Systems and methods for adaptive synthetic micro vascular network generation

Abstract

Systems, software and methods for non-invasively and adaptively generating synthetic microvascular networks are disclosed, including models that can be used for diagnostic assessments. An example computer implemented method includes: generating a model of a coronary vessel of a patient; generating, based on the 3D model, a myocardial blood volume (MBV) map of a region of interest perfused by the coronary vessel; determining, based on the MBV map, a blood volume for the region of interest; generating, based on the 3D model and the blood volume, an initial vascular network model using constraint constructive optimization; optimizing, based on the MBV map, geometric parameters of each segment of the initial vascular network model to generate a synthetic microvascular network model that further includes microvessels emanating from the coronary vessel to perfuse the region of interest; and generating, based on the synthetic microvascular network model, a diagnostic assessment of the region of interest.

Description

SYSTEMS AND METHODS FOR ADAPTIVE SYNTHETICMICRO VASCULAR NETWORK GENERATIONCROSS-REFERENCE TO RELATED APPLICATIONS

[0001] The present application claims priority to U.S. provisional patent application serial number 63 / 659,295 filed June 12, 2024, the entire content of which is incorporated herein by reference and relied upon.GOVERNMENTAL SUPPORT CLAUSE

[0002] This invention was made with government support under I01CX001901 awarded by the U.S. Department of Veterans Affairs, and HL148182 awarded by the National Institutes of Health. The government has certain rights in the invention.FIELD OF USE

[0003] The embodiments disclosed herein are generally directed towards systems, processes and methods that generate microvascular networks.BACKGROUND

[0004] The embodiments disclosed herein are generally directed towards systems, processes and methods that generate microvascular networks.

[0005] Coronary microvascular disease (CMD) remains a major health burden for human populations. Typically, CMD is diagnosed through invasive coronary procedures to obtain hemodynamic metrics such as the index of microcirculatory resistance (IMR), coronary flow reserve (CFR), and fractional flow reserve (FFR). However, the invasiveness of this diagnostic procedure creates gaps for the testing and development of therapeutics to treat CMD and other vascular diseases.

[0006] Although non-invasive approaches to diagnosing CMD using medical imaging data have been developed, they are nonspecific and less effective. Despite recent advances in clinical medical imaging, limitations in spatial resolution prevent depiction of the microvascular arterial network. In particular, adequate myocardial perfusion depends on theintricate balance between the epicardial and microvascular arterial system. Therefore, understanding and accurately mapping this network is required for development of diagnostic and therapeutic strategies in cardiovascular medicine.

[0007] Conventional methodologies for generating arterial networks fail to capture its complexities, particularly at the microvascular level. Despite advancements in modeling techniques, significant unknowns remain, particularly for generating large physiologically- sound vascular and microvascular networks that supply blood to various myocardial segments. These unknowns include the precise replication of the myocardial perfusion and their integration into patient- specific arterial network models. There is thus a desire and need for more accurate, reliable, personalized, and adaptive modeling of vascular networks, particularly as it relates to microvascular networks, in order to more precisely and effectively diagnose and treat CMD and other vascular diseases.

[0008] Various embodiments of the present disclosure address one or more of these shortcomings.SUMMARY

[0009] This specification describes various exemplary embodiments of systems, software and methods for non-invasively and adaptively generating synthetic microvascular networks, including models that can be used for diagnostic assessments. The disclosure, however, is not limited to these exemplary embodiments and applications or to the manner in which the exemplary embodiments and applications operate or are described herein.

[0010] In some aspects, which may be combined with any other aspects, a method for adaptively generating a synthetic microvascular network includes: generating, by a computing device having a processor, a three-dimensional (3D) model of a coronary vessel of a patient; generating, by the computing device, based on the 3D model, a myocardial blood volume (MBV) map of a region of interest perfused by the coronary vessel of the patient; determining, based on the MBV map, a blood volume for the region of interest perfused by the coronary vessel; generating, based on the 3D model and the blood volume for the region of interest, a vascular network model; optimizing, based on the MBV map, one or more geometric parameters of each segment of a plurality of segments of the vascular network model togenerate the synthetic microvascular network model, wherein the synthetic microvascular network model comprises the plurality of segments of the vascular network model and further comprises one or more microvessels emanating from the coronary vessel to perfuse the region of interest; and generating, based on the synthetic microvascular network model, a diagnostic assessment of the region of interest.

[0011] In some embodiments, the method further includes: acquiring patient- specific image data via the imaging modality, the patient-specific image data comprising the coronary vessel of the patient and the region of interest perfused by the coronary vessel. Generating the 3D model of the coronary vessel of the patient may include segmenting the patient- specific image data to extract the coronary vessel from the patient- specific image data.

[0012] In some embodiments, acquiring the patient- specific image data via the imaging modality includes: administering an intravascular agent to the patient; and acquiring the patient-specific image data after the intravascular agent has entered the coronary vessel of the patient and the region of interest perfused by the coronary vessel.

[0013] In some embodiments, generating the vascular network model includes: extracting, by the computing device, a centerline of the coronary vessel; and generating, based on the MBV map, a plurality of virtual terminal nodes and a plurality of arterial segments emanating from the centerline.

[0014] In some embodiments, optimizing the one or more geometric parameters of each segment includes: optimizing a diameter of the segment and optimizing a bifurcation point of the segment. The optimizing the diameter of the segment includes: iteratively minimizing a difference in an estimated blood flow rate based on the diameter of the segment and an actual blood flow rate determined using the MBV map until the difference satisfies a predetermined threshold.

[0015] In some embodiments, the method further includes: determining, using the synthetic microvascular network model, one or more of an index of microcirculatory resistance (IMR), a coronary flow reserve (CFR), or a fractional flow reserve (FFR) of the region of interest; and generating, based on one or more of the IMR, the CFR, or the FFR, the diagnostic assessment of the region of interest.

[0016] In some embodiments, the method further includes: determining, using the synthetic microvascular network model, an IMR by: generating a cyclic pulsatile flow through the synthetic microvascular network model; deploying a particle at a first location of the synthetic microvascular network model; and determining a blood flow transit time based on the particle traveling to a second location of the synthetic microvascular network model, the second location being a predetermined distance downstream of the first location.

[0017] In some embodiments, the first location is a mid point of the coronary artery.

[0018] In some embodiments, the predetermined distance is about 2 to 4 centimeters.

[0019] In some embodiments, the diagnostic assessment includes: a presence of or a degree of a blockage in a segment of the synthetic microvascular network model; a presence of or a degree of a stenosis in a segment of the synthetic microvascular network model; or a presence of or a degree of ischemia in the region of interest.

[0020] In some embodiments, generating the vascular network model and optimizing to generate the synthetic microvascular network model are performed via constraint constructive optimization.

