Angiography-intravascular ultrasound collaborative registration-based angiophysiology generation

Abstract

Devices and methods are provided for generating a physiological three-dimensional (3D) model of a blood vessel from a single angiographic image and a series of intravascular images, and another physical property of the blood vessel, such as, for example, pressure.

Description

Cross-reference to related applications

[0001] This application claims the benefit of U.S. Provisional Patent Application Serial No. 63 / 456,335, filed March 31, 2023, the disclosure of which is incorporated herein by reference. Technical Field

[0002] This invention relates to a virtual physiological model of blood vessel generation. Background Technology

[0003] Currently accepted techniques for assessing the severity of vascular stenosis, including ischemic lesions, include intravascular imaging combined with angiography. Additionally, physicians can use fractional flow reserve (FFR) to assess stenosis. FFR is a calculation of the ratio of distal pressure measurements (obtained distal to the stenosis) to proximal pressure measurements (obtained proximal to the stenosis). FFR provides an indicator of the severity of stenosis, allowing determination of whether the blockage restricts blood flow within the vessel to the extent requiring treatment. A normal FFR value in healthy vessels is 1.00, while values ​​less than approximately 0.80 are generally considered clinically significant and require treatment. Common treatment options for stenosis include percutaneous coronary intervention (PCI, or angioplasty), stent implantation, or coronary artery bypass grafting (CABG). As with all medical procedures, certain risks are associated with PCI, stent implantation, and CABG. To enable surgeons to make more informed decisions regarding treatment options, more information is needed regarding the risks and likelihood of success associated with each treatment.

[0004] However, the location of intravascular stenosis may be difficult to visualize in black-and-white angiography and IVUS images.

[0005] Therefore, there remains a need for improved devices, systems, and methods for assessing the severity of endovascular occlusion and endovascular stenosis. In this regard, there remains a need for improved devices, systems, and methods for providing a visual description of the vessel and any stenosis or lesion that allows for assessment. Furthermore, there remains a need for improved devices, systems, and methods for objectively evaluating the risks and likelihood of success associated with one or more available treatment options for the vessel. Summary of the Invention

[0006] This invention proposes to generate a physiological blood flow model of a blood vessel based on the co-registration of a single angiographic image with a series of intravascular images, and optionally provides one or more additional physiological measurements. As a specific example, this invention proposes to generate a three-dimensional (3D) model representing at least a portion of a patient's heart based on a series of intravascular ultrasound (IVUS) images co-registered with a single angiographic image.

[0007] Therefore, this invention provides a system for generating 3D reconstructions of blood vessels to provide physicians with a virtual physiological state of the vessels. In particular, this invention can be integrated with intravascular ultrasound assessment systems and avoids the use of guidewire-based assessment systems used only for assessing vascular physiological state. This improves physician efficiency and reduces the number of invasive procedures patients undergo during vascular assessment.

[0008] It should be understood that the present invention has significant advantages over conventional techniques for generating vascular physiological models. For example, some conventional methods use multiple angiographic images to generate vascular physiological models. However, as previously mentioned, this method requires multiple (e.g., two (2) or more) angiographic projections, which increases the overhead of the surgical workflow. In addition, boundary tracing on the angiographic images usually requires manual correction, which further increases the overhead of the workflow. Another approach uses only a series of IVUS images. However, this approach cannot properly account for vascular curvature and the size of lateral branches, which are necessary for accurate FFR calculation and vascular physiological modeling.

[0009] This invention proposes using a single angiographic image and a series of IVUS images to generate a vascular physiology model. This approach corrects for inaccuracies in existing methods, such as, for example, shortening and inaccurate vessel size determination resulting from using a single imaging modality to generate a physiology model. The method of this invention utilizes IVUS images to provide accurate distance measurements to correct for the shortening caused by relying on a single angiographic view for vessel modeling. Furthermore, this invention utilizes IVUS cross-sectional area measurements to provide more accurate lumen / vessel dimensions than can be provided using angiographic projection alone. Additionally, this invention utilizes co-registration information between the single angiographic image and the series of IVUS images to provide cross-detection of lateral branch locations and sizes, thereby providing a more accurate vascular physiology structure.

[0010] In some embodiments, the present invention can be implemented as a method for generating a physiological 3D model of blood vessels. The method may include receiving angiographic images of a patient's blood vessels from a fluorescence fluoroscopy device at a computing device; receiving multiple images associated with the patient's blood vessels from an intravascular imaging device at a computing device, the multiple images including multidimensional and multivariable images; and generating a physiological three-dimensional (3D) model of the blood vessels based on the angiographic images and the multiple images.

[0011] In another embodiment, the method may further include generating a graphical information element including an indication of a 3D model by a computing device; and displaying the graphical information element on a display coupled to the computing device by the computing device.

[0012] In another embodiment of the method, generating a physiological 3D model of blood vessels includes co-registration of angiographic images and multiple images.

[0013] In another embodiment, the method may include identifying the start point of a pull-back operation associated with multiple images on the blood vessel presented in the angiographic images; identifying the end point of the pull-back operation associated with multiple images on the blood vessel presented in the angiographic images; and identifying the centerline of the blood vessel between the start point and the end point.

[0014] In another embodiment, the method may include identifying multiple lateral branches of a blood vessel on an angiographic image and in multiple images; and matching one of the multiple lateral branches identified on the angiographic image with one of the multiple lateral branches identified in the multiple images.

[0015] In another embodiment, the method may include mapping frames of multiple images to positions along the centerline of the blood vessel on an angiographic image.

[0016] In another embodiment, the method may include generating an assessment of blood vessels.

[0017] In another embodiment of the method, the evaluation includes the diameter of the blood vessel, the area of ​​the blood vessel, or the diameter and area of ​​the blood vessel.

[0018] In another embodiment of the method, the evaluation includes the diameter of the vascular lumen, the area of ​​the lumen, or the diameter and area of ​​the lumen.

[0019] In another embodiment, the method may include receiving at a computing device an indication of additional physiological characteristics of a patient’s blood vessels; and generating a physiological 3D model of the blood vessels based on angiographic images, multiple images, and the additional physiological characteristics of the blood vessels.

[0020] In another embodiment of the method, additional physiological characteristics of the blood vessels include pressure or flow rate.

[0021] In another embodiment, the method may include at least in part inferences from a machine learning (ML) model generated from an angiographic image and multiple images as input to generate a physiological 3D model of blood vessels.

[0022] In another embodiment of the method, the ML model is trained at least in part based on a supervised learning training algorithm, wherein the expected output of the ML model is derived from a computational fluid dynamics (CFD) model, which takes angiographic images and multiple images as input and generates a 3D vascular physiology model as output.

[0023] In some embodiments, the invention can be implemented as a device including a processor arranged to be coupled to an intravascular imaging device and a fluorescence fluoroscopy device, the device also including a memory containing instructions, the processor being arranged to execute the instructions to implement the methods of any of the embodiments described herein.

[0024] In some embodiments, the present invention may be implemented as a computer-readable storage device including instructions executable by a processor of a computing device coupled to an intravascular imaging device and a fluorescence fluoroscopy device, wherein, when the instructions are executed, the computing device performs the method of any of the embodiments described herein.

[0025] In some embodiments, the present invention can be implemented as a device for a vascular imaging medical apparatus. The apparatus may include a processor arranged to be coupled to an intravascular imaging apparatus and a fluorescence fluoroscopy apparatus; and a memory device coupled to the processor, the memory device including instructions that, when executed by the processor, cause the apparatus to: receive angiographic images of a patient's blood vessels from the fluorescence fluoroscopy apparatus; receive multiple images associated with the patient's blood vessels from the intravascular imaging apparatus, the multiple images including multidimensional and multivariable images; and generate a physiological three-dimensional (3D) model of the blood vessels based on the angiographic images and the multiple images.

[0026] In another embodiment of the device, when executed by the processor, the instructions cause the device to generate graphical information elements including indications of a 3D model; and cause the graphical information elements to be displayed on a display coupled to the computing device.

[0027] In another embodiment of the device, when executed by the processor, the instructions cause the device to perform co-registration of angiographic images and multiple images.

[0028] In another embodiment of the device, when executed by the processor, the instructions cause the device to: identify the start point of a pull-back operation associated with multiple images on the blood vessel presented in the angiographic images; identify the end point of the pull-back operation associated with multiple images on the blood vessel presented in the angiographic images; and identify the centerline of the blood vessel between the start point and the end point.

