Coronary vasoreactivity determination using coronary stimulator and a computer vision system

Abstract

An example medical system includes memory configured to store angiography data of a patient including pre-stimulation angiography data and post-stimulation angiography data. The pre-stimulation angiography data includes at least one angiography image including a vessel of the patient captured prior to delivery of stimulation to the vessel. The post-stimulation angiography data includes at least one angiography image including the vessel captured after initiation of the delivery of stimulation to the vessel. The medical system includes processing circuitry communicatively coupled to the memory. The processing circuitry is configured to obtain the pre-stimulation angiography data and obtain the post-stimulation angiography data. The processing circuitry is configured to determine a size difference of the vessel between the pre-stimulation angiography data and the post-stimulation angiography data and output an indication of the size difference.

Description

CORONARY VASOREACTIVITY DETERMINATION USINGCORONARY STIMULATOR AND A COMPUTER VISION SYSTEM

[0001] This application claims the benefit of U.S. Provisional Application No. 63 / 586,751, filed September 29, 2023, the entire content of which is hereby incorporated by reference.TECHNICAL FIELD

[0002] This disclosure relates to the use imaging during a medical procedure.BACKGROUND

[0003] During a medical procedure, a clinician may use an imaging system to be able to visualize internal anatomy of a patient. Such an imaging system may display anatomy, medical instruments, or the like, and may be used to diagnose a patient condition or assist in guiding a clinician in navigating a device inside a patient, such as moving a medical instrument to an intended location inside the patient. Imaging systems may use sensors to capture image data which may be displayed during the medical procedure. Imaging systems include angiography systems, computed tomography (CT) scan systems (including coronary computed tomography angiography (CCTA) systems), fluoroscopic systems (e.g., isocentric C-arm fluoroscopic systems), intravascular ultrasound (IVUS) systems, other ultrasound imaging systems, optical coherence tomography (OCT) fractional flow reserve (FFR) systems, magnetic resonance imaging (MRI) systems, positron emission tomography (PET) systems, as well as other imaging systems.SUMMARY

[0004] Ischemia with Non-Obstructive Coronary Artery disease (INOCA) is a chronic disease of the coronary microvasculature. INOCA is a symptomatic condition without significant flow restrictions in the epicardial vessel. INOCA is associated with a higher mortality rate than the absence of INOCA. Today, INOCA predominantly takes a relatively long time to detect due to non-user-friendly techniques and techniques that do not fit within a current interventional cardiologist (IC) workflow.

[0005] INOCA includes a plurality of endotypes: microvascular angina, vasospastic angina, and a combination of microvascular angina and vasospastic angina. Guidedmedical therapy, that is particular to endotype of INOCA, has been clinically validated to improve INOCA symptoms. As such, it may be desirable to correctly determine an endotype of INOCA in a patient.

[0006] Traditionally, two tests are generally needed to determine the endotype of INOCA that a patient may have so that an efficacious therapy may be selected for the patient. Today, vasospastic angina (one of the endotypes of INOCA) is determined by administering a drug, acetylcholine, intra coronary. The clinician then measures by eye, via angiogram images, the vasoreactivity response of the coronary artery to the drug (e.g., an acetylcholine receptor antibody (ACH) test). If the artery into which the acetylcholine was injected contracts more than ninety percent (90%), the patient is determined to have vasospastic angina. However, acetylcholine is often not available and, when available for use in determining the presence of vasospastic angina, the acetylcholine is generally administered directly into the coronaries of the patient.

[0007] Because determination of endotype of INOCA may affect treatment options, because acetylcholine may be relatively difficult to acquire, and because some patients may have adverse reactions, such as allergic reactions, to the administration of acetylcholine, it may be desirable to determine whether a particular patient has vasospastic angina without requiring the delivery of acetylcholine to the patient.

[0008] The techniques of this disclosure may provide for a safer, faster, and easier determination of vasospastic angina in a patient. This disclosure is related to determining presence of vasospastic angina in a patient and / or determining and recommending treatment for the patient. This disclosure describes techniques for determining vasospastic angina without need to use an intra coronary drug, such as acetylcholine. Such techniques may include electrically stimulating the coronary artery via electrodes of a device, using temperature stimulation (e.g., a cold pressor test) to stimulate a sympathetic nervous system response in the coronary vessel, and / or removing ambiguity of the “eye ball” measurement by utilizing computer vision techniques to more accurately and automatically measure any response to the stimulation in angiography data.

[0009] In one example, the disclosure describes a medical system comprising: memory configured to store angiography data of a patient, the angiography data comprising pre-stimulation angiography data, the pre-stimulation angiography data including at least one angiography image including a vessel of the patient captured prior to delivery of stimulation to the vessel, the angiography data further comprising poststimulation angiography data, the post-stimulation angiography data including at least oneangiography image including the vessel captured after initiation of the delivery of stimulation to the vessel; and processing circuitry communicatively coupled to the memory, the processing circuitry being configured to: obtain the pre-stimulation angiography data; obtain the post-stimulation angiography data; determine a size difference of the vessel between the pre-stimulation angiography data and the poststimulation angiography data; and output an indication of the size difference.

[0010] In another example, the disclosure describes a method comprising: obtaining pre-stimulation angiography data, the pre-stimulation angiography data comprising at least one angiography image including a vessel of a patient captured prior to delivery of stimulation to the vessel; obtaining post-stimulation angiography data, the poststimulation angiography data comprising at least one angiography image including the vessel captured after initiation of the delivery of stimulation to the vessel; determining a size difference of the vessel between the pre-stimulation angiography data and the poststimulation angiography data; and outputting an indication of the size difference.

[0011] In yet another example, the disclosure describes a non-transitory computer readable medium comprising instructions, which, when executed, cause processing circuitry to: obtain pre-stimulation angiography data, the pre-stimulation angiography data comprising at least one angiography image including a vessel of a patient captured prior to delivery of stimulation to the vessel; obtain post-stimulation angiography data, the post-stimulation angiography data comprising at least one angiography image including the vessel captured after initiation of the delivery of stimulation to the vessel; determine a size difference of the vessel between the pre-stimulation angiography data and the post-stimulation angiography data; and output an indication of the size difference.

[0012] These and other aspects of the present disclosure will be apparent from the detailed description below. In no event, however, should the above summaries be construed as limitations on the claimed subject matter, which subject matter is defined solely by the attached claims.

[0013] This summary is intended to provide an overview of the subject matter described in this disclosure. It is not intended to provide an exclusive or exhaustive explanation of the apparatus and methods described in detail within the accompanying drawings and description below. Further details of one or more examples are set forth in the accompanying drawings and the description below.BRIEF DESCRIPTION OF DRAWINGS

[0014] FIG. l is a schematic perspective view of one example of a system for determining an indication of MVO according to one or more aspects of this disclosure.

[0015] FIG. 2 is a schematic view of one example of a computing system of the system of FIG. 1.

[0016] FIG. 3 is a conceptual diagram illustrating an example guide wire having electrodes according to one or more aspects of this disclosure.

[0017] FIG. 4 is a conceptual diagram illustrating an example angioplasty balloon device having electrodes according to one or more aspects of this disclosure.

[0018] FIG. 5 is a conceptual diagram illustrating an example microcatheter having electrodes according to one or more aspects of this disclosure.

[0019] FIG. 6 is a conceptual diagram illustrating an example spiral or helix shaped microcatheter having electrodes according to one or more aspects of this disclosure.

[0020] FIG. 7 is a conceptual diagram illustrating an example guide catheter having electrodes according to one or more aspects of this disclosure.

[0021] FIG. 8 is a conceptual diagram illustrating an example guide extension catheter having electrodes according to one or more aspects of this disclosure.

[0022] FIG. 9 is a conceptual diagram illustrating an example cold compressor test according to one or more aspects of this disclosure.

[0023] FIG. 10 is a conceptual diagram illustrating an example device for stimulating a sympathetic nervous system response to a coronary vessel according to one or more aspects of this disclosure.

[0024] FIG. 11 is a conceptual diagram illustrating an example handle that may be used with a device configured to deliver stimulation to a coronary vessel according to one or more aspects of this disclosure.

[0025] FIGS. 12A and 12B are conceptual diagrams illustrating a vessel before and after delivery of stimulation.