[0021] In some aspects, which may be combined with any other aspects, a system for adaptive synthetic microvascular network generation is disclosed. The system includes: a processor; and memory storing instructions that, when executed by the processor, cause the processor to: generate a three-dimensional (3D) model of a coronary vessel of a patient; generate, based on the 3D model, a myocardial blood volume (MBV) map of a region of interest perfused by the coronary vessel of the patient; determine, based on the MBV map, a blood volume for the region of interest perfused by the coronary vessel; generate, based on the 3D model of the coronary vessel and the blood volume for the region of interest, an initial vascular network model; optimize, based on the MBV map, one or more geometric parameters of each segment of a plurality of segments of the vascular network model to generate an synthetic microvascular network model, wherein the synthetic microvascular network model comprises the plurality of segments of the vascular network model and further comprises one or more microvessels emanating from the coronary vessel to perfuse the region of interest; andgenerate, based on the synthetic microvascular network model, a diagnostic assessment of the region of interest.

[0022] In some embodiments, the instructions, when executed, further cause the processor to: acquire patient-specific image data via the imaging modality, the patient- specific image data comprising the coronary vessel of the patient and the region of interest perfused by the coronary vessel. Furthermore, generating the 3D model of the coronary vessel of the patient may include segmenting the patient-specific image data to extract the coronary vessel from the patient- specific image data.

[0023] In some embodiments, the instructions, when executed, may cause the processor to acquire the patient- specific image data via the imaging modality by: administering an intravascular agent to the patient; and acquiring the patient- specific image data after the intravascular agent has entered the coronary vessel of the patient and the region of interest perfused by the coronary vessel.

[0024] In some embodiments, the instructions, when executed, may cause the processor to generate the vascular network by: extracting a centerline of the coronary vessel; and generating, based on the MBV map, a plurality of virtual terminal nodes and a plurality of arterial segments emanating from the centerline.

[0025] In some embodiments, the instructions, when executed, may cause the processor to optimize the one or more geometric parameters of each segment by optimizing a diameter of the segment and optimizing a bifurcation point of the segment. Furthermore, the optimizing the diameter of the segment includes: iteratively minimizing a difference in an estimated blood flow rate based on the diameter of the segment and an actual blood flow rate determined using the MBV map until the difference satisfies a predetermined threshold.

[0026] In some embodiments, the instructions, when executed, further cause the processor to: determine, using the synthetic microvascular network model, one or more of an index of microcirculatory resistance (IMR), a coronary flow reserve (CFR), or a fractional flow reserve (FFR) of the region of interest; and generate, based on one or more of the IMR, the CFR, or the FFR, a diagnostic assessment of the region of interest.

[0027] In some embodiments, the instructions, when executed, may further cause the processor to: determine, using the synthetic microvascular network model, the IMR of the region of interest by: generating a cyclic pulsatile flow through the synthetic microvascular network model; deploying a particle at a first location of the synthetic microvascular network model; and determining a blood flow transit time based on the particle traveling to a second location of the synthetic microvascular network model, the second location being a predetermined distance downstream of the first location.

[0028] In some embodiments, the first location is a mid point of the coronary artery.

[0029] In some embodiments, the predetermined distance is about 2 to 4 centimeters.

[0030] In some embodiments, the diagnostic assessment includes: a presence of or a degree of a blockage in a segment of the synthetic microvascular network model; a presence of or a degree of a stenosis in a segment of the synthetic microvascular network model; or a presence of or a degree of ischemia in the region of interest.

[0031] In some embodiments, the instructions, when executed, further may cause the processor to generate the vascular network model and optimize to generate the synthetic microvascular network model via constraint constructive optimization.

[0032] In some aspects, which may be combined with any other aspects, a non-transitory computer-readable medium (CRM) is disclosed. The non-transitory CRM may have stored thereon computer-readable instructions executable to cause performance of operations including any one or more methods, processes, or steps described herein for or in furtherance of adaptively generating synthetic microvascular network models.

[0033] Other aspects, features, and implementations will become apparent to those of ordinary skill in the art, upon reviewing the following description of specific, exemplary aspects in conjunction with the accompanying figures. While features may be discussed relative to certain aspects and figures below, various aspects may include one or more of the advantageous features discussed herein. In other words, while one or more aspects may be discussed as having certain advantageous features, one or more of such features may also be used in accordance with the various aspects. In similar fashion, while exemplary aspects maybe discussed below as device, system, or method aspects, the exemplary aspects may be implemented in various devices, systems, and methods.

[0034] The foregoing has outlined, rather broadly, the features and technical advantages of examples according to the disclosure in order that the detailed description that follows may be better understood. Additional features and advantages will be described hereinafter. The conception and specific examples disclosed may be readily utilized as a basis for modifying or designing other structures for carrying out the same purposes of the present disclosure. Such equivalent constructions do not depart from the scope of the appended claims. Characteristics of the concepts disclosed herein, both their organization and method of operation, together with associated advantages will be better understood from the following description when considered in connection with the accompanying figures. Each of the figures is provided for the purposes of illustration and description, and not as a definition of the limits of the claims.

[0035] While aspects and implementations are described in this application by illustration to some examples, those skilled in the art will understand that additional implementations and use cases may come about in many different arrangements and scenarios. Innovations described herein may be implemented across many differing platform types, devices, systems, shapes, sizes, and packaging arrangements. While some examples may or may not be specifically directed to use cases or applications, a wide assortment of applicability of described innovations may occur.BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In addition to the features described herein, additional features and variations will be readily apparent from the following descriptions of the drawings and exemplary embodiments. It is to be understood that these drawings depict embodiments and are not intended to be limiting in scope.

[0037] FIG. 1 is an illustration of an example network environment and process for adaptive synthetic microvascular network generation, according to example embodiments of the present disclosure.

[0038] FIG. 2A is a block diagram illustrating an example computer-implemented method for adaptively generating a synthetic microvascular network, according to non-limiting embodiments of the present disclosure.

[0039] FIG. 2B is a block diagram illustration an example computer-implemented method for utilizing the adaptively generated synthetic microvascular network to determine an index of microcirculatory resistance (IMR), according to non-limiting embodiments of the present disclosure.

[0040] FIG. 3 is a block diagram illustrating a computer system upon which embodiments of the present teachings may be implemented.

[0041] FIG. 4 is a illustration of the generation and use of the synthetic microvascular network model, according to example embodiments of the present disclosure

[0042] FIG. 5 is a graph showing the precision and reliability of the synthetic microvascular network model, according to non-limiting embodiments of the present disclosure.

