Intravascular ultrasound imaging and calcium detection method

Abstract

Methods are disclosed, including methods for processing intravascular ultrasound images. An example method can include collecting one or more ultrasound images of a blood vessel and segmenting the ultrasound images with a processor. Segmentation can include identifying one or more of a lumen boundary of the blood vessel and a media boundary for an intravascular medium.

Description

[0001] Cross-references to related applications

[0002] This application claims priority to U.S. Provisional Application Serial No. 62 / 906,546, filed September 26, 2019, pursuant to 35 USC §119, the entire contents of which are incorporated herein by reference. Technical Field

[0003] This invention relates to intravascular ultrasound imaging. Background Technology

[0004] A wide variety of medical devices have been developed for medical applications, such as intravascular use. Some of these devices include intravascular ultrasound imaging devices. Additionally, methods for intravascular ultrasound imaging have been developed. Each of these medical devices and methods has certain advantages and disadvantages. There is a continued need to provide alternative devices and methods. Summary of the Invention

[0005] This invention provides alternatives and methods for the design and use of medical devices, including, for example, methods for intravascular ultrasound imaging. The invention discloses a method for processing intravascular ultrasound images. The method includes: acquiring one or more ultrasound images of a blood vessel; segmenting the ultrasound images using a processor; wherein the processor includes a deep neural network; and wherein the segmentation includes identifying one or more of the lumen boundary of the blood vessel and the medial boundary for the intravascular medium.

[0006] Alternatively or additionally for any of the above embodiments, segmentation includes identifying cavity boundaries.

[0007] Alternatively or additionally for any of the above embodiments, segmentation includes identifying the medium boundary.

[0008] Alternatively or additionally for any of the above embodiments, a deep neural network is trained to identify cavity boundaries.

[0009] Alternatively or additionally for any of the above embodiments, the deep neural network is trained to identify medium boundaries.

[0010] Alternatively or additionally, in any of the above embodiments, the deep neural network is trained to identify cavity boundaries and is trained to identify medium boundaries.

[0011] Alternatively or additionally for any of the above embodiments, it also includes displaying a first image of one or more ultrasound images on a display device.

[0012] Alternatively or additionally, any of the above embodiments may also include displaying a digital indication of a narrow area for the first image on the display device.

[0013] Alternatively or additionally for any of the above embodiments, a digital indication of a narrow area is displayed on or near the first image.

[0014] Alternatively or additionally, any of the above embodiments may also include displaying a digital indication of patch load for the first image on a display device.

[0015] Alternatively or additionally, for any of the above embodiments, a digital indication of plaque load is displayed on or near the first image.

[0016] Alternatively or additionally, any of the above embodiments may also include displaying a visual representation of the calcification angle on a display device.

[0017] Alternatively or additionally for any of the above embodiments, the visual representation of the calcification angle includes an arc set along the boundary region of the first image.

[0018] Alternatively or additionally, any of the above embodiments may also include displaying a visual representation of the calcified arc on a display device.

[0019] Alternatively or additionally for any of the above embodiments, the visual representation of the calcified arc includes an arc set along the boundary region of the first image.

[0020] This invention discloses a method for processing intravascular ultrasound images. The method includes: collecting multiple ultrasound images of a blood vessel; segmenting the ultrasound images using a processor; wherein the processor includes a deep neural network; and wherein the segmentation includes identifying the lumen boundary of the blood vessel, the cross-sectional area of ​​the blood vessel, the boundary of the intravascular medium, the cross-sectional area of ​​the medium, the calcification angle of calcified lesions within the blood vessel, the location of lateral branches, or combinations thereof.

[0021] Alternatively or additionally for any of the above embodiments, collecting multiple ultrasound images of a blood vessel includes collecting multiple ultrasound images using an intravascular ultrasound catheter system.

[0022] Alternatively or additionally for any of the above embodiments, collecting multiple ultrasound images of blood vessels includes collecting cross-sectional images of blood vessels.

[0023] Alternatively or additionally for any of the above embodiments, segmenting ultrasound images with a processor includes segmentation using artificial intelligence.

[0024] Alternatively or additionally for any of the above embodiments, segmenting ultrasound images with a processor includes segmentation using a deep neural network.

[0025] Alternatively or additionally, in any of the above embodiments, segmenting ultrasound images with a processor includes quantitative analysis.

[0026] Alternatively or additionally, in any of the above embodiments, segmenting ultrasound images using a processor includes image classification.

[0027] Alternatively or additionally for any of the above embodiments, segmenting ultrasound images with a processor includes identifying lesions within blood vessels.

[0028] Alternatively or additionally, in any of the above embodiments, the ultrasound image is segmented using a processor, including stent detection.

[0029] Alternatively or additionally for any of the above embodiments, segmentation includes identifying the luminal boundaries of the blood vessel.

[0030] Alternatively or additionally for any of the above embodiments, segmentation includes identifying the cross-sectional area of ​​the blood vessel.

[0031] Alternatively or additionally for any of the above embodiments, segmentation includes identifying the media boundary for intravascular media.

