Artificial Intelligence Physics-Based Modeling of Cardiac Parameters

Abstract

Described herein is a software and computer-implemented method for modeling an individual's heart, in which the model presents or displays one or more cardiac parameters of the individual.In some embodiments, the cardiac model generated by the software and computer-implemented method described herein is a three-dimensional representation of the individual's heart that can be displayed on the display of a computing device.

Description

[Technical field]

[0001] cross reference This application claims the benefit of U.S. Provisional Patent Application No. 63 / 320,965, filed March 17, 2022, the entirety of which is incorporated herein by reference. [Background technology]

[0002] Many people suffer from heart disease. A variety of modalities are available to evaluate an individual's heart for the purposes of diagnosing disease and assessing disease progression, including, but not limited to, angiography, magnetic resonance imaging (MRI), ultrasound, and electrocardiogram (ECG). These modalities also sometimes include software that is used to record and display certain data. Summary of the Invention

[0003] Described herein are methods and systems, as well as software, which in combination with the systems described elsewhere herein include, execute, and / or preform the methods described elsewhere herein. Optionally, the methods, systems, and / or software may analyze one or more images of the individual's heart to generate and / or display (e.g., on a computing device display) one or more models of the individual's heart. The methods, systems, and / or software may provide a non-invasive modality for presenting data (displayed in the model of the heart), which typically must be collected through burdensome or invasive testing. The methods, systems, and / or software may provide one efficient modality for presenting multiple specific parameters, which typically are collected from multiple different modalities. The methods, systems, and / or software may generate a specific and / or custom model for the individual whose heart is imaged, rather than a generic model.

[0004] Conventionally, certain intensive medical, imaging modalities, and invasive procedures are used as standard techniques to understand a patient's particular cardiovascular anatomy and physiology. Generally, these conventional techniques are time-consuming, invasive, and / or painful for the patient, and expensive. These techniques are commonly performed to understand parameters describing the patient's heart, including physiological, anatomical, and / or electrophysiological parameters of the patient's heart. In view of current methodologies and approaches, there is an unmet need for a low-cost, non-invasive, and rapid method of determining conventional cardiac parameters. The methods, systems, and / or software described elsewhere herein address such unmet needs by generating patient-specific cardiac models capable of determining, analyzing, and / or displaying anatomical, physiological, and / or electrophysiological parameters of tissues in a non-invasive and / or minimally invasive manner. To further reduce the computational cost of such platforms, the methods, systems, and software described herein are configured to run on standard processing devices (e.g., personal computing devices, laptop computing devices, tablets, smartphones, virtual reality headsets, etc.) rather than requiring expensive supercomputers or clustered computing devices traditionally used when solving brute forward solutions to generate a model of the patient's heart. To reduce processing time, a parallel processing architecture is used instead, e.g., hyper-threading or GPU-based parallel processing.

[0005] Aspects of the disclosure herein describe methods, systems, and / or software that include algorithms that can determine a patient's cardiac parameters, such as physiological parameters, anatomical parameters, and / or electrophysiological parameters. Optionally, the methods, systems, and / or software may be configured to analyze at least one image of the patient's heart. In some embodiments, the at least one image of the patient's heart includes images of a conventional MRI, a time-resolved computed tomography angiography (CTA), a 3D echocardiogram, or any combination thereof. In some embodiments, the methods, systems, and / or software analyze the at least one image and generate a model of the patient's heart that can be viewed on an output display device, e.g., a screen of a computing device. In some embodiments, the output display device may comprise a user interface that includes display information for one or more parameters of the heart. In some embodiments, the systems and / or software execute the methods described elsewhere herein using a typical processor of a system, e.g., a desktop or laptop computer, or other computing device, such as a smartphone, tablet, smartwatch, or any virtual reality device.

[0006] In some embodiments, a computer-implemented method is described herein for using a machine learning algorithm to model an individual's heart, the model including at least one of a functional feature and / or an electrophysiological feature of the heart, the method including: (a) receiving or acquiring an image of the individual's heart by an input software module; (b) segmenting the image of the heart by a segmentation software module, thereby generating at least one image segment; (c) applying a set of partial differential solvers by an analysis software module to the at least one image segment to solve a mathematical model, thereby generating an analysis result; and (d) generating a model of the at least one functional feature of the individual's heart using a modeling software module, the modeling software module using the analysis result of step (c). In some embodiments, the modeling software module uses the analysis result of step (c) to generate the functional feature, the electrophysiological feature, or a combination thereof of the individual's heart. In some embodiments, the set of partial differential solvers includes a finite element analysis. In some embodiments, the modeling software module includes a machine learning algorithm. In some embodiments, the functional feature includes a ventricular gauge pressure. In some embodiments, the functional feature comprises a wall stress of a heart chamber. In some embodiments, the functional feature comprises a representation of wall motion of at least a portion of the heart. In some embodiments, the functional feature comprises a representation of blood flow through a heart chamber. In some embodiments, the functional feature comprises a valve feature. In some embodiments, the functional feature comprises a perfusion feature, the perfusion feature comprising a representation of myocardial perfusion through the cardiac tissue. In some embodiments, the electrophysiological feature comprises current flow in the cardiac tissue. In some embodiments, the functional feature comprises a structural or dynamic property of cardiac scar tissue. In some embodiments, the functional feature comprises spatial and / or temporal passive and / or active stress response of the cardiac tissue. In some embodiments, the functional feature comprises spatial and / or temporal passive and active material properties.In some embodiments, the functional characteristics include spatial and / or temporal tissue strain energy of the cardiac tissue. In some embodiments, the functional characteristics include spatial and / or temporal tissue mechanical efficiency of the cardiac tissue. In some embodiments, the electrophysiological characteristics include spatial and / or temporal time and intensity of tissue activation of the cardiac tissue. In some embodiments, the electrophysiological characteristics include a current density map of the cardiac tissue. In some embodiments, the current density map includes at least one current vector. In some embodiments, the individual suffers from heart failure, congestive heart failure, cardiac ischemia, valvular heart disease, cardiomyopathy, heart attack, hypertrophic cardiomyopathy, pericarditis, pericardial effusion, heart murmurs, congenital heart disease, cardiac arrhythmia, coronary artery disease, or any combination thereof. In some embodiments, the cardiac image is an MRI. In some embodiments, the cardiac image is an echocardiogram. In some embodiments, the echocardiogram includes a 3D echocardiogram. In some embodiments, the segmentation software module includes a level set method, an image processing technique, and a machine learning algorithm trained using cardiac images from a population of individuals. In some embodiments, at least one image segment shows at least a portion of the individual's heart. In some embodiments, the analysis result includes at least one equation representing at least one factor associated with the cardiac image. In some embodiments, the machine learning algorithm is trained using parameter data from the population of individuals. In some embodiments, the method further includes displaying the model on a display of the computing device.

[0007] In some embodiments, described herein is a non-transitory computer-readable medium including software, the software using machine learning to model the individual's heart. In some embodiments, the generated model of the heart may include at least one of the functional features. Optionally, the software can cause a processor of a computer system to: (a) receive an image of the individual's heart; (b) segment the image of the heart, thereby generating at least one image segment; (c) apply an equation solver to the at least one image segment, thereby generating an analysis result; and (d) use a partial differential equation solver and / or a machine learning algorithm to generate a model of at least one functional feature and / or at least one electrophysiological feature of the individual's heart using the analysis result of (c).

[0008] In some embodiments, the segmentation module configured to segment the cardiac image includes a machine learning algorithm. In some cases, the machine learning algorithm may improve the accuracy of the segmentation algorithm by at least about 80%, at least about 82%, at least about 84%, at least about 86%, at least about 88%, at least about 90%, at least about 92%, at least about 94%, at least about 96%, at least about 98%, or at least about 99%.

[0009] In some embodiments, the equation solver comprises a partial differential equation solver. In some embodiments, the partial differential equation solver uses finite element analysis. In some embodiments, the generated model comprises at least one functional feature, at least one electrophysiological feature, or a combination thereof, of the individual's heart. In some embodiments, the functional feature comprises a ventricular gauge pressure and / or an atrial gauge pressure. In some embodiments, the functional feature comprises a wall pressure of one or more chambers of the heart. In some embodiments, the functional feature comprises a representation of wall motion of at least a portion of the heart. In some embodiments, the functional feature comprises a representation of blood flow through one or more chambers of the heart. In some embodiments, the functional feature comprises a feature of a valve of the heart. In some embodiments, the electrophysiological feature comprises a representation of myocardial perfusion through tissue of the heart. In some embodiments, the functional feature comprises structural and / or dynamic properties of scar tissue of the heart. In some embodiments, the functional feature comprises tissue perfusion of the heart. In some embodiments, the functional feature comprises spatial and / or temporal passive and / or active stress response of tissue of the heart. In some embodiments, the functional characteristics include spatial and / or temporal passive and / or active material properties. In some embodiments, the functional characteristics include spatial and / or temporal tissue strain energy of the cardiac tissue. In some embodiments, the functional characteristics include spatial and / or temporal tissue mechanical efficiency of the cardiac tissue. In some embodiments, the electrophysiological characteristics include spatial and / or temporal time and intensity of tissue activation of the cardiac tissue. In some embodiments, the model includes a current density map of the cardiac tissue. In some embodiments, the current density map includes at least one current vector. In some embodiments, the individual suffers from heart failure, congestive heart failure, cardiac ischemia, valvular heart disease, cardiomyopathy, heart attack, hypertrophic cardiomyopathy, pericarditis, pericardial effusion, heart murmur, congenital heart disease, cardiac arrhythmia, coronary artery disease, or any combination thereof. In some embodiments, the cardiac image is an MRI image. In some embodiments, the cardiac image is an echocardiogram image. In some embodiments, the cardiac image is a time-resolved CTA image.In some embodiments, the echocardiogram image is generated by 3D echocardiography. In some embodiments, the MRI image comprises a 4D MRI image or image dataset. In some embodiments, the image comprises a computed tomography angiography (CTA) image. Optionally, the computed tomography angiography image comprises a 4D computed tomography angiography image or image dataset. In some embodiments, the at least one image segment shows at least a portion of the individual's heart. In some embodiments, the analysis result comprises at least one equation representing at least one factor associated with the image of the heart. In some embodiments, the machine learning algorithm is trained using parameter data from a population of individuals. In some embodiments, the method further comprises displaying the model on a display of the computing device. Optionally, segmenting the image of the heart comprises a level set method or other image processing methodology such as cross-correlation, convolution, clustering, applied graph theory, or any combination of those methods.

