SYSTEM AND METHOD FOR IDENTIFYING VASCULAR PROPERTIES USING EXTRAVASCULAR IMAGES - Patent application

Abstract

Systems and methods are disclosed that use extravascular and intravascular images to identify vascular characteristics to estimate a virtual flow reserve (VFR) of an imaged vessel. Aspects of the disclosure include using the extravascular images to estimate the size of the vessel in areas not imaged intravascularly. The VFR estimation can be based on a resistance model that incorporates both the intravascular image data and the estimated vessel size. In other aspects, multi-angle extravascular images are captured and analyzed to identify the size and orientation of the vessel branches.

Description

[Technical field]

[0001] [CROSS REFERENCE TO RELATED APPLICATIONS] This application claims the benefit of the filing date of U.S. Provisional Patent Application No. 63 / 234,916, entitled “Systems and Methods of Identifying Vessel Attributes Using Extravascular Images,” filed August 19, 2021, the disclosure of which is incorporated herein by reference. [Background technology]

[0002] Calculation of a virtual flow reserve ("VFR") of a blood vessel can be used to diagnose lesions in the blood vessel and can assist in determining areas where therapeutic measures, such as placement of a stent, should be performed. VFR calculations can be calculated using intravascular images. However, intravascular imaging is often performed on only a portion of the entire blood vessel. For example, some intravascular optical coherence tomography ("OCT") systems may have a maximum pullback length of 75 mm, but the entire length of the blood vessel may be more than twice that length. In the absence of additional information regarding the structure of the blood vessel in areas not imaged by the intravascular probe, assumptions are made to perform the VFR calculation. In particular, assumptions are made regarding the structure of the blood vessel in areas of the blood vessel not imaged intravascularly. However, in cases where the structure of the blood vessel differs from these assumptions, the VFR calculation may be inaccurate. There is a need for systems and methods to reduce the inaccuracies in these VFR calculations, thereby improving the diagnosis of vascular conditions. Summary of the Invention [Problem to be solved by the invention]

[0003] A system and method are disclosed that uses extravascular and intravascular images to identify vascular features to estimate a virtual flow reserve (VFR) of the imaged vessel. [Means for solving the problem]

[0004] Aspects of the present disclosure include using extravascular images to estimate vessel size in areas not imaged intravascularly. VFR estimation can be based on a resistance model that incorporates both intravascular image data and estimated vessel size. In other aspects, multi-angle extravascular images are captured and analyzed to identify the size and orientation of vascular branches.

[0005] The systems and methods include one or more memories for storing images of a blood vessel and one or more processors configured to: capture multiple extravascular images of the blood vessel during a pullback of an intravascular imaging probe having a defined pullback length along a first region of the blood vessel; detect locations of one or more markers in the multiple extravascular images; correlate the first region of the blood vessel represented in the multiple extravascular images with the pullback length based on the locations of the one or more markers in the multiple extravascular images; and determine a size of a second region of the blood vessel represented in the multiple extravascular images based on a correlation of the first region of the blood vessel represented in the multiple extravascular images with the pullback length.

[0006] In other aspects of the present disclosure, the size of the second region of the vessel can include at least one of a length of the second region, a cross-sectional diameter within the second region, and a cross-sectional area within the second region. In yet another aspect, the one or more processors can be further configured to calculate a virtual flow reserve (VFR) of the vessel based on the plurality of images captured by the intravascular imaging probe and based on the determined size of the second region of the vessel. The VFR of the vessel can also be calculated based at least in part on a distance between a vessel centerline and a boundary of the second region of the vessel in the vessel identified in at least one of the plurality of extravascular images.

[0007] In yet another aspect of the present disclosure, the second region of the vessel can include at least one of a distal epicardial region and a proximal epicardial region of the vessel, and correlating the first region of the vessel represented in the plurality of extravascular images with the pullback length can include scaling a lumen size represented in at least one of the plurality of extravascular images.

[0008] In yet another aspect, the one or more processors can be further configured to analyze the plurality of extravascular images to identify locations and take-off angles of branches relative to the blood vessel, and the one or more processors can be further configured to calculate a virtual flow reserve (VFR) for the blood vessel based on the identified locations and take-off angles of the branches.

[0009] In another aspect of the present disclosure, the one or more processors may be configured to receive a plurality of extravascular images captured at a plurality of angles relative to a patient, generate a three-dimensional model of a blood vessel based on the plurality of extravascular images, identify a location within the blood vessel where an intravascular pullback procedure will be performed, estimate a size of the blood vessel in one or more areas not included within the identified location, where the estimation is based on the three-dimensional model, and calculate a virtual flow reserve (VFR) of the blood vessel based on the estimated size of the blood vessel.

[0010] In yet another aspect of the present disclosure, the one or more processors may be further configured to identify one or more branches along the blood vessel and estimate a size and orientation of the vascular branch at the one or more branches, and calculating the VFR of the blood vessel is based on the estimated size and orientation of the vascular branch, the orientation of the vascular branch including a departure angle of the vascular branch relative to the blood vessel. [Brief description of the drawings]