[0043] It is to be understood that the figures are not necessarily drawn to scale, nor are the objects in the figures necessarily drawn to scale in relationship to one another. The figures are depictions that are intended to bring clarity and understanding to various embodiments of apparatuses, systems, and methods disclosed herein. Wherever possible, the same reference numbers will be used throughout the drawings to refer to the same or like parts. Moreover, it should be appreciated that the drawings are not intended to limit the scope of the present teachings in any way.DETAILED DESCRIPTION

[0044] This specification describes various exemplary embodiments of systems, software and methods for adaptive synthetic generation of microvascular networks. The disclosure, however, is not limited to these exemplary embodiments and applications or to the manner in which the exemplary embodiments and applications operate or are described herein.

[0045] Unless otherwise defined, scientific and technical terms used in connection with the present teachings described herein shall have the meanings that are commonly understood bythose of ordinary skill in the art. Further, unless otherwise required by context, singular terms shall include pluralities and plural terms shall include the singular.

[0046] As discussed, there is a need for non-invasive techniques for diagnosing CMD and other vascular diseases to develop treatment strategies, such non-invasive techniques often rely on medical imaging. However, conventional medical imaging lacks the spatial resolution to accurately and reliably capture pertinent details about microvascular arterial networks. Thus, conventional techniques fail to accurately capture the perfusion of tissues, such as myocardium, based on the arterial (e.g., epicardial) and microvascular networks. Therefore, understanding and accurately mapping vascular and microvascular networks is required for development of diagnostic and therapeutic strategies for diseases such as CMD. Conventional myocardial arterial network generation techniques often have unique challenges. For example, while fractal models can be optimized to capture branched vascular networks, using such continuous models often risks oversimplifying structural details of microvascular networks. There is thus a desire and need for more accurate, reliable, and adaptive modeling of vascular networks, particularly as it relates to microvascular networks, in order to more precisely and effectively diagnose and treat CMD and other vascular diseases

[0047] The present disclosure describe novel and nonobvious solutions to the aforementioned shortcomings by describing systems and methods for adaptive generation of synthetic networks, which can be used to non-invasively, accurately, and reliably diagnose, and develop therapeutic strategies for vascular diseases such as CMD. In various embodiments, the systems and methods involve automatically generating a one-dimensional arterial network in the myocardium, based on myocardial blood volume (MBV) maps, which integrate perfusion imaging and vascular modeling to provide a more integrated and accurate representation of the coronary circulation. The MBV reflects the autoregulatory adaptation necessary to maintain resting myocardial blood flow over a range of coronary perfusion pressure, whereby additional blood supply requires arteriole vasodilation and capillary recruitment.

[0048] In some embodiments, a three-dimensional (3D) model of a coronary vessel (e.g., left anterior descending (LAD) artery) may be generated using image data. For example, the image data may be generated from computed tomography angiograms (CTA), magneticresonance imaging (MRI), or other medical imaging modality. In some aspects, the image data may be generated after administering or during administration of an intravascular agent (e.g., iodinated contrast, gadolinium, ferumoxytol, etc.) in a patient to enhance the quality of the image data. The image data may be further segmented (e.g., according to a 17 segment model as recommended by the American Heart Association (AHA)). In some embodiments, a myocardial blood volume (MBV) map of a region of interest (e.g., left ventricular (LV) myocardial geometry may be determined. In some aspects, myocardial mass-flow rate relationships may be utilized for this determination. The 3D model of the coronary vessel (or other broad arterial vessel leading to a perfused region of interest) may be extracted from the image data. The centerlines for the coronary vessel (e.g., LAD) may be extracted (e.g., a ID model of the LAD).

[0049] Various embodiments of the present disclosure describe generating an arterial network from this initial model of the coronary vessel, for example, using a modified adaptive, multistage constraint constructive optimization (CCO). The arterial network generated using CCO may be referred to herein as a vascular network model. In some embodiments, locations of virtual terminal nodes for the region of interest (e.g., LV of myocardium) may be generated randomly. A plurality (e.g., 15) closest arterial segments may be identified.

[0050] The vascular network model may be optimized further to generate the synthetic microvascular network model (e.g., based on CCO). For example, physiological and geometrical constraints may be used to optimize various geometric parameters (e.g., bifurcation points, diameters) of segments along the vascular network model. The optimization may determine, for example, an ideal location for the bifurcation point based on the total blood volume of the arterial tree (e.g., determined using the MBV map). The construction of the arterial tree for different myocardial segments may continue until the diameter of the terminal segments satisfies a predetermined threshold (e.g., is less than 150 pm in diameter). The optimization may also be used to optimize the diameter of each arterial segment in the vascular network such that the estimated flow rate supplying each segment in the vascular network (e.g., based on a proposed diameter) is consistent with the actual flow rate determined from the MBV map (e.g., the estimated and actual flow rate are similar in value with a tolerance of 0.2 %).

[0051] FIG. 1 is an illustration of an example network environment and process for adaptive synthetic microvascular network generation, according to example embodiments of the present disclosure. The network environment may include but is not limited to one or more medical imaging modalities 102 configured to acquire image data of region of interest (e.g., a myocardium or region of the myocardium) of a patient that is typically perfused by an arterial vessel (e.g., coronary vessel) and a computing device and / or system 104. One or more of the components of the network environment may be communicatively coupled and exchange data via a wire connection or wirelessly. In some aspects, the computing device and / or system 104 may be local. In some aspects, the computing device and / or system 104 may be located remotely. FIG. 3 describes an example of the computing device and / or system 104 in additional detail. The computing device may be configured to perform one or more steps, methods, or processes described herein.

[0052] For example, the computing device and / or system 104 can receive the image data from the medical imaging modality and generate a 3D model 106 of a coronary vessel (or other broad arterial vessel). Furthermore, the image data (e.g., MRI data) may be used to determine a flow rate 108 and other physiological or geometric constraints. Even further, the computing device and / or system 104 may generate a myocardial blood volume (MBV) map 110 of the region of interest.

[0053] The 3D model 106, flow rate 108 (and / or other physiological or geometric constraints) and MBV map 110 may be used as boundary conditions to generate and optimize a vascular network model 112 (e.g., referred to herein a vascular network model) to generate a more optimized and refined vascular network model that include microvessels (also referred to herein as the microvascular network model or synthetic microvascular network model). In some embodiments, the 3D model of the coronary vessel may be coupled with the vascular network model (which may be further optimized to include microvessels, as shown) or the synthetic microvascular network model. In some aspects, the vascular network model 112 may be 1 dimensional (ID). The integration of these models may create microvascular network model 114 that may be a 3D- ID hybrid blood flow model. Based on the synthetic microvascular network model 114, simulations may be performed to non-invasively compute patient-specific IMR, CFR, FFR, as shown in box 116. By using particle tracking in the aforementioned microvascular network models, invasive coronary parameters (e.g., FFR,IMR, and CFR) can be computed non-invasively. An example methodology for using particle tracking on the integrated vascular network model to non-invasively determine IMR is further described herein in relation to FIG. 2B . The multiscale approach of coupled 3D- ID blood flow modeling can address limitations related to small-scale flow structures in the epicardial coronary arteries and the computational cost of simulating a network of arteries with deformable walls.Example Computer Implemented Method

[0054] FIG. 2A is a block diagram illustrating an example computer-implemented method 200A for adaptively generating a synthetic microvascular network, according to non-limiting embodiments of the present disclosure. One or more blocks or processes described in the blocks of FIG. 2A may be performed by one or more computing devices (e.g., such as but not limited to computing device / system 104, and computing system 300 as will be described herein). For example, the one or more blocks or processes may be performed by the processor 304 based on instructions provided by any one of, or a combination of memory components 306 / 308 / 310 and user input (e.g., provided via the input device 314), as will be discussed herein.