[0026] FIG. 13 is a flow diagram illustrating example machine learning model verification techniques according to one or more aspects of this disclosure.

[0027] FIG. 14 is a conceptual diagram illustrating an example machine learning model according to one or more aspects of this disclosure.

[0028] FIG. 15 is a conceptual diagram illustrating an example training process for a machine learning model according to one or more aspects of this disclosure.DETAILED DESCRIPTION

[0029] As discussed above, INOCA is a chronic disease of the coronary microvasculature. Patients experiencing INOCA are typically stable and not experiencing ST-Segment Elevation Myocardial Infarction (STEMI). If undiagnosed and untreated, the prognosis of patients with INOCA is an increased risk of adverse cardiac events. INOCA patients may have a high symptom burden impacting their quality of life and may have an increased incidence of major adverse cardiac events (including Myocardial Infarction).

[0030] Guided medical therapy is clinically validated to improve INOCA symptoms, based on endotype. The “CorMicA” trial demonstrated improved outcomes when invasive coronary function testing during angina was used to stratify medical therapy.

[0031] Identification of the presence of INOCA may occur in a catheterization laboratory (Cath lab). An invasive coronary angiography may be used to first rule in or rule out any obstructive coronary artery disease (CAD). When a clinician sees no obstructive CAD in the angiography data, the clinician may use a pressure-temperature wire to determine a Fractional Flow Reserve (FFR) score, which may be used to further rule in or out the obstructive CAD. The clinician may also use the pressure-temperature wire, along with the administration of adenosine, to measure a coronary flow reserve (CFR) score and an index of microvascular resistance (IMR).

[0032] The clinician may then determine vasoreactivity through an intra-coronary infusion of acetylcholine (ACH test) and visually monitor any reduction in a diameter of the vessel under evaluation. If the reduction is greater than 90%, the clinician may determine the existence of vasospastic angina in the patient.

[0033] In healthy individuals, the administration of acetylcholine into the coronary arteries typically results in a vasodilatory response, increasing the diameter of the coronary arteries and increasing blood flow to the heart. However, in individuals with CAD, the response to acetylcholine can be abnormal, leading to paradoxical vasoconstriction and a decrease in blood flow to the heart.

[0034] In patients with vasospastic angina, the endothelial cells may be dysfunctional and fail to release nitric oxide in response to acetylcholine. In addition, other vasoconstrictor substances such as endothelin-1 and thromboxane A2 may be released in response to acetylcholine, further contributing to coronary artery spasm in patients with vasospastic angina. The mechanisms underlying the abnormal vascular reactivity in vasospastic angina are not fully understood, but are believed to involve a complexinterplay of various signaling pathways and factors, including endothelial dysfunction, smooth muscle hyperreactivity, and autonomic nervous system dysfunction.

[0035] According to the techniques of this disclosure, a medical system may utilize a stimulation device to stimulate a coronary vessel of a patient to promote a vasoreaction that can be measured. In some examples, the stimulation device may be configured to deliver electrical stimulation via electrodes to a coronary vessel. In such examples, the stimulation device may include a device, such as a guide wire, a “plain old balloon angioplasty” (POBA) balloon, a microcatheter, a guide catheter, a diagnostic catheter, or a guide extension catheter, which has electrodes added thereto. In some examples, the stimulation device may be configured to deliver temperature stimulation to the coronary vessel so as to stimulate a sympathetic nervous system response The use of stimulation may replace the need for the injection of acetylcholine into the coronary vessel of the patient.

[0036] The techniques of this disclosure may also utilize computer vision techniques to analyze angiography data, including pre-stimulation angiography image(s) and poststimulation angiography image(s). The use of computer vision techniques to determine differences in the pre-stimulation angiography image(s) and the post-stimulation angiography image(s), such as differences in the size (e.g., diameter) of a vessel, may increase the accuracy of a determination of vasospastic angina.

[0037] FIG. l is a schematic perspective view of one example of a system for determining an indication of vasospastic angina according to one or more aspects of this disclosure. System 100 includes a display device 110, a table 120, an imager 140, and a computing device 150. System 100 may be an example of a system for use in an emergency room or a cath lab. In some examples, system 100 may include other devices, not shown for simplicity purposes. In some examples, system 100 may also include server 160, which may be co-located with the other devices of system 100 or may be located elsewhere. System 100 may be used during a medical procedure, such as an interventional medical procedure like a PCI and / or a diagnostic medical procedure.

[0038] Computing device 150 may include, for example, an off-the-shelf device such as a laptop computer, desktop computer, tablet computer, smart phone, or other similar device or may include a specific purpose device. As such, computing device 150 may be an external computing device, external to a body of a patient. Computing device 150 may perform various control functions with respect to imager 140. In some examples, computing device 150 may include a guidance workstation. Computing device 150 maycontrol the operation of imager 140 and receive the output of imager 140 and may receive angiography data from imager 140. Computing device 150 may execute a computer vision model to determine size differences of a vessel in different angiography data, such as sizes of a diameter of a vessel prior to delivery of stimulation to the vessel and after the commencement of the delivery of stimulation to the vessel. As used herein after the commencement (or initiation) of the delivery of stimulation may be at a time when stimulation is being delivered or within a relatively short period of time, such as within less than 30 seconds, after delivery of stimulation is ceased.

[0039] Display device 110 may be configured to output instructions, images, and messages relating to the medical procedure(s). For example, display device 110 may display angiography data obtained through imager 140, an indication of a size difference of a vessel between pre-stimulation angiography data and the post-stimulation angiography data, an indication of the presence of vasospastic angina, a recommendation of a treatment for the patient, and / or the like. Table 120 may be, for example, an operating table or other table suitable for use during a medical procedure.

[0040] In the example of FIG. 1, imager 140, such as an angiography imager (or other imaging device), may be used to image relevant portions of the patient’s anatomy during a medical procedure to visualize the anatomy, characteristics and locations of lesions or other issues inside the patient’s body through the generation of imaging data. As such, imager 140 may capture angiography data. While described herein primarily as an angiography imager, imager 140 may be any type of imaging device, such as an angiography device, a fluoroscopy device, a CT device, a CCTA device, an IVUS device, an OCT - FFR device, an MRI device, a PET device, an ultrasound device, or the like. In some examples, imager 140 may represent more than one imaging device, such as a plurality of any of the aforementioned devices.

[0041] Imager 140 may image a region of interest in the patient’s body. The particular region of interest may be dependent on anatomy, the medical procedure, patient symptoms, and / or the like. For example, when performing a cardiac medical procedure, a portion of the vasculature and / or the heart may be within the region of interest.

[0042] Stimulation device 170 may include a device configured to deliver electrical stimulation to a vessel of a patient via electrodes and / or a device configured to deliver temperature stimulation to a vessel of the patient. For example, stimulation device 170 may include a guide wire, an angioplasty balloon, a microcatheter, a guide catheter, a diagnostic catheter, a guide extension catheter, a container of ice water, a thermal cuff, orthe like. Various examples of device 170 are set forth and described in more detail with respect to FIGS. 3-10, later in this disclosure.

[0043] The inner lining of blood vessels, known as the endothelium, plays an important role in regulating vascular tone and blood flow through the release of various vasodilators and vasoconstrictors. Electrical stimulation via electrodes may cause a vasodilatory effect by stimulating the inside of the coronary vessel wall. This technique may be referred to as endothelial electrical stimulation and may involve applying a low- level electrical current (or voltage) to the endothelial cells lining the blood vessels to stimulate the release of nitric oxide and other vasodilators. Temperature stimulation from lowering a temperature of a skin of the patient may cause a similar effect to coronary vessels. In patients with vasospastic angina, the response of the endothelial cells to the stimulation may be impaired, leading to paradoxical vasoconstriction of the coronary arteries instead of the expected vasodilation.

[0044] In the example of an electrical stimulation device, the electrodes of stimulation device 170, which may include one or more combinations of a plurality of electrodes, may be in contact with the vessel wall and apply a relatively low-level electrical current (or voltage) to the endothelial cells. While the current is being delivered, processing circuitry 204 may monitor the resulting vasoreactivity and / or changes in blood flow using the computer vision model(s) 222.

