along a respective ray associated with each keypoint;
training a patient-specific Convolutional Neural Network (CNN), based on the respective distance and the respective intensities of each keypoint, to predict sub-pixel or sub-voxel locations of the boundary of the anatomic structure; and
generating, using the trained patient-specific CNN a sub-pixel or sub-voxel boundary of the anatomic structure.
16. The non-transitory computer-readable medium of claim 15 , wherein the generated sub-pixel or sub-voxel boundary of the anatomic structure is a continuous boundary.
17. The non-transitory computer-readable medium of claim 15 , wherein the image data includes a plurality of successive frames that are orthogonal to a centerline of the anatomic structure.
18. The non-transitory computer-readable medium of claim 17 , wherein generating the sub-pixel or sub-voxel boundary of the anatomic structure includes:
generating a respective boundary portion for each frame of the plurality of successive frames; and
generating a continuous three-dimensional surface of the anatomic structure based on the respective boundary portions.
19. The non-transitory computer-readable medium of claim 17 , wherein the annotation includes an identification, in each frame of the plurality of successive frames, of the centerline of the anatomic structure.
20. The non-transitory computer-readable medium of claim 15 , wherein the anatomic structure includes a blood vessel.