[0010] Aspects of the present disclosure describe a computer-implemented method for generating a model of an individual's heart, the method including: (a) receiving or acquiring an image of the individual's heart by an input software module; (b) segmenting the image of the heart by a segmentation software module, thereby generating at least one image segment; (c) applying one or more differential equations to the at least one image segment using an analysis software module, thereby generating at least one analysis result; and (d) generating a model of the individual's heart using a modeling software module, using the analysis result of step (c). In some embodiments, the analysis result includes at least one functional feature, at least one electrophysiological feature, or any combination of those features. In some embodiments, the functional feature includes ventricular gauge pressures of the right and left ventricles. In some embodiments, the functional feature includes wall pressures of the heart chambers. In some embodiments, the functional feature includes wall motion of at least a portion of the heart. In some embodiments, the functional feature includes blood flow through the heart chambers. In some embodiments, the functional feature includes valve features. In some embodiments, the electrophysiological features include electrical properties of cardiac tissue. In some embodiments, the electrical properties include an activation map, a voltage map, or any combination thereof. In some embodiments, the electrical properties include at least one current vector. In some embodiments, the individual is suffering from or suspected of suffering from cardiac dysfunction. In some embodiments, the cardiac image is an MRI image. In some embodiments, the cardiac image is an echocardiogram image. In some embodiments, the echocardiogram includes a 3D echocardiogram. In some embodiments, the segmentation software module includes a machine learning algorithm, artificial intelligence, or a combination thereof, and is trained using one or more cardiac images from a population of individuals. In some embodiments, at least one image segment depicts at least a portion of the individual's heart.In some embodiments, the machine learning algorithm, artificial intelligence, or combination thereof is trained using segmented data from the population of individuals. In some embodiments, the computer-implemented method further comprises (e) displaying the model on a display of a computing device. In some embodiments, the cardiac image may include one or more images of the heart, diagnostic imaging images, or any combination thereof. In some embodiments, the one or more differential equations include one or more partial differential equations, ordinary differential equations, or any combination of such differential equations. In some embodiments, the one or more differential equations include finite element analysis equations. In some embodiments, the computer-implemented method further comprises generating a therapy-guiding parameter model using the analysis results of step (c). In some embodiments, the computer-implemented method further comprises generating a growth remodeling parameter model longitudinally over a period of time using the analysis results of step (c).

[0011] An aspect of the disclosure is a non-transitory computer readable medium including software that uses artificial intelligence to model an individual's heart, the software causing a processor to (a) receive or obtain an image of the individual's heart, (b) segment the image of the heart, thereby generating at least one image segment, (c) apply a series of numerical techniques to the at least one image segment, thereby generating an analysis result, and (d) use the analysis result of (c) to generate a model having at least one functional feature, at least one electrophysiological feature, or a combination thereof. In some embodiments, the functional feature includes a gauge pressure of the ventricle. In some embodiments, the functional feature includes a wall pressure of a heart chamber. In some embodiments, the functional feature includes a wall dynamics or wall kinetics of at least a portion of the heart. In some embodiments, the functional feature includes blood flow through one or more heart chambers. In some embodiments, the functional feature includes a valve feature. In some embodiments, the electrophysiological feature includes electrical properties of tissue of the heart. In some embodiments, the electrical properties include an activation map, a voltage map, or any combination thereof. In some embodiments, the electrical properties include at least one current vector. In some embodiments, the individual suffers from cardiac dysfunction. In some embodiments, the cardiac image is an MRI image. In some embodiments, the MRI includes CINE MRI, an MRI-based technique, or any combination thereof. In some embodiments, the MRI-based technique includes DENSE, tag-MR, SPAMM, or any combination thereof. In some embodiments, the cardiac image is an echocardiogram image. In some embodiments, the echocardiogram includes a 3D echocardiogram. In some embodiments, the at least one image segment illustrates at least a portion of the individual's heart. In some embodiments, the numerical technique includes at least one equation representing at least one functional feature, at least one electrophysiological feature, or a combination thereof associated with the cardiac image. In some embodiments, the software includes a segmentation algorithm for segmenting the cardiac image.In some embodiments, the segmentation algorithm comprises a machine learning algorithm, an artificial intelligence, or a combination thereof. In some embodiments, the machine learning algorithm comprises one or more machine learning algorithms, an ensemble of machine learning algorithms, or any combination thereof. In some embodiments, the machine learning algorithm, the artificial intelligence, or a combination thereof is trained with segmentation data from a population of individuals. In some embodiments, the software further causes the processor to (e) display the model on a display of the computing device, the virtual 3D device, or the virtual 4D device. In some embodiments, the numerical technique comprises a finite element analysis technique. In some embodiments, the display of the computing device comprises a screen of the computing device, an augmented reality display, a virtual reality display, or any combination thereof. In some embodiments, the software further causes the processor to generate a model comprising a therapy guidance parameter determined by at least one functional characteristic, at least one electrophysiological characteristic, or a combination thereof of the individual's heart. In some embodiments, the software further causes the processor to generate a model comprising a growth remodeling parameter determined by at least one functional characteristic, at least one electrophysiological characteristic, or a combination thereof of the individual's heart.

[0012] Aspects of the present disclosure describe a method for determining material properties of a region of an individual's heart, the method comprising: (a) receiving or acquiring an image of the individual's heart; (b) segmenting the image of the heart, thereby generating at least one image segment; (c) applying one or more differential equations to the at least one image segment, thereby generating at least one analysis result, the at least one analysis result comprising a functional parameter, an electrophysiological parameter, or a combination thereof; and (d) determining material properties of the at least one region of the individual's heart by the at least one analysis result. In some embodiments, an analysis software module applies the one or more differential equations to the at least one image segment. In some embodiments, the image is received or acquired by an image input software module. In some embodiments, a segmentation software module segments the image of the heart. In some embodiments, the image comprises one or more time-resolved sequential images. In some embodiments, the functional characteristic comprises ventricular gauge pressure of the right ventricle and the left ventricle. In some embodiments, the functional characteristic comprises blood perfusion of tissue of the heart. In some embodiments, the functional characteristic comprises wall pressure of one or more chambers of the heart. In some embodiments, the functional characteristic comprises wall motion of at least a portion of the heart. In some embodiments, the functional characteristic comprises blood flow through one or more chambers of the heart. In some embodiments, the functional characteristic comprises valve characteristics. In some embodiments, the electrophysiological characteristic comprises electrical properties of tissue of the heart. In some embodiments, the electrical properties of the tissue comprise an activation map, a voltage map, or a combination thereof. In some embodiments, the electrical properties comprise at least one current vector. In some embodiments, the individual is suffering from or suspected of suffering from cardiac dysfunction. In some embodiments, the image of the heart is an MRI, a 4D MRI, a time-resolved computed tomography angiogram (CTA), a 3D echocardiogram, a computed tomography (CT), a 3D CT, a 4D CT, or any combination of those images.In some embodiments, the segmenting step includes threshold segmentation, fast marching level set segmentation, hands-free segmentation, or any combination thereof. In some embodiments, the segmentation software module includes a machine learning algorithm, an artificial intelligence, or any combination thereof, and is configured to segment the image of the heart, the machine learning algorithm, the artificial intelligence, or any combination thereof being trained using an output of the threshold segmentation, the fast marching level set segmentation, the hands-free segmentation, or any combination thereof. In some embodiments, the at least one image segment shows at least a portion of the individual's heart. In some embodiments, the machine learning algorithm, the artificial intelligence, or combination thereof is trained using segmentation data from a population of individuals. In some embodiments, the method further includes (e) displaying a model of the individual's heart, the model being generated using at least one analysis result and material properties of at least one region of the heart. In some embodiments, the model is displayed on a display of the computing device. In some embodiments, the image of the heart may include one or more images of the heart, images of diagnostic imaging, or any combination thereof. In some embodiments, the one or more differential equations include one or more partial differential equations, ordinary differential equations, or any combination of such differential equations. In some embodiments, the one or more differential equations include finite element analysis equations. In some embodiments, the computer-implemented method further includes generating a treatment-guided parameter model using the analysis results of step (c). In some embodiments, the computer-implemented method further includes generating a growth remodeling parameter model longitudinally over a period of time using the analysis results of step (c). In some embodiments, steps (b)-(d) are completed within about 1 hour. [Brief description of the drawings]

[0013] The novel features of the invention are set forth with particularity in the appended claims. To better understand the features and advantages of the present invention, reference should be made to the following detailed description that sets forth illustrative embodiments in which the principles of the invention are utilized and the accompanying drawings in which:

[0014] [Figure 1] 2 illustrates a schematic representation of exemplary inputs and outputs of the software described in some embodiments herein. [Diagram 2] 1 illustrates an exemplary workflow utilizing the software described in some embodiments herein. [Figure 3A] 3A-3C illustrate an exemplary operational workflow and association of various software modules configured to compute and represent data model representations of clinical outcomes and classifications, as described in some embodiments herein. [Figure 3B] 3A-3C illustrate an exemplary operational workflow and association of various software modules configured to compute and represent data model representations of clinical outcomes and classifications, as described in some embodiments herein. [Figure 3C] 3A-3C illustrate an exemplary operational workflow and association of various software modules configured to compute and represent data model representations of clinical outcomes and classifications, as described in some embodiments herein. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0015] Cardiac imaging technology has improved significantly over the past two decades. Current cardiac imaging modalities such as MRI, ultrasound, and computed tomography (CT) provide information of blood flow and cardiac tissue motion. However, such imaging modalities are limited in that they do not measure functional tissue information from their structural imaging data output. Currently, functional imaging of organ systems such as the heart is performed by expensive, ionizing radiation and / or invasive imaging modalities, such as SPECT, PET, and / or PET-MR. Currently, there is no cost-effective, minimally invasive platform for determining cardiac physiological and anatomical information in an integrated manner. Furthermore, current methods, systems, and / or software configured to determine cardiac physiological and anatomical information require extensive computational resources (e.g., computer clusters with more than 16 processor cores) and significant amounts of processing time (e.g., more than 8 hours, up to a week) to generate physiological and anatomical analysis results, making them impractical and cumbersome when utilized in large real-world patient populations.

[0016] Described herein are methods, systems, software, and computer-implemented methods for modeling and analyzing the motion of one or more regions of a patient's heart wall, chamber, tissue, or any combination thereof, as determined from the dynamic (temporal and / or spatial) structural clinical cardiac imaging modalities described above (e.g., MRI, computed tomography, computed tomography angiography (CTA), time-resolved CTA, echocardiogram, etc.). In some examples, the methods, systems, software, and computer-implemented methods described herein may utilize non-ionized imaging data, such as structural MRI, ultrasound, etc., to determine functional and / or electrophysiological information (e.g., electrophysiological current density maps and / or metabolic energetics distribution) of the patient's heart. In some examples, the software and computer-implemented methods described elsewhere herein may be classified as structural and functional imaging techniques (FIT). Some of the unexpected advantages of the software and computer-implemented methods over conventional techniques are described elsewhere herein, but include the following: (1) reduced harmful exposure to ionizing radiation and isotopes, (2) faster processing time compared to conventional FIT, (3) additional functional measurements of the heart, such as local energy density, (4) reduced cost compared to conventional FIT, (5) comprehensive three-dimensional data set of electrophysiological measurements compared to traditional two-dimensional surface electrophysiological measurements, and (6) higher spatial resolution compared to conventional FIT.