[0055] In various embodiments, at block 202, the computing device having a processor (e.g., processor 304 as will be described herein) may generate a three-dimensional (3D) model of a coronary vessel of a patient. The 3D model may be based on patient- specific image data acquired by an imaging modality, and which may be previously received by the computing device (e.g., from medical imaging modality 102). In some embodiments, the patient-specific image data may include the coronary vessel of the patient and the region of interest perfused by the coronary vessel. In some aspects, generating the 3D model of the coronary vessel of the patient may involve segmenting the patient-specific image data to extract the coronary vessel from the patient-specific image data. It is contemplated that, for the adaptive synthetic microvascular network generation in other areas (e.g., non-cardiac areas) of the human anatomy, other cognate arteries (which similarly deliver fluid upstream for perfusion) as the coronary vessel may be extracted and / or modeled from respective image data of said other areas of the human anatomy.

[0056] At block 204, the computing device may generate, based on the 3D model, a myocardial blood volume (MBV) map of a region of interest perfused by the coronary vessel of the patient. For example, region of interest may be a region of the myocardium. In embodiments where the upstream vessel that is 3D modeled is not the coronary vessel, the region of interest may be a volume of tissue being perfused downstream of the vessel. In some embodiments, generating the vascular network may involve extracting, by the computing device, a centerline of the coronary vessel. Furthermore, based on the MBV map, a plurality of virtual terminal nodes and a plurality of arterial segments emanating from the centerline may be determined and / or generated. For example, the plurality of virtual terminal nodes may be end points (e.g., initially randomized) for the vascular network being modeled in the region of interest. The plurality of arterial segments emanating from the centerline may be the next downstream vessels after the coronary vessel.

[0057] At block 206, the computing device may determine, based on the MBV map, a blood volume for the region of interest perfused by the coronary vessel. In some embodiments, the computing device may further determine, based on the MBV map, other physiological and / or geometric constraints for the vascular network to be developed. Such physiological and / or geometric constraints may include but are not limited to a flow rate (e.g., at various segments of the coronary vessel), diameters of the coronary vessel or other upstream vessels, size or shape of the region of interest, etc. In embodiments where other (e.g., non-cardiac) regions of the human body are imaged for the adaptive synthetic microvascular network generation in those regions, blood volume maps of said regions may be generated and the blood volume for that region of interest may be determined.

[0058] At block 208, the computing device may generate, based on the 3D model of the coronary vessel and the blood volume for the region of interest, a vascular network model using constraint constructive optimization. The vascular network model may be referred to as a vascular network model to differentiate from subsequent expansion of the model to include microvessels. In some embodiments, the vascular network model may include a plurality of segments, such as a plurality of segments of an arterial tree network. In some embodiments, the vascular network model may further indicate territories (e.g., of a myocardium) infused by each segment. The territories may be infused via microvessels to be determined via optimization of the vascular network model to generate the microvascular network model.

[0059] At block 210, the computing device may optimize, based on the MBV map, one or more geometric parameters of each segment of a plurality of segments of the vascular network model to generate a microvascular network model. The optimization may result in the plurality of segments to further include one or more microvessels emanating from the coronary vessel to perfuse the region of interest. For example, geometric parameters of the one or more microvessels may be initialized (e.g., randomized, hypothesized, etc.), and then determined by optimizing the initially set geometric parameters to fit geometric and physiological constraints. In some embodiments, the one or more geometric parameters of a segment may include a diameter of the segment or a bifurcation point for that segment. For example, optimizing the one or more geometric parameters of each segment comprises optimizing a diameter of the segment and / or optimizing a bifurcation point of the segment. In at least one embodiment, optimizing the diameter of the segment may involve iteratively minimizing a difference in an estimated blood flow rate based on the diameter of the segment and an actual blood flow rate. The actual blood flow rate may be determined or predicted using the MBV map. The iterations may involve adjusting the diameter to obtain an estimated blood flow rate, such that the difference in diameters is sufficiently low enough to satisfy a predetermined threshold. In some embodiments, that predetermined threshold would be a tolerance level of 2% of below. In some embodiments, optimization of the bifurcation points may involve incorporating the physiological and geometrical constraints obtained using the 3D model and the MBV map into the vascular network model as boundary conditions, and iteratively adjusting bifurcation points until the resulting blood volume predicted by the microvascular network model reaches the total blood volume estimated using the MBV map. In some embodiments, CCO may also be used to generate the microvascular network model.

[0060] At block 220, the computing device may generate a diagnostic assessment of the region of interest. For example, the computing device may use the synthetic microvascular network model to simulate blood flow for diagnostic assessments. Also or alternatively, the computing device may use the optimization, and integration of the microvascular network model, the vascular network model, and / or the 3D model to generate the diagnostic assessment. For example, in some embodiments, the synthetic microvascular network model may be integrated with one or more of the 3D model of the coronary vessel of a ID model of the blood flow to generate an integrated vascular network model. In some embodiments, thediagnostic assessment may include, but is not limited to an assessment based on an index of microcirculatory resistance (IMR), a coronary flow reserve (CFR), or a fractional flow reserve (FFR) of the region of interest. Based on one or more of the IMR, the CFR, or the FFR, the computing device may generate a diagnostic assessment of the region of interest. For example, the computing device may be used to diagnose coronary microvascular disease (CMD). Also or alternatively, the diagnostic assessment may indicate a degree or severity of a stenosis within the region of interest. As such assessments are typically costly, laborious, and invasive in nature, which impedes treatment, the optimized and integrated vascular network model may provide a useful took for non-invasively generating the diagnostic assessment. FIG. 2B provides a non-limiting example of utilizing the adaptively generated synthetic microvascular network model to generate an IMR assessment, as will be described herein.

[0061] In some embodiments, the computing device may generate a patient- specific treatment recommendation based on the diagnostic assessment. For example, the synthetic microvascular network model may be used to indicate a location for surgical intervention after identifying a segment of the vascular or microvascular network that is afflicted with a stenosis or other blockage. Also or alternatively, the computing device may allow a user (e.g., a medical personnel) to simulate surgical treatments and view resulting perfusion.