[0029] In another embodiment of the device, when executed by a processor, the instructions cause the device to: identify multiple lateral branches of a blood vessel on an angiographic image and in multiple images; and to match one of the multiple lateral branches identified on the angiographic image with one of the multiple lateral branches identified in the multiple images.

[0030] In another embodiment of the device, when executed by the processor, the instructions cause the device to map frames of multiple images to positions along the centerline of the blood vessels on angiographic images.

[0031] In another embodiment of the device, when executed by the processor, the instructions cause the device to generate an assessment of the blood vessel, wherein the assessment includes the diameter of the blood vessel, the area of ​​the blood vessel, or the diameter and area of ​​the blood vessel, and wherein the assessment includes the diameter of the lumen of the blood vessel, the area of ​​the lumen, or the diameter and area of ​​the lumen.

[0032] In another embodiment of the device, when executed by the processor, the instructions cause the device to receive indications of additional physiological characteristics of the patient’s blood vessels; and to generate a physiological 3D model of the blood vessels based on angiographic images, multiple images, and the additional physiological characteristics of the blood vessels, wherein the additional physiological characteristics of the blood vessels include pressure or flow rate.

[0033] In another embodiment of the device, when executed by a processor, the instructions cause the device to generate an inference of a physiological 3D model of blood vessels from the ML model, based at least in part on applying angiographic images and multiple images as input to the machine learning (ML) model.

[0034] In another embodiment of the device, the ML model is trained at least in part based on a supervised learning training algorithm, wherein the expected output of the ML model is derived from a computational fluid dynamics (CFD) model, which takes angiographic images and multiple images as input and generates a 3D vascular physiology model as output.

[0035] In some embodiments, the present invention may be implemented as a computer-readable storage device. The storage device may include instructions executable by a processor of a computing device coupled to an intravascular imaging device and a fluorescence fluoroscopy device, wherein, when executed, the instructions cause the computing device to: receive an angiographic image of a patient's blood vessel from the fluorescence fluoroscopy device; receive multiple images associated with the patient's blood vessel from the intravascular imaging device, the multiple images including multidimensional and multivariable images; and generate a physiological three-dimensional (3D) model of the blood vessel based on the angiographic image and the multiple images.

[0036] In another embodiment of the storage device, when executed by the processor, the instructions cause the computing device to generate a graphical information element including an indication of a 3D model; and cause the graphical information element to be displayed on a display coupled to the computing device.

[0037] In another embodiment of the storage device, when executed by a processor, the instructions cause the computing device to: identify the start point of a pull-back operation associated with multiple images on the blood vessel presented in the angiography image; identify the end point of the pull-back operation associated with multiple images on the blood vessel presented in the angiography image; identify the centerline of the blood vessel between the start point and the end point; identify multiple lateral branches of the blood vessel on the angiography image and in the multiple images; match one of the multiple lateral branches identified on the angiography image with one of the multiple lateral branches identified in the multiple images; and map the frames of the multiple images to positions along the centerline of the blood vessel on the angiography image.

[0038] In another embodiment of the storage device, when executed by a processor, the instructions cause the computing device to generate an assessment of the blood vessel, wherein the assessment includes the diameter of the blood vessel, the area of ​​the blood vessel, or the diameter and area of ​​the blood vessel, and wherein the assessment includes the diameter of the lumen of the blood vessel, the area of ​​the lumen, or the diameter and area of ​​the lumen.

[0039] In another embodiment of the storage device, when executed by a processor, the instructions cause the computing device to receive instructions on additional physiological characteristics of the patient's blood vessels; and to generate a physiological 3D model of the blood vessels based on angiographic images, multiple images, and the additional physiological characteristics of the blood vessels, wherein the additional physiological characteristics of the blood vessels include pressure or flow.

[0040] In another embodiment of the storage device, when executed by a processor, the instructions cause the computing device to generate, at least in part, a physiological 3D model of blood vessels from an ML model based on an inference that takes an angiographic image and multiple images as input and applies them as input to a machine learning (ML) model, wherein the ML model is trained, at least in part, based on a supervised learning training algorithm, and wherein the expected output of the ML model is derived from a computational fluid dynamics (CFD) model that takes an angiographic image and multiple images as input and generates a 3D vascular model as output. Attached Figure Description

[0041] For ease of identification of any discussion of a component or behavior, the highest digit or more digits in the reference numerals refer to the drawing number in which the component is first introduced.

[0042] Figure 1 An intravascular treatment system according to at least one embodiment is shown.

[0043] Figure 2A Another endovascular treatment system according to at least one other embodiment is shown.

[0044] Figure 2B It shows Figure 2A It is part of an endovascular treatment system.

[0045] Figure 2CIt shows Figure 2A It is part of an endovascular treatment system.

[0046] Figure 3 A routine 300 for generating a three-dimensional (3D) model of blood vessels according to at least one embodiment is shown.

[0047] Figure 4A , Figure 4B , Figure 4C , Figure 4D , Figure 4E , Figure 4F , Figure 4G and Figure 4H Images of elements or features of the subject matter according to at least one embodiment are shown.

[0048] Figure 5 An example machine learning (ML) environment according to at least one embodiment is shown.

[0049] Figure 6 A computer-readable storage medium according to at least one embodiment is shown.

[0050] Figure 7 A diagram is shown of a machine in the form of a computer system, within which a set of instructions can be executed to cause the machine to perform any or more of the methods discussed herein. Detailed Implementation

[0051] As described above, in one exemplary embodiment, a system is arranged to generate a 3D model of vascular physiology based on a series of intravascular ultrasound (IVUS) images co-registered with a single angiographic image. In some embodiments, the system may also be arranged to further utilize additional vascular characteristics (e.g., pressure measurements, flow measurements, etc.) to generate the model. As a specific example, the present invention proposes to generate a 3D model of vascular physiology based on a series of IVUS images co-registered with a single angiographic image and measurements of aortic pressure (e.g., Pa, FFR, etc.). Although the present invention uses the aorta and coronary arteries as examples, the disclosed systems and methods can be implemented to generate 3D models of other types of blood vessels.

[0052] Figure 1A vascular physiology modeling system 100 according to an embodiment of the present invention is illustrated. Typically, the vascular physiology modeling system 100 is a system that generates virtual models of blood vessels based on various images and characteristics of the vessels. For this purpose, the vascular physiology modeling system 100 includes an intravascular imager 102, an angiography imager 104, a computing device 106, and an optional pressure sensor 108. The intravascular imager 102 can be any of various intravascular imagers (e.g., IVUS, OCT, OCE, etc.). In a specific example, the intravascular imager 102 can be as described below. Figure 2A The endovascular treatment system 200 is described. Similarly, the angiography imager 104 can be any of a variety of angiography imagers (e.g., a fluorescence imaging machine, etc.). Additionally, the pressure sensor 108 can be any of a variety of vascular pressure sensing devices (e.g., a pressure sensing catheter, etc.). In some embodiments, the endovascular imager 102 and the pressure sensor 108 can be integrated into the same device.

[0053] The computing device 106 can be any of a variety of computing devices. In some embodiments, the computing device 106 may be incorporated into and / or implemented by the console of the intravascular imager 102. In some embodiments, the computing device 106 may be a workstation or server communicatively coupled to the intravascular imager 102. In other embodiments, the computing device 106 may be provided by a cloud-based computing device, such as a compute-as-a-service system accessible via a network (e.g., the Internet, an intranet, a wide area network, etc.). The computing device 106 may include a processor 110, a memory 112, input and / or output (I / O) devices 114, and a network interface 118.

[0054] Processor 110 may include circuitry or processor logic, such as, for example, any of a variety of commercial processors. In some examples, processor 110 may include multiple processors, multi-threaded processors, multi-core processors (whether multiple cores coexist on the same die or on separate dies), and / or some other type of multiprocessor architecture, where multiple physically separate processors are linked together in some way through the aforementioned multiprocessor architecture. Additionally, in some examples, processor 110 may include a graphics processing section and may include dedicated memory, multi-threaded processing, and / or some other parallel processing capabilities. In some examples, processor 110 may be an application-specific integrated circuit (ASIC) or a field-programmable integrated circuit (FPGA).