[0017] Described herein are methods, systems, software, and / or computer-implemented methods for modeling an individual's heart, where the model presents or displays one or more cardiac parameters of the individual. In some embodiments, the cardiac model generated by the systems, software, and / or computer-implemented methods described herein may generate a three-dimensional representation of the subject's heart that may be displayed on a screen or display of a computing device. In some cases, the subject is a human, a non-human mammal, a non-human non-mammal, or any combination thereof. As described above, the methods, systems, software, and / or computer-implemented methods are beneficial in that they provide at least a non-invasive, rapid, efficient (in terms of the computing power required) and cost-effective means of acquiring various different types of individual cardiac data. In contrast, conventional techniques are invasive (or otherwise cumbersome), time-consuming, require much greater computing power, and are much more expensive. The software and computer-implemented methods described herein are also beneficial because they provide data and / or analysis results (e.g., functional and / or electrophysiological characteristics of the heart) in a single workflow that would otherwise require multiple different imaging modalities, procedures, tests, and / or workflows.

[0018] The methods, systems, software, and / or computer-implemented methods described herein may use full-field tissue displacements determined from images of the patient's heart. Optionally, the methods, systems, software, and / or computer-implemented methods may use direct displacement velocity measurement MRI-based techniques, such as DENSE, tag-MR, SPAMM, or any combination thereof, as input. These full-field tissue displacements are calculated using only multiple coupled physics-based algorithms and do not require mathematical assumptions. Such mathematical assumptions may include assumptions regarding material mechanical constitutive laws, or assumptions regarding the myocardial electrical tissue network and tissue conductance tensor.

[0019] The methods, systems, software, and / or computer-implemented methods (a) measure complete tissue displacement as a function of time directly from structural images, which is not measured using typical clinical MR-based imaging; (b) do not rely on the aforementioned assumptions; (c) local tissue properties (and thereby passive and / or active tissue health) are determined without ex vivo examination of the tissue; (d) the myocardial electrical tissue network geometry does not need to be known in order to generate the models described herein; (e) are computationally inexpensive, since the software does not require a computer cluster; After collecting sufficient data points, the method, system, and / or software provides better than expected results of anatomical, physiological, and / or electrophysiological characteristics of cardiac tissue for several reasons including: (a) using specific image processing, deep learning, and artificial intelligence (A1) algorithms to provide segmentation and provide analysis results after uploading the cardiac image files to the cloud; (b) the software can predict the patient's mechanical and electrical response to specific treatments such as ACORN (cardiac restraint device), MitroClip, ventricular assist device, gel injection therapy, cardiac resynchronization therapy, or any combination of these treatments.

[0020] overview 1 shows a flow diagram representation of the software (100) described herein. As shown, images of the heart (101) may be provided as input for the software (100), which may output a model that provides or displays information represented by a conventional electrophysiological map (102), a single photon emission computed tomography (SPECT) scan (103), a positron emission tomography (PET) scan (104), a positron emission tomography combined magnetic resonance (PET-MR) scan (105), some additional (e.g., functional, anatomical, and / or electrophysiological) cardiac measurements, or any combination thereof.

[0021] In some embodiments, the cardiac image (101) may include a cardiac magnetic resonance imaging (MRI) scan, an echocardiogram, a computed tomography angiogram (CTA), a time-resolved CTA, or any combination of such cardiac images. In some embodiments, the cardiac image (101) may include a cardiac CINE MRI image. In some embodiments, the cardiac echocardiogram may include an at least one-dimensional, at least two-dimensional, at least three-dimensional, or at least four-dimensional echocardiogram. However, it should be understood that other types of images showing cardiac anatomy as understood by those skilled in the art may be suitable for use with the software and methods described herein, including computed tomography (CT), CT angiogram, two-dimensional x-ray, or any combination thereof.

[0022] In some embodiments, the output of the software, system, and method may provide a non-invasive measurement of ventricular chamber gauge pressure. In some cases, the methods, systems, and / or software described elsewhere herein may include a non-invasive platform that provides better results than would be expected given their invasive counterparts. The disclosure provided herein describes, in some embodiments, a non-invasive software configured to measure the left ventricular pressure and / or the right ventricular pressure of a subject's heart by analyzing non-invasively collected images of the subject's heart as described elsewhere herein. In contrast, invasive approaches directly measure cavity pressures by (1) a transcatheter pressure transducer placed subcutaneously in the lumen cavity, or (2) a microelectromechanical system (MEMS) placed subcutaneously on the outflow tract wall for continuous beat-to-beat blood pressure measurements for ICU patients.

[0023] Furthermore, the software, systems, and / or methods described herein are not limited to a particular breadth of simultaneous measurements that can be performed and analyzed, as compared to conventional devices, systems, and methodologies. For example, a transcatheter pressure transducer is not only an invasive medical device, but its functionality is limited to measuring cardiac chamber pressure alone. On the other hand, the software, systems, and / or methods of the present invention can not only non-invasively determine intraluminal pressure, but can also simultaneously measure tissue mechanical active and / or passive properties at three-dimensional macro- and / or micro-tissue and / or organ scales.

[0024] The software, system, and / or method of the present invention may be configured to measure tissue stored stress in a non-destructive manner. Another potential method, as understood by those skilled in the art, may be to approximate the residual stress in the vertical wall of the heart destructively through ex vivo experiments. Knowledge of stored stress provides useful clinical insight for patients with diastolic heart failure (possibly with heart failure with preserved ejection fraction, HFpEF). Additionally, the software, system, and / or method may directly measure active myocardial contractile stress. Those skilled in the art will appreciate that the software, method, and / or system provide a solution to the unmet need to directly and non-invasively measure local active myocardial contractile stress and / or energy production density.

[0025] In some embodiments, the software, systems, and / or methods of the present invention may use one or more images of a subject's heart, for example, one or more CINE MRI images of the heart, to determine in vivo spatial and temporal measurements of the full strain tensor field (e.g., up to six strains).

[0026] In some cases, the one or more images may include from about 1 image to about 10,000 images. In some cases, the one or more images may include from about 1 image to about 5 images, from about 1 image to about 10 images, from about 1 image to about 25 images, from about 1 image to about 50 images, from about 1 image to about 100 images, from about 1 image to about 150 images, from about 1 image to about 500 images, from about 1 image to about 1,000 images, from about 1 image to about 10,000 images, from about 5 images to about 10 images, from about 5 images to about 25 images, from about 5 images to about 50 images, from about 5 images to about 100 images, about 5 images to about 150 images, about 5 images to about 500 images, about 5 images to about 1,000 images, about 5 images to about 10,000 images, about 10 images to about 25 images, about 10 images to about 50 images, about 10 images to about 100 images, about 10 images to about 150 images, about 10 images to about 500 images, about 10 images to about 1,000 images, about 10 images to about 10,000 images, about 2 5 images to about 50 images, about 25 images to about 100 images, about 25 images to about 150 images, about 25 images to about 500 images, about 25 images to about 1,000 images, about 25 images to about 10,000 images, about 50 images to about 100 images, about 50 images to about 150 images, about 50 images to about 500 images, about 50 images to about 1,000 images, about 50 images to about 10,000 images, about 100 images to about 1 The one or more images may include about 1 image, about 5 images, about 100 images to about 500 images, about 100 images to about 1,000 images, about 100 images to about 10,000 images, about 150 images to about 500 images, about 150 images to about 1,000 images, about 150 images to about 10,000 images, about 500 images to about 1,000 images, about 500 images to about 10,000 images, or about 1,000 images to about 10,000 images. In some cases, the one or more images may include about 1 image, about 5 images, about 10 images, about 25 images, about 50 images, about 100 images, about 150 images, about 500 images, about 1,000 images, or about 10,000 images. In some cases, the one or more images may include at least about 1 image, about 5 images, about 10 images, about 25 images, about 50 images, about 100 images, about 150 images, about 500 images, or about 1,000 images. In some cases, the one or more images may include up to about 5 images, about 10 images, about 25 images, about 50 images, about 100 images, about 150 images, about 500 images, about 1,000 images, or about 10,000 images.

[0027] In some cases, the methods, systems, and / or software may implement tissue displacement tracking to calculate the entire strain field, which in some examples may be used to measure akinetic properties of cardiac tissue.

[0028] In some embodiments, the software, systems, and / or methods described herein can determine in vivo spatial measurements of stored energy, i.e., stored stress and / or residual stress, in a subject's ventricular wall. In some cases, the stored strain and stress can be directly proportional to the health of the myocardial tissue of the heart.

[0029] In some embodiments, the software, systems, and / or methods may determine spatial and / or temporal force, stress, and / or energy fields generated by myocardial contractions of the heart. In some embodiments, the models generated by the methods, systems, and / or software may represent or display the coupling of electrical stimulation and muscle contraction over the entire cardiac cycle.

[0030] In some embodiments, the software, systems, and / or methods may non-invasively determine in vivo measurements of spatial and / or temporal potential difference fields, thereby resulting in measurements of tissue conductivity tensor fields. In some embodiments, the software, systems, and / or methods may determine in vivo electrical activity of the myocardium as a function of time and three-dimensional space, i.e., a four-dimensional measurement that includes both time and three-dimensional space.

[0031] Additional details regarding the software, systems, and / or methods may be found in the following sections.

[0032] Software The software (100) described herein may include a sequence of computer-readable instructions written to perform specified tasks executable by one or more processors of a processor of a computing device, such as a central processing unit (CPU). The computer-readable instructions may be implemented as software modules, such as functions, objects, application programming interfaces (APIs), computing data structures, or any combination thereof, that perform particular tasks or implement particular abstract data types, as seen in Figures 3A-3C. In light of the disclosure provided herein, one skilled in the art will recognize that software can be written in a variety of languages ​​and in a variety of versions.

[0033] The functionality of the computer readable instructions may be combined or distributed as desired in various embodiments. In some embodiments, the software described herein may include one sequence of instructions. In some embodiments, the software described herein may include multiple sequences of instructions. In some embodiments, the software described herein may include at least one sequence of instructions. In some embodiments, the software described herein may be provided from one location, e.g., the software may be loaded onto a standalone computing device. In other embodiments, the software described herein may be accessed from multiple locations, e.g., the software may be located on a cloud computing or other remote server platform and accessed from one or more user locations at a computer via the server. In some embodiments, the software described herein may include one or more software modules. In various embodiments, the software described herein may comprise, in part or in whole, one or more web applications, one or more mobile applications, one or more standalone applications, one or more web browser plug-ins, extensions, add-ins, add-ons, or any combination thereof.