[0045] In general, the electrical current used for stimulation by an electrical stimulation example of simulation device 170 may be in the microampere range, with a frequency in the kilohertz range. The specific amplitude and pulse parameters may vary depending on the desired effect and the type of electrode used. In some examples, the electrodes and / or the stimulation parameters may be configured to specifically target endothelial cells rather than smooth muscle cells.

[0046] In some examples, computing device 150 and stimulation device 170 may be communicatively coupled, for example, by wired, optical, or wireless communications. As such, in some examples, delivery of stimulation by stimulation device 170 may be controlled by computing device 150. In some examples, stimulation device 170 may be configured to notify computing device 150 regarding timing of the delivery of stimulation. For example, stimulation device 170 may communicate with computing device 150 to notify computing device 150 that stimulation is commencing, that stimulation is being delivered, and / or that stimulation is being terminated. In this manner,computing device 150 may determine which angiography images captured by imager 140 are pre-stimulation images and which are post-stimulation images.

[0047] Computing device 150 may be communicatively coupled to imager 140, stimulation device 170, display device 110 and / or server 160, for example, by wired, optical, or wireless communications. Server 160 may be a hospital server which may or may not be located in an emergency room or Cath lab of a hospital, a cloud-based server, or the like. Server 160 may be configured to store patient imaging data (such as angiography data), electronic healthcare or medical records, or the like. In some examples, server 160 may be configured to execute the computer vision model and / or perform one or more of, or a portion of one or more of, the determinations discussed herein.

[0048] Any of, or any combination of, computing device 150, imager 140, and / or server 160 may include a computer vision model. For example, computing device 150, imager 140, and / or server 160 may obtain pre-stimulation and post-stimulation angiography data, e.g., via imager 140. Computing device 150, imager 140, and / or server 160 may execute the computer vision model to determine a size difference of a vessel between the pre-stimulation angiography data and the post-stimulation angiography data. Computing device 150, imager 140, and / or server 160 may output an indication of the size difference. The indication of the size difference may include a percentage of the size difference (e.g., a reduction) between a diameter of a vessel represented in the prestimulation angiography data and the post-stimulation angiography data. If the size difference meets a threshold, such as being greater than 90%, that may be indicative of the presence of vasospastic angina in the patient. The indication of the size difference may include an indication of the percentage difference between the diameter of the vessel, and / or an indication of the presence of, or the lack of presence of, vasospastic angina. Computing device 150, imager 140, and / or server 160 may output the indication of the size difference for display on display device 110. For example, the indication of the size difference may be intended to be visually displayed for viewing by a clinician. In some examples, the indication may not be visual or may include visual, as well as other elements, such as auditory, tactile, or the like. For example, computing device 150, imager 140, and / or server 160 may output a representation of the indication of the size difference for display, for example, to display device 110. For example, display device 110 may overlay a representation of the indication of the size difference on live angiography images from imager 140. As there may be multiple images of a vessel takenbefore stimulation is delivered to the vessel and after the initiation of the delivery of stimulation to the vessel, in some examples, the size difference may be a maximum difference in size of a vessel between the angiography images. For example, computing device 150, imager 140, and / or server 160 may determine a difference between a largest diameter of a vessel represented in pre-stimulation images and a smallest diameter of the same vessel represented in post-stimulation images as the size difference.

[0049] By determining and outputting a representation of indication of the size difference of a vessel to which stimulation is applied between the pre-stimulation angiography data and the post-stimulation angiography data, system 100 may assist clinicians in more effectively determining whether a patient has vasospastic angina and / or how to treat, potential INOCA in a patient. The techniques of this disclosure may be performed during a same medical procedure as one to determine if the patient has obstructive CAD, such that additional diagnostic procedures are not necessary to determine whether treatment is appropriate or to determine which treatment option should be pursued for the patient. As such, the techniques of this disclosure may improve patient outcomes, as patients may be better treated in a more timely manner, and / or improve medical facility efficiency, as a follow-up diagnostic procedure may not be necessary to determine potential treatments for the patient.

[0050] FIG. 2 is a schematic view of one example of a computing device 150 of system 10 of FIG. 1. Computing device 150 may include a workstation, a desktop computer, a laptop computer, a smart phone, a tablet, a dedicated computing device, or any other computing device capable of performing the techniques of this disclosure.

[0051] Computing device 150 may be configured to perform processing, control and other functions associated with imager 140. As shown in FIG. 2, computing device 150 may represent multiple instances of computing devices, each of which may be associated with imager 140. Computing device 150 may include, for example, memory 202, processing circuitry 204, a display 206, a network interface 208, input device(s) 210, and / or output device(s) 212, each of which may represent any of multiple instances of such a device within the computing system, for ease of description.

[0052] While processing circuitry 204 appears in computing device 150 in FIG. 2, in some examples, features attributed to processing circuitry 204 may be performed by processing circuitry of any of computing device 150, imager 140, or server 160, or combinations thereof. In some examples, one or more processors associated with processing circuitry 204 in computing system may be distributed and shared across anycombination of computing device 150, imager 140, and server 160. Computing device 150 may be used to perform any of the techniques described in this disclosure, and may form all or part of devices or systems configured to perform such techniques, alone or in conjunction with other components, such as components of computing device 150, imager 140, server 160, or a system including any or all of such systems / devices.

[0053] Memory 202 of computing device 150 includes any non-transitory computer- readable storage media for storing data or software that is executable by processing circuitry 204 and that controls the operation of computing device 150 and / or imager 140, as applicable. It should be noted that memory 202 may include one or more memory devices. In one or more examples, memory 202 may include one or more solid-state storage devices such as flash memory chips. In one or more examples, memory 202 may include one or more mass storage devices connected to the processing circuitry 204 through a mass storage controller (not shown) and a communications bus (not shown).

[0054] Although the description of computer-readable media herein refers to a solid- state storage, it should be appreciated by those skilled in the art that computer-readable storage media may include any available media that may be accessed by the processing circuitry 204. That is, computer readable storage media includes non-transitory, volatile and non-volatile, removable and non-removable media implemented in any method or technology for storage of information such as computer-readable instructions, data structures, program modules, or other data. For example, computer-readable storage media includes RAM, ROM, EPROM, EEPROM, flash memory and / or other solid state memory technology, CD-ROM, DVD, Blu-Ray and / or other optical storage, magnetic cassettes, magnetic tape, magnetic disk storage and / or other magnetic storage devices, and / or any other medium that may be used to store the desired information and that may be accessed by computing device 150. In one or more examples, computer-readable storage media may be stored in the cloud or remote storage and accessed using any suitable technique or techniques through at least one of a wired or wireless connection.

[0055] Memory 202 may store pre-stimulation angiography data 214 and poststimulation angiography data 216. Pre-stimulation angiography data 214 may include one or more of angiography images obtained, for example, from imager 140 during the medical procedure prior to the delivery of stimulation to a vessel. In some examples, prestimulation angiography data 214 may also include images obtained during a prior diagnostic angiography medical procedure. While the medical procedure is proceeding in time prior to the delivery of stimulation, angiography data may be obtained from imager140 and stored in pre-stimulation angiography data 214. Such angiography data may be displayed via display 206 and / or display device 110 and may be used by a clinician when navigating a medical instrument through anatomy of a patient, such as navigating stimulation device 170 to a location within the patient to commence the delivery of stimulation.

[0056] Post-stimulation angiography data 216 may include one or more of angiography images obtained, for example, from imager 140 during the medical procedure after the delivery of stimulation to the vessel has commenced. The delivery of stimulation to a vessel of a patient having vasospastic angina may cause the diameter of the vessel to shrink. As such, it may be desirable to capture both pre-stimulation angiography data 214 and post-stimulation angiography data 216. In some examples, post-stimulation angiography data 216 includes one or more angiography images obtained while stimulation is being delivered to the vessel via stimulation device 170. In some examples, post-stimulation angiography data 216 includes one or more angiography images obtained after the cessation of the delivery of stimulation, such as within less than 30 seconds of the cessation of the delivery of stimulation.