[0032] Alternatively or additionally for any of the above embodiments, the segmentation includes the cross-sectional area of ​​the identification medium.

[0033] Alternatively or additionally for any of the above embodiments, segmentation includes identifying the calcification angle of intravascular calcified lesions.

[0034] Alternatively or additionally for any of the above embodiments, segmentation includes identifying the location of the side branches.

[0035] Alternatively or additionally, any of the above embodiments may also include displaying a first cross-sectional image of the blood vessel on a display.

[0036] Alternatively or additionally, any of the above embodiments may also include displaying a second cross-sectional image of the blood vessel on the display.

[0037] Alternatively or additionally, any of the above embodiments may also include displaying digital indications on the display for a narrow area of ​​the first cross-sectional image, the second cross-sectional image, or both.

[0038] Alternatively or additionally, any of the above embodiments may also include displaying a digital indication of patch load on the display for the first cross-sectional image, the second cross-sectional image, or both.

[0039] Alternatively or additionally, any of the above embodiments may also include a visual representation showing the calcification angle.

[0040] Alternatively or additionally for any of the above embodiments, the visual representation of the calcification angle includes an arc set along the boundary region of the first cross-sectional image.

[0041] Alternatively or additionally, any of the above embodiments may also include a visual representation showing the calcified arc.

[0042] Alternatively or additionally for any of the above embodiments, the visual representation of the calcification angle includes an arc set along the boundary region of the first cross-sectional image.

[0043] This invention discloses a method for displaying images of blood vessels. The method includes: receiving electrical signals originating from a transducer coupled to a catheter using a processing unit as a transducer rotates and moves longitudinally along the lumen of the blood vessel; processing the received electrical signals to form a series of cross-sectional images; wherein the cross-sectional images are longitudinally offset from each other along the lumen; displaying one or more of the cross-sectional images on a display; and displaying a lumen diameter profile, a blood vessel diameter profile, or both on the display.

[0044] Alternatively or additionally, for any of the above embodiments, the lumen diameter profile is configured to allow clinicians to identify the minimum lumen area within the blood vessel.

[0045] Alternatively or additionally for any of the above embodiments, the vessel diameter profile is configured to allow clinicians to identify lateral branches extending from the vessel.

[0046] Alternatively or additionally, any of the above embodiments may also include displaying a two-dimensional representation of calcium coverage within the blood vessels on a display screen.

[0047] Alternatively or additionally, any of the above embodiments may also include displaying a two-dimensional calcium map on a display.

[0048] Alternatively or additionally, any of the above embodiments may also include displaying a three-dimensional representation of the calcium coverage within the blood vessel on a display screen.

[0049] Alternatively or additionally, any of the above embodiments may also include displaying a three-dimensional calcium map on a display.

[0050] Alternatively or additionally, any of the above embodiments may also include displaying a visual representation of the calcification angle on a display.

[0051] Alternatively or additionally for any of the above embodiments, the visual representation of the calcification angle includes an arc set along a boundary region of one of the cross-sectional images.

[0052] Alternatively or additionally, any of the above embodiments may also include displaying a visual representation of the calcified arc on a display.

[0053] Alternatively or additionally for any of the above embodiments, the visual representation of a calcified arc includes an arc set along a boundary region of one of the cross-sectional images.

[0054] This invention discloses a method for graphically displaying calcifications of blood vessels. The method includes: collecting multiple ultrasound images of the blood vessel; segmenting the images to generate a calcification angle for each of the multiple ultrasound images; and displaying a visual representation of the calcification angle.

[0055] Alternatively or additionally for any of the above embodiments, the visual representation of the calcification angle includes an arc set along a boundary region of one of the images.

[0056] Alternatively or additionally, for any of the above embodiments, the visual representation of the calcification angle includes a two-dimensional calcification map.

[0057] Alternatively or additionally, for any of the above embodiments, the visual representation of the calcification angle includes a three-dimensional calcification map.

[0058] This invention discloses a method for determining a treatment strategy for treating intravascular lesions within a blood vessel. The method includes: determining a first numerical calcium fraction by observing a visual representation of the calcium arc of the intravascular lesion, a two-dimensional calcium map of the blood vessel, a three-dimensional calcium map of the blood vessel, or a combination thereof; determining a second numerical calcium fraction by observing a perspective image of the blood vessel; determining a third numerical calcium fraction by measuring the length of the intravascular lesion; calculating the sum of the first, second, and third numerical calcium fractions; and selecting a treatment modality based on the sum.

[0059] This invention discloses a method for processing intravascular ultrasound images using artificial intelligence.

[0060] This invention discloses a method for processing intravascular ultrasound images using artificial intelligence, as disclosed herein and / or claimed.

[0061] This invention discloses a method for determining the arc size of calcification in blood vessels.

[0062] Alternatively or additionally, any of the above embodiments may also include displaying the amount of calcification on a display device.

[0063] Alternatively or additionally for any of the above embodiments, displaying the amount of calcification on the display device includes displaying an arc of the boundary region of a cross-sectional ultrasound image along the blood vessel.

