Pre-operative planning of surgical revision procedures for orthopedic joints

1 . A method comprising:

obtaining, by a computing system, a 3D model of a joint of a patient;

determining, by the computing system, that the joint includes an existing implant;

segmenting, by the computing system, the 3D model;

identifying, by the computing system in the segmented 3D model, voxels that correspond to the existing implant based on an intensity of voxels in the 3D model;

determining, by the computing system, a number of unconnected objects in the voxels that correspond to the existing implant;

determining, by the computing system, a type for the existing implant based on the number of the unconnected objects, wherein the type for the existing implant comprises one of a reverse shoulder implant type, an anatomical shoulder implant type, or a hemispherical shoulder implant type; and

generating, by the computing system, surgical guidance based on the type for the existing implant.

2 . The method of claim 1 , wherein determining that the joint includes the existing implant comprises determining, by the computing system, that the joint includes the existing implant based on an analysis of the 3D model.

3 . The method of claim 1 , wherein determining that the joint includes the existing implant comprises determining, by the computing system, that the joint includes the existing implant based on a user input.

4 . The method of claim 1 , wherein determining the type for the existing implant based on the number of the unconnected objects comprises:

determining that the voxels that correspond to the existing implant form three unconnected objects; and

determining that the type for the existing implant comprises an undefined type in response to determining that the voxels that correspond to the existing implant form the three unconnected objects.

5 . The method of claim 1 , wherein determining the type for the existing implant based on the number of the unconnected objects comprises:

determining that the voxels that correspond to the existing implant form one connected object;

in response to determining that the voxels that correspond to the existing implant form the one connected object, identifying, based on locations of the voxels that correspond to the existing implant, second locations of voxels;

searching, in the second locations of voxels, for metallic glenoid markers; and

in response to not detecting the metallic glenoid markers, determining that the type for the existing implant comprises the hemispherical shoulder implant type.

6 . The method of claim 5 , further comprising:

generating an output indicating that the type for the existing implant comprises the hemispherical shoulder implant type.

7 . The method of claim 1 , wherein determining the type for the existing implant based on the number of the unconnected objects comprises:

determining that the voxels that correspond to the existing implant form one connected object;

in response to determining that the voxels that correspond to the existing implant form the one connected object, identifying, based on a location of the voxels that correspond to the existing implant, a second location of voxels;

searching, in the second location of voxels, for metallic glenoid markers; and

in response to detecting the metallic glenoid markers, determining that the type for the existing implant comprises the anatomical shoulder implant type.

8 . The method of claim 7 , further comprising:

generating an output indicating that the type for the existing implant comprises the anatomical shoulder implant type.

9 . The method of claim 1 , wherein determining the type for the existing implant based on the number of the unconnected objects comprises:

determining that the voxels that correspond to the existing implant form two unconnected objects; and

in response to determining that the voxels that correspond to the existing implant form the two unconnected objects, determining that the type for the existing implant comprises the reverse shoulder type.

10 . The method of claim 9 , further comprising:

generating an output indicating that the type for the existing implant comprises the reverse shoulder type.

11 . The method of claim 1 , wherein identifying, by the computing system in the segmented 3D model, the voxels that correspond to the existing implant based on the intensity of the voxels in the 3D model comprises:

determining radiodensity values for the voxels in the 3D model; and

identifying a subset of voxels in the 3D model that have radiodensity values exceeding a threshold value.

12 . A device comprising:

a memory; and

one or more processors coupled to the memory, implemented in circuitry, and configured to:

obtain a 3D model of a joint of a patient;

determine that the joint includes an existing implant;

segment the 3D model;

identify, in the segmented 3D model, voxels that correspond to the existing implant based on an intensity of voxels in the 3D model;

determine a number of unconnected objects in the voxels that correspond to the existing implant;

determine a type for the existing implant based on the number of the unconnected objects, wherein the type for the existing implant comprises one of a reverse shoulder implant type, an anatomical shoulder implant type, or a hemispherical shoulder implant type; and

generate surgical guidance based on the type for the existing implant.

13 . The device of claim 12 , wherein the one or more processors are configured to, as part of determining that the joint includes the existing implant, determine that the joint includes the existing implant based on an analysis of the 3D model.

14 . The device of claim 12 , wherein the one or more processors are configured to, as part of determining that the joint includes the existing implant, determine that the joint includes the existing implant based on a user input.

15 . The device of claim 12 , wherein the one or more processors are configured to, as part of determining the type for the existing implant based on the number of the unconnected objects:

determine that the voxels that correspond to the existing implant form three unconnected objects; and

determine that the type for the existing implant comprises an undefined type in response to determining that the voxels that correspond to the existing implant form the three unconnected objects.

16 . The device of claim 12 , wherein the one or more processors are configured to, as part of determining the type for the existing implant based on the number of the unconnected objects:

determine that the voxels that correspond to the existing implant form one connected object;

in response to determining that the voxels that correspond to the existing implant form the one connected object, identify, based on locations of the voxels that correspond to the existing implant, second locations of voxels;

search, in the second locations of voxels, for metallic glenoid markers; and

in response to not detecting the metallic glenoid markers, determine that the type for the existing implant comprises the hemispherical shoulder implant type.

17 . The device of claim 16 , wherein the one or more processors are further configured to generate an output indicating that the type for the existing implant comprises the hemispherical shoulder implant type.

18 . The device of claim 12 , wherein the one or more processors are configured to, as part of determining the type for the existing implant based on the number of the unconnected objects:

determine that voxels that correspond to the existing implant form one connected object;

in response to determining that the voxels that correspond to the existing implant form the one connected object, identify, based on a location of the voxels that correspond to the existing implant, a second location of voxels;

search, in the second location of voxels, for metallic glenoid markers; and

in response to detecting the metallic glenoid markers, determine that the type for the existing implant comprises the anatomical shoulder implant type.

19 . The device of claim 12 , wherein the one or more processors are configured to, as part determining the type for the existing implant based on the number of the unconnected objects:

determine that the voxels that correspond to the existing implant form two unconnected objects; and

in response to determining that the voxels that correspond to the existing implant form the two unconnected objects, determine that the type for the existing implant comprises the reverse shoulder type.

20 . The device of claim 12 , wherein to identify the voxels that correspond to the existing implant based on the intensity of the voxels in the 3D model, the one or more processors are configured to:

determine radiodensity values for the voxels in the 3D model; and

identify a subset of voxels in the 3D model that have radiodensity values exceeding a threshold value.