[0057] In some examples, the delivery of stimulation may occur more than once during a medical procedure. In such cases, pre-stimulation angiography data 214 may include one or more images obtained prior to delivery of stimulation for each vessel to which stimulation is to be delivered, each location of one or more vessels to which stimulation is to be delivered, or the like. In such cases post-stimulation angiography data 216 may include one or more images obtained after the commencement of delivery of stimulation to each vessel to which stimulation is delivered, each location of one or more vessels to which stimulation is delivered, or the like.

[0058] Pre-stimulation angiography data 214 and post-stimulation angiography data 216 may be generated by imager 140 of anatomy of the patient and obtained by computing device 150 via network interface 208 which may be communicatively coupled to imager 140. In some examples, imager 140 may generate other types of imaging data, such as when imager 140 represents more than one imaging device.

[0059] For example, pre-stimulation angiography data 214 and post-stimulation angiography data 216 may be captured by imager 140 (FIG. 1). Processing circuitry 204 may obtain angiography images of pre-stimulation angiography data 214 and poststimulation angiography data 216 from imager 140 and store the angiography images in pre-stimulation angiography data 214 and post-stimulation angiography data 216,respectively, in memory 202. Processing circuitry 204 may execute user interface 218 so as to cause display 206 (and / or display device 110 of FIG. 1) to present user interface 218 to one or more clinicians performing the medical procedure. User interface 218 may display pre-stimulation angiography data 214 and / or post-stimulation angiography data 216. User interface 218 may also display one or more indications of a size difference of a vessel between pre-stimulation angiography 214 data and post-stimulation angiography data 216, such as an indication of a presence of vasospastic angina.

[0060] Memory 202 may also store computer vision model 222 and user interface 218. Computer vision model 222 may be configured to, when executed by processing circuitry 204, compare any of pre-stimulation angiography data 214 with any of poststimulation angiography data 216, such as to determine a size difference of a vessel to which stimulation is applied between pre-stimulation angiography data 214 and poststimulation angiography data 216. In some examples, the size difference is a maximum difference between a size of a particular vessel that is stimulated in pre-stimulation angiography data 214 and post-stimulation angiography data 216. For example, if the size difference between a diameter of a vessel undergoing stimulation is reduced by more than 90% (or 90% or more) between pre-stimulation angiography data 214 and poststimulation angiography data 216, that may be indicative of the patient having vasospastic angina. For example, computer vision model 222 may be configured to determine a vessel in post-stimulation angiography data 216 that is undergoing or has undergone stimulation. Computer vision model 222 may also be configured to determine that same vessel in prestimulation angiography data 214. Computer vision model 222 may be configured to determine a size difference, such as a difference in a diameter of the vessel that was stimulated between pre-stimulation angiography data 214 and post-stimulation angiography data 216. In some examples, computer vision model 222 may be configured to determine whether the size difference meets a threshold. For example, computer vision model 222 may be configured to determine whether the size difference is greater than (or greater than or equal to) a 90% reduction in the size of the diameter of the vessel based on the application of the stimulation to the vessel.

[0061] Processing circuitry 204 may use pre-stimulation angiography data 214 and post-stimulation angiography data 216 to determine the presence of vasospastic angina in the patient. For example, processing circuitry 204 may execute computer vision model to determine the presence of vasospastic angina in the patient and / or determine whether a difference between a size of a diameter of a vessel in pre-stimulation angiography data214 and post-stimulation angiography data 216 meets a threshold, such as is a reduction of greater than (or greater than or equal to) 90%.

[0062] In some examples, computer vision model 222 may include a machine learning model. In such examples, computer vision model 222 may be trained using angiography images of vessels of patients to identify a vessel and / or a diameter of the vessel. In some examples, computer vision model 222 may be trained to identify a vessel in pre-stimulation angiography data 214 that corresponds to a vessel in post-stimulation angiography data 216 that include a portion of stimulation device 170, for example, the electrodes of stimulation device 170, via the use of fiducial points in anatomy in prestimulation angiography data 214 and post-stimulation angiography data 216. In some examples, the angiography images may be annotated by a trained person to identify vessels and / or vessel diameters. In the examples, where computer vision model 222 includes a machine learning model, the machine learning model may include naive Bayes, k-nearest neighbors, random forest, support vector machines, neural networks, linear regression, logistic regression, etc.

[0063] Stimulation device 170 (not shown in FIG. 2) may be connected or coupled (wirelessly, wired, Bluetooth, etc.) to computing device 150 via network interface 208. Computing device 150 may utilize computer vision model 222 to monitor the response to the stimulation in angiography data, e.g., to compare pre-stimulation angiography data 214 to post-stimulation angiography data 216. This comparison may include a comparison of any of one or more images (or frames) of pre-stimulation angiography data 214 to any of one or more images (or frames) of post-stimulation angiography data 216. By being coupled to stimulation device 170, computing device 150 may determine when the stimulation is being delivered and therefore may determine which images of angiography data are pre-stimulation images and which are post-stimulation images.

[0064] In some examples, computing device 150 may prompt a clinician to use imager 140 to capture a cine of angiography image data or may or automatically control imager 140 to capture the cine of angiography image data prior to the delivery of stimulation and may capture cine of the angiography image data during and / or after the delivery of stimulation. As such, processing circuitry 204 may obtain an angiography image before, during, and / or after the stimulation is delivered. Processing circuitry 204 executing computer vision model 222 may compare post-stimulation angiography data 216 to pre-stimulation angiography data 214 to determine the extent of any reduction in the size (e.g., diameter) of the coronary vessel caused by the stimulation. For example,processing circuitry 204 executing computer vision model 222 may determine a percentage reduction of coronary vessel. Processing circuitry 204 may then output a representation of the reduction or an indication that the reduction meets a predetermined threshold. For example, the predetermined threshold may be set such that the predetermined threshold being met is indicative of the presence of vasospastic angina in the patient. In some examples, the predetermined threshold may be 90%. In some examples, the predetermined threshold is met if the reduction is greater than 90%. In some examples, the predetermined threshold is met if the reduction is greater than or equal to 90%.

[0065] Processing circuitry 204 may be implemented by one or more processors, which may include any number of fixed-function circuits, programmable circuits, or a combination thereof. In various examples, control of any function by processing circuitry 204 may be implemented directly or in conjunction with any suitable electronic circuitry appropriate for the specified function. Fixed-function circuits refer to circuits that provide particular functionality and are preset on the operations that may be performed. Programmable circuits refer to circuits that may programmed to perform various tasks and provide flexible functionality in the operations that may be performed. For instance, programmable circuits may execute software or firmware that cause the programmable circuits to operate in the manner defined by instructions of the software or firmware. Fixed-function circuits may execute software instructions (e.g., to receive parameters or output parameters), but the types of operations that the fixed-function circuits perform are generally immutable. In some examples, the one or more of the units may be distinct circuit blocks (fixed-function or programmable), and in some examples, the one or more units may be integrated circuits.

[0066] Instructions may be executed by one or more processors, such as one or more digital signal processors (DSPs), general purpose microprocessors, application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), graphics processing units (GPUs) or other equivalent integrated or discrete logic circuitry. Accordingly, the term processing circuitry 204 as used herein may refer to one or more processors having any of the foregoing processor or processing structure or any other structure suitable for implementation of the techniques described herein. In addition, in some aspects, the functionality described herein may be provided within dedicated hardware or software modules configured for encoding and decoding, or incorporated in acombined codec. Also, the techniques could be fully implemented in one or more circuits or logic elements.

[0067] Display 206 may be touch sensitive or voice activated, enabling display 206 to serve as both an input and output device. Alternatively, a keyboard (not shown), mouse (not shown), or other data input devices (e.g., input device(s) 210) may be employed.

[0068] Network interface 208 may be adapted to connect to a network such as a local area network (LAN) that includes a wired network or a wireless network, a wide area network (WAN), a wireless mobile network, a Bluetooth network, or the internet. For example, computing device 150 may obtain angiography data (e.g., pre-stimulation angiography data 214 and post-stimulation angiography data 216) from imager 140 during a medical procedure and / or information relating to whether stimulation is occurring (e.g., the beginning of stimulation, that stimulation is ongoing, and / or the cessation of stimulation) from stimulation device 170 during a medical procedure. Computing device 150 may receive updates to its software, for example, application(s) 217, via network interface 208. Computing device 150 may also display notifications on display 206 that a software update is available.