[0011] [Figure 1] FIG. 1 is a schematic diagram of a system configured to image blood vessels that automatically detects features / regions of interest on acquired image data, including calculating and displaying data relating to a hypothetical flow reserve within a region of the vessel. [Diagram 2] FIG. 1 illustrates a blood vessel according to an aspect of the present disclosure. [Diagram 3] FIG. 1 is a diagram of a resistance model generated according to aspects of the present disclosure. [Figure 4] FIG. 13 is a diagram depicting intravascular probe marker locations according to aspects of the present disclosure. [Diagram 5] 1 is a diagram illustrating the position of an intravascular probe within a blood vessel according to an aspect of the present disclosure. [Figure 6] 1 is a display of an angiographic image of a blood vessel including an intravascular probe, according to an aspect of the present disclosure. [Figure 7]1 is a display of an angiographic image of a blood vessel including an intravascular probe, according to an aspect of the present disclosure. [Figure 8] 1 is a display of an angiographic image of a blood vessel including an intravascular probe, according to an aspect of the present disclosure. [Figure 9] 1 is a display of a multi-angle angiogram image according to an aspect of the present disclosure. [Figure 10] FIG. 1 is a diagram of a vessel bifurcation and vessel centerline according to an aspect of the present disclosure. [Figure 11] FIG. 1 is a flow diagram for analyzing extravascular images according to aspects of the present disclosure. [Figure 12] FIG. 1 is a flow diagram for analyzing extravascular images according to aspects of the present disclosure. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0012] The disclosed systems and methods provide improved assessment of vascular attributes, including improved calculation of virtual flow reserve ("VFR") in one or more blood vessels. In calculating the VFR of a blood vessel based on OCT images, feature detection and alignment of the imaging dataset relative to an intravascular imaging pullback can be performed. For example, the intravascular imaging pullback can be an OCT, an intravascular ultrasound ("IVUS"), or a near-infrared spectroscopy pullback. The imaging datasets can be taken at one or more time points corresponding to different arterial events or treatments. One or more representations of the artery can be displayed based on the imaging dataset. The representations can include a particular indication of the VFR. The one or more representations can be displayed to a user.

[0013] FIG. 1 is a schematic diagram of a diagnostic system 5 suitable for imaging arteries and other blood vessels and configured to automatically identify vascular attributes of interest based on acquired image data. The system 5 is suitable for viewing and evaluating visual representations of arterial information. These user interfaces may include one or more moving elements that may be controlled by a user using a mouse, joystick, or other control device and operated using one or more processors and memory storage elements. Morphological results automatically obtained on the image data may be displayed as part of a streamlined workflow.

[0014] 1 shows a system 5 including various data acquisition subsystems suitable for collecting data or detecting characteristics of a subject 4 or sensing a condition of the subject 4 or otherwise diagnosing the subject 4. In one embodiment, the subject is positioned on a suitable support 44, such as a table, bed, or chair, or other suitable support. Typically, the subject 4 is a human or another animal having a particular region of interest 25.

[0015] The data acquisition system 5 includes a non-invasive imaging system, such as nuclear magnetic resonance, x-ray, computer-aided tomography, or other suitable non-invasive imaging technique. As a non-limiting example of such a non-invasive imaging system, an angiography system 20 is shown that is suitable for generating cines. The angiography system 20 may include a fluoroscopy system. The angiography system 20 is configured to non-invasively image the subject 4 to generate frames of angiography data in the form of frames of image data. The angiography data may be generated independently of or in association with a pullback procedure performed using the probe 30 such that blood vessels in the region 25 of the subject 4 are imaged using one or more intravascular imaging techniques, such as OCT, IVUS, or near-infrared spectroscopy, as well as non-invasive angiography imaging.

[0016] Angiography system 20 is in communication with angiography data storage and image management system 22, which in one embodiment may be implemented as a workstation or a server. In one embodiment, data processing related to collected angiography signals is performed directly on the detector of angiography system 20. Images from system 20 are stored and managed by angiography data storage and image management system 22.

[0017] In one embodiment, a system server 50 or workstation 85 is responsible for the functions of system 22. In one embodiment, the entire system 20 generates electromagnetic radiation, such as x-rays. System 20 also receives such radiation after it passes through subject 4. Data processing system 22 then uses signals from angiography system 20 to image one or more regions of subject 4, including region 25.

[0018] As shown in this particular example, the region of interest 25 is a subset of the vasculature, such as a particular blood vessel, or the peripheral vasculature. This subset can be imaged using OCT. A catheter-based data collection probe 30 is introduced into the subject 4 and positioned within the lumen of a particular blood vessel, such as a coronary artery. The probe 30 can be various types of data collection probes, such as, for example, an OCT probe, an FFR probe, an IVUS probe, a near-infrared spectroscopy probe, a probe combining features of two or more of the above, and other probes suitable for imaging within a vessel. The probe 30 can include a probe tip, one or more radiopaque markers, an optical fiber, and a torque wire. In addition, the probe tip can include one or more data collection subsystems, such as an optical beam director, an acoustic beam director, a pressure detector sensor, other transducers or detectors, and combinations of the above.

[0019] In the case of a probe including an optical beam director, the optical fiber 28 is in optical communication with the probe using the beam director. The torque wire defines a bore in which the optical fiber is disposed. In FIG. 1, the optical fiber 28 is shown without a torque wire surrounding it. In addition, the probe 30 also includes a sheath, such as a polymer sheath (not shown), that forms part of the catheter. In the context of an OCT system, the optical fiber 28, which is part of the sample arm of the interferometer, is optically coupled to a patient interface unit (PIU) 35 as shown.

[0020] The patient interface unit 35 may include a probe connector suitable for receiving and optically coupling to the end of the probe 30. The data collection probe 30 may be disposable. The PIU 35 includes appropriate joints and elements based on the type of data collection probe used. For example, a combination OCT and IVUS data collection probe works with an OCT and IVUS PIU. The PIU 35 may include motors suitable for pulling back the torque wire, sheath, and optical fiber 28 disposed therein as part of a pullback procedure. In addition to being pulled back, the probe tip may also typically be rotated by the PIU 35. Thus, the blood vessels of the subject 4 may be imaged longitudinally or through a transverse plane.

