Systems and methods for monitoring vascular function - Patents.com

Abstract

A method for monitoring blood vessels, the method including using a system for monitoring vascular function to see, hear, and feel vascular function by imaging a patient's body to obtain vascular geometry, imaging the patient's body to obtain geometry of a location on the patient's body using image analysis, and analyzing vibrations of the patient's body at a location on the patient's body that includes the blood vessel. The method for monitoring vascular function includes illuminating one or more blood vessels through the patient's skin, capturing an image of at least one blood vessel, analyzing the at least one image, and calculating a parameter related to vascular function based on the image analysis. Related devices and methods are also described.

Description

[Technical field]

[0001] This application is a continuation-in-part of U.S. Patent Application No. 16 / 656,585, filed October 18, 2019, the entire contents of which are incorporated by reference as if fully set forth herein in their entirety. [Background technology]

[0002] The present invention relates generally to the field of vascular monitoring of patients. Some embodiments relate more particularly to the early diagnosis of impaired vascular function, and more particularly to the early detection of impaired vascular access in patients undergoing hemodialysis treatment. Some embodiments relate more particularly to the measurement of fistulas.

[0003] Dialysis vascular access (VA, fistula or graft) allows for life-saving hemodialysis treatment but also presents access related problems.

[0004] The term "VA" or "vascular access," in all its grammatical forms, is used throughout the specification and claims to mean all types of vascular access constructs, both biological and artificial, including, as some non-limiting examples, arteriovenous fistulas (AVs), artificial vascular grafts, and intravenous catheters.

[0005] One type of long-term access is an arteriovenous fistula. A surgeon connects an artery to a vein in an arm or leg, creating an arteriovenous fistula. When a surgeon connects an artery to a vein, the vein becomes wider and thicker, making it easier to place a dialysis needle. The fistula also has a larger diameter that allows blood to flow quickly back into the body. The purpose of the fistula is to allow high blood flow so that a large volume of blood can pass through the dialyzer. Over 25% of hospitalizations for hemodialysis (HD) patients in the United States are access-related. Over 30,000 patients required dialysis-associated arterial and venous thrombectomy in 2013.

[0006] The annual cost of access disease is estimated to be close to $1 billion.

[0007] VA function and patency are essential for optimal management of HD patients. Low VA flow and loss of patency can limit hemodialysis delivery, prolong treatment times, and lead to underdialysis, resulting in increased morbidity and mortality. In long-term VA, especially in grafts, thrombosis is the leading cause of loss of VA patency and increases healthcare costs.

[0008] The basic concept of VA monitoring and surveillance is that progressive stenosis occurs over variable intervals in the majority of VAs and, if detected and corrected (corrective procedures such as percutaneous transluminal angioplasty (PTA)), underdialysis can be minimized or avoided (dialysis dose protection) and rates of thrombosis can be reduced. Many monitoring and surveillance methods are available, including continuous VA flow, continuous dynamic or static pressures, recirculation measurements, and physical examinations.

[0009] Surveillance is the examination and evaluation of the VA using a physical examination (usually in the HD unit) to diagnose VA dysfunction and to detect dysfunction prior to VA loss and the presence of correctable impairments.

[0010] The physical examination may be used as a surveillance tool to rule out impending fistulas and low flow rates associated with graft failure.Typically, a VA examination has three components: inspection, palpation, and auscultation.

[0011] A simple visual inspection can reveal the presence of a lump, ischemic fingers, aneurysms, and abundant collateral veins. A strong pulse and weak tremor in the central vein of the anastomosis indicates outflow venous stenosis. The stenosis can be palpated, and the intensity and character of the bruit suggest the location of the stenosis. Focal accentuation of the bruit at the graft or venous anastomosis compared with adjacent sites suggests stricture or stenosis. The physical examination also includes an elevation test, which consists of lifting the limb with a VA and examining the access for normal collapse. This test is considered normal if the fistula collapses after elevating the organ above the patient's cardiac level.