[0069] Input device(s) 210 may include any device that enables a user to interact with computing device 150, such as, for example, a mouse, keyboard, foot pedal, touch screen, augmented-reality input device receiving inputs such as hand gestures or body movements, or voice interface.

[0070] Output device(s) 212 may include any connectivity port or bus, such as, for example, parallel ports, serial ports, universal serial busses (USB), or any other similar connectivity port known to those skilled in the art.

[0071] Application(s) 217 may be one or more software programs stored in memory 202 and executed by processing circuitry 204 of computing device 150. Processing circuitry 204 may execute user interface 218, which may display prestimulation angiography data 214, post-stimulation angiography data 216, and / or indications 228. Indications 228 may include any indications generated by computing device 150 relating to the size difference of a vessel to which stimulation is applied between pre-stimulation angiography data 214 and post-stimulation angiography data 216, such an extent of a reduction in a size (e.g., diameter) of a vessel, whether that reduction meets a threshold, and / or whether the presence of vasospastic angina. Indications 228 may include indications generated by stimulation device 170 or otherdevice(s), such as indications that stimulation is being delivered, stimulation is not being delivered, delivery of stimulation has commenced, and / or delivery of stimulation has ceased. Indications 228 may also include an indication of a recommended treatment of a patient, which computing device 150 may generate based on the size difference of the vessel between pre-stimulation angiography data 214 and post-stimulation angiography data 216. For example, based on the size difference of a vessel to which stimulation is applied between pre-stimulation angiography data 214 and post-stimulation angiography data 216 meeting the predetermined threshold, computing device 150 may output an indication of a recommended treatment to the patient, such as administration of channel blockers and / or beta blockers.

[0072] FIG. 3 is a conceptual diagram illustrating an example guide wire having electrodes according to one or more aspects of this disclosure. Guide wire 300 may be an example of stimulation device 170. Guide wire 300 includes a guide wire body 302 have disposed thereon a plurality of electrodes, such as electrodes 304A-304B (collectively “electrodes 304”). Electrodes 304 may include any number of electrodes greater than one and may be located at any location on guide wire body 302. In some examples, one or more of electrodes 304 may be disposed around a circumference of guide wire body 302. In some examples, one or more of electrodes 304 may be disposed on only a portion of the circumference of guide wire body 302. Electrodes 304 may be configured to deliver electrical stimulation to a coronary vessel of a patient, for example, to an interior wall of the coronary vessel. Computing device 150 may monitor a reaction of the coronary vessel to the stimulation in angiography data from imager 140. For example, computing device 150 may determine a difference between a size of the coronary vessel in pre-stimulation angiography data 214 and post-stimulation angiography data 216.

[0073] FIG. 4 is a conceptual diagram illustrating an example angioplasty balloon device having electrodes according to one or more aspects of this disclosure. Angioplasty balloon device 400 may be an example of stimulation device 170. Angioplasty balloon device 400 includes a balloon portion 402, which may be inflatable and have disposed thereon a plurality of electrodes, such as electrodes 404A-404B (collectively “electrodes 404”). Electrodes 404 may include any number of electrodes greater than one and may be located at any location on balloon portion 402. In some examples, one or more of electrodes 404 may be disposed around a circumference of balloon portion 402. For example, one or more of electrodes 404 may be configured to stretch with balloon portion 402 as balloon portion 402 is inflated. In some examples, one or more of electrodes 404may be disposed on only a portion of the circumference of balloon portion 402. Electrodes 404 may be configured to deliver electrical stimulation to a coronary vessel of a patient, for example, to an interior wall of the coronary vessel. Computing device 150 may monitor a reaction of the coronary vessel to the stimulation in angiography data from imager 140. For example, computing device 150 may determine a difference between a size of the coronary vessel in pre-stimulation angiography data 214 and post-stimulation angiography data 216.

[0074] FIG. 5 is a conceptual diagram illustrating an example microcatheter having electrodes according to one or more aspects of this disclosure. Microcatheter 500 may be an example of stimulation device 170. Microcatheter 500 may be used with guide wire 502 to insert guide wire 502 into a cardiac vessel of a patient. Microcatheter 500 may have disposed thereon a plurality of electrodes, such as electrodes 504A-504B (collectively “electrodes 504”). Electrodes 504 may include any number of electrodes greater than one and may be located at any location on an exterior of microcatheter 500. In some examples, one or more of electrodes 504 may be disposed around a circumference of the exterior of microcatheter 500. In some examples, one or more of electrodes 504 may be disposed on only a portion of the circumference of the exterior of microcatheter 500. Electrodes 504 may be configured to deliver electrical stimulation to a coronary vessel of a patient, for example, to an interior wall of the coronary vessel.Computing device 150 may monitor a reaction of the coronary vessel to the stimulation in angiography data from imager 140. For example, computing device 150 may determine a difference between a size of the coronary vessel in pre-stimulation angiography data 214 and post-stimulation angiography data 216.

[0075] FIG. 6 is a conceptual diagram illustrating an example spiral or helix shaped microcatheter having electrodes according to one or more aspects of this disclosure. Guide wire 300 may be an example of stimulation device 170. Microcatheter 600 may be used with guide wire 502 to insert guide wire 502 into a cardiac vessel of a patient. Microcatheter 600 may have disposed thereon a plurality of electrodes, such as electrodes 604A-604D (collectively “electrodes 604”). Electrodes 604 may include any number of electrodes greater than one and may be located at any location on an exterior of microcatheter 600. In some examples, one or more of electrodes 604 may be disposed around a circumference of the exterior of microcatheter 600. In some examples, one or more of electrodes 604 may be disposed on only a portion of the circumference of the exterior of microcatheter 600. Electrodes 604 may be configured to deliver electricalstimulation to a coronary vessel of a patient, for example, to an interior wall of the coronary vessel. Computing device 150 may monitor a reaction of the coronary vessel to the stimulation in angiography data from imager 140. For example, computing device 150 may determine a difference between a size of the coronary vessel in pre-stimulation angiography data 214 and post-stimulation angiography data 216.

[0076] FIG. 7 is a conceptual diagram illustrating an example guide catheter having electrodes according to one or more aspects of this disclosure. Guide catheter 700 may be an example of stimulation device 170. Guide catheter 700 may be used with guide wire 702 to insert guide wire 702 into a cardiac vessel of a patient. Guide catheter 700 may include a guide catheter body 706 have disposed thereon a plurality of electrodes, such as electrodes 704A-704B (collectively “electrodes 704”). Electrodes 704 may include any number of electrodes greater than one and may be located at any location on an exterior of guide catheter 700. In some examples, one or more of electrodes 704 may be disposed around a circumference of the exterior of guide catheter 700. In some examples, one or more of electrodes 704 may be disposed on only a portion of the circumference of the exterior of guide catheter 700. In some examples, electrodes 704 may be configured to physically contact an inner surface 710 of the coronary vessel when guide catheter 700 is inserted into the coronary vessel. Electrodes 704 may be configured to deliver electrical stimulation to a coronary vessel of a patient, for example, to an interior wall of the coronary vessel. Computing device 150 may monitor a reaction of the coronary vessel to the stimulation in angiography data from imager 140. For example, computing device 150 may determine a difference between a size of the coronary vessel in pre-stimulation angiography data 214 and post-stimulation angiography data 216.

[0077] FIG. 8 is a conceptual diagram illustrating an example guide extension catheter having electrodes according to one or more aspects of this disclosure. Guide extension catheter 800 may be an example of stimulation device 170. Guide extension catheter 800 may be used with guide wire 802 to assist in the insertion of guide wire 802 into a cardiac vessel of a patient. Guide extension catheter 800 may include a guide extension catheter body 806 have disposed thereon a plurality of electrodes, such as electrodes 804A-804B (collectively “electrodes 804”). Electrodes 804 may include any number of electrodes greater than one and may be located at any location on an exterior of guide extension catheter 800. In some examples, one or more of electrodes 804 may be disposed around a circumference of the exterior of guide extension catheter 800. In some examples, one or more of electrodes 804 may be disposed on only a portion of thecircumference of the exterior of guide extension catheter 800. Electrodes 804 may be configured to deliver electrical stimulation to a coronary vessel of a patient, for example, to an interior wall of the coronary vessel. Computing device 150 may monitor a reaction of the coronary vessel to the stimulation in angiography data from imager 140. For example, computing device 150 may determine a difference between a size of the coronary vessel in pre-stimulation angiography data 214 and post-stimulation angiography data 216.