[0021] The PIU 35 is then connected to one or more intravascular data collection systems 40. The intravascular data collection system 40 can be an OCT system, an IVUS system, another imaging system, and combinations of the above. For example, the system 40 in the context of the probe 30 being an OCT probe can include an interferometer sample arm, an interferometer reference arm, a photodiode, a control system, and a patient interface unit. Similarly, as another example, in the context of an IVUS system, the intravascular data collection system 40 can include ultrasound signal generation and processing circuitry, noise filters, a rotatable joint, a motor, and an interface unit. In one embodiment, the data collection system 40 and the angiography system 20 have a shared clock or other timing signal configured to synchronize angiography video frame timestamps and OCT image frame timestamps. In addition to the invasive and non-invasive image data collection systems and devices of FIG. 1, various other types of data can be collected regarding the region 25 of the subject and other parameters of interest of the subject. For example, the data collection probe 30 can include one or more pressure sensors, such as pressure wires. The pressure wire can be used without the addition of an OCT or ultrasound component. Pressure readings can be taken along a segment of a blood vessel within region 25 of subject 4.

[0022] One or more displays 82, 83 may also be used to show various workflows disclosed herein, VFR calculations, calcium angles, EEL detection, calcium detection, proximal frames, distal frames, and associated graphical user interfaces, EEL-based metrics, stent / no stent decisions, scores, debulking and other treatment recommendations, evidence-based recommendations informed by automated detection of regions / features of interest, angiography data frames, OCT frames, image data, stent planning interfaces, morphology interfaces, review interfaces, stent deployment interfaces, user interfaces for OCT and angiography data, and other controls and features of interest. Two exemplary workflows, Workflow A and Workflow B, may be displayed on the displays 82, 83, and may include, without limitation, any of the graphical user interfaces, panels, arterial images, arterial representations, features of interest, regions of interest, and other measurements and graphical elements disclosed or depicted herein, or any subset thereof.

[0023] Intravascular image data, such as frames of intravascular data generated using the data collection probe 30, can be sent to a data acquisition and processing system 40 coupled to the probe via the PIU 35. Noninvasive image data generated using the image management system 22 can be transmitted to, stored on, and processed by one or more servers or workstations, such as a co-registration server 50 workstation 85. A video frame grabber device 55, such as a computer board configured to grab angiographic image data from the system 22, can be used in various embodiments.

[0024] In one embodiment, the server 50 includes one or more co-registration software modules 67 stored in memory 70 and executed by the processor 80. The server can include a trained neural network 52 suitable for implementing various embodiments of the present disclosure. In one embodiment, an AI processor, such as a graphical processing unit 53, is included in the server 50 and is in electrical communication with the memory 70. The computing device / server 50 can include other typical components for a processor-based computing server. Alternatively, one or more databases, such as database 90, can be configured to receive image data generated, subject parameters, and other information generated by one or more of the system devices or components shown in FIG. 1 and received by or transferred to the database 90.

[0025] Although the database 90 is shown connected to the server 50 while being stored in the memory of the workstation 85, this is but one exemplary configuration. For example, the software module 67 can execute on a processor of the workstation 85 and the database 90 can be located in the memory of the server 50. Use of a device or system to execute various software modules is provided as an example. In various combinations, the hardware and software described herein can be used to acquire frames of image data, process such image data, and register such image data.

[0026] Unless otherwise specified herein, software modules 67 may include software such as pre-processing software, transformations, matrices, and other software-based components used to process image data or in response to patient triggers to facilitate co-registration of different types of image data by other software-based components 67 or otherwise perform annotation of the image data to generate ground truth, as well as other software, modules, and functions suitable for implementing various embodiments of the present disclosure. These modules may include workflows, morphology workflows, review workflows, sizing workflows, deployment workflows, computer-directed workflows, computer-assisted workflows, lumen detection using scanline-based or image-based techniques, workflows, indicia generation, VFR calculations, calcium angle / arc generation, stent detection using scanline-based or image-based techniques, indicator generation, coherent bar generation for stent planning, proximal / distal color coding / indicia generation, lumen border detection, stent expansion, lumen profile, target lumen profile, side branch, and missing data, etc.

[0027] The database 90 may be configured to receive and store angiography image data 92, such as image data generated by the angiography system 20 and acquired by the frame grabber 55 of the server 50. The database 90 may be configured to receive and store intravascular image data 95, such as OCT image data, IVUS image data, infrared spectroscopy image data, or OFDI image data, or other non-endovascular arterial image data, such as image data generated by the OCT system 40 and acquired by the frame grabber 55 of the server 50.

[0028] Additionally, subject 4 may be electrically coupled via one or more electrodes to one or more monitors, such as monitor 49. Monitor 49 may include, without limitation, an electrocardiogram monitor configured to generate data related to cardiac function and indicative of various states of the subject, such as systole and diastole.

[0029] The use, or lack thereof, of directional arrows in a given diagram is not intended to limit or dictate the direction in which information may flow. For a given connector, such as the arrows and lines shown connecting elements shown in FIG. 1, information may flow in one or more directions or in only one direction, as appropriate for a given embodiment. The connections may include various suitable data transmission connections, such as optical connections, wired connections, power connections, wireless connections, or electrical connections.