[0034] In some embodiments, the software (100) may include and / or utilize one or more software modules, as shown in FIGS. 3A-3C. The software modules described herein may be implemented in a number of ways. In some embodiments, a software module may include a file, a section of code, a programming object, a programming structure, or any combination thereof. In some cases, a software module may include multiple files, multiple sections of code, multiple programming objects, multiple programming structures, or any combination thereof. In some examples, one or more software modules may include, by way of non-limiting examples, a web application, a mobile application, and / or a standalone application. In some embodiments, multiple software modules may be a single computer program or application. In some cases, one or more software modules may be located within multiple computer programs and / or applications. In some cases, a software module may be hosted on one machine. In some examples, a software module may be hosted on multiple machines. In some cases, a software module may be hosted on a distributed computing platform, e.g., a cloud computing platform. In some embodiments, a software module may be hosted on one or more machines in one location. In some cases, a software module may be hosted on one or more machines in multiple locations. Thus, it should be understood that the software described herein may run on a first computing device and access software modules that are on a second computing device or stored in the cloud.For example, when the software described herein is said to utilize a software module, the software module may be on the same computing device as the software that utilizes it, or it may be on a separate computing device or on the cloud.

[0035] Non-limiting examples of the types of modules that may be found in some embodiments of the innovative software described herein include an input software module, a segmentation software module, an analysis software module, a modeling software module, or any combination thereof.

[0036] Input Software Module In some embodiments, the input software module may include a component of and / or be utilized by the software (100) to generate one or more anatomical, physiological, and / or electrophysiological characteristics of cardiac tissue. The input software module may be configured to receive and / or process data (101) transmitted to a computing device. In some examples, the data received by the input software module may be associated with and / or representative of an individual's heart. In some cases, the data received by the input software module may include an image of a heart or a portion of a heart. In some examples, the data received by the input software module may include non-static, i.e., dynamic, time-varying images, such as images generated by an imaging modality, e.g., indicative of cardiac motion and / or blood flow. Non-limiting examples of modalities indicative of cardiac motion may include echocardiograms, MRI, computed tomography angiograms, time-resolved CTA, or any combination thereof. In some cases, the echocardiograms may include at least one-dimensional, at least two-dimensional, at least three-dimensional, or at least four-dimensional echocardiograms. In some examples, the MRI modality may include CINE MRI. In some examples, the MRI may include 3D MRI or 4D MRI. In some cases, the modality showing cardiac motion may include DENSE, Tag-MR, SPAMM, or any combination thereof. As used herein, "image" may include both a single image or a collection of images (e.g., video or motion capture). As used herein, "static" refers to an image that does not capture cardiac motion (i.e., dynamics). As used herein, "non-static" refers to an image that shows cardiac motion (i.e., dynamics).

[0037] The data received by the input software module may, in some embodiments, include individual-specific non-image data, such as electrocardiogram (ECG), electronic medical record (EMR) data, and / or subject and / or patient demographic data. In some cases, the demographic data includes the subject data's gender, age, ethnicity, city and place of residence, or any combination thereof. In some examples, the EMR data may include blood pressure, cholesterol, antibody panel readings, white blood cell count, troponin levels, blood glucose levels, hematocrit, the individual's past disease or illness history, whether the individual is a smoker or drinks alcohol, and how frequently the individual smokes or consumes alcoholic beverages, or any combination thereof.

[0038] In some cases, non-limiting examples of data received by the input software module may include demographic data, medical record data (including electronic medical record data), ECG data, echocardiogram data including 2D, 3D, and / or 4D echocardiogram data, MRI data including CINE MRI, CT data, CT angiogram data, time-resolved CTA data, X-ray data, angiogram data, or any combination thereof. The received data may be complete or partial in itself. In some cases, the received data may be associated with, relate to, and / or indicative of an individual's heart, the heart of an individual being evaluated for a cardiac disease, cardiac anomaly, and / or suspected of having a cardiac disease. In some cases, the received data may include a retrospective data set of a population of individuals who had or were not suspected of having a cardiac disease at the time the data was recorded.

[0039] The data may be received by the software via any known communication means, including via wired or wireless communication means with another computing device, a server, a cloud, a device capable of sending data to a computing device running the input software module, or any combination thereof.

[0040] In some cases, data received by the input software module may be processed by the input software module. For example, in some cases, the received data may be identified by the input software module (e.g., with respect to content or type of data) and assigned a value based on the identification to further determine how the received data may be processed by a software algorithm. For example, an ECG received by the input software module may be identified as an ECG rather than an image of the heart in some embodiments and then sent to a different software module than the software module that is supposed to process the image of the heart. In some cases, a static image of the heart may be identified and sent to a different software module than a non-static image of the heart. In some examples, the input software module may clean the received data, for example, with respect to associated metadata and labels. In some cases, the input software module may clean the received data to remove data that can identify a patient and / or an individual (e.g., the individual's name, address, etc.). In some cases, the cleaning may include denoising the data to remove image artifact noise to increase the signal-to-noise ratio of the relevant signal and / or region of the data to be analyzed.

[0041] After receiving the data, the software may further process the received data. In some cases, the input software module may send the data (including pre-processed and post-processed data) to another module within the software, such as, for example, a segmentation software module, an analysis software module, and / or a modeling software module.

[0042] Segmentation Software Module In some embodiments, as seen in FIG. 3A, the software described herein may include a segmentation software module (304). In some cases, the segmentation software module (304) may be configured to segment one or more received cardiac images. In some cases, the segmentation software module may remove and / or reduce motion artifacts induced during the initial acquisition of one or more images (101) input to the method, system, and / or software. In some examples, the one or more images may include static and / or non-static images. In some examples, segmentation may include a process of segmenting data found in an image into different data subtypes, i.e., data collections. For example, the segmentation software module may be configured to separate the data of the image into a first component determined to be a signal and a second component determined to be background (i.e., data that is not part of a signal). In some cases, the first component of data determined by the software to be a signal may include data that the software may further analyze to arrive at a diagnostic indicator, a functional parameter, a physiological parameter, an electrophysiological parameter, or any combination thereof. In some cases, the second component of the data determined to be background may be subtracted from the original data. For example, in some cases, the segmentation software module may identify a segment in the image that includes the heart to separate data associated with the heart from background elements in the image. In some examples, the segmentation performed by the segmentation software module may be applied to both static and non-static image components. The segmentation may be applied to different anatomical components of the heart. In some cases, the different anatomical components of the heart may include the aorta, atrium, trileaflet valve, SA node, Purkinje fibers, bileaflet valve, ventricle, or any combination of those components. For example, the image data may be segmented to separate (or isolate) a segment of the image representing the aorta from an image of the heart.

[0043] In some embodiments, the segmentation software module may be configured to remove environmentally induced or patient induced motion artifacts present in the dynamic volumetric images of the patient and / or subject's internal organs. In some cases, the induced motion artifacts may be caused by the patient's breathing and / or macro-scale body movements while one or more volumetric and / or temporal volumetric images of the patient are acquired. In some cases, the environmentally induced motion artifacts may include movement of a stationary surface on which the object and / or patient rests during acquisition of the images. In some examples, the environmentally induced motion artifacts may include movement of the image acquisition system relative to the patient or subject being imaged.

[0044] In some cases, the segmentation software module may remove environmentally or patient-induced motion artifacts present in the imaging dataset by spatially tracking and realigning the identified surfaces of one or more two-dimensional cross-sectional images. In some cases, spatially tracking and realigning the time series of two-dimensional images will significantly improve the sensitivity, accuracy, and / or analysis of one or more downstream software modules (e.g., 306, 308, 310, 312, 314, 315, 316, or any combination thereof). In some cases, the two-dimensional cross-sectional images may include images generated by volumetric imaging modalities described elsewhere herein, such as MRI, CT, time-resolved CTA, echocardiogram, or any combination thereof. In some cases, the volumetric images may represent a time series of volumetric images, such as a series of cross-sectional images over time (i.e., a volumetric dataset) of an organ system of a subject or patient. In some cases, one or more two-dimensional cross-sectional images may be realigned through methods of cross-correlation and / or feature co-registration. In some cases, the segmentation software module may perform at least two sets of realignment of two-dimensional cross-sectional images, where the two sets of two-dimensional cross-sectional images include orthogonal imaging planes. For example, if a three-dimensional spatial coordinate system of X, Y, and Z is to be superimposed on the object at a given orientation of the object, one set of two-dimensional cross-sectional images may include images along the plane of the X and Y axes, while the other set of two-dimensional cross-sectional images may include images along the plane of the YZ axis. In some embodiments, the orthogonal two-dimensional cross-sectional images may include images along any of the following image planes: XY plane, XZ plane, or YZ plane.

[0045] In some embodiments, the segmentation software module may segment the imaging dataset using thresholding segmentation, fast marching level set segmentation, hands-free segmentation, or any combination thereof.

[0046] In some embodiments, the segmentation software module may be configured to utilize one or more artificial intelligence and / or machine learning algorithms. The one or more artificial intelligence or machine learning algorithms may include neural networks. In some examples, the one or more machine learning and / or artificial intelligence algorithms may utilize computer vision to analyze the received one or more images. In some embodiments, the machine learning and / or artificial intelligence algorithms may include algorithms that are first trained on segmented data of a population of subjects segmented using any of the aforementioned segmentation techniques described elsewhere herein. In some cases, the population data may include image data and non-image data. In some embodiments, the population data may include both normal data (i.e., data of individuals identified as not having a cardiac disease or condition) and abnormal data (i.e., data of individuals identified as having a cardiac disease or pre-disease condition).

[0047] In some cases, the segmentation software module may output one or more datasets separated from other data in the image, as described elsewhere herein. For example, the dataset output may include the individual's heart (either static or non-static) segmented from the image background. Additionally or alternatively, the dataset output may include a portion or region, e.g., the aorta, of the individual's heart (either static or non-static) segmented from the image background and / or the remainder of the heart in the image.

[0048] After segmenting the image data, the segmentation software module can send and / or provide one or more segmented data sets to another module within the software, such as, for example, an analysis software module and / or a modeling software module described elsewhere herein.

[0049] Mesh Software Module In some cases, the segmented and / or aligned images processed by the segmentation software module may then be provided and / or sent to a mesh software module (306). In some cases, the mesh software module may generate one or more three-dimensional meshes of one or more segmented and / or aligned temporal volumetric data sets of one or more images of the patient's heart. In some cases, the three-dimensional mesh may include a cubic mesh. In some cases, the size of the cubic mesh elements may be influenced by the degree of motion of the subject's heart, the type of partial differential equation to be solved (e.g., strain, stress, and / or diffusion), an error assessment, or any combination thereof. In some cases, the error assessment may include an estimation or prediction of the degree of segmentation and image realignment errors described elsewhere herein. In some cases, the three-dimensional mesh generated by the mesh software module (306) may be used by other software modules (e.g., 308, 310, 312, 314, 315, 316, or any combination thereof) to calculate functional parameters, physiological parameters, electrophysiological parameters, electrophysiological maps, velocities of cardiac structures, accelerations of cardiac structures, stress and / or strain tensor fields, mechanical stress and / or strain, or any combination thereof. In some examples, the mesh generated by the mesh software module may then be used as an input for the kinematics analysis software module (308) to calculate further physiological, mechanical, electrical, or any combination thereof analysis results.