[0012] Additional background art includes the following: ·Besarab, “Access Monitoring Is Worthwhile and Valuable”, Blood Purif 2006;24:77-89, February 2006 ·Ehsan Rajabi-Jaghargh, Rupak K Banerjee, “Combined functional and anatomical diagnostic endpoints for assessing arteriovenous fistula dysfunction”, World J Nephrol February 6, 2015;4(1):6-18 ISSN 2220-6124 ·Luc Turmel-Rodrigues, “Salvage of immature forearm fistulas for haemodialysis by interventional radiology”, Nephrol Dial Transplant. 2001 December;16(12):2365-71 ·Jurg Schmidli, "Editor's Choice Vascular Access":2018 Clinical Practice Guidelines of the European Society for Vascular Surgery (ESVS) Eur J Vasc Endovasc Surg (2018)55,757e818

[0013] The disclosures of all references cited above and throughout the specification, as well as the disclosures of all references cited in these references, are hereby incorporated by reference. Summary of the Invention [Means for solving the problem]

[0014] The present invention relates generally to automating vascular monitoring in patients, and more particularly to early diagnosis of impaired vascular function, and even more particularly to early detection of impaired vascular access in patients undergoing hemodialysis treatment.

[0015] According to aspects of some embodiments of the invention, there is provided a system for monitoring vascular function comprising an illumination source, a detector, a display, and a processor configured to identify a change in pulse wave velocity relative to a baseline measurement, identify a change in at least one parameter indicative of development of one or more collateral vessels relative to the baseline measurement, identify a change in diameter of the vessel relative to the baseline measurement, identify a change in a spectroscopic analysis of the vessel, correlate the identified changes (identified changes), and determine a probability of vascular dysfunction based on the correlated identified changes.

[0016] According to some embodiments of the invention, the at least one parameter indicative of development of the one or more collateral vessels comprises one or more of shape, density, and distance from the blood vessel.

[0017] According to some embodiments of the invention, the processor is configured to calculate a rate of change of at least one of the pulse wave velocity, the at least one parameter indicative of one or more of collateral vessel development, vessel diameter, and vessel spectroscopic analysis.

[0018] According to some embodiments of the invention, the blood vessel is in the patient's arm, and the processor is further configured to identify a change in collapse of the blood vessel when the patient's arm or leg is elevated.

[0019] According to some embodiments of the invention the processor is further configured to calculate a rate of change of vascular collapse when the patient's arm or leg is elevated.

[0020] According to some embodiments of the invention the processor is further configured to identify changes in the composition of blood flowing within the blood vessel.

[0021] According to aspects of some embodiments of the present invention, there is provided a system for monitoring vascular function comprising an illumination source, a detector, a display, and a processor configured to identify a change in at least one parameter indicative of development of one or more collateral vessels relative to a baseline measurement, and determine a probability of impairment of vascular function based on the identified change.

[0022] According to some embodiments of the invention, the processor is further configured to identify changes relative to baseline measurements in one or more of pulse wave velocity, vascular diameter, and vascular spectroscopic analysis, correlate the identified changes in one or more of pulse wave velocity, vascular diameter, and vascular spectroscopic analysis with identified changes in at least one parameter indicative of development of one or more collateral vessels, and determine a probability of impairment of vascular function based on the correlated changes.

[0023] According to some embodiments of the invention, the blood vessel is located in an arm or leg of the patient, and the processor is further configured to identify a change in vascular collapse when the patient's arm or leg is elevated, correlate the identified change in vascular collapse when the patient's arm or leg is elevated with an identified change in at least one parameter indicative of development of one or more collateral vessels, and determine a probability of impairment of vascular function based on the correlated changes.

[0024] According to aspects of some embodiments of the invention, there is provided a method for monitoring vascular function comprising identifying a change in pulse wave velocity relative to a baseline measurement, identifying a change in a parameter indicative of collateral vessel development relative to the baseline measurement, identifying a change in vascular diameter relative to the baseline measurement, correlating the identified changes (discriminatory changes), and determining a probability of impairment of vascular function based on the correlated discriminatory changes.