[0064] Alternatively or additionally for any of the above embodiments, displaying the amount of calcification on the display device includes a two-dimensional calcium map.

[0065] Alternatively or additionally, for any of the above embodiments, displaying the amount of calcification on the display device includes a three-dimensional calcium map.

[0066] This invention discloses a method for processing intravascular ultrasound images. The method includes: acquiring one or more ultrasound images of a blood vessel; segmenting the ultrasound images using a processor; and wherein the segmentation includes identifying one or more of the lumen boundary of the blood vessel and the media boundary for the intravascular medium.

[0067] Alternatively or additionally for any of the above embodiments, segmentation includes identifying cavity boundaries.

[0068] Alternatively or additionally for any of the above embodiments, segmentation includes identifying the medium boundary.

[0069] Alternatively or additionally for any of the above embodiments, the processor includes a deep neural network.

[0070] Alternatively or additionally for any of the above embodiments, a deep neural network is trained to identify cavity boundaries.

[0071] Alternatively or additionally for any of the above embodiments, the deep neural network is trained to identify medium boundaries.

[0072] Alternatively or additionally, in any of the above embodiments, the deep neural network is trained to identify cavity boundaries and is trained to identify medium boundaries.

[0073] This invention discloses a method for processing intravascular ultrasound images. The method includes: collecting multiple ultrasound images of a blood vessel; segmenting the ultrasound images using a processor; and wherein the segmentation includes identifying the lumen boundary of the blood vessel, the cross-sectional area of ​​the blood vessel, the boundary of the intravascular medium, the cross-sectional area of ​​the medium, the calcification angle of calcified lesions within the blood vessel, the location of lateral branches, or combinations thereof.

[0074] Alternatively or additionally for any of the above embodiments, the processor includes a deep neural network.

[0075] Alternatively or additionally for any of the above embodiments, a deep neural network is trained to identify cavity boundaries.

[0076] Alternatively or additionally for any of the above embodiments, the deep neural network is trained to identify medium boundaries.

[0077] Alternatively or additionally, in any of the above embodiments, the deep neural network is trained to identify cavity boundaries and is trained to identify medium boundaries.

[0078] The above overview of some embodiments is not intended to describe every disclosed embodiment or implementation of the invention. These embodiments are illustrated more specifically by way of example in the following figures and detailed descriptions. Attached Figure Description

[0079] The invention can be more fully understood by considering the following detailed description taken in conjunction with the accompanying drawings, in which:

[0080] Figure 1 An example intravascular ultrasound system is schematically depicted.

[0081] Figure 2 This is a three-dimensional diagram of an example intravascular ultrasound catheter system.

[0082] Figure 3 This is a side view of a portion of an example intravascular ultrasound catheter system.

[0083] Figure 4 This is a flowchart illustrating an example method for processing images.

[0084] Figure 5 This is a flowchart illustrating an example method for processing images.

[0085] Figure 6 The process for image segmentation is illustrated schematically.

[0086] Figure 7 An example of the displayed output is shown.

[0087] Figure 8 An example of the displayed output is shown.

[0088] Figure 9 An example of the displayed output is shown.

[0089] Figures 10 to 12 Some examples of the displayed output are shown.

[0090] While the invention is adaptable to various modifications and alternatives, its specific details have been shown by way of example in the accompanying drawings and will be described in more detail. However, it should be understood that it is not intended to limit the invention to the specific embodiments described. Rather, it is intended to cover all modifications, equivalents, and alternatives falling within the spirit and scope of the invention. Detailed Implementation

[0091] For the purposes of the following definitions, unless otherwise specified in the claims of this specification or elsewhere, these definitions shall apply.

[0092] All numerical values ​​herein are assumed to be modified by the term "about," whether or not explicitly stated otherwise. The term "about" generally refers to a range of numbers that a person skilled in the art would consider equivalent to the referenced value (i.e., having the same function or result). In many cases, the term "about" may include numbers rounded to the nearest significant figure.

[0093] A description of a range of numbers represented by endpoints includes all numbers within that range (e.g., 1 to 5 includes 1, 1.5, 2, 2.75, 3, 3.80, 4, and 5).

[0094] As used in this specification and the appended claims, the singular forms “a,” “an,” and “the” include a plural of indicators unless otherwise expressly indicated. As used in this specification and the appended claims, the term “or” is generally used in the sense of including “and / or” unless otherwise expressly indicated.

[0095] It should be noted that the embodiments described by references to "one embodiment," "some embodiments," "other embodiments," etc., in the specification may include one or more specific features, structures, or characteristics. However, such description does not necessarily mean that all embodiments include that specific feature, structure, and / or characteristic. Furthermore, when a specific feature, structure, and / or characteristic is described in connection with an embodiment, it should be understood that, whether explicitly described or not, such feature, structure, and / or characteristic may also be used in conjunction with other embodiments, unless expressly stated otherwise.

