Augmentation of images with source locations
Systems are provided for generating data representing electromagnetic states of a heart for medical, scientific, research, and/or engineering purposes. The systems generate the data based on source configurations such as dimensions of, and scar or fibrosis or pro-arrhythmic substrate location within, a heart and a computational model of the electromagnetic output of the heart. The systems may dynamically generate the source configurations to provide representative source configurations that may be found in a population. For each source configuration of the electromagnetic source, the systems run a simulation of the functioning of the heart to generate modeled electromagnetic output (e.g., an electromagnetic mesh for each simulation step with a voltage at each point of the electromagnetic mesh) for that source configuration. The systems may generate a cardiogram for each source configuration from the modeled electromagnetic output of that source configuration for use in predicting the source location of an arrhythmia.
1 . One or more computing systems for augmenting image data with a patient source location of an arrhythmia of a heart of a patient, the one or more computing systems comprising:
one or more computer-readable storage media for storing computer-executable instructions for controlling the one or more computing systems to:
access image data that includes a 3D image of the heart of the patient, a patient substrate location, and a patient substrate volume indicating a volume of the substrate at the patient substrate location;
access a patient cardiogram of the patient;
identify a patient source location of an arrhythmia for the patient based on the patient cardiogram;
augment the image data with the patient source location to generate the augmented image data;
access a 4D image of the heart of the patient, the 4D image including a sequence of 3D images collected during a cycle of the heart; and
add a substrate mask to the 4D image at the patient substrate location and having the substrate volume; and
one or more processors for executing the computer-executable instructions stored in the one or more computer-readable storage media.
2 . The one or more computing systems of claim 1 , wherein the identification of the patient source location is based on mappings of cardiograms to source locations.
3 . The one or more computing systems of claim 2 wherein the instructions that identify the patient source location apply a machine learning algorithm that inputs a cardiogram and outputs a source location, the machine learning algorithm being trained based on the mappings.
4 . The one or more computing systems of claim 2 wherein the instructions that identify the patient source location compare the patient cardiogram to the cardiograms of the mappings to identify a cardiogram that is similar to the patient cardiogram.
5 . The one or more computing systems of claim 2 wherein the mappings include mappings based on one or more of clinical data collected from actual patients, simulations of electrical activity of a heart based on varying configuration parameters, and simulations of electrical activity of the patient heart based on configuration parameters derived from the patient.
6 . The one or more computing systems of claim 2 wherein the instructions, prior to identification of the patient source location, calibrate the mappings to the patient heart so that the identification is based on the calibrated mappings.
7 . The one or more computing systems of claim 1 wherein the instructions provide the augmented image data to a planning system for informing care of the patient based on the image data.
8 . The one or more computing systems of claim 1 wherein the instructions provide the augmented image data to a system that supports treating patients.
9 . The one or more computing systems of claim 1 wherein the image data is a Digital Imaging and Communications in Medicine (“DICOM”) format.
10 . The one or more computing systems of claim 1 wherein the patient substrate location is specified by a 3D coordinate and the patient substrate volume is represented by an indication of a radius for each dimension of the 3D coordinate.
11 . The one or more computing systems of claim 1 wherein the 4D image has voxels with intensity values and the instructions further include instructions to set the intensity values of voxels corresponding to the substrate mask to a substrate intensity value.
12 . The one or more computing systems of claim 1 , wherein the identification of the patient source location is based on mappings of cardiograms to source locations, wherein the patient source location is a source location mapped to a cardiogram that is similar to the patient cardiogram, wherein each cardiogram is associated with a 3D image, and wherein the instructions further include instructions to adjust the patient source location based on differences in the geometry of a heart represented by the 3D image associated with a cardiogram that is similar to the patient cardiogram and the geometry of the heart of the patient represented by the 3D image of the heart of the patient.
13 . The one or more computing systems of claim 1 wherein the patient substrate location and the patient source location are superimposed on the 3D image of the heart of the patient.
14 . The one or more computing systems of claim 1 , the instructions further comprising instructions for controlling the one or more computing systems to:
display the 3D image of the heart of the patient with the patient substrate location and the patient source location superimposed on the displayed 3D image.
15 . The one or more computing systems of claim 6 wherein the instructions that calibrate the mappings to the patient heart calibrate based on geometry of the heart of the patient.
16 . The one or more computing systems of claim 6 wherein the instructions that calibrate the mappings to the patient heart calibrate based on a cardiogram of the patient.