[0030] One or more software modules may be used to process frames of angiography data received from an angiography system, such as system 22 shown in Figure 1. A variety of software modules, which may include, without limitation, software, components thereof, or one or more steps of a software-based or processor-implemented method, may be used in a given embodiment of the present disclosure.

[0031] In part, the disclosure relates to an intravascular data collection system and associated methods in which intravascular data collected by an intravascular probe may be transformed or analyzed by a processor-based system. The results of such analysis and transformation may be displayed to an end user in various displays, such as a pipeline of imaging processing software modules for image segmentation / detection of features or regions of interest on image data, machine learning systems with neural networks that classify components of medical images and detect instances of features and regions of interest, and displays that communicate with other image processing and segmentation / detection systems. In one embodiment, a given imaging system, such as OCT, IVUS, infrared spectroscopy, X-ray based imaging systems, etc., may be in electronic communication with the MLS to display modified versions of image data acquired using a given type of imaging system during the same session in which such image data was acquired. V-net, U-net, CUMedVision1, CUMedVision2, VGGNet, Multi-Stage Multi-Recurrent Input Fully Convolutional Network (M 2 Various neural network architectures can be used for image segmentation, such as Multi-stage Multi-recursive-input Fully Convolutional Network (FCN), Coarse-to-Fine Stacked Fully Convolutional Nets, deep active learning frameworks, ResNet, combinations thereof, and other neural networks and software-based machine learning frameworks suitable for image segmentation.

[0032] The system 5 of FIG. 1 can be configured to perform VFR calculations using anatomical information available through imaging of the vessel through both intravascular and extravascular images. For example, an intravascular OCT image collected during a vessel pullback procedure can be co-registered with an extravascular contrast image of the same vessel. During an OCT pullback procedure, an intravascular imaging probe is pulled through a region of the vessel, and often intravascular imaging is performed over only a portion of the entire vessel. In the absence of additional information about the structure of the vessel in the region not imaged by the intravascular probe, assumptions are necessary to perform the VFR calculations. For example, the VFR calculations can be based on the assumption that the intravascular image was captured over a region corresponding to approximately the center of the vessel, and therefore has equal proximal and distal epicardial lengths, and proximal and distal epicardial vessel sizes similar to the proximal and distal vessel sizes of the OCT imaged segment.

[0033] In FIG. 2, blood vessel 200 is shown as having three distinct segments 202, 204, 208 along its longitudinal length (segments are not drawn to scale). Segment 202 is the portion of blood vessel 200 imaged by the intravascular OCT probe. Distal location 212 is the location within blood vessel 200 where the OCT probe begins capturing images as part of a pullback procedure, and proximal location 214 is the location within blood vessel 200 where the OCT probe stops capturing images at the end of the pullback procedure. Segment 204 is a distal epicardial segment that extends distally from location 212 of segment 202, and segment 206 is a proximal epicardial segment that extends proximally from location 214 of segment 202. Segment 202 is shown as varying in size along the longitudinal axis of blood vessel 200. This represents the manner in which the cross-sectional diameter and cross-sectional area of ​​the lumen of blood vessel 200 varies along the longitudinal axis of segment 202. The cross-sectional diameter and area along segment 202 are determined based on an analysis of multiple OCT images captured along the length of segment 202. However, such OCT images are not available for segments 204 and 206 of blood vessel 200. Instead, segments 204 and 206 are represented based on approximations regarding the typical length and cross-sectional size of the lumen along segments 204 and 206.

[0034] As shown in FIG. 2, the lengths of the distal epicardial segment 204 and the proximal epicardial segment 206 are each approximated as 38 mm. This approximation may be based, at least in part, on average vessel length, as provided in the medical literature or as determined from a patient population. For example, if the vessel 200 is a left anterior descending ("LAD") artery, the disclosed system and method may determine that a typical LAD artery has a length that is approximately 76 mm longer than the length of the OCT pullback. As discussed above, it may be assumed that the region of the OCT pullback occurred approximately in the middle of the vessel, and thus the distal segment 204 and the proximal segment 206 are each shown as being 38 mm. Similarly, the widths, i.e., cross-sectional diameters, of the distal segment 204 and the proximal segment 206 are shown as corresponding to the width of the vessel at locations 212 and 214, respectively. Thus, an assumption is made that the cross-sectional diameter of the vessel remains constant as it extends from the imaged segment 202 within the vessel. However, in cases where the vessel 200 differs significantly from these assumptions, the use of these assumptions may result in inaccurate VFR calculations.

[0035] In FIG. 3, a flow resistance model 300 of a blood vessel 302 is shown that can be used to calculate the VFR of the blood vessel 302. Box 310 depicts the region of the blood vessel 302 that is imaged by an intravascular OCT probe. As seen in the model 300, the OCT imaged region of the blood vessel 302 includes blood vessel branches 304, 306, and 308. The OCT image of the blood vessel 302 can be used to calculate the flow resistance of the blood vessel 302, which can be used to determine the length of the blood vessel 302, as well as the cross-sectional diameter or area of ​​the blood vessel 302. The location and cross-sectional diameter or area of ​​the side branches 304, 306, and 308 can also be determined using the OCT image. R1, R2, ...R N+1Resistances such as 312, 314, 316, 318, 320, 322, 323, 324, 325, 326, 327, 328, 329, 330, 331, 332, 333, 334, 335, 336, 337, 338, 339, 340, 341, 342, 343, 344, 345, 346, 347, 348, 349, 350, 351, 352, 353, 354, 355, 356, 357, 358, 359, 360, 361, 362, 363, 364, 365, 366, 367, 368, 369, 370, 371, 372, 373, 374, 375, 376, 377, 378, 379, 380, 381, 382, ​​383, 384, 385, 386, 387, 388, 389, 390, 391, 392, 393, 394, 395, 396, 397, 398, 399, 400, 401, 402, 403, 404, 405, 406, 407, 408, 409, 410, 411, 412, 413, 414, 415, 416, 417,