[0096] The following detailed description should be read with reference to the accompanying drawings, in which similar elements in different drawings have the same numbering. The drawings, which are not necessarily drawn to scale, depict illustrative embodiments and are not intended to limit the scope of the invention.

[0097] Insertable ultrasound devices have proven their diagnostic capabilities for a wide range of diseases and conditions. For example, intravascular ultrasound (“IVUS”) imaging systems can be used as an imaging modality to diagnose blocked blood vessels and to provide information to help practitioners select and place stents and other devices to restore or increase blood flow. IVUS imaging systems can also be used to diagnose atherosclerotic plaque buildup at specific locations within blood vessels. IVUS imaging systems can also be used to determine the presence, nature, and extent of occlusion or stenosis within blood vessels. IVUS imaging systems can also be used to visualize segments of the vascular system that may be difficult to visualize using other intravascular imaging techniques, such as angiography, due to, for example, movement of one or more structures (e.g., one or more vessels that do not need to be imaged) or blockage. IVUS imaging systems can also be used to monitor or evaluate ongoing endovascular treatments, such as angiography and stent placement, in real time (or near real time). In addition, IVUS imaging systems can be used to monitor one or more ventricles.

[0098] IVUS imaging systems have been developed to provide diagnostic tools for visualizing a variety of diseases or conditions. An IVUS imaging system may include a control module (with a pulse generator, image processor, and monitor), a catheter, and one or more transducers disposed within the catheter. The catheter containing the transducers may be positioned within or near a lumen or cavity in the area to be imaged, such as the vessel wall or patient tissue proximal to the vessel wall. The pulse generator in the control module generates electrical pulses, which are delivered to one or more transducers and converted into acoustic pulses that are transmitted through the patient tissue. Reflected pulses from the transmitted acoustic pulses may be absorbed by one or more transducers and converted back into electrical pulses. The converted electrical pulses may be delivered to the image processor and converted into an image that can be displayed on a monitor.

[0099] Figure 1 An example IVUS imaging system 100 is schematically illustrated. The IVUS imaging system 100 includes a catheter 102 that can be coupled to a processing unit or control module 104. The control module 104 may include, for example, a processor 106, a pulse generator 108, a drive unit 110, and one or more displays 112. In some cases, the pulse generator 108 generates electrical pulses that can be input to one or more transducers disposed in the catheter 102. Figure 3 (312 in the middle).

[0100] In some cases, the mechanical energy derived from the drive unit 110 can be used to drive the imaging core disposed in the conduit 102. Figure 3 306 in the middle). In some cases, from one or more transducers ( Figure 3The electrical signal transmitted by 312 in the transducer can be input to processor 106 for processing. In some cases, the signal originates from one or more transducers ( Figure 3 The processed electrical signal (312) can be displayed as one or more images on one or more displays 112. For example, a scan converter can be used to map scan line samples (e.g., radial scan line samples, etc.) to a two-dimensional Cartesian grid to display one or more images on one or more displays 112.

[0101] In some cases, processor 106 can also be used to control the functions of one or more other components of control module 104. For example, processor 106 can be used to control the frequency or duration of electrical pulses transmitted from pulse generator 108, and the driving unit 110's control over the imaging core (…). Figure 3 The rotation rate of 306 in the middle, the drive unit 110 to the imaging core ( Figure 3 At least one of the following properties: the pull-back rate or pull-back length of (306) or one or more images formed on one or more displays 112.

[0102] Figure 2 It is an IVUS imaging system ( Figure 1 A schematic side view of one embodiment of catheter 102 (100 in the diagram). Catheter 102 includes an elongated member 202 and a connector 204. The elongated member 202 includes a proximal end 206 and a distal end 208. Figure 2 In this configuration, the proximal end 206 of the elongated member 202 is coupled to the catheter connector 204, and the distal end 208 of the elongated member is configured and arranged for percutaneous insertion into a patient. Optionally, the catheter 102 may define at least one flushing port, such as flushing port 210. Flushing port 210 may be defined in connector 204. Connector 204 may be configured and arranged to connect to a control module (…). Figure 1 (104 in the original text). In some cases, the elongated member 202 and the connector 204 are formed as a single unit. In other cases, the elongated member 202 and the conduit connector 204 are formed separately and then assembled together.

[0103] Figure 3This is a schematic perspective view of one embodiment of the distal end 208 of the elongated member 202 of catheter 102. The elongated member 202 includes a sheath 302 having a longitudinal axis 303 and a lumen 304. An imaging core 306 is disposed in the lumen 304. The imaging core 306 includes an imaging device 308 coupled to the distal end of a drive shaft 310 that can be rotated manually or using a computer-controlled drive mechanism. One or more transducers 312 may be mounted to the imaging device 308 and used for transmitting and receiving acoustic signals. The sheath 302 may be made 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, etc., or combinations thereof.