[0055] Memory 112 may include logic, a portion of which includes an array of integrated circuits to form non-volatile memory for persistent storage of data or a combination of non-volatile and volatile memory. It should be understood that memory 112 may be based on any of a variety of technologies. In particular, the array of integrated circuits included in memory 112 may be arranged to form one or more types of memory, such as, for example, dynamic random access memory (DRAM), NAND memory, NOR memory, etc.

[0056] I / O device 114 can be any of a variety of devices for receiving input and / or providing output. For example, I / O device 114 may include a keyboard, mouse, joystick, foot pedal, haptic feedback device, LED, etc. Display 116 can be a conventional display or a touch-enabled display. In addition, display 116 can utilize various display technologies, such as liquid crystal display (LCD), light-emitting diode (LED), or organic light-emitting diode (OLED).

[0057] Network interface 118 may include logical and / or features for supporting communication interfaces. For example, network interface 118 may include one or more interfaces operating according to various communication protocols or standards for communication via direct or network communication links. Direct communication may occur via communication protocols or standards described in one or more industry standards (including their successors and variations). For example, network interface 118 may facilitate communication via buses such as, for example, Peripheral Component Interconnect High Speed ​​(PCIe), Non-Volatile Memory High Speed ​​(NVMe), Universal Serial Bus (USB), System Management Bus (SMBus), SAS (e.g., Serial Attached Small Computer System Interface (SCSI)) interfaces, Serial AT Attachment (SATA) interfaces, etc. Additionally, network interface 118 may include logical and / or features for implementing communication via various wired or wireless network standards (e.g., the 802.11 communication standard). For example, network interface 118 may be configured to support wired communication protocols or standards such as Ethernet, etc. As another example, network interface 118 can be configured to support wireless communication protocols or standards, such as, for example, Wi-Fi, Bluetooth, ZigBee, LTE, 5G, etc.

[0058] The memory 112 may contain instructions 120, angiography images 122, IVUS images 124, vascular pressure 126, vascular lumen contour information 128, co-registration information 130, vascular physiology model 132, and graphic information elements 134.

[0059] During operation, processor 110 may execute instructions 120 to cause computing device 106 to receive IVUS images 124 from intravascular imager 102. Typically, IVUS image 124 is a multidimensional, multivariate image that includes indications of vessel type, lesions in the vessel, lesion type, stent detection, lumen boundary, lumen size, minimum lumen area (MLA), media boundary (e.g., media boundary for intravascular media), media size, calcification angle / radian, calcification coverage, and combinations thereof.

[0060] The processor 110 may also execute instructions 120 to cause the computing device 106 to receive an angiography image 122 from the angiography imager 104. Typically, the angiography image 122 is an X-ray image of the blood vessels in a patient's heart. A contrast agent is injected into the blood vessels (e.g., via a catheter, etc.), and an X-ray image is captured when the contrast agent takes effect, thus making the blood vessels visible to X-rays.

[0061] Optionally, the processor 110 may also execute instructions 120 to cause the computing device 106 to receive vascular pressure 126. In some embodiments, the processor 110 may execute instructions 120 to cause the computing device 106 to automatically receive vascular pressure 126 (e.g., from a pressure sensor 108, etc.). In other embodiments, the processor 110 may execute instructions 120 to cause the computing device 106 to receive vascular pressure 126 from a user of the vascular physiology modeling system 100. For example, a physician may input vascular pressure 126 using I / O device 114.

[0062] Processor 110 can also execute instructions 120 to cause computing device 106 to determine vascular lumen contour information 128 based on IVUS image 124. For example, processor 110 can execute instructions 120 to automatically determine the lumen area at various points along the blood vessel based on IVUS image 124. As another example, processor 110 can execute instructions 120 to automatically determine the blood vessel boundary at various points along the blood vessel based on IVUS image 124. As another example, processor 110 can execute instructions 120 to automatically determine the plaque load of the blood vessel at various points along the blood vessel based on IVUS image 124. These are just a few examples of evaluations that can be presented in vascular lumen contour information 128.

[0063] Processor 110 can also execute instructions 120 to cause computing device 106 to perform co-registration of angiographic image 122 and IVUS image 124. It should be understood that IVUS image 124 is a series of multiple cross-sectional views of the blood vessel acquired during the retraction of an intracoronary ultrasound transducer (e.g., intravascular imager 102), depicting its lumen and arterial walls; while angiographic image 122 is an image captured by an X-ray beam emitted at the blood vessel (e.g., angiography imager 104) during the injection of contrast agent into the blood vessel, thus outlining the intraluminal contour of the vessel. Therefore, angiographic image 122 and IVUS image 124 are complementary. However, given that they are captured by different devices (e.g., intravascular imager 102 and angiography imager 104, etc.), the position of the captured IVUS image 124 is not related to the position on angiographic image 122. Therefore, a process is provided for registering or mapping IVUS image 124 to a location on angiographic image 122, and this process is referred to herein as co-registration.

[0064] Several co-registration procedures are available. Therefore, a complete discussion of co-registration procedures is not provided herein. However, typically, processor 110 can execute instructions 120 to receive (or determine) the start and end positions of a “pull-back” operation generated on the angiographic image 124 on the angiographic image 122. Furthermore, processor 110 can execute instructions 120 to determine the positions of markers (e.g., lateral branches, etc.) in both the IVUS image 124 and the angiographic image 122, and map these positions to each other, thereby generating co-registration information 130.

[0065] The processor 110 may also execute instructions 120 to cause the computing device 106 to generate a vascular physiological model 132 based on the angiographic image 122 and the IVUS image 124. In some embodiments, the processor 110 may execute instructions 120 to cause the computing device 106 to generate the vascular physiological model 132 based on the angiographic image 122, the IVUS image 124, and vascular pressure 126. The processor 110 may execute instructions 120 to generate the vascular physiological model 132 based on the angiographic image 122, the IVUS image 124, vascular lumen contour information 128, co-registration information 130, and optionally vascular pressure 126. In some embodiments, the vascular physiological model 132 is a 3D vascular physiological model presented in the IVUS image 124 and captured on the angiographic image 122.

[0066] In some embodiments, processor 110 may execute instructions 120 to generate a vascular physiology model 132 using a machine learning model (e.g., a neural network (NN), convolutional neural network (CNN), random forest model, etc.) based on angiographic images 122, IVUS images 124, vascular lumen contour information 128, co-registration information 130, and optional vascular pressure 126. In other examples, processor 110 may execute instructions 120 to generate a vascular physiology model 132 using a numerical analysis model, such as a computational fluid dynamics (CFD) model. Processor 110 may execute instructions 120 to generate a vascular physiology model 132 based on a machine learning model trained using the inputs described herein and the expected output of a vascular physiology model generated using a CFD model. This will be about Figure 5 This will be described in more detail below.

[0067] Additionally, in some embodiments, the processor 110 may execute instructions 120 to generate a graphical information element 134 including an indication of a vascular physiology model 132, and to display the image information element 134 to a user on a display 116.

[0068] Figure 2A , Figure 2B and Figure 2C An example endovascular treatment system 200 is shown and described together herein. Figure 2A It is a component-level view, and Figure 2B and Figure 2C They are Figure 2A Side view and perspective view of a portion of the endovascular treatment system 200. The endovascular treatment system 200 is in the form of an IVUS imaging system and can be used as... Figure 1 This is part of a vascular physiology modeling system 100. The endovascular treatment system 200 includes a catheter 202 and a control subsystem 204. The control subsystem 204 includes a computing device 106, a drive unit 206, and a pulse generator 208. The catheter 202 and the control subsystem 204 are operatively coupled, or more specifically, the catheter 202 is electrically and / or mechanically coupled to the computing device 106, the drive unit 206, and the pulse generator 208, such that signals (e.g., control, measurement, image data, etc.) can communicate between the catheter 202 and the control subsystem 204.

[0069] It should be noted that the computing device 106 includes a display 116. However, in some applications, the display 116 may be provided as a separate unit from the computing device 106, for example, in a different housing. In some cases, the pulse generator 208 generates electrical pulses that can be input to one or more transducers 230 disposed in the conduit 202.

[0070] In some cases, the mechanical energy from the drive unit 206 can be used to drive the imaging core 224 disposed in the catheter 202. In some cases, electrical signals transmitted from one or more transducers 230 can be input to the processor 110 of the computing device 106 for processing, as outlined herein. For example, for generating vascular lumen contour information 128 and graphic information elements 134. In some cases, the processed electrical signals from one or more transducers 230 can also be displayed as one or more images on the display 116.