[0036] In addition, the resistance value used for the VFR calculation may include a representation of microvascular resistance. For example, as shown in FIG. 3, resistance R may be used to represent the microvascular resistance of the peripheral coronary bed. mv can be used. An estimate of microvascular resistance can be determined using information obtained from one or more extravascular images. As described below, information regarding the length of the OCT pullback can be used in combination with the extravascular images to generate a more accurate determination of the proximal resistance, distal resistance, and microvascular resistance within the vessel. With respect to microvascular resistance, it is possible to determine the resistance based on the maximum blood flow that can be achieved in the vessel if the pressure drop across the epicardial artery is negligible. For example, a hyperemia velocity value can be used to determine the microvascular resistance. In addition, a hyperemia microvascular resistance index can be determined and used in connection with the VFR calculation. The determination of microvascular resistance, including hyperemia velocity and hyperemia microvascular resistance index, is provided in U.S. Patent Application Serial No. 13 / 796,710, which is incorporated herein by reference.

[0037] System 5 of FIG. 1 may be configured such that catheter-based data collection probe 30 includes one or more radiopaque markers. For example, in FIG. 4, catheter-based data collection probe 30 includes three radiopaque markers along its length. Marker 310 is a distal marker located at the distal end of probe 30. Marker 312 is a lens marker located on a lens used to capture intravascular images. Marker 314 is a pullback marker that may be located proximate to a location on the catheter corresponding to or near where the distal end of probe 30 will be at the end of the pullback procedure. The distance between lens marker 312 and pullback marker 314 is L in FIG. 4. (Lens→PBK)-Groundtruth while the distance between the distal marker 310 and the lens marker 312 is shown as L (Dist→Lens)-Groundtruth These lengths are called the "ground truth" because they correspond to the actual distances between the markers.

[0038] FIG. 5 is a representation of an angiographic image 500 in which the probe 30 has been placed in a blood vessel 502. When the probe 30 is placed in the blood vessel 502, the distal end of the probe 30 may be located at an initial pullback location within the blood vessel 502. The initial pullback location corresponds to the location of the probe 30 when the pullback procedure is initiated. Prior to contrast fluid being introduced into the blood vessel 502, an angiographic image 500 of the blood vessel 502 may be acquired when the probe 30 is at the initial pullback location shown in FIG. 5. The system 5 of FIG. 1 is configured to identify the location of the markers 310, 312, and 314 in the angiographic image 500 when the probe 30 is at the initial pullback location. Once the pullback is initiated, the system 5 is also configured to track the location of the probe markers 310, 312, and 314 in subsequent angiographic images. The system 5 may then calculate the apparent distance traveled within the blood vessel by one or more of the markers, as depicted in the angiographic image.

[0039] 6 is an angiogram image 600 that includes a centerline 604 extending through a blood vessel 602. The location of the marker 312 within the blood vessel 602 is shown. This location corresponds to the initial pullback position of the marker 312 prior to initiating the pullback procedure. Various methods can be used to calculate the accurate vessel centerline, such as a fast marching algorithm and a narrow band method. Regardless of which method is used, the disclosed system is capable of identifying and displaying the centerline for both the main vessel and any identified side branches.

[0040] 7 is an angiographic image 700 of a blood vessel 602 once a pullback procedure has been performed, thus changing the position of the marker 312' within the blood vessel 602 as the probe has been pulled through the vessel. To determine the apparent pullback length in the angiographic images, the disclosed system can transformably register one or more of the subsequent angiographic images to an initial angiographic image captured when the probe is in the initial pullback position.

[0041] For example, Figure 8 shows a modified angiogram 800 where the original angiogram 600 has been modified to include the location of the marker 312' from the angiogram 700. The distance between the markers 312 and 312' measured along the centerline 604 represents the apparent length of the pullback in the angiogram, and therefore L pullback-angio It can be called the length L pullback-angio is the actual pullback length L, so as to determine the extent to which the vessel depth and orientation affect the projected length of the vessel in the angiographic image. pullback-groundtruth Since the depth and orientation of the vessel can cause a shortening of the apparent vessel length, the length L pullback-angio L pullback-groundtruth It is often shorter than L pullback-groundtruthBy correlating the distance between the markers 312 and 312′ in the angiographic image 800, the disclosed system can take into account the depth and orientation of the vessel to identify the true vessel length within the angiographic image. The same analysis may be performed between different markers in the same image. For example, the length L described above may be (Lens→PBK)-Groundtruth may be correlated with the distance along the vessel centerline between the pullback marker 310 and the lens marker 312 as seen in the angiogram image. (Dist→Lens)-Groundtruth may be correlated with the distance along the vascular centerline between the lens marker 312 and the distal marker 314.

[0042] Returning to the system 5 shown in FIG. 1, the angiography system 20 can be configured to take a plurality of angiography images from a plurality of different positions relative to the subject 4. In capturing a plurality of angiography images, the system 5 can determine a three-dimensional orientation of the region of interest, such as by identifying the position and departure angle of a side branch from a particular vessel. The position of the side branch can be identified based on the centerline calculation discussed above. U.S. Patent 10,172,582, the disclosure of which is incorporated herein by reference, also discloses a system and method for identifying the position and orientation of a vascular branch within an image frame.