[0050] In some examples, the mesh software module may generate a mesh composed of discrete mesh elements. In some cases, the discrete elements may include cubic mesh elements, tetrahedral mesh elements, or any combination of these element types. In some cases, the discrete mesh elements may comprise one or more nodes, which may be located at the junction of two or more edges for each mesh element of the mesh generated by one or more volumetric images of the patient's heart.

[0051] In some cases, the mesh elements may include from about 4 nodes to about 64 nodes. In some cases, the mesh elements may include from about 4 nodes to about 8 nodes, from about 4 nodes to about 10 nodes, from about 4 nodes to about 20 nodes, from about 4 nodes to about 27 nodes, from about 4 nodes to about 64 nodes, from about 8 nodes to about 10 nodes, from about 8 nodes to about 20 nodes, from about 8 nodes to about 27 nodes, from about 8 nodes to about 64 nodes, from about 10 nodes to about 20 nodes, from about 10 nodes to about 27 nodes, from about 10 nodes to about 64 nodes, from about 20 nodes to about 27 nodes, from about 20 nodes to about 64 nodes, or from about 27 nodes to about 64 nodes. In some cases, the mesh elements may include about 4 nodes, about 8 nodes, about 10 nodes, about 20 nodes, about 27 nodes, or about 64 nodes. In some cases, the mesh elements may include at least about 4 nodes, about 8 nodes, about 10 nodes, about 20 nodes, or about 27 nodes. In some cases, the mesh elements may include up to about 8 nodes, about 10 nodes, about 20 nodes, about 27 nodes, or about 64 nodes.

[0052] Analysis Software Module In some embodiments, the methods, systems, and / or software described herein may comprise and / or be configured to comprise or utilize one or more analysis software modules (308, 310, 312, 314, 315, 316, or any combination thereof), as seen in FIG. 3A. The analysis software module may be configured to perform an analysis process on one or more data sets received by the software. In some examples, the data received by the analysis software module may be pre-processed by an input software module and / or a segmentation software module described elsewhere herein. In some examples, the analysis software module may be configured to perform an analysis function on the data it receives. In some cases, the analysis function may include applying a mathematical function or method (e.g., finite element analysis, convolution, cross-correlation, deconvolution, maximum intensity projection, etc.) to solve a physics-based mathematical model (e.g., partial differential equations that govern the laws of physics) constructed by the input data. The data received by the analysis software module may comprise image data, non-image data, or any combination thereof, as described elsewhere herein. In some cases, the partial differential equations may relate to the physical laws of conductance, diffusion (eg, of a fluid), strain, stress, or any combination thereof, as described elsewhere herein.

[0053] In some cases, the analysis software module may perform finite element analysis mathematical operations on the data it receives, thereby generating an analysis result. In some cases, the analysis result may include at least one equation that represents the kinematic characteristics of the heart. In some examples, the analysis result may represent a quality and / or characteristic of the data that directly correlates to physiological, anatomical, and / or electrophysiological parameters of the heart. In some cases, finite element analysis may be applied by the analysis software module to the three-dimensional mesh cardiac data described elsewhere herein to generate an analysis result that includes a mathematical representation of the motion of the heart wall and / or a portion of the heart wall. In some examples, finite element analysis may be applied by the analysis software module to the cardiac image data to generate an analysis result that includes a mathematical representation of the strain tensor of the heart wall and / or a portion of the heart wall. In some cases, finite element analysis may be applied by the analysis software module to the cardiac image data to generate an analysis result that includes a mathematical representation of the density or flow of electrical current through the cardiac tissue or a portion of the cardiac tissue. In some examples, finite element analysis may be applied by the analysis software module to the cardiac image data to generate analysis results including a mathematical representation of motion or deformation gradients of the heart walls, valves, substructures, any combination thereof, and / or any portion of the heart walls, valves, and / or substructures. In some cases, finite element analysis may be applied by the analysis software module to cardiac image data obtained from an image of the heart to generate analysis results including a mathematical representation of blood flow and / or perfusion through the heart or a portion of the heart.

[0054] In some embodiments, the analysis software module may utilize non-image data, as described elsewhere herein, to generate the analysis results. In some cases, the analysis software module may utilize non-image data along with the image data to generate the analysis results. In some examples, the non-image data may provide a framework and / or inform how finite element analysis techniques may be applied to generate the analysis results.

[0055] In some cases, after generating the analysis results, the analysis software module may transmit the analysis results to another module of the software, for example, a modeling software module. In some cases, the modeling software module and the analysis software module may be a single combined module of the software. In some examples, the modeling software module and the analysis software module may be separate modules of the software. In some examples, the modeling software module may display the generated model via a display module. In some cases, the display module may include an open source software package such as Para View.

[0056] Kinematic Analysis Software Module In some cases, the analysis software module may comprise a kinematic analysis software module (308), as seen in FIGS. 3A-3C. In some examples, the kinematic analysis software module may receive as input the output of the mesh module (306), described elsewhere herein. In some cases, the kinematic analysis software module may be configured to determine the velocity and / or acceleration of each of the plurality of nodes of the mesh generated by the mesh module (306). In some examples, the kinematic analysis software module (308) may calculate the displacement of each of the plurality of nodes of the mesh. In some cases, the kinematic analysis software module may calculate the Lagrangian displacement of each of the plurality of nodes of the mesh.

[0057] In some cases, the velocity, acceleration, displacement, strain, or any combination of these calculated metrics determined by the kinematic analysis software module may then be used as input to a pressure and flow analysis software module (312), a fiber orientation analysis software module (310), an energetics analysis software module (316), or any combination thereof, analysis software modules to further process the dynamic kinematic data and arrive at physiological analysis results, as described elsewhere herein.

[0058] Pressure and flow analysis software module In some cases, the analysis software module may include a pressure and flow analysis software module (312). In some cases, the pressure and flow analysis module may be configured to receive the velocity, acceleration, displacement, strain, or any combination of calculated metrics thereof from the kinematics analysis software module (308) and determine cardiac anatomical features related to flow or pressure generated by the patient's heart walls and / or blood within the patient's heart. In some cases, the cardiac anatomical features may include heart valves. In some examples, the flow of blood through the atria and into the ventricles may be calculated by the pressure and flow analysis module. In some cases, the flow of blood through the ventricles and into the supporting vasculature may be calculated by the pressure and flow analysis module. In some cases, pressure and / or flow parameters of blood flow within the heart may be calculated by applying Navier-Stokes equations to the interaction between the motion of the heart walls and / or cardiac anatomical features as determined by the kinematics analysis software module (308) and the blood within the heart chambers. In some examples, blood may be considered a non-Newtonian fluid for purposes of calculating flow and pressure. In some cases, the pressure and blood flow calculated by the pressure and blood flow analysis module (312) can be used as inputs to a dynamics analysis module (315) to calculate stress and strain in the patient's heart wall and / or anatomical features of the heart.

[0059] Dynamics Analysis Software Module In some examples, the analysis software module may include a kinetic analysis software module (315) configured to calculate a stress and / or strain tensor matrix for each element of the mesh generated by the mesh software module (306). In some cases, the kinetic analysis module (315) may receive as input the pressure and flow determined by the pressure and flow analysis software module (312) to calculate the stress and / or strain tensor matrix. In some cases, the strain tensor and / or stress tensor matrix may include a matrix size of 3×3. In some cases, the strain tensor and / or stress tensor matrix may include stress and / or strain generated internally within the cardiac wall tissue. In some cases, the kinetic analysis software module (315) may be configured to determine active stress at each node of the plurality of nodes of each mesh element independent of other nodes of the plurality of nodes of the mesh element. Optionally, the calculated stress and / or strain tensor matrices may then be provided as input to a fiber analysis software module (310) in addition to displacement, velocity, acceleration, or any combination thereof.

[0060] In some cases, the kinetic analysis module (315) may iteratively refine and / or modify the fiber orientation of the myocardium of the patient's heart. In some cases, the iterative refinement and / or modification of the fiber orientation may be completed in conjunction with the fiber analysis software module (310) described elsewhere herein.

[0061] In some cases, the dynamics analysis module 315 may calculate an activation time field as a function of time and space. In some cases, the activation time field may include myocardial conductivity data of the subject's and / or patient's heart.

[0062] Fiber Analysis Software Module In some cases, the analysis software module may include a fiber analysis software module (310) configured to determine the orientation of myocardial fibers of the patient's cardiac tissue. In some examples, the fiber analysis software module (310) may determine the orientation of at least one fiber. In some cases, the fiber analysis software module (310) may determine the orientation of multiple fibers. In some examples, the fiber analysis software module (310) may determine the orientation of myocardial fibers by considering the displacement, velocity, acceleration, or any combination thereof output in combination with the calculated stress and / or strain tensor output of the kinetic analysis software module (315). In some cases, the displacement, velocity, acceleration, stress, strain, or any combination thereof parameters are considered by the fiber analysis software module as parameters having values ​​that vary in spatial and temporal domains and / or dimensions.

[0063] Energetics Analysis Software Module In some cases, the analysis software module may include an energetics analysis software module (316) configured to determine the metabolic activity, i.e., viability, of a particular region of the patient's cardiac tissue. In some cases, the energetics analysis software module (316) may receive as input the displacement, velocity, acceleration, or any combination of outputs thereof, of the kinematics analysis module (308) in combination with the stress and / or strain output of the kinetics analysis software module (315). In some examples, the energetics analysis software module (316) may calculate strain energy, which includes the integral of stress multiplied by the strain output of the kinematics analysis module (308). In some cases, the analysis software module (316) may calculate mechanical forces of the cardiac tissue. In some cases, the mechanical forces may include the integral of stress multiplied by strain rate as a function of time. In some cases, healthy tissue may be determined from a threshold of strain energy and / or mechanical force. For example, moving regions of a subject's myocardium may be associated with low values ​​of strain energy and / or mechanical force. In some instances, dead, necrotic, and / or apoptotic myocardium may also be associated with low values ​​of strain energy and / or mechanical force.

[0064] Electrophysiology Analysis Software Module In some examples, the analysis software module may include an electrophysiology analysis software module (314) that may be configured to determine the spatial distribution of electrical currents and how they propagate through the patient's cardiac tissue. In some examples, the electrophysiology analysis software module (314) may receive as input the output of the energetics analysis software module (316) and the kinetics analysis software module (315) and output a current density plot superimposed on a three-dimensional mesh as described elsewhere herein. In some cases, the output of the kinetics analysis software module may include an activation time map as described elsewhere herein. In some examples, the electrophysiology analysis software module may calculate the current density plot by solving Maxwell and / or Maxwell-like differential equations. In some examples, the electrophysiology analysis software module may determine the electrical properties of the patient's cardiac tissue by an inverse finite element approach. In some cases, the electrophysiology analysis software module (314) may estimate the cardiac electrical conductance network that shares a relationship with the cardiac Purkinje fibers.

