Weight-based registration of location sensors

Abstract

Provided are systems and methods for weight-based registration of location sensors. In one aspect, a system includes an instrument and a processor configured to provide a first set of commands to drive the instrument along a first branch of the luminal network, the first branch being outside a path to a target within a model. The processor is also configured to track a set of one or more registration parameters during the driving of the instrument along the first branch and determine that the set of registration parameters satisfy a registration criterion. The processor is further configured to determine a registration between a location sensor coordinate system and a model coordinate system based on location data received from a set of location sensors during the driving of the instrument along the first branch and a second branch.

What is claimed is: 
     
         1 . A method of determining a registration between a sensor coordinate system and a model coordinate system, the method comprising:
 generating a set of sensor location points in the sensor coordinate system based on location data generated by location sensors of an instrument, the location data indicative of a position of a distal end of the instrument in the sensor coordinate system;   determining a set of model location points in the model coordinate system,   determining an initial registration between the sensor coordinate system and the model coordinate system based on the set of sensor location points and the set of model location points;   determining a set of weight values corresponding to the set of sensor location points; and   determining an updated registration between the sensor coordinate system and the model coordinate system based on the set of sensor location points, the set of model location points, and the set of weight values.   
     
     
         2 . The method of  claim 1 , wherein:
 the model comprises a skeleton defined by midpoints along lumens of the luminal network,   the method further comprises:
 transforming the sensor location points from the sensor coordinate system to the model coordinate system using the initial registration; and 
 determining a distance between each of the transformed sensor location points in the model coordinate system and the skeleton, and 
   the determination of the weight values is further based on distances between the transformed sensor location points and the skeleton.   
     
     
         3 . The method of  claim 2 , wherein the set of weight values are binary. 
     
     
         4 . The method of  claim 3 , further comprising:
 comparing each distance between each of the transformed sensor location points and the skeleton to a distance threshold, and   assigning each of the transformed sensor location points on of the binary weight values based on the comparison.   
     
     
         5 . The method of  claim 1 , wherein:
 the model further comprises diameter values for the lumens of the luminal network, and   the determination of the weight values is further based on the diameter values of the lumens.   
     
     
         6 . The method of  claim 1 , wherein:
 the instrument further comprises a camera configured to capture images of an interior of the luminal network,   the method further comprises, for each of the sensor location points, determining a distance between the distal end of the instrument and a centerline of a lumen in which the distal end of the instrument is located based on the captured images, and   the determination of the weight values for the sensor location points is further based on distances between the distal end of the instrument and corresponding centerlines of the lumens.   
     
     
         7 . The method of  claim 1 , wherein:
 the model comprises a skeleton defined by midpoints along lumens of the luminal network,   the method further comprises:
 sorting the sensor location points based on a distance from each of the sensor location points to the skeleton for a given lumen, and 
 assigning the weights to the sensor location points based on the sorted sensor location points. 
   
     
     
         8 . The method of  claim 7 , wherein the sorting of the sensor location points includes:
 sorting a defined percentage of the sensor location points having a smallest distance into a first group and remaining sensor location points into a second group.   
     
     
         9 . The method of  claim 8 , wherein:
 the set of weight values are binary, and   the method further comprises:
 assigning the sensor location points in the first group a weight of 1, and 
 assigning the sensor location point in the second group a weight of 0. 
   
     
     
         10 . The method of  claim 1 , wherein:
 the set of weight values are binary,   a subset of the set of sensor location points correspond to the distal end of the instrument located in a second generation lumen, and   the subset of the set of model location points are assigned a value of 1.   
     
     
         11 . The method of  claim 1 , wherein:
 the method further comprises:
 determining an error associated with the initial registration for a first one the sensor location points; and 
 in response to the error being greater than a threshold error, locking the initial registration. 
   
     
     
         12 . The method of  claim 11 , wherein the determining of the updated registration is further the first sensor location point in response to the error being less than or equal to the threshold error.