[0104] In some cases, for example, Figure 3 As shown, an array of transducers 312 is mounted to the imaging device 308. Alternatively, a single transducer may be used. Any suitable number of transducers 312 may be used. For example, there may be two, three, four, five, six, seven, eight, nine, ten, twelve, fifteen, sixteen, twenty, twenty-five, fifty, one hundred, five hundred, one thousand, or more transducers. Other numbers of transducers may also be used, as will be appreciated. When multiple transducers 312 are used, the transducers 312 can be configured in any suitable arrangement, including, for example, a ring arrangement, a rectangular arrangement, etc.

[0105] One or more transducers 312 may be formed of a material capable of converting an applied electrical pulse into pressure deformation on the surface of one or more transducers 312, 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.).

[0106] Pressure deformation on the surface of one or more transducers 312 generates an acoustic pulse at a frequency based on the resonant frequency of the one or more transducers 312. The resonant frequency of the one or more transducers 312 may be influenced by the size, shape, and material used to form the one or more transducers 312. The one or more transducers 312 can be formed in any shape suitable for positioning within the conduit 102 and propagating an acoustic pulse of the desired frequency in one or more selected directions. For example, the transducer can be disc-shaped, box-shaped, rectangular, elliptical, etc. The one or more transducers can be formed into the desired shape by any process, including, for example, cutting, dicing and filling, machining, micromachining, etc.

[0107] As an example, each of one or more transducers 312 may include a piezoelectric material layer sandwiched between a matching layer and a conductive backing material formed of a sound-absorbing material (e.g., an epoxy resin substrate with tungsten particles). During operation, the piezoelectric layer can be electrically excited to induce the emission of acoustic pulses.

[0108] One or more transducers 312 can be used to form radial cross-sectional images of the surrounding space. Thus, for example, when one or more transducers 312 are disposed in catheter 102 and inserted into a patient's blood vessel, one or more transducers 312 can be used to form images of the blood vessel and the walls of the tissue surrounding the blood vessel.

[0109] The imaging core 306 rotates about the longitudinal axis 303 of the conduit 102. As the imaging core 306 rotates, one or more transducers 312 emit acoustic signals in different radial directions (e.g., along different radial scan lines). For example, one or more transducers 312 may emit acoustic signals in regular (or irregular) increments, such as 256 radial scan lines per revolution. It should be understood that other numbers of radial scan lines may be emitted per revolution instead.

[0110] When a emitted acoustic pulse with sufficient energy encounters one or more medium boundaries, such as one or more tissue boundaries, a portion of the emitted acoustic pulse is reflected back to the transmitting transducer as an echo pulse. Each echo pulse arriving at the transducer with sufficient energy is converted into an electrical signal in the receiving transducer. One or more converted electrical signals are transmitted to the control module (…). Figure 1 In 104), the processor 106 processes electrical signal characteristics based at least in part on a set of information from each of the transmitted acoustic pulses and the received echo pulses to form a displayable image of the imaging area. In some cases, the rotation of the imaging core 306 is controlled by a control module ( Figure 1 The drive unit 110 in (104) drives the transducer. In an alternative embodiment, one or more transducers 312 are fixed in place and do not rotate. In this case, the drive shaft 310 may instead rotate a mirror that reflects the acoustic signal to and from the fixed transducers 312.

[0111] When one or more transducers 312 rotate about the longitudinal axis 303 of the catheter 102 that emits acoustic pulses, multiple images can be formed that collectively form radial cross-sectional images (e.g., tomographic images) of a region surrounding the one or more transducers 312, such as the vessel wall of interest and a portion of the tissue surrounding the vessel. Optionally, the radial cross-sectional images can be displayed on one or more displays 112. At least one of the imaging cores 306 can be rotated manually or using a computer-controlled mechanism.

[0112] The imaging core 306 can also move longitudinally along the blood vessel into which the catheter 102 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 312 can retract (e.g., pull back) along the longitudinal length of the catheter 102. The catheter 102 may include at least one telescopic section that can retract during the retraction of one or more transducers 312. In some cases, the actuation unit 110 actuates the retraction of the imaging core 306 within the catheter 102. The distance by which the actuation unit 110 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 102 can retract during the imaging process, regardless of whether the imaging core 306 moves independently of the longitudinal movement of the catheter 102.

[0113] Optionally, a stepper motor can be used to pull back the imaging core 306. The stepper motor can pull the imaging core 306 back a short distance and stop it for a sufficient time to allow one or more transducers 306 to capture an image or a series of images before pulling the imaging core 306 back another short distance and capturing another image or a series of images again.

[0114] The quality of images generated from one or more transducers 312 at different depths may be affected by one or more factors, including, for example, bandwidth, transducer focus, beammap, and the frequency of the acoustic pulse. The frequency of the acoustic pulse output from one or more transducers 312 can also affect the penetration depth of the acoustic pulse output from one or more transducers 312. 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 IVUS imaging system 100 operates in a frequency range of 5 MHz to 100 MHz.

[0115] One or more conductors 314 can electrically connect the transducer 312 to the control module 104 (see example). Figure 1 In this case, one or more conductors 314 may extend along the longitudinal length of the rotatable drive shaft 310.