[0078] The examples of FIGS. 3-8 are set forth as exemplary devices configured to deliver electrical stimulation via electrodes to a coronary vessel. It should be understood that additional or alternative devices may be used to deliver electrical stimulation via electrodes to a coronary vessel and remain within the scope of this disclosure.

[0079] In some examples, stimulation device 170 may be a device configured to deliver a type of stimulation other than electrical stimulation. For examples, stimulation device 170 may be a device configured to deliver temperature stimulation, such as a cold pressor test or other technique to stimulate a sympathetic nervous system response that may contract coronary vessels.

[0080] FIG. 9 is a conceptual diagram illustrating an example cold compressor test according to one or more aspects of this disclosure. In the example of FIG. 9, stimulation device 170 may include a container 904 of ice water 902. For example, cold pressor test may include placing a portion of a body (e.g., a hand 900, such as a left hand) into a cold or frigid substance, such as ice water 902 held in container 904, or otherwise lowering a temperature of an environment of the portion of the body, typically for 1-2 minutes or so, while measuring changes in blood pressure, heart rate, skin conductance, skin temperature, and / or other physiological parameters, for example, through one or more sensors (not shown). The act of placing hand 900 into ice water 902 may stimulate a sympathetic nervous system response, thereby constricting or contracting coronary vessels and increasing blood pressure.

[0081] In one examples, a device 906, such as a finger cuff or ring, may be placed on the finger of a patient during the cold pressor test. This device may be configured to sense when the cold pressor test has started and indicate or determine when system 100 should record sensed parameters and / or capture angiography data. For example, device 906 may be configured to sense physiological markers on the skin, such as temperature and / or conductance, from which device 906 and / or other devices of system 100 may determine the cold pressor test has started.

[0082] Device 906 may be coupled (e.g., wirelessly, wired, Bluetooth, etc.) to computing device 150 via network interface 208, for example, such that computing device 150 may obtain sensed physiological markers from device 906 and / or an indication that a cold compressor test has started. In some examples, device 906 may be similarly coupled to imager 140. Because computing device 150 and / or imager 140 may be coupled to device 906, system 100 may determine when stimulation affected by the cold pressor test is being applied. In some examples, computing device 150 and / or imager 140 may prompt a clinician to capture a cine of angiography data or may automatically control imager 140 to capture the cine of angiography data, based on the cold pressor test being applied. The system may capture the angiography data before, during and / or after the stimulation of the sympathetic nervous system response.

[0083] FIG. 10 is a conceptual diagram illustrating an example device for stimulating a sympathetic nervous system response to a coronary vessel according to one or more aspects of this disclosure. In the example of FIG. 10, a device, such as cuff 1000, may be used to replicate or emulate the cold pressor test. While described as a cuff, the device may take other forms, such as a glove, a patch, a sleeve, or the like. Cuff 1000 may be place on wrist 1002 of a patient, or in other examples, on another location of the patient. Cuff 1000 may be configured to induce a sudden drop in temperature (e.g., a relatively cold temperature) to the skin, similar to that of ice water 902 of the cold pressor test of FIG. 9, and thus promote the stimulation of the sympathetic nervous system. Cuff 1000 may be coupled to computing device 150 and / or imager 140 similarly to container 904 of FIG.9.

[0084] FIG. 11 is a conceptual diagram illustrating an example handle that may be used with a device configured to deliver stimulation to a coronary vessel according to one or more aspects of this disclosure. Device 1100 may be an example device of any of the devices described with respect to FIGS. 3-8 or 10.

[0085] Device 1100 may include a handle 1102 and body 1104. Handle 1102 may be usable to control device 1100 to deliver stimulation. For example, handle 1102 may include telemetry circuitry 1106 which may be configured to communicate with computing device 150 via network interface 208. Telemetry circuitry 1106 may be configured similarly to network interface 208 and may facilitate communication between device 1100 and computing device 150. In some examples, processing circuitry 204 may send a command via network interface 208 to telemetry circuitry 1106 to initiate and / or to terminate the delivery of stimulation. In such examples, processing circuitry 204 maydetermine angiography images obtained prior to sending the command as being prestimulation angiography data 214 and angiography images obtained after sending the command as being post-stimulation angiography data 216.

[0086] Alternatively, or additionally, handle 1102 may include a stimulation button 1108. By pressing stimulation button 1108, a clinician may to initiate and / or to terminate the delivery of stimulation, such as electrical stimulation in the examples of FIGS. 3-8 or temperature stimulation in the example of FIG. 10. In such examples, telemetry circuitry 1106 may send an indication, such as a message, to network interface 208 to indicate to computing device 150 when stimulation is being delivered. In this manner, processing circuitry 204 may utilize information received in indication(s) from device 1100 to determine which angiography images are pre-stimulation angiography data 214 and which angiography images are post-stimulation angiography data 216.

[0087] FIGS. 12A-12B are conceptual diagrams illustrating a vessel before and after delivery of stimulation. In FIG. 12 A, vessel 1200 represents a vessel depicted in presimulation angiography data 214. Vessel 1200 may be a vessel to which stimulation is applied after the image represented in FIG. 12A is captured by imager 140. While not shown in FIG. 12A for simplicity purposes, in some examples, at least a portion of stimulation device 170 may be present in vessel 1200 or around vessel 1200 when the image is captured. In some examples, no portion of stimulation device 170 may be present in vessel 1200 or around vessel 1200 when the image is captured.

[0088] Vessel 1200 may have a diameter 1202 before stimulation is delivered to vessel 1200. In some examples, processing circuitry 204 may execute computer vision model 222 to determine the value of diameter 1202.

[0089] In FIG. 12B, vessel 1204 represents the same vessel as vessel 1200, but in post-stimulation angiography data 216. As such, vessel 1204 is the same vessel as vessel 1200, but after the initiation of stimulation to the vessel. While not shown in FIG. 12B for simplicity purposes, in some examples, at least a portion of stimulation device 170 may be present in vessel 1204 when the image is captured. For example, stimulation device 170 may be actively delivering stimulation to some portion of vessel 1204 while the image is captured.

[0090] Thus, the size difference between vessel 1200 and vessel 1204 may be determined based on diameter 1202 and diameter 1206. In examples where the size difference is determined as a percentage, for example, to be compared to a pre-determined threshold, such as 90%, processing circuitry 204 may determine the size difference as (diameter 1202 - diameter 1206) / diameter 1202.

[0091] FIG. 13 is a flow diagram of example techniques for determining MVO according to one or more aspects of this disclosure. The techniques of FIG. 13 are described below with respect to processing circuitry 204, but such techniques may be performed by any of, or any combination of, processing circuitry of devices depicted in FIG. 1 or capable of performing such techniques.

[0092] Processing circuitry 204 may obtain pre-stimulation angiography data 214, pre-stimulation angiography data 214 including at least one angiography image including a vessel of a patient captured prior to delivery of stimulation to the vessel (1300). For example, imager 140 may capture one or more angiography images including the vessel before system 100 delivers electrical stimulation and / or temperature stimulation to the vessel. Processing circuitry 204 may obtain the one or more angiography images from imager 140, e.g., via network interface 208.

[0093] Processing circuitry 204 may obtain post-stimulation angiography data 216, post-stimulation angiography data 216 including at least one angiography image including the vessel captured after initiation of the delivery of stimulation to the vessel (1302). For example, imager 140 may capture one or more angiography images including the vessel to which electrical stimulation and / or temperature stimulation was delivered by stimulation device 170 after the initiation of the delivery of electrical stimulation and / or temperature stimulation to the vessel. Processing circuitry 204 may obtain the one or more angiography images from imager 140, e.g., via network interface 208.