[0071] In some cases, processor 110 may also be used to control the operation of one or more other components of control subsystem 204. For example, processor 110 may be used to control the frequency or duration of electrical pulses transmitted from pulse generator 208, the rotational rate of imaging core 224 implemented by drive unit 206, the pull-back speed or length of imaging core 224 implemented by drive unit 206, or one or more properties of one or more images formed on display 116, such as vascular lumen contour information 128 and graphic information element 134.

[0072] Figure 2B yes Figure 2A A side view of an embodiment of the catheter 202 of the endovascular treatment system 200. The catheter 202 includes an elongated member 210 and a hub 212. The elongated member 210 includes a proximal end 214 and a distal end 216. Figure 2B In this system, the proximal end 214 of the elongated member 210 is coupled to the catheter hub 212, and the distal end 216 of the elongated member 210 is configured and arranged for percutaneous insertion into a patient. Optionally, the catheter 202 may define at least one flushing port, such as flushing port 218. Flushing port 218 may be defined in the hub 212. Hub 212 may be configured and arranged to couple to the control subsystem 204 of the endovascular treatment system 200. In some cases, the elongated member 210 and hub 212 are formed integrally. In other cases, the elongated member 210 and catheter hub 212 are formed separately and subsequently assembled.

[0073] Figure 2CThis is a perspective view of one embodiment of the distal end 216 of the elongated member 210 of catheter 202. The elongated member 210 includes a sheath 220 having a longitudinal axis (e.g., a central longitudinal axis extending axially through the center of the sheath 220 and / or catheter 202) and a lumen 222. An imaging core 224 is disposed within the lumen 222. The imaging core 224 includes an imaging device 226 coupled to the distal end of a drive shaft 228 rotatable manually or using a computer-controlled drive mechanism. One or more transducers 230 may be mounted to the imaging device 226 and used for transmitting and receiving acoustic signals. The sheath 220 may be formed of any flexible, biocompatible material suitable for insertion into a patient. Examples of suitable materials include, for example, polyethylene, polyurethane, plastics, spirally cut stainless steel, nitinol, and similar or combinations thereof.

[0074] In some cases, such as those shown in these figures, an array of transducers 230 is mounted to the imaging device 226. Alternatively, a single transducer may be used. Any suitable number of transducers 230 may be used. For example, there may be 2, 3, 4, 5, 6, 7, 8, 9, 10, 12, 15, 16, 20, 25, 50, 100, 500, 1000 or more transducers. Other numbers of transducers may also be used, as will be appreciated. When multiple transducers 230 are used, the transducers 230 can be configured in any suitable arrangement, including, for example, a ring arrangement, a rectangular arrangement, etc.

[0075] One or more transducers 230 may be formed of a material capable of converting an applied electrical pulse into a pressure distortion on the surface of one or more transducers 230, and vice versa. Examples of suitable materials include piezoelectric ceramic materials, piezoelectric composite materials, piezoelectric plastics, barium titanate, lead zirconate titanate, lead metaniobate, polyvinylidene fluoride, etc. Other transducer technologies include composite materials, single-crystal composite materials, and semiconductor devices (e.g., capacitive micromechanical ultrasonic transducers (“cMUT”), piezoelectric micromechanical ultrasonic transducers (“pMUT”), etc.).

[0076] Pressure distortion on the surface of one or more transducers 230 forms an acoustic pulse at a frequency based on the resonant frequency of the one or more transducers 230. The resonant frequency of the one or more transducers 230 may be influenced by the size, shape, and material used to form the one or more transducers 230. The one or more transducers 230 can be formed in any shape suitable for positioning within the conduit 202 and propagating an acoustic pulse of the desired frequency in one or more selected directions. For example, the transducer can be disc-shaped, block-shaped, rectangular, elliptical, etc. The one or more transducers can be formed in the desired shape by any process, including, for example, dicing, dicing and filling, machining, microfabrication, etc.

[0077] As an example, each of one or more transducers 230 may include a piezoelectric material layer sandwiched between a matching layer and a conductive backing material formed of an acoustically absorbable material (e.g., an epoxy-based plate with tungsten particles). During operation, the piezoelectric layer can be electrically excited to induce the emission of acoustic pulses.

[0078] One or more transducers 230 can be used to form radial cross-sectional images of the surrounding space. Thus, for example, when one or more transducers 230 are disposed in catheter 202 and inserted into a patient's blood vessel, one or more transducers 230 can be used to form images of the blood vessel and the walls of the tissue surrounding the blood vessel.

[0079] The imaging core 224 rotates about the longitudinal axis of the conduit 202. As the imaging core 224 rotates, one or more transducers 230 emit acoustic signals in different radial directions (e.g., along different radial scan lines). For example, one or more transducers 230 may emit acoustic signals in regular (or irregular) increments, such as 256 radial scan lines per revolution. It should be understood that a different number of radial scan lines may be emitted per revolution instead.

[0080] When an emitted acoustic pulse with sufficient energy encounters one or more media boundaries, such as one or more tissue boundaries, a portion of the emitted acoustic pulse is reflected as an echo pulse to the transmitting transducer. Each echo pulse arriving at the transducer with sufficient energy to be detected is converted into an electrical signal in the receiving transducer. One or more converted electrical signals are transmitted to the processor 110 of the computing device 106, where the electrical signals are processed to form an IVUS image 124 and subsequently generate vascular lumen contour information 128 and graphic information elements 134 for display on the display 116. In some cases, the rotation of the imaging core 224 is driven by a drive unit 206, which may be located in the control subsystem 204. In an alternative embodiment, one or more transducers 230 are fixed in place and do not rotate. In this case, the drive shaft 228 may be replaced by a rotating mirror that reflects acoustic signals to and from the fixed one or more transducers 230.

[0081] When one or more transducers 230 rotate about the longitudinal axis of the catheter 202 that emits acoustic pulses, multiple images can be formed that collectively form radial cross-sectional images (e.g., tomographic images) of a region surrounding one or more transducers 230, such as a vessel of interest and a portion of the wall of the tissue surrounding the vessel. The radial cross-sectional images can form the basis of IVUS image 124 and can optionally be displayed on display 116. At least one of the imaging cores 224 can be rotated manually or using a computer-controlled mechanism.

[0082] The imaging core 224 can also move longitudinally along the blood vessel into which the catheter 202 is inserted, allowing multiple cross-sectional images to be formed along the longitudinal length of the vessel. During the imaging process, one or more transducers 230 can retract (e.g., pull back) along the longitudinal length of the catheter 202. The catheter 202 may include at least one telescopic section that can retract during the retraction of one or more transducers 230. In some cases, the actuation unit 206 actuates the retraction of the imaging core 224 within the catheter 202. The distance by which the actuation unit 206 retracts the imaging core can be any suitable distance, including, for example, at least 5 cm, 10 cm, 15 cm, 20 cm, 25 cm, or more. The entire catheter 202 can retract during the imaging process, regardless of whether the imaging core 224 moves independently of the longitudinal movement of the catheter 202.

[0083] Optionally, a stepper motor can be used to pull back the imaging core 224. The stepper motor can pull the imaging core 224 back a short distance and stop it for a sufficient time so that one or more transducers 230 can capture images and a series of images, etc., before pulling the imaging core 224 back another short distance and capturing another image or another series of images.

[0084] The quality of images generated at different depths from one or more transducers 230 may be affected by one or more factors, including, for example, bandwidth, transducer focus, beammap, and the frequency of the acoustic pulses. The frequency of the acoustic pulses output from one or more transducers 230 can also affect the penetration depth of the acoustic pulses output from one or more transducers 230. Generally, as the frequency of the acoustic pulse decreases, the penetration depth of the acoustic pulse within the patient tissue increases. In some cases, the endovascular treatment system 200 operates in a frequency range of 5 MHz to 200 MHz.

[0085] One or more conductors 232 can electrically couple the transducer 230 to the control subsystem 204. In this case, one or more conductors 232 can extend along the longitudinal length of the rotatable drive shaft 228.

[0086] A catheter 202 having one or more transducers 230 mounted to the distal end 216 of an imaging core 224 can be percutaneously inserted into the patient at a site remote from the selected portion of the selected area to be imaged, such as a blood vessel, via an accessible blood vessel, such as the femoral artery, femoral vein, or jugular vein. The catheter 202 can then be advanced through the patient's blood vessels to the selected imaging site, such as a portion of a selected blood vessel.