[0116] A catheter 102 having one or more transducers 312 mounted to the distal end 208 of an imaging core 308 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 102 can then be advanced through the patient's blood vessels to reach the selected imaging site, such as a portion of a selected blood vessel.

[0117] Each time one or more acoustic signals are output to surrounding tissue and one or more corresponding echo signals are received by imager 308 and transmitted to processor 106, an image or image frame (“frame”) can be generated. Alternatively, the image or image frame can be a composite of scan lines from a fully or partially rotated imaging core or device. Multiple (e.g., a sequence) frames can be acquired over time during any type of movement of imaging device 308. For example, frames can be acquired during rotation and retraction of imaging device 308 along a target imaging position. It should be understood that frames can be acquired with or without rotation of imaging device 308 and with or without retraction. Furthermore, it should be understood that other types of movement processes can be used to acquire frames in addition to or instead of at least one of rotation or retraction of imaging device 308.

[0118] In some cases, the retraction can be performed at a constant rate, thus providing a tool for potential applications that can calculate longitudinal vessel / plaque measurements. In some cases, the imaging device 308 is retracted at a constant rate of at least 0.3 mm / s. In some cases, the imaging device 308 is retracted at a constant rate of at least 0.4 mm / s. In some cases, the imaging device 308 is retracted at a constant rate of at least 0.5 mm / s. In some cases, the imaging device 308 is retracted at a constant rate of at least 0.6 mm / s. In some cases, the imaging device 308 is retracted at a constant rate of at least 0.7 mm / s. In some cases, the imaging device 308 is retracted at a constant rate of at least 0.8 mm / s.

[0119] In some cases, one or more acoustic signals are output to surrounding tissue at constant time intervals. In some cases, one or more corresponding echo signals are received by imager 308 and transmitted to processor 106 at constant time intervals. In some cases, the generated frames are produced at constant time intervals.

[0120] At least some conventional IVUS imaging systems display only a single image (e.g., cross-sectional, longitudinal, etc.) during or after an IVUS procedure, such as a pull-back procedure. However, it may be useful to simultaneously display at least two images in real time during an IVUS procedure (e.g., a pull-back procedure), such as a recently processed image and a previously acquired image with some specific or selected image characteristics (e.g., maximum or minimum cavity area or diameter).

[0121] Some diagnostic and / or therapeutic interventions may involve the analysis of images generated by an IVUS imaging system. However, such analysis may require substantial training / experience to effectively interpret the images. Furthermore, automated analysis and / or evaluation can be challenging due to the frequent presence of blotches in IVUS images. This paper discloses methods for processing and / or analyzing images, such as those generated by / from an IVUS imaging system. Such methods can leverage machine learning, artificial intelligence, deep neural networks, and / or similar approaches to improve the processing and / or analysis of images generated by / from an IVUS imaging system.

[0122] Figure 4 This is a flowchart illustrating an example process or framework. The process may include generating and / or collecting vascular images (e.g., IVUS images generated via an IVUS pull-back procedure, cross-sectional images, etc.) at box 401. At box 403, the generated / collected images may be subjected to cross-sectional analysis. Cross-sectional analysis may include processing and / or segmenting the images using a deep learning network (e.g., a deep neural network, such as a U-Net deep neural network) to obtain image segmentation for quantitative analysis and image classification for automatic identification of lesion types, stent detection, etc. For example, the output of the cross-sectional analysis marked at box 405 may include identification of lumen boundaries, lumen dimensions, media boundaries (e.g., media boundaries for intravascular media), media dimensions, calcification angles / arcs, calcification coverage, lesion types, etc. In addition to identifying such boundaries / sizes, the output may be displayed on a display unit in a suitable format (e.g., graphically, digitally, as a real or schematic image, with text or symbols, etc.). In some cases, multiple images from the IVUS pull-back or "run" may be analyzed at box 407. The output of this run analysis, marked at box 409, may include lumen profiles (e.g., including, for example, longitudinal cross-sections or "long views"), vessel profiles (e.g., including, for example, longitudinal cross-sections or "long views"), representations of calcification lengths (e.g., visualizations or images, digital visualizations, graphical visualizations, etc.), depictions / displays of reference frames (e.g., minimum lumen area or "MLA", minimum stent area or "MSA", etc.), representations of lateral branch locations (e.g., visualizations or images, digital visualizations, graphical visualizations, etc.), representations of the distance between two frames of interest (e.g., visualizations or images, digital visualizations, graphical visualizations, etc.), representations of stent extensions (e.g., visualizations or images, digital visualizations, graphical visualizations, etc.), and combinations thereof. This may also include analyzing the images using deep neural networks (e.g., deep neural networks such as UNet) and / or machine learning and / or artificial intelligence.

[0123] Figure 5This is a flowchart depicting an example process by which images (e.g., IVUS images generated via an IVUS pull-back process, cross-sectional images, etc.) can be processed / segmented. For example, an example cross-sectional image (e.g., at box 501) or a group / set of images can be classified (e.g., at box 503), for example, to identify the type of lesion (e.g., at box 505). In some cases, the output can be displayed on a display unit in a suitable format (e.g., graphically, digitally, as a real or schematic image, with text or symbols, etc.). In some cases, the image (e.g., at box 501) can undergo calcification detection (e.g., at box 507) to identify the extent of calcium / calcification angle or arc coverage (e.g., at box 509).

