Systems and methods for identifying ablation locations using principal component analysis
View Patent ↗Systems and methods for identifying potential ablation sites using principal component analysis (PCA) are provided. A method includes generating a dataset for analysis, the dataset including a plurality of variables and generated using imaging data associated with a three-dimensional geometry that includes a plurality of vertices. The method further includes performing PCA on the generated dataset to identify a plurality of principal components and to generate, for each vertex of the plurality of vertices, a score associated with each of the plurality of principal components. The method further includes transposing the scores for each vertex onto the three-dimensional geometry, and displaying, using the computing device, the three-dimensional geometry including the transposed scores to facilitate identifying potential ablation sites.
1. A computer-implemented method for identifying potential ablation sites using principal component analysis (PCA), the method comprising:
generating, using a computing device, a dataset for analysis, the dataset including a plurality of variables and generated using imaging data associated with a three-dimensional geometry that includes a plurality of vertices;
performing, using the computing device, PCA on the generated dataset to identify a plurality of principal components and to generate, for each vertex of the plurality of vertices, a score associated with each of the plurality of principal components;
transposing, using the computing device, the scores for each vertex onto the three-dimensional geometry; and
displaying, using the computing device, the three-dimensional geometry including the transposed scores to facilitate identifying potential ablation sites.
2. The method of claim 1 , wherein generating a dataset comprises generating a dataset including raw variables and processed variables.
3. The method of claim 2 , further comprising calculating the processed variables for each vertex based on neighboring vertices located within a predetermined radius of the vertex.
4. The method of claim 1 , further comprising normalizing the dataset prior to performing PCA.
5. The method of claim 1 , wherein performing PCA comprises calculating a loading for each of the plurality of variables for each of the plurality of principal components.
6. The method of claim 5 , wherein displaying the three-dimensional geometry comprises:
identifying a score window for one principal component based on the loading of one variable relative to that principal component; and
adjusting a color scale of the displayed three-dimensional geometry based on the identified score window.
7. The method of claim 1 , wherein at least some of the plurality of variables are associated with perfusion.
8. A computing device for identifying potential ablation sites using principal component analysis (PCA), the computing device comprising:
a memory device; and
a processor communicatively coupled to the memory device, the processor configured to:
generate a dataset for analysis, the dataset including a plurality of variables and generated using imaging data associated with a three-dimensional geometry that includes a plurality of vertices;
perform PCA on the generated dataset to identify a plurality of principal components and to generate, for each vertex of the plurality of vertices, a score associated with each of the plurality of principal components;
transpose the scores for each vertex onto the three-dimensional geometry; and
display the three-dimensional geometry including the transposed scores to facilitate identifying potential ablation sites.
9. The computing device of claim 8 , wherein to generate a dataset, the processor is configured to generate a dataset including raw variables and processed variables.
10. The computing device of claim 9 , wherein the processor is further configured to calculate the processed variables for each vertex based on neighboring vertices located within a predetermined radius of the vertex.
11. The computing device of claim 8 , wherein the processor is further configured to normalize the dataset prior to performing PCA.
12. The computing device of claim 8 , wherein to perform PCA, the processor is configured to calculate a loading for each of the plurality of variables for each of the plurality of principal components.
13. The computing device of claim 12 , wherein to display the three-dimensional geometry, the processor is configured to:
identify a score window for one principal component based on the loading of one variable relative to that principal component; and
adjust a color scale of the displayed three-dimensional geometry based on the identified score window.
14. The computing device of claim 8 , wherein at least some of the plurality of variables are associated with perfusion.
15. Non-transitory computer-readable media having computer-executable instructions thereon, wherein when executed by a processor of a computing device, cause the processor of the computing device to:
generate a dataset for analysis, the dataset including a plurality of variables and generated using imaging data associated with a three-dimensional geometry that includes a plurality of vertices;
perform PCA on the generated dataset to identify a plurality of principal components and to generate, for each vertex of the plurality of vertices, a score associated with each of the plurality of principal components;
transpose the scores for each vertex onto the three-dimensional geometry; and
display the three-dimensional geometry including the transposed scores to facilitate identifying potential ablation sites.
16. The non-transitory computer-readable media of claim 15 , wherein to generate a dataset, the processor is configured to generate a dataset including raw variables and processed variables.
17. The non-transitory computer-readable media of claim 16 , wherein the computer-executable instructions are configured to further cause the processor to calculate the processed variables for each vertex based on neighboring vertices located within a predetermined radius of the vertex.
18. The non-transitory computer-readable media of claim 15 , wherein the computer-executable instructions are configured to further cause the processor to normalize the dataset prior to performing PCA.
19. The non-transitory computer-readable media of claim 15 , wherein to perform PCA, the computer-executable instructions are configured to cause the processor to calculate a loading for each of the plurality of variables for each of the plurality of principal components.
20. The non-transitory computer-readable media of claim 19 , wherein to display the three-dimensional geometry, the computer-executable instructions are configured to cause the processor to:
identify a score window for one principal component based on the loading of one variable relative to that principal component; and
adjust a color scale of the displayed three-dimensional geometry based on the identified score window.