[0025] According to some embodiments of the invention, the method further comprises calculating a rate of change of at least one of the pulse wave velocity, the at least one parameter indicative of one or more collateral vessel development and blood vessel diameter.

[0026] According to aspects of some embodiments of the present invention there is provided a method for monitoring vascular function comprising identifying a change in at least one parameter indicative of development of one or more collateral vessels relative to a baseline measurement and determining a probability of impairment of vascular function based on the identified change.

[0027] According to some embodiments of the invention, the method further includes identifying changes relative to baseline measurements in one or more of pulse wave velocity, vascular diameter, and vascular spectroscopic analysis; correlating the identified changes in one or more of pulse wave velocity, vascular diameter, and vascular spectroscopic analysis with the identified changes in at least one parameter indicative of development of one or more collateral vessels; and determining a probability of impairment of vascular function based on the correlated changes.

[0028] According to some embodiments of the invention, the blood vessel is in an arm or leg of the patient, and the method further comprises identifying a change in vascular collapse when the patient's arm or leg is elevated, correlating the identified change in vascular collapse when the patient's arm or leg is elevated with an identified change in at least one parameter indicative of development of one or more collateral vessels, and determining a probability of impairment of vascular function based on the correlated changes.

[0029] According to some embodiments of the invention, the method further comprises identifying changes in the composition of blood flowing within the vessel.

[0030] According to some embodiments of the invention, the blood vessel is in the patient's arm or leg and the measurement is taken while the patient's arm or leg is positioned approximately parallel to the ground.

[0031] According to some embodiments of the invention, the blood vessel is in the patient's arm or leg and the measurement is taken while the patient's arm or leg is positioned approximately perpendicular to the ground.

[0032] According to some embodiments of the invention, the blood vessel is in the patient's arm or leg, and the measurement is taken while the patient's arm or leg is lower than the patient's heart.

[0033] According to some embodiments of the invention, the blood vessel is in the patient's arm or leg and the measurement is taken while the patient's arm or leg is elevated above the patient's heart.

[0034] According to an aspect of some embodiments of the invention, there is provided a method for monitoring vascular function comprising illuminating one or more blood vessels through a patient's skin, capturing at least one image of the blood vessels, analysing the at least one image, and calculating a parameter related to the vascular function based on the image analysis.

[0035] According to some embodiments of the present invention, the method further comprises automatically detecting a location of a vascular access (VA) in the at least one image.

[0036] According to some embodiments of the invention, the method further comprises automatically detecting the location of the fistula in the at least one image.

[0037] According to some embodiments of the present invention, the method further comprises a step of a physician marking a location of a vascular access (VA) in the at least one image.

[0038] According to some embodiments of the invention, the step of capturing at least one image of the blood vessel is performed by a device configured to provide an image including at least one artery and at least one vein beneath the patient's skin.

[0039] According to some embodiments of the invention, irradiating one or more blood vessels through the patient's skin comprises transirradiating an organ of the patient.

[0040] According to some embodiments of the invention, calculating the parameter related to vascular function comprises calculating at least one parameter selected from the group consisting of pulse wave velocity, a parameter indicative of development of one or more collateral vessels, the number of collateral vessels, the diameter of the vessel, a spectral analysis of the vessel, the size of the arteriovenous fistula, and the size of the artificial vascular graft VA.

[0041] According to some embodiments of the invention, the method further comprises estimating a probability of impairment of vascular function based on the parameters.

[0042] According to some embodiments of the invention, the method further includes calculating a rate of change of one or more of the parameters based on performing several measurements of the one or more parameters at different times, some of the measurements being based on historical data associated with the patient retrieved from the database.

[0043] According to some embodiments of the invention, the method further comprises estimating a probability of impairment of vascular function based on the rate of change of the one or more parameters.

[0044] According to some embodiments of the present invention, the method further comprises estimating a maturity of the VA based on a rate of change of one or more parameters.

[0045] According to some embodiments of the present invention, the method further includes automatically detecting collateral veins by counting the number of veins in specific image regions in different images taken at different times.