[0087] An image or image frame (“frame”) can be generated whenever one or more acoustic signals are output to surrounding tissue and one or more corresponding echo signals are received by imaging device 226 and transmitted to processor 110 of computing device 106. Alternatively, the image or image frame can be a synthesis of scan lines from a fully or partially rotated imaging core or device. Multiple (e.g., a series) frames can be acquired over time during any type of movement of imaging device 226. For example, frames can be acquired during rotation and retraction of imaging device 226 along a target imaging position. It should be understood that frames can be acquired regardless of whether imaging device 226 rotates or retracts. Furthermore, it should be understood that other types of movement procedures can be used to acquire frames as a supplement to or alternative to at least one of rotation or retraction of imaging device 226.

[0088] In some cases, when pull-back is performed, the pull-back can be carried out at a constant rate, thus providing a tool for potential applications to calculate longitudinal vessel / plaque measurements. In some cases, the imaging device 226 is pulled back at a constant rate of about 0.3-0.9 mm / s or about 0.5-0.8 mm / s. In some cases, the imaging device 226 is pulled back at a constant rate of at least 0.3 mm / s. In some cases, the imaging device 226 is pulled back at a constant rate of at least 0.4 mm / s. In some cases, the imaging device 226 is pulled back at a constant rate of at least 0.5 mm / s. In some cases, the imaging device 226 is pulled back at a constant rate of at least 0.6 mm / s. In some cases, the imaging device 226 is pulled back at a constant rate of at least 0.7 mm / s. In some cases, the imaging device 226 is pulled back at a constant rate of at least 0.8 mm / s.

[0089] In some cases, one or more acoustic signals are output to the surrounding tissue at constant time intervals. In some cases, one or more corresponding echo signals are received by the imaging device 226 and transmitted to the processor 110 of the computing device 106 at constant time intervals. In some cases, the resulting frames are generated at constant time intervals.

[0090] Figure 3 Routine 300 according to some embodiments of the present invention is illustrated. Routine 300 may be implemented by vascular physiology modeling system 100 or another computing device as outlined herein to provide a 3D physiological representation of blood vessels based on a single angiographic image, a series of intravascular images, and pressure or flow.

[0091] Routine 300 may begin at block 302. At block 302, “Receive angiographic images associated with patient vessels from a fluoroscopic apparatus at a computing device,” the computing device 106 of the vascular physiology modeling system 100 receives angiographic image 122 from an angiography imager 104, wherein the angiographic image 122 is an angiographic image captured by an X-ray machine when the vessels are exposed to a contrast agent. For example, processor 110 may execute instruction 120 to receive data including an indication of angiographic image 122 from an angiography imager 104 via network interface 118.

[0092] Continuing to box 304, “Receiving multiple images associated with a patient’s blood vessels from an intravascular imaging device at a computing device, the multiple images including multidimensional and multivariable images,” the computing device 106 of the vascular physiology modeling system 100 receives IVUS images 124 from an intravascular imager 102, wherein IVUS images 124 are multidimensional and multivariable images of blood vessels. For example, processor 110 may execute instructions 120 to receive data including indications of IVUS images 124 from the intravascular imager 102 via a network interface 118.

[0093] Continuing to box 306, "Generating information at the computing device including indications for co-registration between multiple images and angiography images," information indicating a mapping or registration between a portion of a blood vessel presented in the image received at box 302 and an image of that portion of the blood vessel received at box 304 can be generated. For example, processor 110 can execute instruction 120 to identify the start and end points of a pull-back operation through the blood vessel on angiography image 122. Furthermore, processor 110 can execute instruction 120 to identify one or more other markers (e.g., vessel centerline, lateral branches, etc.) in both angiography image 122 and IVUS image 124, and can map or coordinate the positions of frames in IVUS image 124 with those in angiography image 122 based on the identified start and end points and other markers. As mentioned above, co-registration is a complex process, and the specific details of actual co-registration are beyond the scope of this specification. Additionally, processor 110 can execute instruction 120 to store the co-registration indications as co-registration information 130.

[0094] Continuing to box 308, “Generating information including indications for lumen assessment of blood vessels at a computing device based on multiple images,” information including indications for lumen assessment of blood vessels can be generated based on the image received at box 304. For example, processor 110 can execute instruction 120 to automatically identify the geometric characteristics (e.g., diameter, area, etc.) of blood vessels and lumens presented in the images received at boxes 302 and 304, and store these indications as lumen contour information 128. In some embodiments, processor 110 can execute instruction 120 to generate assessments of lumens and blood vessels based on machine learning, image processing, geometric image analysis, etc.

[0095] Continuing to box 310, “Did you utilize additional physiological features?”, the computing device 106 of the vascular physiology modeling system 100 can determine whether additional physiological features (e.g., as outlined above) were utilized during the 3D model generation process. From box 310, method 300 can continue to box 312 or box 316. Based on the determination at box 310 that additional physiological features will be utilized in generating the vascular physiology 3D model, method 300 can continue from box 310 to box 312; while based on the determination at box 310 that additional physiological features will not be utilized in generating the vascular 3D model, method 300 can continue from box 310 to box 316.

[0096] At box 312, “Receiving Instructions on Physiological Characteristics of Vascular Vessels at a Computing Device,” the computing device 106 of the vascular physiology modeling system 100 receives vascular pressure 126. For example, processor 110 may execute instruction 120 to automatically receive vascular pressure 126 from pressure sensor 108. As another example, processor 110 may execute instruction 120 to receive vascular pressure 126 from a user via I / O device 114, etc. In some embodiments, vascular pressure 126 may include aortic pressure. In other embodiments, vascular pressure 126 may include blood flow velocity measurements. In some embodiments, vascular pressure 126 may include aortic pressure measurements (e.g., FFR, DFR, etc.) acquired during a pull-back operation associated with IVUS image 124.

[0097] Continuing from box 312 to box 314, “Generating a Physiological 3D Model of a Blood Vessel at a Computing Device Based on Multiple Images, Angiographic Images, and Optional Physiological Properties,” a physiological 3D model of the blood vessel presented in angiographic image 122 and IVUS image 124 can be generated. For example, processor 110 can execute instruction 120 to generate a physiological 3D model or representation of a blood vessel (or a portion thereof) presented in IVUS image 124 and depicted in 2D form on angiographic image 122, and store the indication of the 3D model as a vascular physiological model 132. Processor 110 can execute instruction 120 to generate a 3D model using vascular lumen contour information 128 and co-registration information 130, as well as another physiological property (e.g., vascular pressure 126, etc.). More specifically, processor 110 can execute instruction 120 to generate a 3D representation based on the generated lumen diameter, the generated centerline, and the 2D representation of the blood vessel depicted in angiographic image 122. Specifically, given the mapping between IVUS image 124 and angiography image 122 from co-registration information 130, the lumen diameter of vascular lumen contour information 128 can be used to form a 3D model indicated by vascular physiology model 132.

[0098] At box 316, “Generation of a physiological 3D model of a blood vessel at a computing device based on multiple images and angiography images,” a physiological 3D model of the blood vessel presented in angiography image 122 and IVUS image 124 can be generated. For example, processor 110 can execute instruction 120 to generate a physiological 3D model or representation of a blood vessel (or a portion thereof) presented in IVUS image 124 and depicted in 2D form on angiography image 122, and store the indication of the 3D model as a vascular physiological model 132. Processor 110 can execute instruction 120 to generate a 3D model using vascular lumen contour information 128 and co-registration information 130. More specifically, processor 110 can execute instruction 120 to generate a 3D representation based on the generated lumen diameter, the generated centerline, and the 2D representation of the blood vessel depicted in angiography image 122. Specifically, given the mapping between IVUS image 124 and angiography image 122 from co-registration information 130, the lumen diameter of vascular lumen contour information 128 can be used to form a 3D model indicated by vascular physiology model 132.

[0099] Method 300 may continue from block 316 to block 318. At block 318, “Generate a graphical information element including an indication of a 3D model at a computing device,” a graphical information element including an indication of a vascular physiology model 132 (e.g., a 3D model) may be generated. For example, processor 110 may execute instruction 120 to generate graphical information element 134, which includes an indication of a 3D model of a blood vessel presented in angiographic image 122 and IVUS image 124 and indicated in vascular physiology model 132.