[0062] FIG. 2B is a block diagram illustration an example computer-implemented method 200B for utilizing the adaptively generated synthetic microvascular network to determine an index of microcirculatory resistance (IMR), according to non-limiting embodiments of the present disclosure. Although FIG. 2B shows the applicability of the model to determining IMR, it is contemplated that similar techniques may be used to simulate and / or determine other diagnostic metrics (e.g., FFR, CFR, etc.) that would otherwise involve invasive procedures. In some embodiments, method 200B may include an example of generating a diagnostic assessment, as explained in relation to block 220. Also or alternatively, in some embodiments, method 200B may be a basis for and / or may be performed prior to the generating the diagnostic assessment. One or more blocks or processes described in the blocks of FIG. 2 may be performed by one or more computing devices (e.g., such as but not limited to computing device / system 104, and computing system 300 as will be described herein). For example, the one or more blocks or processes may be performed by the processor 304 based on instructionsprovided by any one of, or a combination of memory components 306 / 308 / 310 and user input (e.g., provided via the input device 314), as will be discussed herein.

[0063] At block 212, the computing device may receive the presently disclosed synthetic microvascular network model. For example, the synthetic microvascular network model may be generated using techniques described herein, such as but not limited to method 200A shown in FIG. 2A, and / or obtained from block 210 of FIG. 2A.

[0064] At block 214, the computing device may generate a cyclic pulsatile flow through the synthetic microvascular network model. For example, a user may use the synthetic microvascular network model to simulate the flow of blood (or fluid generally) through cardiac cycles. The blood flow may be simulated based on the geometric and physiological constraints dictating how, where, and the velocity at which a particle (e.g., in blood or other fluid) may flow through the microvascular network and / or may perfuse the region of interest. In some embodiments, a user may input a heart rate, blood pressure, and / or other patientspecific parameters of a patient into the computing device. Such patient- specific parameters may be used as further physiological constraints to simulate the cyclic pulsatile flow of a particle (e.g., in blood) through the synthetic microvascular network model.

[0065] At block 216, the computing device may deploy a particle at a first location of the synthetic microvascular network model. The first location may mimic the flow of a blood from a first position in a pressure-temperature guidewire used for measuring IMR invasively. In some embodiments, the first location may be in a coronary vessel, such as the LAD.

[0066] At block 218, the computing device may determine a blood flow transit time based on the particle traveling to a second location of the synthetic microvascular network model. In some embodiments, a one dimensional Lagrangian particle tracking solver may be utilized to determine the blood flow transit time. The second location may be at a predetermined distance downstream of the first location. In some embodiments, the predetermined distance may be about 0.5 centimeters (cm), 1 cm, 2 cm, 3 cm, 4 cm, 5 cm, 6 cm, 7 cm, 8 cm, 9 cm, or 10 cm. In some aspects, the predetermined distance may be within a range formed by any two of the preceding values, for example, 2 cm to 6 cm, or 0.5 cm to about 5 cm. In some aspects, the predetermine distance may be about 3 cm.Example Computer Implemented System

[0067] In various embodiments, the systems and methods for adaptively generating a synthetic microvascular network can be implemented via computer software or hardware.

[0068] FIG. 3 is a block diagram illustrating a computer system 300 upon which embodiments of the present teachings may be implemented. In various embodiments of the present teachings, computer system 300 can include a bus 302 or other communication mechanism for communicating information and a processor 304 coupled with bus 302 for processing information. In various embodiments, computer system 300 can also include a memory, which can be a random-access memory (RAM) 306 or other dynamic storage device, coupled to bus 302 for determining instructions to be executed by processor 304. Memory can also be used for storing temporary variables or other intermediate information during execution of instructions to be executed by processor 304. In various embodiments, computer system 300 can further include a read only memory (ROM) 308 or other static storage device coupled to bus 302 for storing static information and instructions for processor 304. A storage device 310, such as a magnetic disk or optical disk, can be provided and coupled to bus 302 for storing information and instructions.

[0069] In various embodiments, computer system 300 can be coupled via bus 302 to a display 312, such as a cathode ray tube (CRT) or liquid crystal display (LCD), for displaying information to a computer user. In some embodiments, the display 312 may be enable user input (e.g., via a touchscreen). For example, the display 312 may enable a user (e.g., a medical personnel) to enter patient-specific vitals data (e.g., a peripheral non-invasive blood pressure (NIBP) reading, a heart rate, etc.) by touching the display 312. An input device 314, including alphanumeric and other keys, can also enable the same and can be coupled to bus 302 for communication of information and command selections to processor 304. Another type of user input device is a cursor control 316, such as a mouse, a trackball or cursor direction keys for communicating direction information and command selections to processor 304 and for controlling cursor movement on display 312. This input device 314 typically has two degrees of freedom in two axes, a first axis (i.e., x) and a second axis (i.e., y), that allows the device to specify positions in a plane. However, it should be understood that input devices 314 allowing for 3-dimensional (x, y and z) cursor movement are also contemplated herein.

[0070] Consistent with certain implementations of the present teachings, results can be provided by computer system 300 in response to processor 304 executing one or more sequences of one or more instructions contained in memory 306. Such instructions can be read into memory 306 from another computer-readable medium or computer-readable storage medium, such as storage device 310. Execution of the sequences of instructions contained in memory 306 can cause processor 304 to perform the processes described herein. Alternatively, hard-wired circuitry can be used in place of or in combination with software instructions to implement the present teachings. Thus, implementations of the present teachings are not limited to any specific combination of hardware circuitry and software.

[0071] The term “computer-readable medium” (e.g., data store, data storage, etc.) or “computer-readable storage medium” as used herein refers to any media that participates in providing instructions to processor 304 for execution. Such a medium can take many forms, including but not limited to, non-volatile media, volatile media, and transmission media. Examples of non-volatile media can include, but are not limited to, dynamic memory, such as memory 306. Examples of transmission media can include, but are not limited to, coaxial cables, copper wire, and fiber optics, including the wires that comprise bus 302.

[0072] Common forms of computer-readable media include, for example, a floppy disk, a flexible disk, hard disk, magnetic tape, or any other magnetic medium, a CD-ROM, any other optical medium, punch cards, paper tape, any other physical medium with patterns of holes, a RAM, PROM, and EPROM, a FLASH-EPROM, another memory chip or cartridge, or any other tangible medium from which a computer can read.

[0073] In addition to computer-readable medium, instructions or data can be provided as signals on transmission media included in a communications apparatus or system to provide sequences of one or more instructions to processor 304 of computer system 300 for execution. For example, a communication apparatus may include a transceiver having signals indicative of instructions and data. The instructions and data are configured to cause one or more processors to implement the functions outlined in the disclosure herein. Representative examples of data communications transmission connections can include, but are not limited to, telephone modem connections, wide area networks (WAN), local area networks (LAN), infrared data connections, NFC connections, etc.