[0065] Modeling Software Module In some cases, the software may include a modeling software module. In some examples, the modeling software module may be configured to generate a model of the individual's heart based on data of the individual's heart and / or data related to the individual's heart (including image data and non-image data as described elsewhere herein). In some cases, the modeling software module may generate the model (or other type of output) using analysis results generated by the analysis software module. In some examples, the modeling software module may generate the model using one or more analysis results of one or more analysis software modules and a mesh software module.

[0066] In some cases, the model generated by the modeling software may include one or more of functional, physiological, and / or electrophysiological parameters. In some examples, the model generated may include a grayscale and / or color two-dimensional or three-dimensional model of the individual's heart and / or a portion thereof. In some examples, the model of the individual's heart and / or a portion thereof may be displayed on a display of a computing device. In some cases, the model may be an interactive model that allows one or more users to manipulate the model displayed on a computer display, view different portions of the model, and / or view slices across the model. In some cases, the model may be viewed in virtual reality. In some examples, one or more users may utilize a virtual reality headset and input devices to visualize and / or manipulate the model. In some cases, one or more users may manipulate the model through physical touch (e.g., in examples where the display is a touchscreen display), a mouse and keyboard, or any combination thereof. In some examples, the physical touch may include one or more gestures that may allow the user to manipulate the model. In some cases, the one or more gestures may include pinching in to zoom in on the model or pinching out to zoom out on the model.

[0067] In some cases, the modeling software module may utilize an artificial intelligence or machine learning algorithm configured to assist and / or complete one or more methods and / or calculations described by one or more analysis modules. The artificial intelligence or machine learning algorithm may include a neural network. In some cases, the machine learning algorithm and / or artificial intelligence may be first trained on data of a population of individuals. In some cases, the data of a population of individuals may include image data and non-image data. In some embodiments, the data of a population of individuals may include both normal data (e.g., data of healthy individuals without a disease) and abnormal data (e.g., data of individuals with a disease or pre-disease state, as described elsewhere herein).

[0068] In some cases, the model may include and / or display one or more of physiological parameters, anatomical parameters, and / or electrophysiological parameters. In some examples, the one or more physiological, anatomical, and / or electrophysiological parameters may be overlaid directly on the model when displayed with and / or associated with the model or a section and / or region of the model, e.g., the physiological, anatomical, and / or electrophysiological parameters may appear when a mouse or cursor is held over the model or a section of the model by one or more users.

[0069] In some embodiments, the modeling software module may generate a model that includes in vivo spatial and temporal measurements of the complete strain tensor field. In some examples, the strain tensor field may include up to six components. In some cases, the stress tensor field may include up to six components. In some examples, the modeling software module may generate a model that may include in vivo spatial measurements of stored energy, e.g., stored stress and / or residual stress in the heart wall, particularly the ventricular (LV) wall. In some cases, the modeling software module may generate a model that includes spatial and temporal force, stress, and energy fields generated by myocardial contraction. In some examples, the models generated by the software and methods described herein may present and / or display the coupling of electrical stimulation and muscle contraction throughout a complete cardiac cycle. In some cases, the modeling software module may non-invasively generate a model that includes in vivo measurements of the spatial and temporal potential difference fields of the heart to enable the determination of the cardiac tissue conductance tensor field. In some examples, the modeling software module may generate a model including myocardial in vivo electrical activity as a function of time and / or in three-dimensional space. In some cases, the model generated by the modeling software module may include a voltage map and / or activation time map of the entire heart and / or a portion thereof of the individual. In some cases, the model generated by the modeling software module may include at least one vector representing electrical current through the heart or a portion thereof of the individual. In some cases, the model generated by the modeling software module may include an individual's heart wall thickness measurement or a thickness of a portion of the heart wall. In some examples, the model generated by the modeling software module may include information related to at least one valve of the heart, including, for example, the mechanics of the operation of the valve and / or the performance of the valve. In some cases, the model generated by the modeling software module may include measurements of blood flow and / or blood diffusion through the heart, cardiac tissue, or portions or regions thereof.In some cases, the model generated by the modeling software module may include oxygen metabolism measurements of at least a portion of the individual's heart. In some cases, the model generated by the modeling software module may include measurements of cardiac tissue perfusion, e.g., myocardial tissue perfusion. In some examples, the model generated by the modeling software module may include measurements of scar tissue formation over a portion of the myocardium of the heart. In some cases, the model, when displayed, may include range-based visual indicators of each dimension or parameter of the model, as described elsewhere herein. In some cases, the visual indicators may include overlays of grayscale maps, color maps, heat maps, or any combination thereof, where the overlays are spatially superimposed on the three-dimensional model of the heart. In some examples, the displayed overlays may be correlated with simultaneously displayed legends that may inform one or more users of the numerical values ​​or categorical descriptions of particular dimensions or parameters, as described elsewhere herein.

[0070] In some embodiments, certain data may not be associated with the displayed model, but rather is output in other formats, such as, for example, raw numerical values. In some examples, data not associated with a model may include cardiac efficiency values. In some cases, data not associated with a model may include quantitative values ​​associated with one or more of the American Heart Association (AHA) cardiac segments. In some cases, the model and / or data not associated with a model may be output as text, data (e.g., ".txt", ".dat") for future review, recording, and / or transfer of HIPPA compliant data between a patient and a provider and / or between two different providers.

[0071] It should be understood that any of the software modules may be combined into a single module or may be implemented by fewer modules. The software modules described herein provide exemplary ways for implementing the methods and / or software algorithms described herein, and one of ordinary skill in the art will understand that modules with different names or different functions are equally suitable for use with the software described herein. One or more of the software modules described herein can accept and / or receive as input one or more output results of the calculated and / or processed data. For clarity, one or more software modules are described independently of each other, but one of ordinary skill in the art will readily recognize and understand that the software described herein may include one or more of such software modules to provide one or more analytical results as described elsewhere herein.

[0072] Treatment Optimization Module In some cases, the method, system, and / or software may include a treatment optimization module (317), as seen in FIG. 3B. In some cases, the treatment optimization module may receive as inputs mesh (306), kinematics (308), fibers (310), electrophysiology (314), pressure and flow (312), kinematics (315), or any combination of the outputs of these analysis modules. In some examples, the treatment optimization module may suggest and / or guide a surgical intervention of the subject's heart. In some examples, the treatment optimization module may output a three-dimensional map of the patient's heart and recommendations of regions that would benefit from gel injection. In some examples, the gel injection may be configured to reduce local stress on regions of failing cardiac tissue and / or prevent further dilation of diseased ventricles and / or atria of the subject's heart. In some cases, the output of the treatment optimization module may guide the design of material properties and / or stiffness of the cardiac-based implant. In some cases, a physician may implant a rigid structure over one or more regions of the subject's heart to constrain the one or more regions of the subject's heart and prevent expansion caused by heart failure. In this example, the treatment optimization module may be used to determine parameters of the implant based on the analysis and output provided by the inputs described above.

[0073] In some cases, the treatment optimization module (317) may output one or more treatment-guiding parameters. In some cases, the one or more treatment-guiding parameters may be displayed as a three-dimensional model of the treatment-guiding parameters superimposed on a three-dimensional volumetric representation of the subject's heart. In some cases, co-registration between the two models may provide the healthcare provider and / or physician with a view to relating the treatment-guiding parameters to the cardiac anatomy.

[0074] Active Growth Remodeling Module In some cases, the method, system, and / or software may include an active growth remodeling module (319), as seen in FIG. 3C. In some examples, the active growth remodeling module (319) may receive as input the mesh (306), kinematics (308), fiber (310), pressure and flow (312), dynamics (315), energetics (316), or any combination of the outputs of these analysis modules. In some examples, the active growth remodeling module may be configured to determine the effectiveness and / or outcome of a clinical intervention to treat a cardiac disease and / or condition of a subject. The active growth remodeling module may be configured to monitor the resulting effects of providing a gel-based infusion therapy for heart failure in a patient. The active growth remodeling module may analyze both in vivo and / or in vitro datasets generated by one or more of the aforementioned modules described elsewhere herein. In some cases, the in vivo and / or in vitro datasets may include one or more longitudinal datasets of an MRI scan of the subject over a period of time.

[0075] In some cases, the output of the active growth remodeling module may include one or more growth rate parameters. In some examples, the one or more growth rate parameters may include the growth rate of the patient's myocardium in both the spatial and temporal domains. In some cases, the one or more growth rate parameters may be modeled into three-dimensional growth rate parameters that are overlaid on a three-dimensional volumetric model, described elsewhere herein, of the subject's heart. In some cases, coregistration between the two models may provide the healthcare provider and / or physician with a view to relating the therapy-guided parameters to the cardiac anatomy.

[0076] Computer-Implemented Method FIG. 2 shows a schematic diagram of an exemplary workflow that may include the computer-implemented method (200) described herein. In step (201), a patient undergoes an imaging procedure that may capture and / or record the individual's heart in image form. As shown in FIG. 2, the imaging procedure may include imaging modalities of MRI, DENSE, Tag-MR, SPAMM, 4D flow, echocardiogram, CTA, or any combination thereof. In some cases, the MRI may include CINE MRI. In some examples, the echocardiogram may include 2D, 3D, 4D, or any combination thereof. In some cases, the imaging procedure may include CT, MRI, CT angiogram, time-resolved CTA, X-ray, conventional angiogram, or any combination thereof. In some cases, the data may include MRI sequences determined from compressed sensing or accelerated acquisition. In step (202), one or more images generated by the imaging procedure of step (201) may be received by an input software module described elsewhere herein. In some cases, the one or more images may be transferred to the input software module (202) via a network, an online secure HIPPA compliant portal and / or a cloud-based server. In some examples, the one or more images may be transferred to the input software module (202) via Bluetooth or Wi-Fi communication protocols. In some cases, the one or more images may be transferred to the image input software module through wired electrical communication. The images may be transferred to the input software module via a non-transitory storage medium, e.g., flash memory thumb drive, CD-ROM, DVD-ROM, etc. The input software module (202) may be configured to receive and process data transmitted to a computing device. In some cases, the data received by the input software module may be associated with and / or representative of the individual's heart. In some examples, the data received by the input software module may include one or more images of a heart or a portion of a heart.In some cases, the received data may include non-static images, such as images showing cardiac motion and / or blood flow. Non-limiting examples of imaging procedures that can generate one or more images showing cardiac motion may include echocardiograms, time-resolved CTA, MRI, CT, or any combination thereof imaging procedures. In some cases, echocardiograms may include 4-dimensional echocardiograms. In some examples, MRI may include CINE MRI. As used herein, "image" includes both a single image or a collection of images (e.g., video or motion capture). "Static" refers to an image that does not capture cardiac motion (i.e., kinetics). "Non-static" refers to an image that shows cardiac motion (i.e., kinetics).

[0077] The data received by the input software module (202) may in some cases comprise non-image data specific to an individual, such as ECG, medical record data, and / or demographic data.