[0124] In some cases, the image (e.g., at box 501) can be segmented (e.g., at box 511). This can include boundary extraction (e.g., at box 513) to identify cavity boundaries, cavity dimensions, medium boundaries, medium dimensions, etc. (e.g., at box 515). Some example outputs of image segmentation (e.g., which may be displayed on a display unit) are shown in... Figure 6 As shown in the figure. The image of blood vessel 517 can be segmented. This can include analyzing the image using deep neural networks (e.g., U-Net deep neural networks and / or other networks trained to identify lumen boundaries, media boundaries, or both) and / or machine learning and / or artificial intelligence. This can result in visualization 519 of the identified lumen boundaries 521 and media boundaries 523.

[0125] Figure 7 This is an example display output 601 that can be displayed on a display unit. Multiple features can be shown. One or more representative images 603a, 603b of a cross-section of the vessel can be shown. In some cases, digital indications of stenosis regions 605a, 605b and / or plaque load 607a, 607b can be shown next to or adjacent to images 603a, 603b. In some cases, a representation / visualization of a longitudinal cross-section of the vessel 609 can be shown. In some cases, a visual representation of calcification angles / arcs can be displayed on display output 601. For example, a visual representation of calcification angles / arcs may include an arc or curve set along the boundary region of images 603a, 603b. In some cases, the display may include a representation / visualization of vessel diameter contour 611 and / or lumen diameter contour 613. These contours 611, 613 can enable clinicians to more effectively identify vascular regions with minimal area (e.g., MLA) and / or other regions of interest within the vessel.

[0126] Figure 8Another example of a display output 701 that can be displayed on a display unit is shown. This display output 701 can take the form of a calcium map (e.g., a two-dimensional calcium map depicting calcification angles / arcs). In this example, the longitudinal position is shown along the X-axis, and the calcification angles / arcs are shown along the Y-axis. Several bright spots indicating the presence of calcification are shown on the calcium map. For example, a first calcification point 703 and a second calcification point 705 are shown. The first calcification point 703 may have a relatively long longitudinal component but a smaller / shorter calcification angle / arc, while the second calcification point 705 may include longitudinal segments 707a, 707b (e.g., having a relatively long longitudinal component) and a circumferential segment 709 (e.g., having a larger, more circumferential calcification angle / arc).

[0127] Figure 9 This is another example of a display output 801 that can be displayed on a display unit. This display output 801 can take the form of a calcium map (e.g., a two-dimensional calcium map depicting calcification angles / arcs). In this example, the vertical position is shown along the X-axis, and the calcification angles / arcs are shown using variations in brightness and / or color / grayscale. In this example, the calcium map shows multiple bright spots indicating the presence of calcification. For example, a first calcification point 803 and a second calcification point 805 are shown. The first calcification point 803 can have a first brightness, while the second calcification point 805 can have a second brightness that is brighter than the first brightness.

[0128] Figures 10 to 12 An example display output 901 that can be displayed on a display unit is depicted. Although each part / display output is shown and labeled with a separate figure, one or more (or all) of the various display outputs can be located on the same or different displays. In other words, all of them can be displayed on the same display. Figures 10 to 12 , or in Figures 10 to 12 The display output shown may originate from one or more different displays. Display output 901 may include a perspective image 903 depicting a portion of a vessel 905. A calcium map 907 may be shown on the same display unit or separately, illustrating the vessel 909 and a representation 911 of the calcification angle / arc. In some cases, ultrasound lines may be included in the representation 911 of the calcification angle / arc (e.g., when the maximum brightness in the lesion segment between the lumen and the media boundary is significantly higher than the maximum brightness outside the media boundary) to identify ultrasound lines passing through the calcified lesion. In other words, ultrasound lines may be included / added to the representation 911 of the calcification angle / arc to aid in the identification of calcified lesions. A calcium score 913 may be shown on the same display unit or separately. Here, a two-dimensional calcium map 915 and / or a three-dimensional calcium map 917 may be shown. A representation of the lumen 919 may also be shown. Finally, a display 921 representing the calculation of the calcification / calcification score may be shown.