[0100] Continuing to box 320, “Displaying Graphical Information Elements on a Display by a Computing Device,” the graphical information elements generated at box 314 can be displayed on a display. For example, processor 110 can execute instruction 120 to display graphical information element 134 on display 116.

[0101] Figures 4A to 4H Examples of the images and evaluations described in this article are depicted. These figures are for reference. Figure 3 The routine 300 is described in terms of its operations or boxes. However, it should be understood that this is done solely for clarity and is not intended to be limiting. [Go to...] Figure 4A The angiography image 400a is depicted. As discussed above, the vascular physiology modeling system 100 can execute instructions 120 to receive the angiography image 400a (or information elements and / or data structures including indications of the angiography image 400a) at box 302.

[0102] Figure 4B and Figure 4C On-axis IVUS image view 400b and IVUS image 400c are shown respectively. For example, on-axis IVUS image view 400b depicts an on-axis (or short-axis) view of the blood vessel presented by IVUS image 124 at a frame of IVUS image 124, while IVUS image 400c depicts a longitudinal view of the blood vessel between the start and end points of the pull-back operation that generated IVUS image 124. As discussed above, the vascular physiology modeling system 100 can execute instruction 120 to receive on-axis IVUS image view 400b and IVUS image 400c (or information elements and / or data structures including indications of on-axis IVUS image view 400b and IVUS image 400c) at block 304.

[0103] Figure 4DAn angiography image 400a is shown, in which the origin 402, end 404, midpoint 406, and central line 408 of the vessel (or vessel portion) presented in IVUS image 124 are marked. As discussed above, routine 300 may include box 306 for generating co-registration information 130 based on angiography image 122 and IVUS image 124. The origin 402, end 404, and central line 408, as well as lateral branches (see reference...) are identified. Figure 4E This can be used as part of the collaborative registration process implemented in box 306.

[0104] Figure 4E An angiography image 400a is shown, in which lateral branches 410 are marked. Five (5) lateral branches (A, B, C, D, and E) are marked on the centerline of the vessels presented in angiography images 122 and IVUS images 124. In some examples, processor 110 can execute instruction 120 to receive (e.g., via I / O device 114, etc.) indications of a start point 402, an end point 404, and a midpoint 406, and generate a centerline 408 from the indicated start point 402, end point 404, midpoint 406, and angiography image 122. As another example, processor 110 can execute instruction 120 to receive (e.g., via I / O device 114, etc.) adjustments to the generated centerline 408. Furthermore, processor 110 can execute instruction 120 to generate the positions of the lateral branches 410. As another example, processor 110 may execute instruction 120 to receive (e.g., via I / O device 114, etc.) an adjustment to the position of the generated side branch 410.

[0105] Figure 4F A graphical information element (GUI) 400f is shown, illustrating representations of co-registration information 130, vascular contour information 128, angiographic image 122, and IVUS image 124. For example, indications of the angiographic image 122 and IVUS image 124 with longitudinal vascular contour view 412 and vascular assessment 414 are depicted. It should be understood that frames of IVUS image 124 are mapped to positions along the vascular centerline 408 between the start point 402 and the end point 404. Therefore, positions 416a and 416b are co-registered or co-located. Furthermore, a vascular assessment 414 (representing the vascular contour information 128 generated at box 308) is shown for frames of IVUS image 124 corresponding to positions 416a and 416b.

[0106] Figure 4GA pressure curve 400g, including an indication of vascular pressure 126, is shown. As discussed above, vascular pressure 126 can be received by the vascular physiology modeling system 100 at box 310 of routine 300 and can optionally be used to generate a 3D representation of the blood vessel. In this case, the graph depicted in curve 400g illustrates the pressure along the distance of IVUS pullback corresponding to a series of IVUS images 124.

[0107] Figure 4H A 3D model 400h of a blood vessel 418 presented by angiographic image 122 and IVUS image 124 is shown. More specifically, the 3D model 400h shows a 3D representation of a 2D view of the blood vessel 418 shown in angiographic image 400a (e.g., angiographic image 122). As can be seen, the physiological representation of the 3D model 400h depicts both the geometric gradient and pressure gradient of the blood vessel 418. As summarized above, routine 300 may include a box 312 for generating the 3D model 400h based on angiographic image 122, IVUS image 124, blood vessel pressure 126, vascular lumen contour information 128, and co-registration information 130.

[0108] As previously described, in some embodiments, the processor 110 of computing device 106 may execute instructions 120 to generate a vascular physiology model 132 using a machine learning (ML) model. In such an example, the ML model may be stored in the memory 112 of computing device 106. It should be understood that the ML model must be trained prior to deployment. Figure 5 An ML environment 500 is illustrated, which can be used to train an ML model that can later be used to generate (or infer) a vascular physiology model 132, as described herein. The ML environment 500 may include an ML system 502, such as a computational device that applies ML algorithms to learn relationships. In this example, the ML algorithm can learn the relationship between a set of inputs (e.g., angiographic images 122, IVUS images 124, vascular lumen contour information 128, co-registration information 130, and optional vascular pressure 126) and an output (e.g., the vascular physiology model 132).

[0109] The ML system 502 can utilize experimental data 508 collected during several prior procedures. Experimental data 508 may include angiographic images 122 and IVUS images 124 for several patients. Experimental data 508 may be co-located with the ML system 502 (e.g., stored in the storage device 510 of the ML system 502), may be remote from the ML system 502 and accessed via a network interface 504, or may be a combination of local and remote data.

[0110] Experimental data 508 can be used to form training data 512. As described above, the ML training system 502 may include a storage device 510, which may include a hard disk drive, a solid-state storage device, and / or random access memory. The storage device 510 may hold the training data 512. Typically, the training data 512 may include information elements or data structures that include indications of angiographic images 122 and IVUS images 124 for several patients. Additionally, the training data 512 may optionally include vascular pressure 126 for the patients. Furthermore, in some embodiments, the training data 512 may include vascular lumen contour information 128 and co-registration information 130 for each of the patients. In some embodiments, experimental data 508 includes only angiographic images 122 and IVUS images 124 for the patients, and the ML system 502 is configured (e.g., having a processor and instructions executable by the processor) to generate vascular lumen contour information 128 and co-registration information 130 based on the angiographic images 122 and IVUS images 124 for each patient presented in the experimental data 508.

[0111] Training data 512 can be used to train ML model 514. Depending on the application, different types of models can be used to form the basis of ML model 514. For example, in this example, artificial neural networks (ANNs) may be particularly well-suited for learning the correlation between 3D models of angiography images (e.g., angiography image 122) and IVUS images (e.g., IVUS image 124) and vascular physiology (e.g., vascular physiology model 132). Convolutional neural networks may also be well-suited for this task. Any suitable training algorithm 516 can be used to train ML model 514. However, Figure 5The examples depicted may be particularly well-suited for supervised training algorithms or reinforcement learning training algorithms. For supervised training algorithms, ML system 502 can apply angiography image 122 and IVUS image 124 (and optional vascular pressure 126, vascular lumen contour information 128, and / or co-registration information 130) as model input 518. The expected output (e.g., vascular physiology model 132) generated by CFD modeler 520 based on training data 512 can be mapped to this model input 518 to learn the correlation between model input 518 and vascular physiology model 132. In a reinforcement learning scenario, training algorithm 516 can attempt to maximize some or all (or a weighted combination) of the mappings to model input 518 to vascular physiology model 132 to produce an ML model 514 with minimum error. In some embodiments, training data 512 may be divided into “training” data and “test” data, wherein a subset of training data 512 may be used to adjust ML model 514 (e.g., internal weights of the model, etc.), while another non-overlapping subset of training data 512 may be used to measure the accuracy of ML model 514 in order to infer (or generalize) vascular physiology model 132 based on “unseen” training data 512 (e.g., training data 512 not used to train ML model 514).

[0112] The ML model 514 can be applied using processor circuitry 506, which may include suitable hardware processing resources for operating on the logic and structure in storage device 510. The development of training algorithm 516 and / or the trained ML model 514 may depend at least in part on hyperparameters 522. In an exemplary embodiment, model hyperparameters 522 may be automatically selected based on hyperparameter optimization logic 524, which may include any known hyperparameter optimization techniques suitable for the selected ML model 514 and the training algorithm 516 to be used. In an alternative embodiment, the ML model 514 may be retrained over time to incorporate new knowledge and / or updated experimental data 508.