[0074] It should be appreciated that the methodologies described herein, flow charts, diagrams and accompanying disclosure can be implemented using computer system 300 as a standalone device or on a distributed network or shared computer processing resources such as a cloud computing network.

[0075] The methodologies described herein may be implemented by various means depending upon the application. For example, these methodologies may be implemented in hardware, firmware, software, or any combination thereof. For a hardware implementation, the processing unit may be implemented within one or more application specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), processors, controllers, micro-controllers, microprocessors, electronic devices, other electronic units designed to perform the functions described herein, or a combination thereof.

[0076] In various embodiments, the methods of the present teachings may be implemented as firmware and / or a software program and applications written in conventional programming languages such as C, C++, Python, etc. If implemented as firmware and / or software, the embodiments described herein can be implemented on a non-transitory computer-readable medium in which a program is stored for causing a computer to perform the methods described above. It should be understood that the various engines described herein can be provided on a computer system, such as computer system 300, whereby processor 304 would execute the analyses and determinations provided by these engines, subject to instructions provided by any one of, or a combination of, memory components 306 / 308 / 310 and user input.

[0077] In describing the various embodiments, the specification may have presented a method and / or process as a particular sequence of steps. However, to the extent that the method or process does not rely on the particular order of steps set forth herein, the method or process should not be limited to the particular sequence of steps described. As one of ordinary skill in the art would appreciate, other sequences of steps may be possible. Therefore, the particular order of the steps set forth in the specification should not be construed as limitations on the claims. In addition, the claims directed to the method and / or process should not be limited to the performance of their steps in the order written, and one skilled in the art can readily appreciate that the sequences may be varied and still remain within the spirit and scope of thevarious embodiments. Similarly, any of the various system embodiments may have been presented as a group of particular components. However, these systems should not be limited to the particular set of components, now their specific configuration, communication and physical orientation with respect to each other. One skilled in the art should readily appreciate that these components can have various configurations and physical orientations (e.g., wholly separate components, units and subunits of groups of components, different communication regimes between components).

[0078] Although specific embodiments and applications of the disclosure have been described in this specification, these embodiments and applications are exemplary only, and many variations are possible. For example, although examples and embodiments have been described with respect to adaptively generating synthetic microvascular networks in regions pertaining to the heart, it is contemplated that similarly described synthetic microvascular networks may be formed using similar techniques in other regions of the body associated with other organs (e.g., liver, spleen, brain, lungs, etc.)Example Experiments

[0079] The presently disclosed techniques for generating adaptive synthetic vascular network models for diagnostic assessment were further tested for their accuracy and reliability.

[0080] In at least one experiment, an ideal left ventricular (LV) myocardial geometry was generated from coronary computed tomography angiograms (CTA) and was segmented according to the American Heart Association (AHA) 17-segment model. Representative MBV maps of the LV were estimated using Kassab’s myocardial mass-flow rate relationship.

[0081] A 3D model of left anterior descending (LAD) artery was extracted from the CTA images. The centerlines for the LAD were extracted and a ID model of LAD was reconstructed. Lor the arterial network generation, an adaptive, multistage constraint constructive optimization (CCO) model was developed to generate the vascular network. In brief, locations of virtual terminal nodes were generated randomly, and 15 closest arterial segments were identified. To find the best location for each bifurcation point, physiological and geometrical constraints were incorporated, and an optimization problem was solved where the objective function was the total volume of the arterial tree. The construction of the arterialtree for different myocardial segments continued until the diameter of the terminal segments reached a desired threshold (e.g., about 150 |am). It is contemplated that other thresholds could also be reached (e.g., about 100 pm, 110 pm, 120 pm, 130 pm, 140 pm, 150 pm, 160 pm, 170 pm, 180 pm, 190 pm, or 200 pm) or a threshold formed as a range between any two aforementioned values (e.g., about 100 pm - 200 pm, 125 pm - 175 pm).

[0082] The next step conducted was a global optimization of diameters (e.g., as in block 210). An iterative optimization method was developed to correct each arterial segment diameter until the flow rate supplying each myocardial segment matched the MB V to a desired tolerance level (e.g., of about 0.2 %).

[0083] Since the terminal node selection process was based on a random coordinate generator, five arterial networks were generated based on different seeds, and the distributions of arterial segment diameters were compared. Also, the resultant synthetic MBV maps were compared with the prescribed MBV maps.

[0084] FIG. 4 is an illustration of the adaptive synthetic microvascular network that was generated, according to example embodiments of the present disclosure. In particular, the adaptive synthetic microvascular network developed using the aforementioned experiment functioned as a model (also referred to herein as synthetic microvascular network model) to generate diagnostic assessments (e.g., as shown and described in relation to FIG. 2B). Part 420 of FIG. 4 shows the construction of the coronary vessel of interest, which was the left anterior descending (LAD) artery in the experiment. During this stage, the model may included a territory governed by the coronary vessel of interest, as well as a segmentation of the coronary vessel and corresponding territory. Thus, as shown in part 420, there were three territories (422, 424, and 426) corresponding to three segments of the LAD. In some embodiments, the initial model may be a 3D model of the coronary vessel of interest. Also or alternatively, aspects of the initial model may be 1-dimensional (ID), such as a ID tree of the coronary vessel of interest, with the territory covered by the coronary vessel of interest shown, along with corresponding segments of the initial tree.

[0085] FIG. 4 also shows the synthetic arterial network generated through the experiment using the techniques disclosed herein. As shown in part 440, the synthetic arterial network has a plurality of arterial segments (e.g., about 1500 arterial segments). Also as discussed, thesynthetical arterial network generated through the experiment was able to function as a model based on blood flow simulations. For example, as shown in part 460, the synthetic arterial network was used to simulate blood flow, allowing a user to view various characteristics of the blood flow and determine medical indices that may otherwise involve invasive procedures (e.g., FFR, IMR, CFR, etc.). In particular, part 460 shows that the distribution of a flow rate in the LAD arterial tree, with near uniform flow rate distribution near the terminal segments.

[0086] FIG. 5 is a graph showing the precision and reliability of the computer-implemented techniques for adaptively generating a synthetic microvascular network, according to nonlimiting embodiments of the present disclosure. In particular, FIG. 5 shows the distribution of terminal segment diameters for five synthetic microvascular networks generated using the presently disclosed techniques. The terminal segment distributions were found to be similar for all five synthetic microvascular networks (e.g., based on their coefficient of variation being about 0.21). The mean terminal segment diameter for all seeds was 131+28 pm and the average arterial tree volume was 392+13 mm3. Thus, the experiments, based on the presently disclosed techniques, shows accuracy (e.g., in modeling the physiology of the human heart) as well as precision and reliability (e.g., based on the low variability shown in FIG. 5).