[0043] In FIG. 9, two different angiographic images 900 and 910 are displayed, each including an image of a blood vessel 902 from two different angles. As shown in angiographic image 900, the image is captured at a left anterior oblique angulation of 42 degrees and a cranial angulation of 0 degrees. In image 910, the angiographic image is captured at a left anterior oblique angle of 0 degrees and a cranial angle of 0 degrees. Multiple angiographic images, such as images 900 and 910, can be used to determine the orientation of the blood vessel 902 and the branch vessels 904 branching off from the blood vessel 902. For example, the x-ray source and detector of the angiographic system can be moved around the patient to capture angiographic images at various lateral, cranial and caudal angulations. These multi-angle angiographic images can then be processed by the system to generate a three-dimensional model of the blood vessel and surrounding structures.

[0044] A determination can be made as to which angiographic image frames should be used when generating a three-dimensional model or co-registering angiographic images with intravascular images. For example, angiographic images can be captured over multiple cardiac cycles and the angiographic images can be selected to analyze image frames that correspond to the same or similar portions of the patient's cardiac cycle.

[0045] In FIG. 10, a portion of an angiogram image 1000 is shown in which a centerline 1002 of a vessel has been identified and a centerline 1004 of a branch vessel has also been identified. As described above, multiple angiogram images can be taken at various lateral, cranial and caudal angles and similarly analyzed to identify centerlines 1002 and 1004 in those images. A three-dimensional model of the vessel can then be generated using the multi-angle angiogram images to identify the orientation of the branch vessel centerline 1004 relative to the vessel centerline 1002. The orientation of the branch vessel can be determined using the identified location and departure angle of the branch vessel. For example, in FIG. 10, the vessel centerline 1002 and the vessel centerline 1004 are used to generate a three-dimensional model that can be used to identify the location 1006 where the branch occurs and the departure angle 1008 of the branch from the vessel.

[0046] As discussed above, one or more processors of the system 5 may be configured to analyze the intravascular and extravascular images to determine the VFR of a particular region of the imaged vessel. Image processing techniques and / or machine learning (i.e., image processing techniques and / or machine learning) may also calculate the VFR. The pullback frame may be stretched and aligned using various windows or bins of alignment features. This image data may be presented using various graphical user interfaces. FIG. 11 is a flow diagram 1100 including functions according to aspects of the present disclosure. For example, the functions of the flow diagram 1100 may be performed using one or more processors of the disclosed system to improve the calculation of the VFR of the vessel.

[0047] At block 1102, the system may receive an indication of an intravascular probe type or pullback length to be used in capturing an intravascular image of the blood vessel. The indication of the intravascular probe or pullback length may be provided by a user of the system. For example, the user may select from a number of intravascular probe types. The system may identify the pullback length by accessing stored data related to the identified probe type, or the user may provide an input that identifies a particular pullback length to be used in capturing the intravascular image. At block 1104, one or more extravascular images of the blood vessel and the intravascular probe within the blood vessel are captured. The extravascular image may be an angiographic image of the blood vessel. One or more of the extravascular images may be analyzed to identify an initial location of one or more probe markers within the extravascular image (block 1106). As discussed above, the intravascular probe may include one or more radiopaque markers, the location of which may be identified when the intravascular probe is positioned into an initial position for the pullback procedure.

[0048] At block 1108, a pullback procedure is initiated. This may include flushing at least a portion of the blood vessel with contrast fluid and capturing intravascular images over the pullback length of the intravascular probe. One or more markers of the intravascular probe may then be located after the probe has traversed a portion of the blood vessel as part of the pullback procedure (block 1110). At block 1112, the position of the intravascular probe is deformably co-registered with the extravascular image. As discussed above, the "ground truth" pullback length of the intravascular probe may be associated with the apparent distance traveled by the probe in the intravascular image. In particular, the initial and final locations of one or more probe markers may be mapped onto a single extravascular image as part of the deformable co-registration. Based on this mapping, a vessel size determination may be made (block 1114).

[0049] This vessel size determination may include regions beyond the region imaged by the intravascular probe. For example, the total length of the vessel may be extrapolated based on the known distance traveled by the probe markers during the pullback procedure. Additionally, the cross-sectional diameter and area of ​​the vessel may be extrapolated by comparing the apparent width of the vessel in the deformably coregistered extravascular image with the known diameter and area for the region of the vessel imaged by the intravascular probe. The vessel length in the extravascular image may be estimated by identifying the luminal centerline and by dividing the vessel into three segments: a proximal epicardial segment, an intravascularly imaged segment, and a distal epicardial segment. The intravascularly imaged segment represents the "ground truth" distance traveled by the intravascular probe. The lengths of the proximal and distal epicardial segments may be determined by comparing the apparent lengths in one or more extravascular images with the apparent lengths of the intravascularly imaged segments. The ratio of the compared segment lengths, along with the "ground truth" distance of the intravascularly imaged segment, may be used to determine the actual lengths of the proximal and distal epicardial segments. Thus, the intravascularly imaged segments may be used to scale the proximal and distal epicardial segments.

[0050] The cross-sectional size of the vessel may also be determined by analyzing the contrast border of the vessel's lumen to determine the cross-sectional width of the vessel in the extravascular image. This cross-sectional width may be correlated with the known diameter of the vessel based on the intravascular image, and the cross-sectional diameter of the vessel may then be extrapolated to the proximal and distal epicardial segments. For example, intravascular images captured at the distal and proximal ends of the pullback may be used to determine the lumen diameter at these locations. The diameters determined at these locations may then be used to scale the cross-sectional diameter of the vessel in the extravascular image, including the cross-sectional diameter along the proximal and distal epicardial segments. Thus, the size of the vessel, including the length and cross-sectional size, may be determined for all three vessel segments.