[0094] Processing circuitry 204 may determine a size difference of the vessel between pre-stimulation angiography data 214 and post-stimulation angiography data 216 (1304). For example, processing circuitry 204 may execute computer vision model 222 to determine the vessel in pre-stimulation angiography data 214 and post-stimulation angiography data 216 and / or determine the size difference, such as (diameter 1202 - diameter 1206) / diameter 1202 or another measure of size difference between diameter 1202 and diameter 1206.

[0095] Processing circuitry 204 may output an indication of the size difference (1306). For example, processing circuitry 204 may control output device(s) 212, display 206, and / or network interface 208 to output the indication of the size difference, such as an indication of (diameter 1202 - diameter 1206) / diameter 1202.

[0096] In some examples, as part of determining the size difference, processing circuitry 204 is configured to execute computer vision model 222. In some examples, processing circuitry 204 is further configured to determine whether the size difference meets a threshold; and based a determination that the size difference meets the threshold, outputting an indication of the size difference meeting the threshold. In some examples, the size difference is a percentage of reduction of diameter of the vessel between prestimulation angiography data 214 and post-stimulation angiography data 216 and the threshold is a pre-determined percentage, such as 90 percent. In some examples, the indication of the size difference meeting the threshold includes an indication of the presence of vasospastic angina. In some examples, processing circuitry 204 is further configured to, based on the determination that the size difference meets the threshold, output a recommendation for a treatment of the patient.

[0097] In some examples, processing circuitry 204 is further configured to control a device (e.g., stimulation device 170) to deliver the stimulation. In some examples, processing circuitry 204 is further configured to receive an indication from the device of the delivery of stimulation. In some examples, the stimulation includes at least one of electrical stimulation or temperature stimulation. In some examples, the vessel is a coronary vessel.

[0098] FIG. 14 is a conceptual diagram illustrating an example machine learning model according to one or more aspects of this disclosure. Machine learning model 1400 may be an example of computer vision model(s) 222. Machine learning model 1400 may be an example of a neural network, such as a convolutional neural network, or other machine learning model, trained to compare pre-stimulation angiography data 214 with the post-stimulation angiography data 216 to determine a size difference between a vessel to which stimulation is applied between pre-stimulation angiography data 214 and poststimulation angiography data 216. For example, this size difference may be a difference in size (e.g., diameter) of a vessel (to which stimulation is applied) before the stimulation is applied and after the stimulation is applied.

[0099] One or more of computing device 150 and / or server 160 may train, store, and / or utilize machine learning model 1400, but other devices of system 100 may apply inputs to machine learning model 1400 in some examples. In some examples, various types of machine learning and deep learning models or algorithms may be utilized. For example, a convolutional neural network model, e.g., ResNet-18, may be used. Some non-limiting examples of models that may be used for transfer learning include AlexNet,VGGNet, GoogleNet, ResNet50, or DenseNet, etc. Some non-limiting examples of machine learning techniques include support vector machines, naive Bayes, k-nearest neighbor, multi-layer perceptron, random forest, support vector machines, neural networks, convolutional neural networks, recurrent neural networks, ensemble networks, decision trees, linear regression, logistic regression, long short-term memory, etc.

[0100] As shown in the example of FIG. 14, machine learning model 1400 may include three types of layers. These three types of layers include input layer 1402, hidden layers 1404, and output layer 1406. Output layer 1406 comprises the output from the transfer function 1405 of output layer 1406. Input layer 1402 represents each of the input values XI through X4 provided to machine learning model 1400. In some examples, the input values may include any of the values input into the machine learning model, as described above. For example, the input values may include angiography data 214 and / or non-angiography data 216, as described above.

[0101] Each of the input values for each node in the input layer 1402 is provided to each node of a first layer of hidden layers 1404. In the example of FIG. 14, hidden layers 1404 include two layers, one layer having four nodes and the other layer having three nodes, but fewer or greater number of nodes may be used in other examples. Each input from input layer 1402 is multiplied by a weight and then summed at each node of hidden layers 1404. During training of machine learning model 1400, the weights for each input are adjusted to establish a relationship between vessels in pre- stimulation angiography data 214 and post-stimulation angiography data 216, and / or the sizes thereof. In some examples, one hidden layer may be incorporated into machine learning model 1400, or three or more hidden layers may be incorporated into machine learning model 1400, where each layer includes the same or different number of nodes.

[0102] The result of each node within hidden layers 1404 is applied to the transfer function of output layer 1406. The transfer function may be linear or non-linear, depending on the number of layers within machine learning model 1400. Example nonlinear transfer functions may be a sigmoid function or a rectifier function. The output 1407 of the transfer function may be a classification that a particular vessel in preangiography data 214 is a same vessel in post-angiography data 216 to which stimulation was delivered.

[0103] As shown in the example above, by applying machine learning model 1400 to input data such as pre-stimulation angiography data 214 and / or post-stimulation angiography data 216, processing circuitry 204 is able to determine a difference in a sizeof a vessel in pre-stimulation angiography data 214 and / or post-stimulation angiography data 216 to which stimulation has been applied. Such a size difference may be indicative of a likelihood and / or severity of vasospastic angina in a patient. This may improve the ability of a clinician to determine whether or not to treat a patient for vasospastic angina and / or how to treat a patient for vasospastic angina, thereby improving patient quality of life and / or decreasing a likelihood the patient may experience a cardiac event.

[0104] FIG. 15 is a conceptual diagram illustrating an example training process for a machine learning model according to one or more aspects of this disclosure. Process 1570 may be used to train machine learning model 1400. A machine learning model 1574 (which may be an example of machine learning model 1400) may be implemented using any number of models for supervised and / or reinforcement learning, such as but not limited to, an artificial neural network, convolutional neural network, recurrent neural network, a decision tree, naive Bayes network, support vector machine, k-nearest neighbor model, ensemble network, to name only a few examples.

[0105] In some examples, one or more of computing device 150 and / or server 160 initially trains machine learning model 1574 based on a corpus of training data 1572. Training data 1572 may include, for example, angiography images, such as fluoroscopy with contrast images. In some examples, training data 1572 may include annotations indicating a same vessel in different angiography images. In some examples, the different angiography images may include pre-stimulation angiography data and post-stimulation angiography data of a plurality of patients.

[0106] While training machine learning model 1574, processing circuitry of system 100 may compare 1576 a prediction or classification with a target output 1578.Processing circuitry 204 may utilize an error signal from the comparison to train (learning / training 1580) machine learning model 1574. Processing circuitry 204 may generate machine learning model weights or other modifications which processing circuitry 204 may use to modify machine learning model 1574. For examples, processing circuitry 204 may modify the weights of machine learning model 1574 based on the learning / training 1280. For example, one or more of computing device 150 and / or server 160, may, for each training instance in training data 1572, modify, based on training data 1572, the manner in which the identification of a same vessel in pre-stimulation angiography data 214 and post-stimulation angiography data 216 is and / or the difference in size of which is determined.

[0107] The techniques described in this disclosure may be implemented, at least in part, in hardware, software, firmware or any combination thereof. For example, various aspects of the described techniques may be implemented within one or more processors or processing circuitry, including one or more microprocessors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), or any other equivalent integrated or discrete logic circuitry, as well as any combinations of such components. The terms “controller”, “processor”, or “processing circuitry” may generally refer to any of the foregoing logic circuitry, alone or in combination with other logic circuitry, or any other equivalent circuitry. A control unit comprising hardware may also perform one or more of the techniques of this disclosure. Such hardware, software, and firmware may be implemented within the same device or within separate devices to support the various operations and functions described in this disclosure. In addition, any of the described units, circuits or components may be implemented together or separately as discrete but interoperable logic devices. Depiction of different features as circuits or units is intended to highlight different functional aspects and does not necessarily imply that such circuits or units must be realized by separate hardware or software components. Rather, functionality associated with one or more circuits or units may be performed by separate hardware or software components or integrated within common or separate hardware or software components.

[0108] The techniques described in this disclosure may also be embodied or encoded in a computer-readable medium, such as a computer-readable storage medium, containing instructions. Instructions embedded or encoded in a computer-readable storage medium may cause a programmable processor, or other processor, to perform the method, e.g., when the instructions are executed. Computer readable storage media may include random access memory (RAM), read only memory (ROM), programmable read only memory (PROM), erasable programmable read only memory (EPROM), or electronically erasable programmable read only memory (EEPROM), or other computer readable media.