[0078] In some examples, non-limiting examples of data received by the input software module may include demographic data of an individual, medical record data (including electronic medical record data), ECG data, 2D, 3D, and / or 4D echocardiogram data, MRI data, CINE MRI data, CT data, CT angiography data, time-resolved CTA, X-ray data, conventional angiography data, or any combination of those data. The received data may be complete or partial with respect to the data itself. In some cases, the received data may be associated with, related to, and / or indicative of the heart of an individual being evaluated for cardiac disease. In some cases, the received data may include data from individuals of a population not directly evaluated using the method and / or software of the present invention. In some cases, the received data may include data that is retrospectively analyzed (i.e., obtained at an earlier time point than the analysis).

[0079] The data may be received by the input software module (202) via any known communication means, including via wired or wireless communication with another computing device, a server, a cloud, and / or any device capable of transmitting data to the computing device running the input software module.

[0080] In some cases, the data received by the input software module may also be processed by the input software module. For example, in some examples, the received data may be identified by the input software module (e.g., with respect to content or type of data) and, based on that identification, assigned a certain value to further determine how the received data is processed by the software. For example, an ECG received by the input software module may in some cases be identified as an ECG rather than an image of the heart and then sent to a different software module than the received image of the heart. In some examples, a static image of the heart may be identified and sent to a different software module than a non-static image of the heart. In some embodiments, the input software module may clean the received data in optional step (203), for example, with respect to associated metadata and labels. In some cases, the cleaning process may include denoising the data to remove image artifact noise to increase the signal-to-noise ratio of the relevant signal and / or region of the data to be analyzed.

[0081] In an optional step (203), the input software module (202) can further process the received data as described above. In some cases, the further processing can include (1) removing patient information from the data (de-identifying), (2) reordering the data, (3) re-arranging the data, (4) filtering the data, and (5) superimposing the data.

[0082] In some cases, the segmentation software module (204) may segment one or more images received by the input software module (202) and optionally processed in step (203). In some examples, the segmentation software module (204) may be configured to segment one or more images of the received heart. In some cases, segmentation may include a process of identifying and separating one or more image data into different data sets. For example, the segmentation software module described elsewhere herein may be configured to separate image data determined by the software to be relevant (i.e., signal) for the analysis of the individual's heart from that deemed to be background or noise and / or not relevant for the analysis of the individual's heart. In some cases, the segmentation software module may identify the heart in the image and separate the cardiac image data from background elements in the image. In some examples, segmentation may be applied to both static and / or non-static image components. Segmentation may further be applied to different anatomical components of the heart. For example, the image may be segmented to separate (or isolate) the aorta from the heart from the macroscopic structure of the heart in the image. In some cases, the segmentation software module may be configured to segment and / or separate heart wall tissue (ie, myocardium) from the heart's blood pool and / or the heart's pericardium.

[0083] In some cases, the segmentation software module may comprise and / or utilize an artificial intelligence or machine learning algorithm to segment the received one or more images. The artificial intelligence and / or machine learning algorithm may include a neural network and / or a convolutional neural network configured to use computer vision to analyze the one or more received images and / or determine where the one or more images should be segmented into one or more data sets. In some cases, the machine learning algorithm and / or the neural network may be first trained on a population dataset. In some examples, the population dataset may include image data, non-image data, or any combination thereof. In some examples, the population data may include normal data (i.e., data of healthy individuals without a disease or pre-disease condition), abnormal data (i.e., data of individuals with a disease or pre-disease condition), or any combination thereof.

[0084] In some cases, the segmentation software module (204) may output one or more data sets of image data separated from other data in the image. For example, the output of the one or more data sets may include the individual's heart (either static or non-static) segmented from the image background surrounding the heart. In some cases, the output of the one or more data sets may include a portion of the individual's heart, e.g., the aorta (either static or non-static), separated and / or segmented from the image background and / or the remainder of the heart in the image.

[0085] After segmenting the image data, the segmentation software module (204) may send one or more data sets to another module of software, such as, for example, an analysis software module (205) and / or a modeling software module (206).

[0086] In some cases, the analysis software module (205) may receive the image segmented by the segmentation software module (204) into one or more data sets. The analysis software module (205) may analyze one or more data sets of the segmented image and generate one or more analysis results. In some cases, the analysis software module (205) may be configured to solve physics-based partial and / or ordinary differential equations that describe the motion, strain and / or stress of the heart wall; blood flow; dynamics, stress and / or strain of the heart valves; and cardiac tissue conductance. In some cases, the physics-based partial and / or ordinary differential equations may be solved by artificial intelligence approaches, numerical methods, finite element analysis, or any combination thereof. In some cases, the analysis software module may be configured to perform an analysis process on one or more data sets received by the software. In some examples, the data received by the analysis software module may be pre-processed by the input software module and / or the segmentation software module. In some cases, the analysis software module may be configured to perform an analytical function on one or more data sets it receives, which may include applying a certain mathematical function to one or more data sets. The data received by the analysis software module may include image data, non-image data, or any combination thereof, as the case may be.

[0087] In some cases, the analysis software module may perform finite element analysis on one or more data sets and generate one or more analysis results. In some cases, the analysis results generated by the analysis software module may include at least one equation that describes kinematic characteristics of the heart. In some cases, the one or more analysis results may include qualities or characteristics of the one or more data sets that directly correlate to anatomical, physiological, and / or electrophysiological parameters of the heart.

[0088] In some cases, finite element analysis may be performed by the analysis software module on the cardiac image data to generate analytical results including a mathematical representation of the motion of the heart wall or a portion of the heart wall. In some examples, finite element analysis may be performed by the analysis software module on the acquired cardiac image data to generate analytical results including a mathematical representation of the constitutive material properties of the heart wall or a portion of the heart wall. In some examples, finite element analysis may be performed by the analysis software module on the acquired cardiac image data to generate analytical results including a mathematical representation of the density or flow of electrical current through the heart or a portion of the heart. In some examples, finite element analysis may be performed by the analysis software module on the acquired cardiac image data to generate analytical results including a mathematical representation of the motion or constitutive material properties of one or more valves of the heart or a portion of one or more valves of the heart. In some cases, finite element analysis may be performed by the analysis software module on the cardiac image data to generate analytical results that may include a mathematical representation of the flow and / or diffusion of blood through the heart and / or cardiac tissue.

[0089] In some cases, the analysis software module may utilize non-image data, as described elsewhere herein, to generate the analysis results. In some cases, the analysis software module may utilize the non-image data in conjunction with the image data to generate the analysis results. For example, the non-image data may provide information regarding initial conditions, boundary conditions, model weighting parameters, or any combination of those finite element analysis parameters for the finite element analysis.

[0090] After generating the analysis results, the analysis software module may transmit the analysis results to another module in the software, such as the modeling software module (206). However, it should be understood that the modeling software module and the analysis software module as described herein may be combined into a single module and / or may be separate individual modules of software.

[0091] In some cases, the modeling software module (206) may generate a model (or other output) based on the analysis results generated by the analysis software module (205). The modeling software module (206) may be configured to generate a model of the individual's heart based on data of the individual's heart and / or data related to the individual's heart (including image data and non-image data as described elsewhere herein). In some cases, the modeling software module (206) may generate a model (or other type of output) using analysis results generated by the analysis software module (or analysis results generated by a module that combines the functionality of the analysis and the modeling software module). In some cases, the analysis results may be plotted on two-dimensional and / or three-dimensional plots for viewing by one or more users of the software. In some cases, the two-dimensional and / or three-dimensional analysis results may be overlaid and co-registered to a three-dimensional model of the heart (i.e., a three-dimensional mesh as described elsewhere herein).

[0092] In some cases, the model generated by the modeling software may include one or more of functional, physiological, and / or electrophysiological parameters. In some cases, the model may include a black and white and / or color two-dimensional or three-dimensional model of the individual's heart and / or a portion of the individual's heart. In some examples, the individual's heart may be displayed on a display of a computing device. In some embodiments, the model may include an interactive model that allows a user to manipulate the model within a computer display to view different portions of the model or to view slices through the model. In some examples, a slice through the model may include a slice that does not intersect the entire model. In some examples, a slice through the model may include a slice that intersects the entire model. In some examples, a slice through the model may include a slice parallel to a planar axis formed between at least two dimensions (e.g., the xy, yz, or zx planes) of the three-dimensional space of the model.

[0093] In some examples, the models may be viewable and manipulated by one or more users of the software via an augmented reality (AR), virtual reality (VR), and / or metaverse environment. In some cases, the software, methods, and systems described herein may recognize gestures and / or movements of a user input device (AR or VR joystick and / or controller), which may be configured to enable one or more users to interact with and manipulate the models.

[0094] In some cases, the modeling software module may include and / or utilize artificial intelligence and / or machine learning algorithms. The artificial intelligence and / or machine learning algorithms may include neural networks. In some examples, the machine learning algorithms and / or artificial intelligence may be initially trained on population data. In some cases, the population data may include image data and / or non-image data. In some examples, the population data may include both normal (i.e., healthy) and abnormal data (i.e., indicative of a disease or pre-disease state).

[0095] In some cases, the model may include and / or display one or more of functional parameters, physiological parameters, and / or electrophysiological parameters. In some examples, one or more functional parameters, physiological parameters, and / or electrophysiological parameters may be overlaid on the model and / or otherwise associated with the model or a section of the model (e.g., data for one or more physiological and / or electrophysiological parameters may be displayed when a cursor is held over the model or a section of the model). In some cases, the cursor may be moved and / or moved across the display in response to a movement of an input device. In some examples, the input device may comprise a mouse, a trackpad joystick, a user's finger or hand, or any combination thereof. In some cases, the input device may comprise an AR and / or VR input device (e.g., a joystick incorporating a gyroscope, an accelerometer, a magnetometer, and / or a positioning sensor).