[0051] In block 1116, the extravascular and intravascular images may be analyzed to determine the location and size of vascular side branches based on identifying bifurcations along the luminal centerline for the imaged vessel. These bifurcations in the proximal and distal epicardial segments may be used to identify location markers for the vessel taper. In addition, the size of the microvasculature extending from the vessel may also be determined by comparing the length and width data of the intravascular image to the microvasculature visible in the extravascular image. As discussed above, this microvasculature may be treated as another resistive value that is part of the analyzed vessel segment.

[0052] The determined vessel size, as well as the size and location of the side branches, can then be used to calculate the VFR of the vessel (block 1118). For example, the sizes of the three vessel segments, as determined by the extravascular image, along with information gathered from the intravascular image, can be introduced into a flow resistance model, such as model 300 of FIG. 3, which is used to calculate the pressure drop across a region of the vessel.

[0053] The blocks of flow diagram 1100 may be performed using angiographic images captured from a single location. However, multi-angle angiographic images may also be used in connection with flow diagram 1100. For example, block 1104 may include capturing multiple angiographic images at multiple angles relative to the patient. In addition, block 1114 may include determining a vessel size based at least in part on a three-dimensional model of the vessel based on the multi-angle angiographic images. For example, the vessel's luminal diameter may be estimated by detecting a distance of an enhancement border in the angiographic images from an identified centerline of the vessel. In addition, the location of the side branches identified in block 1116 may include analysis of the three-dimensional model to determine the take-off angle of each side branch. Thus, the orientation of the identified side branches, including the location and take-off angle of each side branch, may be used as part of the VFR calculation performed in block 1118.

[0054] 12 is a flow diagram 1200 in which the disclosed system collects and analyzes multi-angle extravascular images. In block 1202, multi-angle extravascular images are captured, and in block 1204, a three-dimensional model of one or more imaged vessels is generated based on the multi-angle extravascular images. The user may then identify proximal and distal locations within the imaged vessels that represent proximal and distal locations between which an endovascular pullback procedure should be performed (block 1206). For example, the user may identify the proximal and distal locations on one of the displayed extravascular images or on a representation of the generated three-dimensional model. The length between the proximal and distal locations may be displayed to the user based on an analysis of the lengths within the three-dimensional model.

[0055] In block 1208, the size of the blood vessel can be estimated, including the size of the blood vessel in regions distal and proximal to the region to be imaged in the blood vessel. This estimation can be based on identifying the centerline of the blood vessel, determined by tracing the contrast border within the lumen of the blood vessel, and can include both an estimation of the blood vessel length and an estimation of the blood vessel diameter / area. For example, the blood vessel diameter can be estimated by measuring the radial distance of the contrast border in the extravascular image of the blood vessel, which is analyzed in the generated three-dimensional model. The intravascular image is collected in block 1210 as part of a pullback procedure between the identified proximal and distal locations. The intravascular image can be co-registered with the extravascular image and incorporated into the three-dimensional model data. In block 1212, bifurcations along the centerline of the imaged blood vessel are identified. The size and orientation of the blood vessel branch corresponding to the identified bifurcations can then be estimated (block 1214). As discussed above, the orientation of the blood vessel branch can include identifying the location of the bifurcations as well as the departure angle of the blood vessel branch, as determined by the identified centerline of the bifurcations. In addition, the size of the microvasculature extending from the vessel may also be determined by comparing the length and width data of the intravascular image to the microvasculature visible in the extravascular image. As discussed above, this microvasculature may be treated as another resistance that is part of the analyzed vessel segment. The VFR of the vessel is calculated in block 1216. This VFR calculation may use any set or subset of estimated vessel and branch sizes and orientations determined by analysis of the extravascular image. For example, the proximal and distal lengths of the vessel outside the intravascularly imaged region, including the vessel's microvasculature, may be incorporated into the resistance model used to calculate the vessel's VFR. The size, location, and departure angle of each vessel branch may also be incorporated into the resistance model used for VFR calculation.

[0056] Some portions of the detailed description are presented in terms of methods, such as algorithms and symbolic representations of operations on data bits within a computer memory. These algorithmic descriptions and representations may be used by those skilled in the art of computers and software related arts. In one embodiment, an algorithm is herein generally conceived to be a self-consistent sequence of operations leading to a desired result. The operations performed, described herein as method steps or otherwise, are those requiring physical manipulations of physical quantities. These quantities usually, though not necessarily, take the form of electrical or magnetic signals capable of being stored, transferred, combined, transformed, compared, and otherwise manipulated.

[0057] The algorithms and displays presented herein are not inherently related to any particular computer or other apparatus. Various general-purpose systems may be used with programs in accordance with the teachings herein, or it may prove convenient to construct more specialized apparatus to perform the required method steps. The required structure for a variety of these systems will appear from the description below.

[0058] The aspects, embodiments, features, and examples of the present disclosure are considered in all respects to be illustrative and are not intended to be limiting of the disclosure, the scope of which is defined solely by the claims. Other embodiments, modifications, and uses will be apparent to those skilled in the art without departing from the spirit and scope of the claimed invention.

[0059] The use of headings and paragraphs in this application is not meant to limit the invention. Each paragraph may apply to any aspect, embodiment, or feature of the invention.

