Systems, methods, and apparatuses for generating regions of interest from voxel mode based thresholds
The described implementations relate to systems, methods, and apparatuses for generating regions of interest ( 214 ) from imaging data ( 212 ). Specifically, the regions of interest are generated for tracking treatment efficacy in a more consistent and repeatable manner. The regions of interest can be generated from contrast medium and non-contrast medium enhanced scans ( 102 ) of a patient. Voxel data derived from the scans can be collected and distributed according to respective intensity values in order to identify mode voxels ( 116, 118, 120 ) for particular ranges ( 128 ) of intensities. Regions of interest ( 110, 112, 114 ) can then be generated for each identified mode voxel, and standard deviations for the regions of interest can be determined. One or more thresholds can be derived from the determined standard deviations in order to further filter the intensity values and identify filtered groups of voxels to be the resulting regions of interest.
1. A method implemented by one or more processors, the method comprising:
receiving imaging data corresponding to three-dimensional scans of organ tissue, the imaging data based on a comparison between one or more contrast medium enhanced scans of a patient and one or more non-contrast medium enhanced scans of the patient;
processing voxels of the imaging data to identify one or more modes from the imaging data, wherein the one or more modes are identified from one or more distributions of enhancement values of the voxels over ranges of the enhancement values;
generating a region of interest for a mode voxel corresponding to the determined one or more modes, wherein the region of interest identifies a volume of data corresponding to a region surrounding the mode voxel;
generating a tissue threshold value for the enhancement values based on standard deviations of the enhancement values for particular voxels within the region of interest by arranging the standard deviations according to an absolute value of each standard deviation of the standard deviations and designating a range of the arranged standard deviations as corresponding to healthy organ tissue; and
identifying a group of voxels corresponding to threshold enhancement values that satisfy the tissue threshold value.
2. The method of claim 1 , wherein the comparison between the one or more contrast medium enhanced scans of the patient and the one or more non-contrast medium enhanced scans corresponds to a subtraction of non-contrast medium enhanced scans from contrast medium enhanced scan data.
3. The method of claim 1 , wherein processing the voxels of the imaging data includes identifying a first mode corresponding to a first distribution of enhancement values and a second mode corresponding to a second distribution of enhancement values that are different than the first distribution of enhancement values.
4. The method of claim 1 , wherein generating the tissue threshold value for the enhancement values is further based on a mean, medium, or mode of the standard deviations of the enhancement values for the particular voxels within the region of interest.
5. The method of claim 1 , wherein the ranges of enhancement values correspond to bins and processing the voxels of the imaging data to identify the one or more modes from the imaging data includes assigning the voxels to the bins.
6. The method of claim 5 , wherein the mode voxel corresponds to a bin of the bins having a largest number of assigned voxels for a particular distribution of enhancement values.
7. A non-transitory computer-readable medium configured to store instructions that, when executed by one or more processors, cause the one or more processors to perform operations that include:
receiving imaging data corresponding to three-dimensional scans organ tissue, the imaging data based on a comparison between one or more contrast medium enhanced scans of a patient and one or more non-contrast medium enhanced scans of the patient;
processing voxels of the imaging data to identify one or more modes from the imaging data, wherein the one or more modes are identified from one or more distributions of enhancement values of the voxels over ranges the enhancement values;
generating a region of interest for a mode voxel corresponding to the determined one or more modes, wherein the region of interest identifies a volume of data corresponding to a region surrounding the mode voxel;
generating a tissue threshold value for the enhancement values based on standard deviations of the enhancement values for particular voxels within the region of interest by arranging the standard deviations according to an absolute value of each standard deviation of the standard deviations and designating a range of the arranged standard deviations as corresponding to healthy organ tissue; and
identifying a group of voxels corresponding to threshold enhancement values that satisfy the tissue threshold value.
8. The non-transitory computer-readable medium of claim 7 , wherein the comparison between the one or more contrast medium enhanced scans of the patient and the one or more non-contrast medium enhanced scans corresponds to a subtraction of non-contrast medium enhanced scans from contrast medium enhanced scan data.
9. The non-transitory computer-readable medium of claim 7 , wherein processing the voxels of the imaging data includes identifying a first mode corresponding to a first distribution of enhancement values and a second mode corresponding to a second distribution of enhancement values that are different than the first distribution of enhancement values.
10. The non-transitory computer-readable medium of claim 7 , wherein generating the tissue threshold value for the enhancement values is further based on a mean, medium, or mode of the standard deviations of the enhancement values for the particular voxels within the region of interest.
11. The non-transitory computer-readable medium of claim 7 , wherein the ranges of enhancement values correspond to bins and processing the voxels of the imaging data to identify the one or more modes from the imaging data includes assigning the voxels to the bins.
12. The non-transitory computer-readable medium of claim 11 , wherein the mode voxel corresponds to a bin of the bins having a largest number of assigned voxels for a particular distribution of enhancement values.
13. A system, comprising:
one or more processors; and
memory configured to store instructions that, when executed by the one or more processors, cause the one or more processors to perform operations that include:
receiving imaging data corresponding to three-dimensional scans of organ tissue, the imaging data based on a comparison between one or more contrast medium enhanced scans of a patient and one or more non-contrast medium enhanced scans of the patient;
processing voxels of the imaging data to identify one or more modes from the imaging data, wherein the one or more modes are identified from one or more distributions of enhancement values of the voxels over ranges of the enhancement values;
generating a region of interest for a mode voxel corresponding to the determined one or more modes, wherein the region of interest identifies a volume of data corresponding to a region surrounding the mode voxel;
generating a tissue threshold value for the enhancement values based on standard deviations of the enhancement values for particular voxels within the region of interest by arranging the standard deviations according to an absolute value of each standard deviation of the standard deviations and designating a range of the arranged standard deviations as corresponding to healthy organ tissue; and
identifying a group of voxels corresponding to threshold enhancement values that satisfy the tissue threshold value.
14. The non-transitory computer-readable medium of claim 13 , wherein the comparison between the one or more contrast medium enhanced scans of the patient and the one or more non-contrast medium enhanced scans corresponds to a subtraction of non-contrast medium enhanced scans from contrast medium enhanced scan data.
15. The non-transitory computer-readable medium of claim 13 , wherein processing the voxels of the imaging data includes identifying a first mode corresponding to a first distribution of enhancement values and a second mode corresponding to a second distribution of enhancement values that are different than the first distribution of enhancement values.
16. The non-transitory computer-readable medium of claim 13 , wherein generating the tissue threshold value for the enhancement values is further based on a mean, medium, or mode of the standard deviations of the enhancement values for the particular voxels within the region of interest.
17. The non-transitory computer-readable medium of claim 13 , wherein the ranges of enhancement values correspond to bins and processing the voxels of the imaging data to identify the one or more modes from the imaging data includes assigning the voxels to the bins; and wherein the mode voxel corresponds to a bin of the bins having a largest number of assigned voxels for a particular distribution of enhancement values.