[0109] This disclosure includes the following non-limiting examples.

[0110] Example 1. A medical system comprising: memory configured to store angiography data of a patient, the angiography data comprising pre-stimulation angiography data, the pre-stimulation angiography data including at least one angiography image including a vessel of the patient captured prior to delivery of stimulation to the vessel, the angiography data further comprising post-stimulationangiography data, the post-stimulation angiography data including at least one angiography image including the vessel captured after initiation of the delivery of stimulation to the vessel; and processing circuitry communicatively coupled to the memory, the processing circuitry being configured to: obtain the pre-stimulation angiography data; obtain the post-stimulation angiography data; determine a size difference of the vessel between the pre-stimulation angiography data and the poststimulation angiography data; and output an indication of the size difference.

[0111] Example 2. The medical system of example 1, wherein as part of determining the size difference, the processing circuitry is configured to execute a computer vision model.

[0112] Example 3. The medical system of example 1 or example 2, wherein the processing circuitry is further configured to: determine whether the size difference meets a threshold; and based a determination that the size difference meets the threshold, output an indication of the size difference meeting the threshold.

[0113] Example 4. The medical system of example 3, wherein the size difference is a percentage of reduction of diameter of the vessel between the prestimulation angiography data and the post-stimulation angiography data and wherein the threshold is a pre-determined percentage.

[0114] Example s. The medical system of example 3 or example 4, wherein the indication of the size difference meeting the threshold comprises an indication of the presence of vasospastic angina.

[0115] Example 6. The medical system of any of examples 3-5, wherein the processing circuitry is further configured to, based on the determination that the size difference meets the threshold, output a recommendation for a treatment of the patient.

[0116] Example 7. The medical system of any of examples 1-6, wherein the processing circuitry is further configured to control a device to deliver the electrical stimulation.

[0117] Example 8. The medical system of example 7, wherein the processing circuitry is further configured to receive an indication from the device of the delivery of electrical stimulation.

[0118] Example 9. The medical system of any of examples 1-8, wherein the stimulation comprises at least one of electrical stimulation or temperature stimulation.

[0119] Example 10. The medical system of any of examples 1-9, wherein the vessel is a coronary vessel.

[0120] Example 11. A method comprising: obtaining, by processing circuitry of an external computing device, pre-stimulation angiography data, the pre-stimulation angiography data comprising at least one angiography image including a vessel of a patient captured prior to delivery of stimulation to the vessel; obtaining, by the processing circuitry, post-stimulation angiography data, the post-stimulation angiography data comprising at least one angiography image including the vessel captured after initiation of the delivery of stimulation to the vessel; determining, by the processing circuitry, a size difference of the vessel between the pre-stimulation angiography data and the poststimulation angiography data; and outputting, by the processing circuitry, an indication of the size difference.

[0121] Example 12. The method of example 11, wherein determining the size difference comprises executing a computer vision model.

[0122] Example 13. The method of example 11 or example 12, further comprising: determining, by the processing circuitry, whether the size difference meets a threshold; and based a determination that the size difference meets the threshold, outputting, by the processing circuitry, an indication of the size difference meeting the threshold.

[0123] Example 14. The method of example 13, wherein the size difference is a percentage of reduction of diameter of the vessel between the pre-stimulation angiography data and the post-stimulation angiography data and wherein the threshold is a pre-determined percentage.

[0124] Example 15. The method of example 13 or example 14, wherein the indication of the size difference meeting the threshold comprises an indication of the presence of vasospastic angina.

[0125] Example 16. The method of any of examples 13-15, further comprising, based on the determination that the size difference meets the threshold, outputting, by the processing circuitry, a recommendation for a treatment of the patient.

[0126] Example 17. The method of any of examples 11-16, further comprising controlling, by the processing circuitry, a device to deliver the electrical stimulation.

[0127] Example 18. The method of example 17, further comprising receiving, by the processing circuitry, an indication from the device of the delivery of electrical stimulation.

[0128] Example 19. The method of any of examples 11-18, wherein the stimulation comprises at least one of electrical stimulation or temperature stimulation.

[0129] Example 20. A non-transitory computer-readable storage medium storing instructions, which when executed cause processing circuitry to: obtain pre-stimulation angiography data, the pre-stimulation angiography data comprising at least one angiography image including a vessel of a patient captured prior to delivery of stimulation to the vessel; obtain post-stimulation angiography data, the post-stimulation angiography data comprising at least one angiography image including the vessel captured after initiation of the delivery of stimulation to the vessel; determine a size difference of the vessel between the pre-stimulation angiography data and the poststimulation angiography data; and output an indication of the size difference.

Claims

What is claimed is:

1. A medical system comprising: memory configured to store angiography data of a patient, the angiography data comprising pre-stimulation angiography data, the pre-stimulation angiography data including at least one angiography image including a vessel of the patient captured prior to delivery of stimulation to the vessel, the angiography data further comprising poststimulation angiography data, the post-stimulation angiography data including at least one angiography image including the vessel captured after initiation of the delivery of stimulation to the vessel; and processing circuitry communicatively coupled to the memory, the processing circuitry being configured to: obtain the pre-stimulation angiography data; obtain the post-stimulation angiography data; determine a size difference of the vessel between the pre-stimulation angiography data and the post-stimulation angiography data; and output an indication of the size difference.

2. The medical system of claim 1, wherein as part of determining the size difference, the processing circuitry is configured to execute a computer vision model.

3. The medical system of claim 1 or claim 2, wherein the processing circuitry is further configured to: determine whether the size difference meets a threshold; and based a determination that the size difference meets the threshold, output an indication of the size difference meeting the threshold.

4. The medical system of claim 3, wherein the size difference is a percentage of reduction of diameter of the vessel between the pre-stimulation angiography data and the post-stimulation angiography data and wherein the threshold is a pre-determined percentage.

5. The medical system of claim 3 or claim 4, wherein the indication of the size difference meeting the threshold comprises an indication of the presence of vasospastic angina.

6. The medical system of any of claims 3-5, wherein the processing circuitry is further configured to, based on the determination that the size difference meets the threshold, output a recommendation for a treatment of the patient.

7. The medical system of any of claims 1-6, wherein the processing circuitry is further configured to control a device to deliver electrical stimulation.

8. The medical system of claim 7, wherein the processing circuitry is further configured to receive an indication from the device of the delivery of electrical stimulation.

9. The medical system of any of claims 1-8, wherein the stimulation comprises at least one of electrical stimulation or temperature stimulation.

10. The medical system of any of claims 1-9, wherein the vessel is a coronary vessel.

11. A method comprising: obtaining, by processing circuitry of an external computing device, prestimulation angiography data, the pre-stimulation angiography data comprising at least one angiography image including a vessel of a patient captured prior to delivery of stimulation to the vessel; obtaining, by the processing circuitry, post-stimulation angiography data, the poststimulation angiography data comprising at least one angiography image including the vessel captured after initiation of the delivery of stimulation to the vessel; determining, by the processing circuitry, a size difference of the vessel between the pre-stimulation angiography data and the post-stimulation angiography data; and outputting, by the processing circuitry, an indication of the size difference.

12. The method of claim 11, wherein determining the size difference comprises executing a computer vision model.

13. The method of claim 11 or claim 12, further comprising: determining, by the processing circuitry, whether the size difference meets a threshold; and based a determination that the size difference meets the threshold, outputting, by the processing circuitry, an indication of the size difference meeting the threshold.

14. The method of claim 13, wherein the size difference is a percentage of reduction of diameter of the vessel between the pre-stimulation angiography data and the poststimulation angiography data and wherein the threshold is a pre-determined percentage.

15. A non-transitory computer-readable storage medium storing instructions, which when executed cause processing circuitry to: obtain pre-stimulation angiography data, the pre-stimulation angiography data comprising at least one angiography image including a vessel of a patient captured prior to delivery of stimulation to the vessel; obtain post-stimulation angiography data, the post-stimulation angiography data comprising at least one angiography image including the vessel captured after initiation of the delivery of stimulation to the vessel; determine a size difference of the vessel between the pre-stimulation angiography data and the post-stimulation angiography data; and output an indication of the size difference.

Images