[0060] Throughout this application, when a composition is described as having, including, or comprising particular components, or a process is described as having or including particular process steps, it is intended that the composition of the present teachings consists essentially of or consists of the recited components, and that the process of the present teachings consists essentially of or consists of the recited process steps.

[0061] When an element or component is referred to in this application as being included and / or selected from a list of enumerated elements or components (i.e., included in and / or selected from a list of components), it is to be understood that the element or component can be any one of the listed elements or components, or can be selected from a group consisting of two or more of the listed elements or components. Furthermore, it is to be understood that the elements and / or features (i.e., elements and / or features) of the compositions, devices, or methods described herein can be combined in various ways, whether expressly or implicitly stated herein, without departing from the spirit and scope of the present teachings.

[0062] Use of the terms "include," "includes," "including," "have," "has," or "having" should generally be understood to be open-ended and non-limiting, unless otherwise specified.

[0063] The use of the singular herein includes the plural (and vice versa) unless otherwise specified. Furthermore, the singular forms "a," "an," and "the" or "the" include the plural unless the context clearly dictates otherwise. Furthermore, where the term "about" is used before a quantitative value, the present teachings also include the specific quantitative value itself unless otherwise specified. As used herein, the term "about" refers to a ±10% variation from the nominal value. All numerical values ​​and numerical ranges disclosed herein are deemed to include "about" before each value.

[0064] It should be understood that the order of steps or order for performing certain actions is immaterial so long as the present teachings remain operable. Further, two or more steps or actions may be performed simultaneously, and steps may be eliminated or substituted depending on the aspects of the present disclosure.

[0065] When a range or list of values ​​is provided, each intervening value between the upper and lower limits of that range or list of values ​​is individually contemplated and encompassed within the invention as if each value were specifically recited herein. Additionally, smaller ranges between and including the upper and lower limits of a given range are contemplated and encompassed within the invention. A list of exemplary values ​​or ranges does not exclude other values ​​or ranges between and including the upper and lower limits of a given range.

Claims

1. receiving, by one or more processors, a plurality of extravascular images of a blood vessel during a pullback of an intravascular imaging probe having a pullback length defined along a first region of the blood vessel; detecting, by the one or more processors, locations of one or more markers in the plurality of extravascular images; correlating, by the one or more processors, the first region of the vessel represented in the plurality of extravascular images with the pullback length based on the locations of the one or more markers in the plurality of extravascular images; determining, by the one or more processors, a size of a second region of the blood vessel represented in the plurality of extravascular images based on the correlation with the pullback length for the first region of the blood vessel represented in the plurality of extravascular images; A method for identifying attributes of a blood vessel, including:

2. 2. The method of claim 1, wherein the size of the second region of the blood vessel includes at least one of a length of the second region, a cross-sectional diameter within the second region, and a cross-sectional area within the second region.

3. 2. The method of claim 1, further comprising calculating, by the one or more processors, a virtual flow reserve (VFR) of the blood vessel based on a plurality of images captured by the intravascular imaging probe and based on the determined size of the second region of the blood vessel.

4. 4. The method of claim 3, wherein the VFR of the vessel is calculated based on a distance between a vessel centerline and a boundary of the second region of the vessel identified in at least one of the plurality of extravascular images.

5. The method of claim 1 , wherein the second region of the blood vessel includes at least one of a distal epicardial region and a proximal epicardial region of the blood vessel.

6. The method of claim 5 , wherein determining the size of the second region of the blood vessel includes determining a length of the distal epicardial region and a length of the proximal epicardial region.

7. 2. The method of claim 1, wherein correlating the first region of the blood vessel represented in the plurality of extravascular images with the pullback length comprises scaling a lumen size represented in at least one of the plurality of extravascular images.

8. A system for identifying attributes of a blood vessel, comprising: one or more memories for storing images of blood vessels; one or more processors configured to: capture a plurality of extravascular images of a blood vessel during a pullback of an intravascular imaging probe having a defined pullback length along a first region of the blood vessel; detect locations of one or more markers in the plurality of extravascular images; correlate the first region of the blood vessel represented in the plurality of extravascular images with the pullback length based on the locations of the one or more markers in the plurality of extravascular images; and determine a size of a second region of the blood vessel represented in the plurality of extravascular images based on the correlation of the first region of the blood vessel represented in the plurality of extravascular images with the pullback length; A system comprising:

9. 9. The system of claim 8, wherein the size of the second region of the blood vessel includes at least one of a length of the second region, a cross-sectional diameter within the second region, and a cross-sectional area within the second region.

10. 10. The system of claim 8, wherein the one or more processors are further configured to calculate a virtual flow reserve (VFR) of the vessel based on a plurality of images captured by the intravascular imaging probe and based on the determined size of the second region of the vessel.

11. 11. The system of claim 10, wherein the VFR of the vessel is calculated based on a distance between a vessel centerline and a boundary of the second region of the vessel identified in at least one of the plurality of extravascular images.

12. The system of claim 8 , wherein the second region of the blood vessel includes at least one of a distal epicardial region and a proximal epicardial region of the blood vessel.

13. 9. The system of claim 8, wherein correlating the first region of the blood vessel represented in the plurality of extravascular images with the pullback length comprises scaling a lumen size represented in at least one of the plurality of extravascular images.

14. 9. The system of claim 8, wherein the one or more processors are further configured to analyze the plurality of extravascular images to identify a branch location and a departure angle relative to the vessel.

15. 15. The system of claim 14, wherein the one or more processors are further configured to calculate a virtual flow reserve (VFR) of the vessel based on the identified locations and departure angles of the branches.

Images