17 . The one or more computing systems of claim 9 , the instructions further comprising instructions for controlling the one or more computing systems to:
store the patient substrate location and patient source locations in the image data as metadata.
18 . The one or more computing systems of claim 9 , the instructions further comprising instructions for controlling the one or more computing systems to:
store the patient substrate location and the patient source location external to the image data.
19 . One or more computing systems for augmenting image data with a patient source location of an arrhythmia of a heart of a patient, the one or more computing systems comprising:
one or more computer-readable storage media for storing computer-executable instructions for controlling the one or more computing systems to:
access image data that includes a 3D image of the heart of the patient and a patient substrate location;
access a patient cardiogram of the patient;
identify a patient source location of an arrhythmia for the patient based on the patient cardiogram; and
augment the image data with the patient source location to generate the augmented image data; and
one or more processors for executing the computer-executable instructions stored in the one or more computer-readable storage media,
wherein the identification of the patient source location is based on mappings of cardiograms to source locations, wherein the patient source location is a source location mapped to a cardiogram that is similar to the patient cardiogram, wherein each cardiogram is associated with a 3D image, and wherein the instructions further include instructions to adjust the patient source location based on differences in the geometry of a heart represented by the 3D image associated with a cardiogram that is similar to the patient cardiogram and the geometry of the heart of the patient represented by the 3D image of the heart of the patient.
20 . The one or more computing systems of claim 19 wherein the instructions provide the augmented image data to a planning system for informing care of the patient based on the image data.
21 . The one or more computing systems of claim 19 wherein the adjustment is based on aligning designated locations of the geometries.
22 . The one or more computing systems of claim 21 wherein the designated location of the 3D image of the heart of the patient is specified by fiducial markers added to that 3D image.
23 . The one or more computing systems of claim 19 , wherein the instructions for controlling the one or more computing systems to identify the patient source location include instructions for controlling the one or more computing systems to apply a machine learning algorithm that inputs a cardiogram and outputs a source location, the machine learning algorithm being trained based on mappings of cardiograms to source locations.
24 . The one or more computing systems of claim 19 , wherein the instructions for controlling the one or more computing systems to identify the patient source location include instructions for controlling the one or more computing systems to identify the patient source location based on mappings of cardiograms to source locations, and wherein the mappings include mappings based on one or more of clinical data collected from actual patients, simulations of electrical activity of a heart based on varying configuration parameters, and simulations of electrical activity of the patient heart based on configuration parameters derived from the patient.
25 . The one or more computing systems of claim 19 , wherein the instructions further comprise instructions for controlling the one or more computing systems to access a 4D image of the heart of the patient, the 4D image including a sequence of 3D images collected during a cycle of the heart.
26 . The one or more computing systems of claim 25 , wherein the instructions for controlling the one or more computing systems to add a source mask to the 4D image at the patient source location and having a patient source volume.
27 . One or more computing systems for augmenting image data with a patient source location of an arrhythmia of a heart of a patient, the one or more computing systems comprising:
one or more computer-readable storage media for storing computer-executable instructions for controlling the one or more computing systems to:
access image data that includes a 3D image of the heart of the patient and a patient substrate location;
access a patient cardiogram of the patient;
identify a patient source location of an arrhythmia for the patient based on the patient cardiogram;
augment the image data with the patient source location to generate the augmented image data;
identify a patient source volume associated with the patient source location;
access a 4D image of the heart of the patient, the 4D image including a sequence of 3D images collected during a cycle of the heart; and
add a source mask to the 4D image at the patient source location and having the patient source volume; and
one or more processors for executing the computer-executable instructions stored in the one or more computer-readable storage media.
28 . The one or more computing systems of claim 27 wherein the patient source location is specified by a 3D coordinate and the patient source volume is represented by an indication of a radius for each dimension of the 3D coordinate.
29 . The one or more computing systems of claim 28 wherein the 4D image has voxels with intensity values and the instructions further include instructions to set the intensity values of voxels corresponding to the source mask to a source intensity value.
30 . The one or more computing systems of claim 27 , wherein the instructions for controlling the one or more computing systems to identify the patient source location include instructions for controlling the one or more computing systems to apply a machine learning algorithm that inputs a cardiogram and outputs a source location, the machine learning algorithm being trained based on mappings of cardiograms to source locations.
31 . The one or more computing systems of claim 27 , wherein the instructions for controlling the one or more computing systems to identify the patient source location include instructions for controlling the one or more computing systems to identify the patient source location based on mappings of cardiograms to source locations, and wherein the mappings include mappings based on one or more of clinical data collected from actual patients, simulations of electrical activity of a heart based on varying configuration parameters, and simulations of electrical activity of the patient heart based on configuration parameters derived from the patient.
