Image reliability determination for instrument localization

1. A system comprising:

one or more processors configured to execute instructions to cause the system to:

access a plurality of images generated by one or more imaging devices of an endoscope when the endoscope is disposed within anatomy of a patient;

for each of the plurality of images, determine a value for each of one or more image reliability metrics; and

determine a position of the endoscope within the anatomy of the patient based at least in part on the one or more image reliability metrics of each of the plurality of images.

2. The system of claim 1 , wherein the one or more processors are further configured to:

determine that a first image of the plurality of images is reliable based at least in part on the values of the one or more image reliability metrics associated with the first image;

determine that a second image of the plurality of images is unreliable based at least in part on the values of the one or more image reliability metrics associated with the second image;

in response to the determination that the second image is unreliable, automatically discard the second image; and

in response to the determination that the first image is reliable, utilize the first image for said determining the position of the endoscope.

3. The system of claim 1 , wherein the one or more image reliability metrics comprise:

blurness;

specularness; and

featureness.

4. The system of claim 3 , wherein the instructions further cause the system to:

determine a weighting factor for each of blurness, specularness, and featureness; and

determine a composite metric for each of the plurality of images, the composite metric being based on:

the values for blurness, specularness, and featureness for the respective image of the plurality of images; and

the weighting factors for blurness, specularness, and featureness.

5. The system of claim 1 , wherein the instructions further cause the system to:

determine a weighting factor for each of a plurality of the one or more image reliability metrics; and

determine a composite metric for each of the plurality of images, the composite metric being based on:

the values for each of the plurality of the one or more image reliability metrics for the respective image of the plurality of images; and

the weighting factors for each of the plurality of the one or more image reliability metrics.

6. The system of claim 5 , wherein the composite metric is based on a linear combination of the products of the value and the weighting factor of each of the plurality of the one or more image reliability metrics.

7. The system of claim 5 , wherein the instructions further cause the system to:

determine, for each of the plurality of images, whether the composite metric associated with the respective image meets a predetermined threshold.

8. The system of claim 7 , wherein said determining the position of the endoscope comprises:

utilizing, for endoscope position calculation, each image of the plurality of images associated with a composite metric that meets the predetermined threshold; and

not utilizing, for endoscope position calculation, each image of the plurality of images that is associated with a composite metric that does not meet the predetermined threshold.

9. The system of claim 5 , wherein said determining the position of the endoscope comprises:

labeling as reliable each image of the plurality of images associated with a composite metric that meets the predetermined threshold; and

labeling as unreliable each image of the plurality of images that is associated with a composite metric that does not meet the predetermined threshold.

10. The system of claim 1 , wherein the instructions further cause the system to determine a threshold value for each of the one or more image reliability metrics.

11. The system of claim 1 , wherein said determining the position of the endoscope within the anatomy of the patient is based at least in part on the one or more image reliability metrics of each of the plurality of images in that the one or more image reliability metrics of each of the plurality of images are relied upon to determine which of the plurality of images to utilize for said determining the position of the endoscope.

12. The system of claim 1 , wherein the one or more processors are embodied in at least one of a control tower or a robotic cart of the system.

13. A system comprising:

one or more processors configured to execute instructions to cause the system to:

access preoperative model data relating to a luminal network of a patient;

generate a virtual model of the luminal network based at least in part on the preoperative model data;

identify one or more features in the virtual model;

access a plurality of images captured by an endo scope camera when the endoscope is disposed in the luminal network;

identify one or more of the plurality of images as reliable images based on one or more image reliability metrics;

identify one or more features in the one or more reliable images, the one or more features relating to the identified one or more virtual features in the virtual model; and

determine a position of the endoscope based on a comparison of the one or more features with the one or more virtual features.

14. The system of claim 13 , wherein the preoperative model data comprises computed tomography (CT) data.

15. The system of claim 13 , wherein the one or more virtual features and the one or more features are indicative of anatomical lumen position.

16. The system of claim 13 , wherein said identifying the one or more of the plurality of images as reliable images is based on a machine learning model of images that meet one or more reliability thresholds.

17. The system of claim 13 , wherein said identifying the one or more of the plurality of images as reliable images is based on a machine learning model of images that fail one or more reliability thresholds.

18. The system of claim 13 , wherein the preoperative model data comprises machine learning model data.

19. The system of claim 13 , wherein the instructions further cause the system to determine a plurality of image reliability metrics for each of the plurality of images.

20. The system of claim 19 , wherein said identifying the one or more reliable images involves determining that, for each of the one or more reliable images, a predetermined target number of the plurality of image reliability metrics for the respective image meet a respective predetermined threshold.