Surface and image integration for model evaluation and landmark determination
Embodiments of the present disclosure provide a software program that displays both a volume as images and segmentation results as surface models in 3D. Multiple 2D slices are extracted from the 3D volume. The 2D slices may be interactively rotated by the user to best follow an oblique structure. The 2D slices can “cut” the surface models from the segmentation so that only half of the models are displayed. The border curves resulting from the cuts are displayed in the 2D slices. The user may click a point on the surface model to designate a landmark point. The corresponding location of the point is highlighted in the 2D slices. A 2D slice can be reoriented such that the line lies in the slice. The user can then further evaluate or refine the landmark points based on both surface and image information.
1. A system for determining an accuracy of a bone model, comprising:
at least one processor; and
at least one memory having a plurality of instructions stored thereon that, in response to execution by the at least one processor, causes the system to:
create a three-dimensional surface model of a portion of a patient's joint based on raw image data of the patient's joint;
determine a border curve defined by an intersection of an image plane and the three-dimensional surface model of the portion of the patient's joint; and
compare an intersection of the raw image data of the patient's joint and the image plane with the determined boundary curve to evaluate an accuracy of the three-dimensional surface model.
2. The system of claim 1 , wherein to create the three-dimensional surface model comprises to:
generate a three-dimensional volume image from a set of magnetic resonance imaging (MRI) data slices; and
create the three-dimensional surface model based on the three-dimensional volume image.
3. The system of claim 2 , wherein the three-dimensional surface model is a polygonal representation of the patient's joint.
4. The system of claim 2 , wherein to create the three-dimensional volume image comprises interpolation of the raw image data.
5. The system of claim 1 , wherein to create the three-dimensional surface model comprises to:
generate a three-dimensional volume image based on a set of points identified in the raw image data; and
create the three-dimensional surface model based on the three-dimensional volume image.
6. The system of claim 1 , wherein to create the three-dimensional surface model comprises to
filter the raw image data to generate smoothed image data;
generate a three-dimensional volume image based on the smoothed image data; and
create the three-dimensional surface model based on the three-dimensional volume image; and
wherein the accuracy of the three-dimensional surface model is based on errors introduced by at least one of filtering the raw image data or generating the three-dimensional volume image.
7. The system of claim 1 , wherein the raw image data is volume data.
8. A method for determining an accuracy of a bone model, comprising:
creating a three-dimensional surface model of a portion of a patient's joint based on raw image data of the patient's joint;
determining a border curve defined by an intersection of an image plane and the three-dimensional surface model of the portion of the patient's joint; and
comparing an intersection of the raw image data of the patient's joint and the image plane with the determined boundary curve to evaluate an accuracy of the three-dimensional surface model.
9. The method of claim 8 , wherein creating the three-dimensional surface model comprises:
generating a three-dimensional volume image from a set of magnetic resonance imaging (MRI) data slices; and
creating the three-dimensional surface model based on the three-dimensional volume image.
10. The method of claim 9 , wherein the three-dimensional surface model is a polygonal representation of the patient's joint.
11. The method of claim 9 , wherein creating the three-dimensional volume image comprises interpolating the raw image data.
12. The method of claim 8 , wherein creating the three-dimensional surface model comprises:
generating a three-dimensional volume image based on a set of points identified in the raw image data; and
creating the three-dimensional surface model based on the three-dimensional volume image.
13. The method of claim 8 , wherein creating the three-dimensional surface model comprises:
filtering the raw image data to generate smoothed image data;
generating a three-dimensional volume image based on the smoothed image data; and
creating the three-dimensional surface model based on the three-dimensional volume image; and
wherein the accuracy of the three-dimensional surface model is based on errors introduced by at least one of filtering the raw image data or generating the three-dimensional volume image.
14. The method of claim 8 , wherein the raw image data is volume data.
15. The method of claim 14 , further comprising displaying the volume data and the three-dimensional surface model as an integrated image.
16. The method of claim 8 , wherein the raw image data is captured along one of a transverse plane, a sagittal plane, or a coronal plane of the patient.
17. One or more non-transitory machine-readable storage media comprising a plurality of instructions stored thereon that, in response to execution by a computing device, causes the computing device to:
create a three-dimensional surface model of a portion of a patient's joint based on raw image data of the patient's joint;
determine a border curve defined by an intersection of an image plane and the three-dimensional surface model of the portion of the patient's joint; and
compare an intersection of the raw image data of the patient's joint and the image plane with the determined boundary curve to evaluate an accuracy of the three-dimensional surface model.
18. The one or more non-transitory machine-readable storage media of claim 17 , wherein to create the three-dimensional surface model comprises to:
generate a three-dimensional volume image from a set of magnetic resonance imaging (MRI) data slices; and
create the three-dimensional surface model based on the three-dimensional volume image.
19. The one or more non-transitory machine-readable storage media of claim 17 , wherein to create the three-dimensional surface model comprises to:
generate a three-dimensional volume image based on a set of points identified in the raw image data; and
create the three-dimensional surface model based on the three-dimensional volume image.
20. The one or more non-transitory machine-readable storage media of claim 17 , wherein to create the three-dimensional surface model comprises to:
filter the raw image data to generate smoothed image data;
generate a three-dimensional volume image based on the smoothed image data; and
create the three-dimensional surface model based on the three-dimensional volume image,
wherein the accuracy of the three-dimensional surface model is based on errors introduced by at least one of filtering the raw image data or generating the three-dimensional volume image.