32 . The one or more computing systems of claim 27 , wherein the identification of the patient source location is based on mappings of cardiograms to source locations, wherein the patient source location is a source location mapped to a cardiogram that is similar to the patient cardiogram, wherein each cardiogram is associated with a 3D image, and wherein the instructions further include instructions to adjust the patient source location based on differences in the geometry of a heart represented by the 3D image associated with a cardiogram that is similar to the patient cardiogram and the geometry of the heart of the patient represented by the 3D image of the heart of the patient.
33 . A method, performed by one or more computing systems having one or more computer-readable storage media and one or more processors, for augmenting image data with a patient source location of an arrhythmia of a heart of a patient, the method comprising:
accessing image data that includes a 3D image of the heart of the patient, a patient substrate location, and a patient substrate volume indicating a volume of the substrate at the substrate location;
accessing a patient cardiogram of the patient;
identifying a patient source location of an arrhythmia for the patient based on the patient cardiogram;
augmenting the image data with the patient source location to generate the augmented image data;
accessing a 4D image of the heart of the patient, the 4D image including a sequence of 3D images collected during a cycle of the heart; and
adding a substrate mask to the 4D image at the substrate location and having the substrate volume.
34 . The method of claim 33 wherein the 3D image of the heart of the patient is included in a file in a standard format and wherein the standard format is a Digital Imaging and Communications in Medicine (“DICOM”) format.
35 . The method of claim 33 , wherein identifying the patient source location is based on mappings of cardiograms to source locations, wherein the patient source location is a source location mapped to a cardiogram that is similar to the patient cardiogram, wherein each cardiogram is associated with a 3D image, the method further comprising:
adjusting the patient source location based on differences in the geometry of a heart represented by the 3D image associated with a cardiogram that is similar to the patient cardiogram and the geometry of the heart of the patient represented by the 3D image of the heart of the patient.
36 . A method, performed by one or more computing systems having one or more computer-readable storage media and one or more processors, for augmenting image data with a patient source location of an arrhythmia of a heart of a patient, the method comprising:
accessing image data that includes a 3D image of the heart of the patient and a patient substrate location;
accessing a patient cardiogram of the patient;
identifying a patient source location of an arrhythmia for the patient based on the patient cardiogram and mappings of cardiograms to source locations, wherein the patient source location is a source location mapped to a cardiogram that is similar to the patient cardiogram, and wherein each cardiogram is associated with a 3D image;
adjusting the patient source location based on differences in the geometry of a heart represented by the 3D image associated with a cardiogram that is similar to the patient cardiogram and the geometry of the heart of the patient represented by the 3D image of the heart of the patient; and
augmenting the image data with the patient source location to generate the augmented image data.
37 . The method of claim 36 , further comprising:
accessing a 4D image of the heart of the patient, the 4D image including a sequence of 3D images collected during a cycle of the heart; and
adding a source mask to the 4D image at the patient source location and having the patient source volume.
38 . The method of claim 36 , further comprising:
accessing a 4D image of the heart of the patient, the 4D image including a sequence of 3D images collected during a cycle of the heart; and
adding a substrate mask to the 4D image at the substrate location and having the substrate volume.
39 . A method, performed by one or more computing systems having one or more computer-readable storage media and one or more processors, for augmenting image data with a patient source location of an arrhythmia of a heart of a patient, the method comprising:
accessing image data that includes a 3D image of the heart of the patient and a patient substrate location;
accessing a patient cardiogram of the patient;
identifying a patient source location of an arrhythmia for the patient based on the patient cardiogram;
augmenting the image data with the patient source location to generate the augmented image data;
identifying a patient source volume associated with the patient source location;
accessing a 4D image of the heart of the patient, the 4D image including a sequence of 3D images collected during a cycle of the heart; and
adding a source mask to the 4D image at the patient source location and having the patient source volume.
40 . The method of claim 39 , wherein identifying the patient source location is based on mappings of cardiograms to source locations, wherein the patient source location is a source location mapped to a cardiogram that is similar to the patient cardiogram, wherein each cardiogram is associated with a 3D image.
41 . The method of claim 40 , further comprising:
adjusting the patient source location based on differences in the geometry of a heart represented by the 3D image associated with a cardiogram that is similar to the patient cardiogram and the geometry of the heart of the patient represented by the 3D image of the heart of the patient.