Multi-rigid registration of magnetic navigation to a computed tomography volume

1. A system for updating a 3D model of a luminal network, the system comprising:

a computing device including a processor and a memory storing instructions which, when executed by the processor, cause the computing device to:

access a 3D model of a luminal network inside a patient based on images of the luminal network;

select a plurality of reference points within the 3D model of the luminal network;

obtain a plurality of survey points within the luminal network;

divide the 3D model of the luminal network into different regions of a lung;

assign a plurality of weights to the different regions of the lung;

determine an alignment of the plurality of reference points with the plurality of survey points based on the plurality of weights; and

generate a registration based on the alignment.

2. The system according to claim 1 , wherein the registration enables conversion of the plurality of survey points within the luminal network to points within the 3D model of the luminal network.

3. The system according to claim 1 , wherein the instructions, when executed by the processor, further cause the computing device to:

determine which region of the different regions of the lung in which each of the plurality of survey points is obtained; and

assign a corresponding weight to each of the plurality of survey points based on the determined region in which each of the plurality of survey points is obtained.

4. The system according to claim 3 , wherein the instructions, when executed by the processor, further cause the computing device to:

minimize a divergence between the plurality of reference points and the plurality of survey points based on the corresponding weight assigned to each of the plurality of survey points.

5. The system according to claim 1 , wherein the instructions, when executed by the processor, further cause the computing device to:

for each particular region of the different regions of the lung:

assign a particular plurality of weights that favor the particular region;

minimize a divergence between the plurality of reference points and the plurality of survey points based on the particular plurality of weights, the minimized divergence corresponding to a particular alignment; and

generate a particular registration based on the particular alignment, the particular registration being associated with the particular region and enabling conversion of locations within the luminal network to locations within the 3D model of the luminal network.

6. The system according to claim 1 , wherein the different regions of the lung include at least one transition region.

7. The system according to claim 6 , wherein the different regions of the lung include a right lung region, a central region, and a left lung region, and the at least one transition region includes a left-central region and a right-central region.

8. A system for registering a patient's lung to a 3D model of the lung, the system comprising:

a computing device including a processor and a memory storing instructions which, when executed by the processor, cause the computing device to:

access a 3D model of a patient's lung based on images of the lung;

select a plurality of reference points within the 3D model;

obtain a plurality of survey points within the lung;

divide the 3D model into different regions of the lung;

assign a plurality of weights to the different regions of the lung;

determine an alignment of the plurality of reference points with the plurality of survey points based on the plurality of weights; and

generate a registration based on the alignment.

9. The system according to claim 8 , wherein the instructions, when executed by the processor, further cause the computing device to:

determine which region of the different regions of the lung in which each of the plurality of survey points is obtained; and

assign a corresponding weight to each of the plurality of survey points based on the determined region in which each of the plurality of survey points is obtained.

10. The system according to claim 9 , wherein the instructions, when executed by the processor, further cause the computing device to:

minimize a divergence between the plurality of reference points and the plurality of survey points based on the corresponding weight assigned to each of the plurality of survey points.

11. The system according to claim 8 , wherein the instructions, when executed by the processor, further cause the computing device to:

for each particular region of the different regions of the lung:

assign a particular plurality of weights that favor the particular region;

minimize a divergence between the plurality of reference points and the plurality of survey points based on the particular plurality of weights, the minimized divergence corresponding to a particular alignment; and

generate a particular registration based on the particular alignment, the particular registration being associated with the particular region and enabling conversion of locations within the luminal network to locations within the 3D model of the luminal network.

12. A method of registering a luminal network to a 3D model of the luminal network, the method comprising:

selecting a plurality of reference points within a 3D model of a luminal network;

obtaining a plurality of survey points within the luminal network;

dividing the 3D model of the luminal network into different regions of a lung;

assigning a plurality of weights to the different regions of the lung;

determining an alignment of the plurality of reference points with the plurality of survey points based on the plurality of weights; and

generating a registration based on the alignment.

13. The method according to claim 12 , wherein the luminal network is an airway of a patient.

14. The method according to claim 13 , wherein the 3D model is a model of the airway of the patient.

15. The method according to claim 12 , further comprising:

determining which region of the different regions of the lung in which each of the plurality of survey points is obtained; and

assigning a corresponding weight to each of the plurality of survey points based on the determined region in which each of the plurality of survey points is obtained.

16. The method according to claim 15 , wherein determining an alignment of the plurality of reference points with the plurality of survey points includes minimizing a divergence between the plurality of reference points and the plurality of survey points based on the corresponding weight assigned to each of the plurality of survey points.

17. The method according to claim 12 , further comprising:

for each particular region of the different regions of the lung:

assigning a particular plurality of weights that favor the particular region;

minimizing a divergence between the plurality of reference points and the plurality of survey points based on the particular plurality of weights, the minimized divergence corresponding to a particular alignment; and

generating a particular registration based on the particular alignment, the particular registration being associated with the particular region and enabling conversion of locations within the luminal network to locations within the 3D model of the luminal network.

18. The method according to claim 12 , wherein the different regions of the lung include at least one transition region.

19. The method according to claim 18 , wherein the different regions of the lung include a right lung region, a central region, and a left lung region, and the at least one transition region includes a left-central region and a right-central region.

20. The method according to claim 12 , wherein the 3D model is based on computed tomography (CT) images of the luminal network.