[0129] In some cases, the display output 901 can be used to determine a treatment strategy for treating endovascular lesions within a blood vessel. For example, a first numerical calcium score can be determined by observing a visual representation 911 of the calcium / calcification arc of the endovascular lesion, a two-dimensional calcium map 915 of the blood vessel, a three-dimensional calcium map 917 of the blood vessel, or a combination thereof. In some cases, calcification angles / arcs greater than 180 degrees can be assigned a score of two or three, and calcification angles / arcs less than or equal to 180 degrees can be assigned a score of zero or one. A second numerical calcium score can be obtained by observing a fluoroscopic image 903 of the blood vessel. For example, the fluoroscopic image 903 can be used to determine whether the calcified lesion has a thickness of 0.5 mm or less. If the calcified lesion has a thickness greater than 0.5 mm (e.g., as observed in the fluoroscopic image 903), the second numerical calcium score can be one or two. If the calcified lesion has a thickness less than or equal to 0.5 mm (e.g., as observed in the fluoroscopic image 903), the second numerical calcium score can be zero. Furthermore, a third numerical calcium score can be determined by measuring the length of the calcified lesion (e.g., using the designation 919). If the calcified lesion is longer than 5 mm, the third numerical calcium score can be one or two points. If the calcified lesion is shorter than or equal to 5 mm, the third numerical calcium score can be zero or one point. These are merely examples. Other calcium scoring parameters are conceivable. The sum of the first, second, and third numerical calcium scores can be determined. Treatment modalities can be selected based on the sum. In some cases, treatment modalities may include treatment using non-compliant balloons (e.g., angioplasty), treatment using high-pressure balloons (e.g., angioplasty), treatment using notched balloons (e.g., angioplasty), treatment using cutting balloons (e.g., angioplasty), treatment with rotational atherosclerotic devices, treatment with orbital atherosclerotic devices, treatment with laser atherosclerotic devices, treatment with intravascular ultrasonic lithotripsy, combinations thereof, etc.

[0130] The process and / or display output can be used to extract clinically relevant IVUS features, guide treatment strategies such as calcium management, present intuitive maps, and / or combine information on a single display unit or a group of display units.

[0131] Some example IVUS imaging systems that can be used with methods such as those disclosed herein include, but are not limited to, those disclosed in, for example, U.S. Patent Nos. 7,246,959, 7,306,561, and 6,945,938, and U.S. Patent Application Publications Nos. US2006 / 0100522, US2006 / 0106320, US2006 / 0173350, US2006 / 0253028, US2007 / 0016054, and US2007 / 0038111, all of which are incorporated herein by reference.

[0132] U.S. Patent Application Publication No. US2015 / 0073279 is incorporated herein by reference.

[0133] It should be understood that the present invention is merely illustrative in many respects. Changes may be made in details, particularly in terms of shape, size, and arrangement of steps, without departing from the scope of the invention. To the appropriate extent, this may include the use of any of the features of an example embodiment used in other embodiments. Of course, the scope of the invention is defined by the language of the appended claims.

Claims

1. A method for processing intravascular ultrasound images, the method comprising: collecting one or more ultrasound images of a blood vessel; wherein each of the one or more ultrasound images depicts a wall of the blood vessel; segmenting, with a processor, the ultrasound images; wherein the processor comprises a deep neural network; wherein segmenting comprises identifying one or more of a lumen boundary of the blood vessel and a media boundary for a media within the blood vessel; displaying, on a display device, a first image of the one or more ultrasound images; wherein the first image depicts a wall of the blood vessel; and displaying, on the display device, a visual representation of a calcification angle, a calcification arc, or both, wherein the visual representation of the calcification angle, the calcification arc, or both, is disposed on the first image radially outward of the lumen boundary and spaced radially outward from the wall of the blood vessel on the first image.

2. The method of claim 1, wherein segmenting comprises identifying the lumen boundary.

3. The method of any one of claims 1-2, wherein segmenting comprises identifying the media boundary.

4. The method of any one of claims 1-2, wherein the deep neural network is trained to identify the lumen boundary.

5. The method of any one of claims 1-2, wherein the deep neural network is trained to identify the media boundary.

6. The method of any one of claims 1-2, wherein the deep neural network is trained to identify the lumen boundary and the deep neural network is trained to identify the media boundary.

7. The method of claim 1, further comprising displaying, on the display device, a numerical indication of a stenosis region for the first image.

8. The method of claim 7, wherein the numerical indication of the stenosis region is displayed on or adjacent to the first image.

9. The method of claim 1, further comprising displaying, on the display device, a numerical indication of a plaque burden for the first image.

10. The method of claim 1, wherein the visual representation of the calcification angle comprises an arc disposed along a border region of the first image.

11. The method of claim 1, wherein the visual representation of the calcification arc comprises an arc disposed along a border region of the first image.

12. A method for processing intravascular ultrasound images, the method comprising: collecting a plurality of ultrasound images of a blood vessel; segmenting, with a processor, the ultrasound images; wherein the processor comprises a deep neural network; and wherein segmenting comprises identifying one or more of a lumen boundary of the blood vessel, a cross-sectional area of the blood vessel, a media boundary for a media within the blood vessel, a cross-sectional area of the media, a calcification angle of a calcification lesion within the blood vessel, a side branch location, or a combination thereof; displaying, on a display device, a first image of the plurality of ultrasound images; wherein the first image depicts a wall of the blood vessel; and displaying a visual representation of the calcification angle, the calcification arc, or both on the display device, wherein the visual representation of the calcification angle, the calcification arc, or both is disposed on the first image radially outward of the lumen boundary and spaced radially outward from the wall of the blood vessel on the first image.

Images