[0113] Once the ML model 514 is trained, it can be applied (e.g., via processor circuitry 506, processor 110, etc.) to new input data (e.g., angiographic images 122 and IVUS images 124 captured during pre-PCI intervention, etc.). This input to the ML model 514 can be formatted according to a predefined model input 518, which mirrors the way the training data 512 is provided to the ML model 514. The ML model 514 can generate vascular physiology 132, which can be, for example, an induction or inference of the 3D vascular physiology of the vessels presented in the angiographic images 122 and IVUS images 124 provided as input to the ML model 514.

[0114] The above description relates to a specific type of ML system 502, the application of which provides a regulated learning technique with available training data having input / outcome pairs. However, the invention is not limited to use with a particular ML paradigm, and other types of ML techniques can be used. For example, in some embodiments, ML system 502 may apply, for example, evolutionary algorithms or other types of ML algorithms and models to generate a vascular physiology model 132 based on angiographic images 122 and IVUS images 124.

[0115] Figure 6 A computer-readable storage medium 600 is illustrated. The computer-readable storage medium 600 may include any non-transitory computer-readable or machine-readable storage medium, such as optical, magnetic, or semiconductor storage media. In various embodiments, the computer-readable storage medium 600 may include an article of manufacture. In some embodiments, the computer-readable storage medium 600 may store computer-executable instructions 602 that circuitry (e.g., processor 110, etc.) can execute with the instructions 602. For example, the computer-executable instructions 602 may include instructions for performing operations related to routine 300, which may be specifically programmed to cause the vascular physiology modeling system 100 to execute reference routine 300 and... Figure 3 The operations described herein. As another example, computer-executable instructions 602 may include instructions 120, ML model 514, and / or training algorithm 516. Examples of computer-readable storage medium 600 or machine-readable storage medium may include any tangible medium capable of storing electronic data, including volatile or non-volatile memory, removable or non-removable memory, erasable or non-erasable memory, writable or rewritable memory, etc. Examples of computer-executable instructions 602 may include any suitable type of code, such as source code, compiled code, interpreted code, executable code, static code, dynamic code, object-oriented code, visual code, etc.

[0116] Figure 7 A diagram is shown of a machine 700 in the form of a computer system, within which a set of instructions can be executed to cause the machine to perform any or more of the methods discussed herein. More specifically, Figure 7 A diagram illustrates a machine 700 in an example form employing a computer system, within which instructions 708 (e.g., software, programs, applications, applets, applications, or other executable code) can be executed to cause machine 700 to perform any or more of the methods discussed herein. For example, instruction 708 can cause machine 700 to execute instruction 120, Figure 3Examples include routine 300, training algorithm 516, etc. More typically, instruction 708 enables machine 700 to generate 3D models or vascular physiological structures based on a single algorithm, a series of IVUS images, and vascular pressure measurements, as described herein.

[0117] Instruction 708 transforms a general, non-programmable machine 700 into a specific machine 700 programmed to perform the described and illustrated functions in a particular manner. In alternative embodiments, machine 700 operates as a standalone device or may be coupled (e.g., networked) to other machines. In a networked deployment, machine 700 may operate as a server machine or client machine in a server-client network environment, or as a peer machine in a peer-to-peer (or distributed) network environment. Machine 700 may include, but is not limited to, server computers, client computers, personal computers (PCs), tablet computers, laptop computers, netbooks, set-top boxes (STBs), PDAs, entertainment media systems, cellular phones, smartphones, mobile devices, wearable devices (e.g., smartwatches), smart home devices (e.g., smart appliances), other smart devices, network devices, network routers, network switches, bridges, or any machine capable of sequentially or otherwise executing instructions 708 specifying actions to be taken by machine 700. Furthermore, although only a single machine 700 is shown, the term "machine" should also be considered as a collection of machines 200 that individually or jointly execute instructions 708 to perform any one or more of the methods discussed herein.

[0118] Machine 700 may include processor 702, memory 704, and I / O components 742, which may be configured to communicate with each other, for example, via bus 744. In one example embodiment, processor 702 (e.g., a central processing unit (CPU), a reduced instruction set computing (RISC) processor, a complex instruction set computing (CISC) processor, a graphics processing unit (GPU), a digital signal processor (DSP), an ASIC, a radio frequency integrated circuit (RFIC), another processor, or any suitable combination thereof) may include, for example, processor 706 and processor 710 capable of executing instructions 708. The term "processor" is intended to include multi-core processors, which may include two or more independent processors (sometimes referred to as "cores") capable of executing instructions simultaneously. Although Figure 7 Multiple processors 702 are shown, but machine 700 may also include a single processor with a single core, a single processor with multiple cores (e.g., a multi-core processor), multiple processors with a single core, multiple processors with multiple cores, or any combination thereof.

[0119] Memory 704 may include main memory 712, static memory 714, and memory cell 716, all of which may be accessed by processor 702, for example, via bus 744. Main memory 704, static memory 714, and memory cell 716 store instructions 708 that embody any one or more of the methods or functions described herein. During execution of instructions 708 by machine 700, instructions 708 may also reside wholly or partially in main memory 712, static memory 714, machine-readable medium 718 within memory cell 716, at least one of processor 702 (e.g., within processor cache), or any suitable combination thereof.

[0120] I / O component 742 may include a wide variety of components to receive input, provide output, generate output, transmit information, exchange information, capture measurement results, and so on. The specific I / O component 742 included in a particular machine will depend on the type of machine. For example, a portable machine, such as a mobile phone, may include a touch input device or other such input mechanism, while a headless server machine may not include such a touch input device. It should be understood that I / O component 742 may include... Figure 7 Many other components are not shown. The I / O components 742 are grouped according to function only for the sake of simplicity in the discussion below, and this grouping is by no means limiting. In various example embodiments, the I / O components 742 may include output components 728 and input components 730. Output components 728 may include visual components (e.g., displays, such as plasma display panels (PDPs), light-emitting diode (LED) displays, liquid crystal displays (LCDs), projectors, or cathode ray tubes (CRTs)), acoustic components (e.g., speakers), haptic components (e.g., vibration motors, resistance mechanisms), other signal generators, and so on. Input components 730 may include alphanumeric input components (e.g., keyboards, touchscreens configured to receive alphanumeric input, photoelectric keyboards, or other alphanumeric input components), point-based input components (e.g., mice, touchpads, trackballs, joysticks, motion sensors, or other orientation devices), haptic input components (e.g., physical buttons, touchscreens providing position and / or force for touch or touch gestures, or other haptic input components), audio input components (e.g., microphones), and so on.

[0121] In another example embodiment, I / O component 742 may include biometric component 732, motion component 734, environmental component 736 or position component 738, and various other components. For example, biometric component 732 may include components for detecting facial expressions (e.g., hand gestures, facial expressions, vocal expressions, body posture, or eye tracking), measuring biosignals (e.g., blood pressure, heart rate, body temperature, sweating, or brain waves), and recognizing a person (e.g., voice recognition, retinal recognition, facial recognition, fingerprint recognition, or EEG-based recognition). Motion component 734 may include accelerometer components (e.g., accelerometer), gravity sensor components, rotation sensor components (e.g., gyroscope), etc. Environmental component 736 may include, for example, an illuminance sensor component (e.g., a photometer), a temperature sensor component (e.g., one or more thermometers for detecting ambient temperature), a humidity sensor component, a pressure sensor component (e.g., a barometer), an acoustic sensor component (e.g., one or more microphones for detecting background noise), a proximity sensor component (e.g., an infrared sensor for detecting nearby objects), a gas sensor (e.g., a gas detection sensor for detecting hazardous gas concentrations to ensure safety or measuring pollutants in the atmosphere), or other components that can provide indications, measurements, or signals corresponding to the surrounding physical environment. Position component 738 may include a position sensor component (e.g., a GPS receiver component), an altitude sensor component (e.g., an altimeter or barometer from which altitude can be derived), an orientation sensor component (e.g., a magnetometer), etc.

[0122] Communication can be implemented using various technologies. I / O component 742 may include communication component 740 operable to couple machine 700 to network 720 or device 722 via coupler 724 and coupler 726, respectively. For example, communication component 740 may include a network interface component or another suitable device interfacing with network 720. In further examples, communication component 740 may include wired communication component, wireless communication component, cellular communication component, near field communication (NFC) component, etc. Components (e.g.) (low power consumption) Components and other communication components that provide communication via other means. Device 722 can be any of another machine or various peripheral devices (e.g., a peripheral device coupled via USB).

