Motion correction of angiography images for 3D reconstruction of coronary arteries

1. A method comprising:

detecting one or more landmarks in a first medical image of an anatomical structure and a second medical image of the anatomical structure;

generating a first tree of the anatomical structure from the first medical image based on the one or more landmarks detected in the first medical image and a second tree of the anatomical structure from the second medical image based on the one or more landmarks detected in the second medical image;

mapping the one or more landmarks detected in the first medical image to the one or more landmarks detected in the second medical image based on the first tree and the second tree; and

computing a transformation to align the first medical image and the second medical image based on the mapping;

wherein the first tree comprises the one or more landmarks detected in the first medical image, the second tree comprises the one or more landmarks detected in the second medical image, and mapping the one or more landmarks detected in the first medical image to the one or more landmarks detected in the second medical image based on the first tree and the second tree comprises:

for each respective landmark of the one or more landmarks in the first tree:

computing a set of candidate mappings between the respective landmark and the one or more landmarks in the second tree;

filtering the set of candidate mappings to remove candidate mappings where a descendant of the respective landmark is not mapped to a descendant of a particular landmark of the candidate mapping in the second tree; and

selecting a candidate mapping from the filtered set of candidate mappings based on a distance associated with each candidate mapping.

2. The method of claim 1 , wherein the set of candidate mappings comprises all possible mappings between the respective landmark and the one or more landmarks in the second tree.

3. The method of claim 1 , wherein computing a transformation to align the first medical image and the second medical image based on the mapping comprises:

projecting the one or more landmarks detected in the first medical image to respective epipolar lines of the one or more landmarks in the second medical image;

determining a transformation of the second medical image to move the one or more landmarks in the second medical image towards a closest point of its respective epipolar line;

applying the transformation to the second medical image to move the one or more landmarks in the second medical image; and

repeating the projecting, the determining, and the applying until a stopping condition is satisfied.

4. The method of claim 1 , wherein generating a first tree of the anatomical structure from the first medical image based on the one or more landmarks detected in the first medical image and a second tree of the anatomical structure from the second medical image based on the one or more landmarks detected in the second medical image comprises:

generating the first tree to include the one or more landmarks detected in the first medical image between a first start point and a first end point selected by a user; and

generating the second tree to include the one or more landmarks detected in the second medical image between a second start point and a second end point selected by the user.

5. The method of claim 1 , wherein the anatomical structure is a coronary artery.

6. The method of claim 5 , wherein detecting one or more landmarks in a first medical image of an anatomical structure and a second medical image of the anatomical structure comprises:

detecting one or more bifurcations of the coronary artery in the first medical image and the second medical image.

7. The method of claim 1 , wherein the first medical image and the second medical image are different views of the anatomical structure.

8. The method of claim 1 , wherein the first medical image and the second medical image are x-ray angiography images.

9. The method of claim 1 , further comprising:

detecting the one or more landmarks in one or more additional medical images of the anatomical structure; and

generating a tree of the anatomical structure for each respective image of the one or more additional medical images based the one or more landmarks detected in the respective image;

wherein mapping the one or more landmarks detected in the first medical image to the one or more landmarks detected in the second medical image based on the first tree and the second tree comprises:

mapping the one or more landmarks detected in the first medical image with the one or more landmarks detected in the second medical image and the one or more landmarks detected in the one or more additional medical images; and

wherein computing a transformation to align the first medical image and the second medical image based on the mapping comprises:

computing the transformation to align the first medical image, the second medical image, and the one or more additional medical images based on the mapping.

10. An apparatus, comprising:

means for detecting one or more landmarks in a first medical image of an anatomical structure and a second medical image of the anatomical structure;

means for generating a first tree of the anatomical structure from the first medical image based on the one or more landmarks detected in the first medical image and a second tree of the anatomical structure from the second medical image based on the one or more landmarks detected in the second medical image;

means for mapping the one or more landmarks detected in the first medical image to the one or more landmarks detected in the second medical image based on the first tree and the second tree; and

means for computing a transformation to align the first medical image and the second medical image based on the mapping;

wherein the first tree comprises the one or more landmarks detected in the first medical image, the second tree comprises the one or more landmarks detected in the second medical image, and the means for mapping the one or more landmarks detected in the first medical image to the one or more landmarks detected in the second medical image based on the first tree and the second tree comprises:

means for computing a set of candidate mappings for each respective landmark of the one or more landmarks in the first tree, each comprising candidate mappings between the respective landmark and the one or more landmarks in the second tree;

means for filtering the set of candidate mappings for each respective landmark in the first tree to remove candidate mappings where a descendant of the respective landmark is not mapped to a descendant of a particular landmark of the candidate mapping in the second tree; and

means for selecting a candidate mapping from the filtered set of candidate mappings for each respective landmark in the first tree based on a distance associated with each candidate mapping.

