Determining position of medical device in branched anatomical structure
Information extracted from sequential images captured from the perspective of a distal end of a medical device moving through an anatomical structure are compared with corresponding information extracted from a computer model of the anatomical structure. A most likely match between the information extracted from the sequential images and the corresponding information extracted from the computer model is then determined using probabilities associated with a set of potential matches so as to register the computer model of the anatomical structure to the medical device and thereby determine the lumen of the anatomical structure which the medical device is currently in. Sensor information may be used to limit the set of potential matches. Feature attributes associated with the sequence of images and the set of potential matches may be quantitatively compared as part of the determination of the most likely match.
1 . A system comprising:
memory that stores information representing a model of an anatomical structure;
a medical device including a distal end that is configured to be inserted into the anatomical structure, the distal end supporting an image capturing device configured to capture images as the medical device is moved through branches of the anatomical structure; and
one or more processing devices communicatively coupled to the memory and the medical device, the one or more processing devices configured to:
receive, from the medical device, representations of sequential images captured using the image capturing device, wherein the sequential images form a tracklet associated with a first lumen of the anatomical structure and depict a set of blobs corresponding to a set of lumens in the anatomical structure that are tracked across the sequential images,
process the captured sequential images to detect a change in the set of blobs;
responsive to detecting the change in the set of blobs, process the sequential images to determine that the change in the set of blobs is due to a false positive or a false negative;
correct the false positive or false negative by maintaining the tracking of the set of blobs as a corrected set of blobs;
determine that the distal end of the medical device transitioned into a second lumen of the anatomical structure; and
determine, based in part on the corrected set of blobs, a location of the distal end of the medical device within the anatomical structure.
2 . The system of claim 1 , wherein:
the change in the set of blobs is a removal of a removed blob; and
to determine that the change is due to a false negative, the one or more processing devices are configured to detect that the removed blob was incorrectly removed in the set of blobs.
3 . The system of claim 2 , wherein to determine that the change is due to a false negative, the one or more processing devices are configured to:
determine a position of a remaining blob in the set of blobs within an image of the captured sequential images; and
detect that the removed blob was incorrectly removed in the set of blobs, based upon the determined position of the remaining blob.
4 . The system of claim 1 , wherein:
the change in the set of blobs is an inclusion of an additional blob; and
to determine that the change is due to a false positive, the one or more processing devices are configured to detect that the additional blob was incorrectly included in the set of blobs.
5 . The system of claim 4 , wherein to determine that the change is due to a false positive, the one or more processing devices are configured to:
analyze an image of the captured sequential images to determine that the additional blob represents a foreign object.
6 . The system of claim 1 , wherein to determine that the change is due to a false positive or a false negative, the one or more processing devices are configured to:
compare an image of the captured sequential images in which the change is detected to reference data.
7 . The system of claim 6 , wherein the reference data is a synthetic image generated based upon a position of the medical device with respect to the model of the branched anatomical structure.
8 . The system of claim 6 , wherein the reference data includes characteristics of an expected blob topology derived from a position of the medical device with respect to the model of the branched anatomical structure.
9 . The system of claim 1 , wherein to determine that the change is due to a false positive or a false negative, the one or more processing devices are configured to:
analyze successive images of the captured sequential images to detect a temporal inconsistency.
10 . The system of claim 1 , wherein to determine that the change is due to a false positive or a false negative, the one or more processing devices are configured to:
analyze successive images of the captured sequential images to track a position of (i) an additional blob after its inclusion in the set of blobs, or (ii) a removed blob prior to its removal from the set of blobs.
11 . A method comprising:
receiving, from a medical device including a distal end that (i) is configured to be inserted into an anatomical structure and (ii) supports an image capturing device configured to capture images as the medical device is moved through branches of the anatomical structure, representations of sequential images captured using the image capturing device, wherein the sequential images form a tracklet associated with a first lumen of the anatomical structure and depict a set of blobs corresponding to a set of lumens in the anatomical structure that are tracked across the sequential images,
processing, via one or more processors, the captured sequential images to detect a change in the set of blobs;
responsive to detecting the change in the set of blobs, processing, via one or more processors, the sequential images to determine that the change in the set of blobs is due to a false positive or a false negative;
correcting, via one or more processors, the false positive or false negative by maintaining the tracking of the set of blobs as a corrected set of blobs;
determining, via one or more processors, that the distal end of the medical device transitioned into a second lumen of the anatomical structure; and
determining, via one or more processors and based in part on the corrected set of blobs, a location of the distal end of the medical device within the anatomical structure.
12 . The method of claim 11 , wherein:
the change in the set of blobs is a removal of a removed blob; and
determining that the change is due to a false negative comprises detecting, via one or more processors, that the removed blob was incorrectly removed in the set of blobs.
13 . The method of claim 12 , wherein determining that the change is due to a false negative comprises:
determining, via one or more processors, a position of a remaining blob in the set of blobs within an image of the captured sequential images; and
detecting, via one or more processors, that the removed blob was incorrectly removed in the set of blobs, based upon the determined position of the remaining blob.
14 . The method of claim 11 , wherein:
the change in the set of blobs is an inclusion of an additional blob; and
determining that the change is due to a false positive comprises detecting, via one or more processors, that the additional blob was incorrectly included in the set of blobs.
15 . The method of claim 11 , wherein determining that the change is due to a false positive or a false negative comprises:
comparing, via one or more processors, an image of the captured sequential images in which the change is detected to reference data derived from a model of the branched anatomical structure.
16 . The method of claim 15 , wherein the reference data is a synthetic image generated based upon a position of the medical device with respect to the model of the branched anatomical structure.
17 . The method of claim 15 , wherein the reference data includes characteristics of an expected blob topology derived from a position of the medical device with respect to the model of the branched anatomical structure.
18 . The method of claim 11 , wherein determining that the change is due to a false positive or a false negative comprises:
analyzing, via one or more processors, successive images of the captured sequential images to detect a temporal inconsistency.
19 . The method of claim 11 , wherein determining that the change is due to a false positive or a false negative comprises:
analyzing, via one or more processors, successive images of the captured sequential images to track a position of (i) an additional blob after its inclusion in the set of blobs, or (ii) a removed blob prior to its removal from the set of blobs.
20 . A non-transitory computer-readable storage medium storing processor-executable instructions, that, when executed by one or more processors, cause the one or more processors to:
receive, from a medical device including a distal end that (i) is configured to be inserted into an anatomical structure and (ii) supports an image capturing device configured to capture images as the medical device is moved through branches of the anatomical structure, representations of sequential images captured using the image capturing device, wherein the sequential images form a tracklet associated with a first lumen of the anatomical structure and depict a set of blobs corresponding to a set of lumens in the anatomical structure that are tracked across the sequential images,
process the captured sequential images to detect a change in the set of blobs;
responsive to detecting the change in the set of blobs, process the sequential images to determine that the change in the set of blobs is due to a false positive or a false negative;
correct the false positive or false negative by maintaining the tracking of the set of blobs as a corrected set of blobs;
determine that the distal end of the medical device transitioned into a second lumen of the anatomical structure; and
determine, based in part on the corrected set of blobs, a location of the distal end of the medical device within the anatomical structure.