[0123] Furthermore, the communication component 740 can detect identifiers or include components operable to detect identifiers. For example, the communication component 740 may include a radio frequency identification (RFID) tag reader component, an NFC smart tag detection component, an optical reader component (e.g., for detecting one-dimensional barcodes such as Universal Product Code (UPC) barcodes, multi-dimensional barcodes such as Quick Response (QR) codes, Aztec codes, Data Matrix, Dataglyph, MaxiCode, PDF417, Ultra Code, UCCRSS-2D barcodes, and other optical codes) or an acoustic detection component (e.g., a microphone for identifying audio signals from tags). Additionally, various information can be exported via the communication component 740, such as location via Internet Protocol (IP) geolocation, etc. The location of signal triangulation, the location of NFC beacon signals that can be detected to indicate a specific location, and so on.

[0124] Various memories (i.e., memory 704, main memory 712, static memory 714, and / or the memory of processor 702) and / or storage units 716 may store one or more sets of instructions and data structures (e.g., software) that embody or are utilized by any one or more of the methods or functions described herein. These instructions (e.g., instruction 708) cause various operations to implement the disclosed embodiments when executed by processor 702.

[0125] As used herein, the terms “machine storage medium,” “device storage medium,” and “computer storage medium” refer to the same thing and are used interchangeably in this invention. The terms refer to one or more storage devices and / or media (e.g., centralized or distributed databases and / or associated caches and servers) that store executable instructions and / or data. Therefore, the terms should be considered to include, but are not limited to, solid-state memory and optical and magnetic media, including memory internal or external to the processor. Specific examples of machine storage media, computer storage media, and / or device storage media include non-volatile memory, such as semiconductor memory devices, e.g., erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), FPGAs, and flash memory devices; disks, such as internal hard disks and removable disks; magneto-optical disks; and CD-ROM and DVD-ROM disks. The terms “machine storage medium,” “computer storage medium,” and “device storage medium” explicitly exclude carrier waves, modulated data signals, and other such media, at least some of which are covered under the term “signal medium” discussed below.

[0126] In various example embodiments, one or more portions of network 720 may be an ad hoc network, intranet, extranet, VPN, LAN, WLAN, WAN, WWAN, MAN, the Internet, a portion of the Internet, a portion of PSTN, a common old-style telephone service (POTS) network, a cellular telephone network, a wireless network, etc. The network, another type of network, or a combination of two or more such networks. For example, network 720 or a portion thereof may include a wireless or cellular network, and coupler 724 may be a Code Division Multiple Access (CDMA) connection, a Global System for Mobile Communications (GSM) connection, or another type of cellular or wireless coupling. In this example, coupler 724 may implement any of a variety of data transmission technologies, such as Single Carrier Radio Transmission (1xRTT), Evolved Data Optimization (EVDO), General Packet Radio Service (GPRS), Enhanced Data Rate Evolution of GSM (EDGE), 3rd Generation Partnership Project (3GPP) (including 3G), 4th Generation Wireless (4G) networks, Universal Mobile Telecommunications System (UMTS), High-Speed ​​Packet Access (HSPA), Global Microwave Access Interoperability (WiMAX), Long Term Evolution (LTE) standards, other standards defined by various standards-setting organizations, other remote protocols, or other data transmission technologies.

[0127] Instruction 708 may be transmitted or received via network 720 using a transmission medium via a network interface device (e.g., a network interface device included in communication component 740) and utilizing any of several well-known transmission protocols (e.g., Hypertext Transfer Protocol (HTTP)). Similarly, instruction 708 may be transmitted or received via a transmission medium via a coupler 726 to device 722 (e.g., a peer-to-peer coupler). The terms "transmission medium" and "signal medium" refer to the same thing and are used interchangeably in this invention. The terms "transmission medium" and "signal medium" should be considered to include any intangible medium that can store, encode, or carry instructions 708 for execution by machine 700; and include digital or analog communication signals or other intangible media to facilitate communication of such software. Therefore, the terms "transmission medium" and "signal medium" should be considered to include any form of modulated data signal, carrier wave, etc. The term "modulated data signal" refers to a signal whose characteristics are set or altered in a manner to encode information in the signal.

[0128] The terms used in this document shall conform to their ordinary meaning in the relevant field, or the meaning indicated by their use in the context, unless a clear definition is provided.

[0129] Throughout this document, references to “one embodiment” or “embodiment” do not necessarily refer to the same embodiment, although they may refer to the same embodiment. Unless the context explicitly requires otherwise, throughout the specification and claims, the words “comprising,” “including,” etc., should be interpreted in an inclusive sense, rather than an exclusive or exhaustive sense; that is, meaning “including but not limited to.” Use of singular or plural terms also includes both singular and plural, unless explicitly limited to one or more. Additionally, the words “this article,” “above,” “below,” and similar terms, when used in this application, refer to the entire application and not any part thereof. When a claim uses the word “or” to refer to a list of two or more items, the word covers all of the following interpretations: any one of the items in the list, all the items in the list, and any combination of the items in the list, unless explicitly limited to one or the other. Any term not explicitly defined herein has its conventional meaning as commonly understood by one of ordinary skill in the art.

Claims

1. A method for generating a physiologic 3D model of a blood vessel, comprising: receiving, at a computing device, an angiogram image of a patient blood vessel from a fluoroscopy device; receiving, at the computing device, a plurality of images associated with the patient blood vessel from an intravascular imaging device, the plurality of images including multi-dimensional images and multivariate images; and generating a physiologic three-dimensional (3D) model of the blood vessel from the angiogram image and the plurality of images.

2. The method of claim 1, further comprising: generating, by the computing device, a graphical information element including an indication of the 3D model; and causing, by the computing device, the graphical information element to be displayed on a display coupled to the computing device.

3. The method of claim 1 or 2, wherein generating a physiologic 3D model of the blood vessel includes co-registering the angiogram image and the plurality of images.

4. The method of claim 3, comprising: identifying, on the blood vessel presented in the angiogram image, a starting point of a pullback operation associated with the plurality of images; identifying, on the blood vessel presented in the angiogram image, an ending point of the pullback operation associated with the plurality of images; and identifying a centerline of the blood vessel between the starting point and the ending point.

5. The method of claim 4, comprising: identifying, on the angiogram image and in the plurality of images, a plurality of side branches of the blood vessel; and matching one of the plurality of side branches identified on the angiogram image with one of the plurality of side branches identified in the plurality of images.

6. The method of claim 5, mapping frames of the plurality of images to a location along the centerline of the blood vessel on the angiogram image.

7. The method of any one of claims 3 to 6, comprising generating an assessment of the blood vessel.

8. The method of claim 7, wherein the assessment includes a diameter of the blood vessel, an area of the blood vessel, or a diameter and area of the blood vessel.

9. The method of claim 7, wherein the assessment includes a diameter of the lumen, an area of the lumen, or a diameter and area of the lumen.

10. The method of any one of claims 1 to 9, comprising receiving, at the computing device, an indication of an additional physiologic property of the patient blood vessel; and generating a physiologic 3D model of the blood vessel from the angiogram image, the plurality of images, and the additional physiologic property of the blood vessel.

11. The method of claim 10, wherein the additional physiologic property of the blood vessel includes pressure or flow.

12. The method of any one of claims 1 to 11, comprising generating an inference of a physiologic 3D model of the blood vessel from a machine learning (ML) model based at least in part on applying the angiogram image and the plurality of images as inputs to the ML model. ​ ​ 13. The method of claim 12, wherein the ML model is trained based at least in part on a supervised learning training algorithm, wherein an expected output of the ML model is derived based on a computational fluid dynamics (CFD) model, wherein the CFD model takes as input an angiogram image and a plurality of images and generates as output a 3D model of vascular physiology.

14. An apparatus comprising a processor arranged to be coupled to an intravascular imaging device and a fluoroscopy device, the apparatus further comprising a memory comprising instructions, the processor arranged to execute the instructions to implement the method of any one of claims 1-13.

15. A computer readable storage device comprising instructions executable by a processor of a computing device coupled to an intravascular imaging device and a fluoroscopy device, wherein when the instructions are executed, cause the computing device to implement the method of any one of claims 1-13.

Images