[0046] According to some embodiments of the present invention, automatically detecting a location of a vascular access (VA) in the at least one image includes detecting the location of the VA by detecting an intersection of a vein and an artery.

[0047] According to some embodiments of the present invention, detection of vein-artery intersections is performed using a device capable of providing images of both arteries and veins beneath the patient's skin.

[0048] According to some embodiments of the present invention, automatically detecting a location of a vascular access (VA) in the at least one image comprises performing a spectral analysis of the at least one image.

[0049] According to some embodiments of the present invention, the method further includes measuring a parameter of the pulse wave by detecting the position of the pulse wave in two images taken at different times and comparing the positions of the pulse wave in the two images.

[0050] According to some embodiments of the invention, the method further includes measuring pulse wave velocity by detecting the position of the pulse wave in the two images, and dividing the distance along the centerline of the blood vessel in the two images by the time difference between capturing the two images.

[0051] According to aspects of some embodiments of the present invention, there is provided a method for replacing physical examinations performed by medical staff for monitoring vascular function of a dialysis patient, the method including generating at least one image of the patient's organ instead of manually manipulating the patient's organ, analyzing the at least one image, and classifying the patient's condition as being one of a condition suitable for dialysis or a condition at risk of stenosis.

[0052] According to some embodiments of the invention, the method further includes illuminating one or more blood vessels through the patient's skin, and analyzing the at least one image includes calculating a parameter related to vascular function based on the image analysis.

[0053] According to some aspects of embodiments of the present invention, there is provided a system for monitoring vascular function comprising an illuminator configured to illuminate a patient's blood vessel through the patient's skin, a camera configured to capture at least one image of the blood vessel through the patient's skin, an image analyzer configured to process the at least one image, a calculator configured to calculate a parameter related to the vascular function based on the image analysis, a classifier configured to classify the patient's condition as one of a condition suitable for dialysis or a condition at risk of dialysis, and a display configured to provide a caregiver with a report of the patient's condition and at least one of the parameters related to the vascular function.

[0054] According to an aspect of some embodiments of the present invention there is provided a system and method for measuring parameters related to a fistula.

[0055] In some embodiments, a system is provided that includes an optical device for acquiring one or more images of a fistula in the same patient along a surveillance period.

[0056] In some embodiments, one or more measurements and / or features are optionally extracted from the images and their changes over time are optionally monitored, in some embodiments the feature is a timeline derivative of a parameter measured or estimated in the images, as a non-limiting example of changes in the number and size of collateral veins occurring over a period of days / weeks / months etc.

[0057] In some embodiments, features of interest are derived from the graph representation of the identified vessels and / or changes in this representation over time, by way of non-limiting examples, changes in the number of junctions, the average or distribution of the number of branches at graph junctions.

[0058] In some embodiments, machine learning derived methods are used to identify patterns within the above changes that could potentially lead to significant clinical endpoints (e.g., fistula stenosis) before there are clinical signs or symptoms that a human nurse can identify.

[0059] In some embodiments, a system is provided for measuring a parameter related to a stoma by optical means.

[0060] In some embodiments, structured light is projected onto a patient's body or limb and the body is imaged. In some embodiments, the structured light can include horizontal and / or vertical stripes of equal or different widths, and / or various light patterns other than stripes.

[0061] In some embodiments, structured light imaging is used to provide information regarding the extent of the fistula, such as, as some non-limiting examples, the length of the long axis of the fistula along the body, the width of the short axis of the fistula along the body, the shape of the fistula as it appears in the image, the shape and / or segmentation of the fistula perimeter, the eccentricity index and / or aspect ratio of the fistula or segmented fistula, respectively, the smoothness and / or roughness index of the fistula contour.

[0062] In some embodiments, a pattern of structured light is projected onto the patient's body or limb and the body is imaged to provide information about the three-dimensional shape of a stoma or a body organ such as an arm, leg, etc.

[0063] In some embodiments, the system identifies changes in the shape of the fistula and / or body organ. In some embodiments, a projector is used to project one or more light patterns (e.g., structured light). In some embodiments, the method measures and / or estimates how the pattern deforms on the patient's organ to measure how the organ's shape and geometry change over time.

