System and method for controlling user repeatability and reproducibility of automated image annotation correction
Systems and methods are disclosed for controlling image annotation. One method includes acquiring a digital representation of image data and generating a set of image annotations for the digital representation of the image data. The method also may include determining an association between members of the set of image annotations and generating one or more groups of members based on the association. A representative annotation from the one or more groups may also be determined, presented for selection, and the selection may be recorded in memory.
1. A computer-implemented method of controlling image annotation, using at least one computer system, the method comprising using a processor for:
generating, by the at least one computer system, a plurality of image annotations of anatomic features identified within a digital representation of image data;
presenting, by the at least one computer system, one or more image annotations among the plurality of image annotations of anatomic features to a user;
receiving feedback from the user regarding the one or more image annotations;
based on the received feedback, adjusting the digital representation of image data;
generating, by the at least one computer system, alternative image annotations of anatomic features identified within the adjusted digital representation of image data;
determining an association between the generated alternative image annotations;
automatically categorizing the generated alternative image annotations to one or more groups based on the determined association;
determining a representative annotation for each group of the one or more groups; and
presenting the representative annotation of each group of the one or more groups for selection or correction by a user.
2. The computer-implemented method of claim 1 , further comprising:
determining, by the at least one computer system, one or more associations between members of a set of the generated alternative image annotations.
3. The computer-implemented method of claim 1 , wherein the digital representation of image data is acquired electronically via a network.
4. The computer-implemented method of claim 1 , wherein the representative annotation identifies anatomic features identified within the image data.
5. The computer-implemented method of claim 1 , wherein the plurality of image annotations are generated using multiple image analysis algorithms.
6. The computer-implemented method of claim 2 , wherein each of the one or more associations between members of the set of the generated alternative image annotations is determined by assigning a similarity score between the members.
7. The computer-implemented method of claim 2 , wherein each of the one or more associations between members of the set of the generated alternative image annotations is determined by assigning a pair of the generated alternative image annotations among the set of the generated alternative image annotations to a group if the pair of the generated alternative image annotations are the same.
8. The computer-implemented method of claim 1 , wherein each image annotation among the plurality of image annotations comprises a box around a target feature.
9. The computer-implemented method of claim 8 , further comprising applying a k-means algorithm to a centroid of the box.
10. A system of controlling image annotation, the system comprising:
a data storage device storing instructions for controlling image annotation; and
a processor configured to execute the instruction to perform a method including:
generating, by the processor, a plurality of image annotations of anatomic features identified within a digital representation of image data;
presenting, by the processor, one or more image annotations among the plurality of image annotations of anatomic features to a user;
receiving feedback from the user regarding the one or more image annotations;
based on the received feedback, adjusting the digital representation of image data;
generating, by the processor, alternative image annotations of anatomic features identified within the adjusted digital representation of image data;
determining an association between the generated alternative image annotations;
automatically categorizing the generated alternative image annotations to one or more groups based on the determined association;
determining a representative annotation for each group of the one or more groups; and
presenting, by the at least one computer system, the representative annotation of each group of the one or more groups for selection or correction by a user.
11. The system of claim 10 , wherein the processor is further configured to electronically acquire the digital representation of image data via a network.
12. The system of claim 10 , wherein the processor is further configured to determine one or more associations between members of a set of the generated alternative image annotations.
13. The system of claim 10 , wherein the processor is further configured to automatically generate a set of the generated alternative image annotations using multiple image analysis algorithms.
14. The system of claim 12 , wherein the processor in configured to determine each of the one or more associations between members of the set of the generated alternative image annotations by assigning a similarity score between the members.
15. The system of claim 12 , wherein processor is configured to determine each of the one or more associations between members of the set of the generated alternative image annotations by assigning a pair of image annotations among the set of the generated alternative image annotations to a group if the pair of the generated alternative image annotations are the same.
16. The system of claim 10 , wherein the processor is configured to generate a box around a target feature.
17. A non-transitory computer-readable medium for use on a computer system containing computer-executable programming instructions for controlling image annotation, the instructions being executable by the computer system for:
generating, by the at least one computer system, a plurality of image annotations of anatomic features identified within a digital representation of image data;
presenting, by the at least one computer system, one or more image annotations among the plurality of image annotations of anatomic features to a user;
receiving feedback from the user regarding the one or more image annotations;
based on the received feedback, adjusting the digital representation of image data;
generating, by the at least one computer system, alternative image annotations of anatomic features identified within the adjusted digital representation of image data;
determining an association between the generated alternative image annotations;
automatically categorizing the generated alternative image annotations to one or more groups based on the determined association;
determining a representative annotation for each group of the one or more groups; and
presenting the representative annotation of each group of the one or more groups for selection or correction by a user.
18. The non-transitory computer readable medium of claim 17 , the instructions being executable by the computer system further comprising determining one or more associations between members of a set of the generated alternative image annotations,
wherein each of the one or more associations between members of the set of the generated alternative image annotations is determined by assigning a similarity score between the members.