[0087] Experiments were also conducted comparing the use of the adaptively generated synthetic microvascular network models to generate diagnostic assessments. For example, in at least one experiment, the presently disclosed synthetic microvascular network was used to generate blood flow transit times for an IMR (e.g., as discussed in relation to FIG. 2B), and the results were compared to known blood flow transit times obtained by invasive IMR. In particular, known blood flow transit times of swine subjects were determined invasively using conventional IMR techniques to the blood flow transit times determined according to techniques described herein (e.g., method 200B of FIG. 2B) based on the adaptive synthetic vascular network model described herein (e.g., generated via method 200A of FIG. 2A). The present disclosed techniques were found to simulate the thermodilution-based transit time and IMR calculation with an error of 1.2% and 0.4%, respectively. Also, the IMR value determined using the presently discussed techniques for subjects with large ischemia in mid-distal anterior wall (IMR=25.1) were found to be significantly higher than the IMR in subjects with small ischemia in mid-proximal anterior wall. The results thus showed that the presently disclosed techniques for non-invasively determining IMR using the adaptive synthetic microvascularnetwork models described herein could successfully replicate the coronary arterial networks in subjects with IHD while accurately providing the hemodynamic environment to calculate synthetic IMR values with an error of less than 0.4% when compared to invasive IMR measurements. These results underscore the promise for the presently disclosed techniques for non-invasive diagnosis, management, and treatment planning of IHD, including CMD, and its potential use in research settings for therapeutic development.Conclusion

[0088] Aspects of the present embodiment are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to the embodiment. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer readable program instructions.

[0089] These computer readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions / acts specified in the flowchart and / or block diagram block or blocks. These computer readable program instructions may also be stored in a computer readable storage medium that can direct a computer, a programmable data processing apparatus, and / or other devices to function in a particular manner, such that the computer readable storage medium having instructions stored therein comprises an article of manufacture including instructions which implement aspects of the function / act specified in the flowchart and / or block diagram block or blocks.

[0090] The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process, such that the instructions which execute on the computer, other programmable apparatus, or other device implement the functions / acts specified in the flowchart and / or block diagram block or blocks.

[0091] The flowchart and block diagrams in the Figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and / or flowchart illustration, and combinations of blocks in the block diagrams and / or flowchart illustration, can be implemented by special purpose hardwarebased systems that perform the specified functions or acts or carry out combinations of special purpose hardware and computer instructions.

[0092] The descriptions of the various embodiments of the present embodiment have been presented for purposes of illustration but are not intended to be exhaustive or limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein was chosen to best explain the principles of the embodiments, the practical application or technical improvement over technologies found in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

What is claimed is:

1. A computer-implemented method for adaptively generating a synthetic microvascular network, the method comprising: generating, by a computing device having a processor, a three-dimensional (3D) model of a coronary vessel of a patient; generating, by the computing device, based on the 3D model, a myocardial blood volume (MBV) map of a region of interest perfused by the coronary vessel of the patient; determining, based on the MBV map, a blood volume for the region of interest perfused by the coronary vessel; generating, based on the 3D model and the blood volume for the region of interest, a vascular network model; optimizing, based on the MBV map, one or more geometric parameters of each segment of a plurality of segments of the vascular network model to generate the synthetic microvascular network model, wherein the synthetic microvascular network model comprises the plurality of segments of the vascular network model and further comprises one or more microvessels emanating from the coronary vessel to perfuse the region of interest; and generating, based on the synthetic microvascular network model, a diagnostic assessment of the region of interest.

2. The method of claim 1, further comprising: acquiring patient-specific image data via the imaging modality, the patient-specific image data comprising the coronary vessel of the patient and the region of interest perfused by the coronary vessel; wherein generating the 3D model of the coronary vessel of the patient comprises segmenting the patient- specific image data to extract the coronary vessel from the patientspecific image data.

3. The method of claim 2, wherein acquiring the patient-specific image data via the imaging modality comprises: administering an intravascular agent to the patient; and acquiring the patient-specific image data after the intravascular agent has entered the coronary vessel of the patient and the region of interest perfused by the coronary vessel.

4. The method of claim 2 or 3, wherein the imaging modality is magnetic resonance imaging.

5. The method of any one of the preceding claims, wherein generating the vascular network model comprises: extracting, by the computing device, a centerline of the coronary vessel; and generating, based on the MBV map, a plurality of virtual terminal nodes and a plurality of arterial segments emanating from the centerline.

6. The method of any one of the preceding claims, wherein optimizing the one or more geometric parameters of each segment comprises optimizing a diameter of the segment and optimizing a bifurcation point of the segment; wherein the optimizing the diameter of the segment comprises: iteratively minimizing a difference in an estimated blood flow rate based on the diameter of the segment and an actual blood flow rate determined using the MBV map until the difference satisfies a predetermined threshold.

7. The method of any one of the preceding claims, further comprising: determining, using the synthetic microvascular network model, one or more of an index of microcirculatory resistance (IMR), a coronary flow reserve (CFR), or a fractional flow reserve (FFR) of the region of interest; and generating, based on one or more of the IMR, the CFR, or the FFR, the diagnostic assessment of the region of interest.

8. The method of any one of the preceding claims, further comprising: determining, using the synthetic microvascular network model, an IMR by: generating a cyclic pulsatile flow through the synthetic microvascular network model; deploying a particle at a first location of the synthetic microvascular network model; anddetermining a blood flow transit time based on the particle traveling to a second location of the synthetic microvascular network model, the second location being a predetermined distance downstream of the first location.

9. The method of claim 8, wherein the first location is a mid point of the coronary artery.

10. The method of claim 8 or 9, wherein the predetermined distance is about 2 to 4entimeters.

11. The method of any one of the preceding claims, wherein the diagnostic assessment comprises: a presence of or a degree of a blockage in a segment of the synthetic microvascular network model; a presence of or a degree of a stenosis in a segment of the synthetic microvascular network model; or a presence of or a degree of ischemia in the region of interest.

12. The method of any one of the preceding claims, wherein generating the vascular network model and optimizing to generate the synthetic microvascular network model are performed via constraint constructive optimization.

13. A system for adaptive synthetic microvascular network generation, the systemomprising: a processor; and memory storing instructions that, when executed by the processor, cause the processor to: generate a three-dimensional (3D) model of a coronary vessel of a patient; generate, based on the 3D model, a myocardial blood volume (MBV) map of a region of interest perfused by the coronary vessel of the patient; determine, based on the MBV map, a blood volume for the region of interest perfused by the coronary vessel;generate, based on the 3D model of the coronary vessel and the blood volume for the region of interest, an initial vascular network model; optimize, based on the MBV map, one or more geometric parameters of each segment of a plurality of segments of the vascular network model to generate an synthetic microvascular network model, wherein the synthetic microvascular network model comprises the plurality of segments of the vascular network model and further comprises one or more microvessels emanating from the coronary vessel to perfuse the region of interest; and generate, based on the synthetic microvascular network model, a diagnostic assessment of the region of interest.