11. The apparatus of claim 10 , wherein the set of candidate mappings comprises all possible mappings between the respective landmark and the one or more landmarks in the second tree.

12. The apparatus of claim 10 , wherein the means for computing a transformation to align the first medical image and the second medical image based on the mapping comprises:

means for projecting the one or more landmarks detected in the first medical image to respective epipolar lines of the one or more landmarks in the second medical image;

means for determining a transformation of the second medical image to move the one or more landmarks in the second medical image towards a closest point of its respective epipolar line;

means for applying the transformation to the second medical image to move the one or more landmarks in the second medical image; and

means for repeating the projecting, the determining, and the applying until a stopping condition is satisfied.

13. The apparatus of claim 10 , wherein the means for generating a first tree of the anatomical structure from the first medical image based on the one or more landmarks detected in the first medical image and a second tree of the anatomical structure from the second medical image based on the one or more landmarks detected in the second medical image comprises:

means for generating the first tree to include the one or more landmarks detected in the first medical image between a first start point and a first end point selected by a user; and

means for generating the second tree to include the one or more landmarks detected in the second medical image between a second start point and a second end point selected by the user.

14. A non-transitory computer readable medium storing computer program instructions, the computer program instructions when executed by a processor cause the processor to perform operations comprising:

detecting one or more landmarks in a first medical image of an anatomical structure and a second medical image of the anatomical structure;

generating a first tree of the anatomical structure from the first medical image based on the one or more landmarks detected in the first medical image and a second tree of the anatomical structure from the second medical image based on the one or more landmarks detected in the second medical image;

mapping the one or more landmarks detected in the first medical image to the one or more landmarks detected in the second medical image based on the first tree and the second tree; and

computing a transformation to align the first medical image and the second medical image based on the mapping;

wherein the first tree comprises the one or more landmarks detected in the first medical image, the second tree comprises the one or more landmarks detected in the second medical image, and mapping the one or more landmarks detected in the first medical image to the one or more landmarks detected in the second medical image based on the first tree and the second tree comprises:

for each respective landmark of the one or more landmarks in the first tree:

computing a set of candidate mappings between the respective landmark and the one or more landmarks in the second tree;

filtering the set of candidate mappings to remove candidate mappings where a descendant of the respective landmark is not mapped to a descendant of a particular landmark of the candidate mapping in the second tree; and

selecting a candidate mapping from the filtered set of candidate mappings based on a distance associated with each candidate mapping.

15. The non-transitory computer readable medium of claim 14 , wherein computing a transformation to align the first medical image and the second medical image based on the mapping comprises:

projecting the one or more landmarks detected in the first medical image to respective epipolar lines of the one or more landmarks in the second medical image;

determining a transformation of the second medical image to move the one or more landmarks in the second medical image towards a closest point of its respective epipolar line;

applying the transformation to the second medical image to move the one or more landmarks in the second medical image; and

repeating the projecting, the determining, and the applying until a stopping condition is satisfied.

16. The non-transitory computer readable medium of claim 15 , wherein detecting one or more landmarks in a first medical image of an anatomical structure and a second medical image of the anatomical structure comprises:

detecting one or more bifurcations of a coronary artery in the first medical image and the second medical image.

17. The non-transitory computer readable medium of claim 14 , the operations further comprising:

detecting the one or more landmarks in one or more additional medical images of the anatomical structure; and

generating a tree of the anatomical structure for each respective image of the one or more additional medical images based the one or more landmarks detected in the respective image;

wherein mapping the one or more landmarks detected in the first medical image to the one or more landmarks detected in the second medical image based on the first tree and the second tree comprises:

mapping the one or more landmarks detected in the first medical image with the one or more landmarks detected in the second medical image and the one or more landmarks detected in the one or more additional medical images; and

wherein computing a transformation to align the first medical image and the second medical image based on the mapping comprises:

computing the transformation to align the first medical image, the second medical image, and the one or more additional medical images based on the mapping.