[0096] In some cases, the modeling software module may generate a model that includes and / or displays in vivo spatial and / or temporal measurements of the strain tensor field and / or stress tensor field. In some examples, the strain tensor field includes the total strain tensor field. In some cases, the strain tensor field may include up to 1 strain, up to 2 strains, up to 3 strains, up to 4 strains, up to 5 strains, or up to 6 strains. In some examples, the stress tensor may include up to 1 stress, up to 2 stresses, up to 3 stresses, up to 4 stresses, up to 5 stresses, or up to 6 stresses. In some cases, each stress or strain component of the stress tensor and / or strain tensor may include active and / or passive components. In some examples, the stress tensor and / or strain tensor may be determined in the fiber direction, the cross-fiber direction, the sheet direction, or any combination of these directions. In some embodiments, the modeling software module may generate models that include and / or display in vivo spatial measurements of stored energy, i.e., stored stress, or residual stress, of the individual's heart wall and / or left ventricular (LV) wall. In some cases, the modeling software module may generate models that include and / or display spatial and temporal forces, e.g., stress and energy fields generated by myocardial contraction. In some examples, models generated by the software, systems, and / or methods described elsewhere herein may present and / or display coupling of electrical stimulation and muscle contraction throughout the entire cardiac cycle. In some cases, the coupling of electrical stimulation and muscle contraction may be displayed as an overlay of spatially and / or temporally superimposed data on a structural model of the individual's heart. In some embodiments, the modeling software module may generate models that include and / or display in vivo measurements of spatial and temporal potential difference fields non-invasively. In some cases, the measurement of spatial and temporal potential difference may allow for determining tissue conductance tensor fields.In some instances, the modeling software module may generate a model that includes and / or displays myocardial in vivo electrical activity (i.e., four-dimensional measurements) as a function of time and space. In some examples, the model generated by the modeling software module may display and / or present a current density map of the entire heart or a portion of the heart of an individual. In some instances, the model generated by the modeling software module may display and / or present at least one vector representing the electrical current through the individual's heart or a portion of the heart. In some examples, the model generated by the modeling software module may display and / or present a wall thickness of at least one wall of the individual's heart. In some instances, the model generated by the modeling software module may display and / or present information related to at least one valve of the heart, including, for example, the mechanics of valve motion and the performance of the valve. In some examples, the model generated by the modeling software module may display and / or present the flow of blood through a portion of the heart and / or cardiac tissue (e.g., myocardium). In some instances, the model generated by the modeling software module may display and / or present oxygen and / or fatty acid metabolic measurements of at least a portion of the individual's heart. In some examples, the models generated by the modeling software modules described herein may display and / or present a level of tissue perfusion of the individual's myocardial tissue. In some cases, the models generated by the modeling software modules may display and / or present identified scar tissue overlaid on a portion of the individual's myocardium. In some cases, the models generated by the modeling software modules may display and / or present data regarding spatial and / or temporal tissue mechanical efficiency.

[0097] In some cases, some data may not be associated with the model being displayed, but rather is output in other formats, such as, for example, raw numerical values.

[0098] In some examples, a communication interface (207), such as a secure communication, can transmit the output of the modeling software module to a display device for display (208, 209). The display device may be a component of the same computing device running the software described herein or may be a remotely located display. In some cases, the display device may comprise a remote display device, a personal computing device, a laptop computing device, a tablet, a smartphone, an AR display, a VR display, or any combination thereof. In some cases, one or more users may be able to view the model and / or associated non-model data (e.g., raw numerical values) from a web portal and / or from a web browser window. In some examples, the web browser may point to a URL of a web-based server where the model and / or associated non-model data may be viewed by one or more users. In some examples, the model and / or associated non-model may be downloaded from the web-based server and / or portal to a local device (i.e., a personal computer, a laptop computer, a tablet, a smartphone, etc.). In some cases, the downloaded data of the model and / or associated non-model may be visualized using ParaView open source software or other open source software configured to display or view a model of an individual's heart.

[0099] In some cases, the output of the modeling software module may include models in the form of functional maps (208) and / or electrophysiological parameter (EP) maps (209). In these example models (208) and (209), one or more functional, physiological, and / or electrophysiological parameters may be overlaid on the model and / or otherwise associated with the model or a section of the model (e.g., data appears when a mouse or cursor of a user input device described elsewhere herein is held over the model or a section of the model).

[0100] It should be understood that any of the software modules may be combined into a single module or may be implemented by fewer modules. The software modules described herein may provide exemplary ways to implement the software algorithms described herein, and one of ordinary skill in the art will understand that modules having different names or different functions are equally suitable for use with the software described herein.

[0101] It is further understood that both the methods and software described herein can utilize one or more computers. The computer can include a monitor or other graphical interface for displaying data, results, models, or other output. The computer can also include a means for inputting data or information. The computer can include a processing unit and fixed or removable media or a combination thereof. The computer can be accessed by a user in physical proximity to the computer, for example, via a keyboard and / or mouse, or by a user who does not necessarily have access to the physical computer, through a communication medium, such as a carrier wave of a wired or wireless communication signal. In some cases, the computer can be connected to a server or other communication device to relay information from the user to the computer or from the computer to the user. In some cases, the user can store data or information obtained from the computer via the communication medium in a medium, such as a removable medium. It is envisioned that data related to the computer-implemented methods described herein can be transmitted over such networks or connections for receipt and / or review by a party. The receiving party and / or user can be, but is not limited to, an individual, a health care provider, or a health care manager. In some cases, computer-readable media includes media suitable for transmission of the output of the software or computer-implemented methods described herein.

[0102] Although preferred embodiments of the present invention have been shown and described herein, it is obvious to those skilled in the art that such embodiments are provided by way of example only. Numerous variations, changes, and substitutions are currently contemplated by those skilled in the art without departing from the present invention. One or more of the embodiments and / or software modules, algorithms, machine learning models, methods, or any combination thereof, can be combined together into a single embodiment, as described elsewhere herein. It should be understood that various alternatives of the embodiments of the present invention described herein can be used to implement the present invention. The following claims define the scope of the present invention, and it is intended that methods and structures within the scope of these claims and their equivalents are covered thereby.

[0103] Although the above steps show each of the methods or sets of operations according to the embodiments, one skilled in the art will recognize many variations based on the teachings described herein. Steps may be completed in different orders. Steps may be added or omitted. Some of the steps may include substeps. Many of the steps may be repeated as many times as is beneficial. One or more of the steps of each of the methods or sets of operations may be performed using one or more of the circuits described herein, e.g., processors or logic circuits such as programmable array logic for a field programmable gate array. The circuits may be programmed to provide one or more of the steps of each of the methods or sets of operations, and the programs may comprise program instructions stored on a computer-readable memory, or programmed steps of logic circuits, e.g., programmable array logic or field programmable gate arrays.

[0104] Further exemplary embodiments are further described with reference to the following examples; however, these exemplary embodiments are not limited to such examples. EXAMPLES

[0105] Example 1: Using software to determine an individual's cardiac disease status from an image of the individual's heart An individual suspected of having a cardiac disease and / or disorder will walk into a cardiology clinic and describe their symptoms to a physician and / or medical practitioner, who will then order imaging of the individual's heart. The individual will then undergo spatial-temporal imaging of the heart (e.g., 3D echocardiogram, MRI, Tag-MR, CINE MRI, or any combination of these imaging) that generates one or more images. The one or more images generated by the imaging system will be transmitted to an input software module through wired or wireless communication with the imaging system. The data will then be further cleaned (e.g., denoised) and processed by the input software module. After cleaning and processing by the input software module, a software segmentation module will then segment the one or more images output by the input software module and segment the individual's heart from the background of the individual's other tissues and / or organ systems into a data set. The heart is then further segmented into one or more additional data sets including one or more anatomical features of the heart (e.g., ventricles, atria, heart walls, heart valves, etc.) for further analysis. The heart and / or the one or more additional data sets will then be sent to an analysis software module that analyzes each of the one or more data sets and generates one or more analysis results. The one or more analysis results will include, for example, finite element analysis to represent the density or flow of electrical current through the individual's heart, the motion and / or constituent material properties of one or more valves of the individual's heart, the flow and / or diffusion of blood through the individual's heart and / or cardiac tissue, or any combination of those analysis results. The analysis results will then be transmitted to a modeling software module that combines the analysis results into a model. The model will then be displayed to one or more users via a personal computer, a smartphone, a web browser, a tablet, a laptop computer, a cloud-based computing platform, an AR environment, a VR environment, a metaverse, or any combination of those interactive displays.The models are interactive such that one or more users can interact with the model through interactions with a cursor or pointer controlled by a user input device (e.g., a mouse, mouse pad, joystick, etc.), bisect and / or slice the model, and determine analytical results associated with spatial locations on the model. The resulting models and / or associated raw numerical values ​​may be exported for offline analysis or filed in an individual's medical record and / or imported into an electronic medical record system.

Claims

1. A computer-implemented method for generating a model of an individual's heart, wherein the method is: (a) The step of receiving or acquiring an image of the heart of the individual by an input software module, (b) A step of segmenting the image of the heart using a segmentation software module, thereby generating at least one image segment; (c) A step of applying one or more differential equations to at least one image segment using an analysis software module, thereby generating at least one analysis result; (d) A step of generating a model of the heart of the individual using a modeling software module, wherein the analysis results of step (c) are used in step (d) Methods that include...

2. The method according to claim 1, wherein the analysis result includes at least one functional feature, at least one electrophysiological feature, or any combination thereof.

3. The method according to claim 2, wherein the functional features include ventricular gauge pressure of the right ventricle and the left ventricle.

4. The method according to claim 2, wherein the functional features include the wall pressure of the cardiac chambers of the heart.

5. The method according to claim 2, wherein the functional feature includes wall motion of at least a portion of the heart.

6. The method according to claim 2, wherein the electrophysiological features include the electrical properties of the cardiac tissue, and the electrical properties include an activation map, a voltage map, or any combination thereof.

7. The method according to claim 6, wherein the electrical characteristics include at least one current vector.

8. The method according to claim 1, wherein the image of the heart is an echocardiogram.

9. The method according to claim 8, wherein the echocardiogram includes a 3D echocardiogram.

10. The method according to claim 1, further comprising the step of generating a growth remodeling parameter model over a period of time in the longitudinal direction using the analysis results of step (c).

11. A non-temporary computer-readable medium including software that uses artificial intelligence to model the heart of an individual, wherein the software is on a processor (a) Receiving or obtaining an image of an individual's heart, (b) Segmenting the image of the heart, thereby generating at least one image segment, (c) Applying a series of numerical techniques to at least one image segment to generate and apply an analysis result, (d) Using the analysis results of (c), generate a model of the heart of the individual having at least one functional feature, at least one electrophysiological feature, or a combination thereof. A non-temporary computer-readable medium that enables the operation of a computer.

12. The non-transient computer-readable medium according to claim 11, wherein the functional feature includes ventricular gauge pressure.

13. The non-temporary computer-readable medium according to claim 11, wherein the functional features include the wall pressure of the cardiac chambers of the heart.

14. The non-transient computer-readable medium according to claim 11, wherein the electrophysiological features include the electrical properties of the tissue of the heart, and the electrical properties of the tissue of the heart include an activation map, a voltage map, or any combination thereof.

15. The non-transient computer-readable medium according to claim 14, wherein the electrical characteristics include at least one current vector.

16. The non-transient computer-readable medium of claim 11, wherein the image of the heart is an MRI image, and the MRI includes CINE MRI, MRI-based technology, or any combination thereof.

17. The non-transient computer-readable medium according to claim 16, wherein the MRI-based technology includes DENSE, Tag-MR, SPAM, or any combination thereof.

18. The non-temporary computer-readable medium according to claim 11, wherein the image of the heart is an echocardiogram image.

19. The non-temporary computer-readable medium according to claim 18, wherein the echocardiogram includes a 3D echocardiogram.

20. The non-temporary computer-readable medium according to claim 11, wherein the at least one image segment shows at least a portion of the heart of the individual.

Images