14. The system of claim 13, wherein the instructions, when executed, further cause the processor to: acquire patient-specific image data via the imaging modality, the patient- specific image data comprising the coronary vessel of the patient and the region of interest perfused by the coronary vessel; wherein generating the 3D model of the coronary vessel of the patient comprises segmenting the patient- specific image data to extract the coronary vessel from the patientspecific image data.

15. The system of claim 14, wherein the instructions, when executed, cause the processor to acquire the patient- specific image data via the imaging modality by: administering an intravascular agent to the patient; and acquiring the patient-specific image data after the intravascular agent has entered the coronary vessel of the patient and the region of interest perfused by the coronary vessel.

16. The system of claim 14 or 15, wherein the imaging modality is magnetic resonance imaging.

17. The system of any one of claims 13-16, wherein the instructions, when executed, cause the processor to generate the vascular network by: extracting a centerline of the coronary vessel; andgenerating, based on the MBV map, a plurality of virtual terminal nodes and a plurality of arterial segments emanating from the centerline.

18. The system of any one of claims 13-17, wherein the instructions, when executed, cause the processor to optimize the one or more geometric parameters of each segment by optimizing a diameter of the segment and optimizing a bifurcation point of the segment; wherein the optimizing the diameter of the segment comprises: iteratively minimizing a difference in an estimated blood flow rate based on the diameter of the segment and an actual blood flow rate determined using the MBV map until the difference satisfies a predetermined threshold.

19. The system of any one of claims 13-18, wherein the instructions, when executed, further cause the processor to: determine, using the synthetic microvascular network model, one or more of an index of microcirculatory resistance (IMR), a coronary flow reserve (CFR), or a fractional flow reserve (FFR) of the region of interest; and generate, based on one or more of the IMR, the CFR, or the FFR, a diagnostic assessment of the region of interest.

20. The system of any one of claims 13-19, wherein the instructions, when executed, further cause the processor to: determine, using the synthetic microvascular network model, the IMR of the region of interest by: generating a cyclic pulsatile flow through the synthetic microvascular network model; deploying a particle at a first location of the synthetic microvascular network model; and determining a blood flow transit time based on the particle traveling to a second location of the synthetic microvascular network model, the second location being a predetermined distance downstream of the first location.

21. The system of claim 20, wherein the first location is a mid point of the coronary artery.

22. The system of claim 20 or 21, wherein the predetermined distance is about 2 to 4 centimeters.

23. The system of any one of claims 13-22, wherein the diagnostic assessment comprises: a presence of or a degree of a blockage in a segment of the synthetic microvascular network model; a presence of or a degree of a stenosis in a segment of the synthetic microvascular network model; or a presence of or a degree of ischemia in the region of interest.

24. The system of any one of claims 13-23, wherein the instructions, when executed, further cause the processor to generate the vascular network model and optimize to generate the synthetic microvascular network model via constraint constructive optimization.

25. A non-transitory computer-readable medium (CRM) having stored thereon computer- readable instructions executable to cause performance of operations comprising: generating, by a computing device having a processor, a three-dimensional (3D) model of a coronary vessel of a patient; generating, by the computing device, based on the 3D model, a myocardial blood volume (MBV) map of a region of interest perfused by the coronary vessel of the patient; determining, based on the MBV map, a blood volume for the region of interest perfused by the coronary vessel; generating, based on the 3D model of the coronary vessel and the blood volume for the region of interest, a vascular network model; optimizing, based on the MBV map, one or more geometric parameters of each segment of a plurality of segments of the vascular network model to generate a synthetic microvascular network model, wherein the synthetic microvascular network model comprises the plurality of segments of the vascular network model and further comprises one or more microvessels emanating from the coronary vessel to perfuse the region of interest; and generating, based on the synthetic microvascular network model, a diagnostic assessment of the region of interest.

26. The non-transitory CRM of claim 25, the operations further comprising: acquiring patient- specific image data via an imaging modality, the patient- specific image data comprising the coronary vessel of the patient and the region of interest perfused by the coronary vessel; wherein generating the 3D model of the coronary vessel of the patient comprises segmenting the patient- specific image data to extract the coronary vessel from the patientspecific image data.

27. The non-transitory CRM of claim 26, wherein acquiring the patient-specific image data via the imaging modality comprises: administering an intravascular agent to the patient; and acquiring the patient-specific image data after the intravascular agent has entered the coronary vessel of the patient and the region of interest perfused by the coronary vessel.

28. The non-transitory CRM of claim 26 or 27, wherein the imaging modality is magnetic resonance imaging.

29. The non-transitory CRM of any one of claims 25-28, wherein generating the vascular network model comprises: extracting, by the computing device, a centerline of the coronary vessel; generating, based on the MBV map, a plurality of virtual terminal nodes and a plurality of arterial segments emanating from the centerline.

30. The non-transitory CRM of any one of claims 25-29, wherein optimizing the one or more geometric parameters of each segment comprises optimizing a diameter of the segment and optimizing a bifurcation point of the segment; wherein the optimizing the diameter of the segment comprises: iteratively minimizing a difference in an estimated blood flow rate based on the diameter of the segment and an actual blood flow rate determined using the MBV map until the difference satisfies a predetermined threshold.

31. The non-transitory CRM of any one of claims 25-30, the operations further comprising: determining, using the synthetic microvascular network model, one or more of an index of microcirculatory resistance (IMR), a coronary flow reserve (CFR), or a fractional flow reserve (FFR) of the region of interest; and generating, based on one or more of the IMR, the CFR, or the FFR, the diagnostic assessment of the region of interest.

32. The non-transitory CRM of claim 31, the operations further comprising: determining, using the synthetic microvascular network model, the IMR by: generating a cyclic pulsatile flow through the synthetic microvascular network model; deploying a particle at a first location of the synthetic microvascular network model; and determining a blood flow transit time based on the particle traveling to a second location of the synthetic microvascular network model, the second location being a predetermined distance downstream of the first location.

33. The non-transitory CRM of claim 32, wherein the first location is a mid point of the coronary artery.

34. The non-transitory CRM of claim 32 or 33, wherein the predetermined distance is about 2 to 4 centimeters.

35. The non-transitory CRM of any one of claims 25-34, wherein the diagnostic assessment comprises: a presence of or a degree of a blockage in a segment of the synthetic microvascular network model; a presence of or a degree of a stenosis in a segment of the synthetic microvascular network model; or a presence of or a degree of ischemia in the region of interest.

36. The non-transitory CRM of any one of claims 25-35, wherein generating the vascular network model and optimizing to generate the synthetic microvascular network model are performed via constraint constructive optimization.

Images