[0064] In some embodiments, a pattern of structured light is projected onto the patient's body or limb and the body is imaged to provide information about the three-dimensional shape of the fistula, e.g., one or more of the following: total or segmented fistula volume (e.g., needle insertion point), curvature function and variance, changes in shape / volume of the underlying arm / organ portion near the fistula, and three-dimensional surface features, e.g., smoothness and / or roughness.

[0065] In some embodiments, Laser Speckle Interferometry (LSI) is used. In some embodiments, LSI is used to record and observe vibrations of the fistula surface that correlate with internal blood flow and turbulence. Changes in blood flow and turbulence typically correlate with stenotic events and the potential occurrence of clinical conditions.

[0066] In some embodiments, imaging speckle light is used to provide information about dynamic effects within the fistula, e.g., heart rate, blood flow turbulence, and optionally generate a spectrogram of fistula vibrations.

[0067] In some embodiments, images of the body are taken a period of time apart and the differences between the images are optionally used to determine differences in the shape of the stoma.

[0068] In some embodiments, images are taken days, weeks, months, or years apart, and the differences between the images are optionally used to measure and / or monitor changes in size or shape of the fistula.

[0069] In some embodiments, images are taken seconds or minutes apart, for example with the hand held horizontally and then vertically, and the difference between the images is optionally used to measure and / or monitor whether at least a portion of the blood in the fistula is able to drain the fistula, the rate and / or extent of blood drainage from the fistula, or a particular portion of the fistula, such as, for example, collapse of the needle insertion point.

[0070] In some embodiments, images are taken at 1 second intervals as a video clip or movie, and the difference between image frames is optionally used to measure and / or monitor dynamic parameters associated with the fistula, such as heart rate, blood flow turbulence, etc., optionally generating a spectrogram of the fistula vibrations.

[0071] In some embodiments, analysis of changes in dynamic parameters associated with the fistula between imaging sessions is performed to monitor changes in the fistula and patient condition.

[0072] In some embodiments, implementing the above in conjunction with near infrared imaging potentially allows for the collection of data that correlates with tests required to be performed by nurses and / or physicians and has already been clinically proven to have predictive value for identifying stenosis events.

[0073] According to aspects of some embodiments of the present invention, systems and methods are provided for performing and recording two or more techniques or modalities, such as one or more of structured light, laser speckle interferometry, image analysis, and near-infrared imaging modalities, using a single imaging device.

[0074] In some embodiments, the system includes a processor and an imaging device including a Digital Light Processing (DLP) projector and a near-infrared camera.

[0075] According to aspects of some embodiments of the present disclosure, a method for monitoring blood vessels is provided, the method including using a system for monitoring vascular function to see, hear and feel the vascular function by imaging a patient's body to obtain a geometry of the blood vessel, imaging the patient's body to obtain a geometry of a location of the patient's body using image analysis, and analyzing vibrations of the patient's body at a location of the patient's body including the blood vessel.

[0076] According to some embodiments of the present disclosure, acquiring the shape of the location on the patient's body includes illuminating the location with structured light.

[0077] According to some embodiments of the present disclosure, analyzing the vibrations includes illuminating with laser speckle interferometry (LSI).

[0078] According to some embodiments of the present disclosure, the step of irradiating with the LSI is performed at a location based on the step of obtaining a geometry of the location on the patient's body using image analysis.

[0079] According to some embodiments of the present disclosure, the step of illuminating with the LSI is performed automatically by controlling a digital light processing (DLP) projector at the location.

[0080] According to some embodiments of the present disclosure, the step of illuminating with an LSI is performed by a physician directing the LSI illumination to a location on the patient's body.

[0081] According to some embodiments of the present disclosure, obtaining the geometry of the patient's body position includes calculating a three-dimensional (3D) geometry of the patient's stoma.

[0082] According to some embodiments of the present disclosure, the drainage rate of the patient's fistula is calculated based on changes in the 3D shape of the patient's fistula.

[0083] According to some embodiments of the present disclosure, this is performed during an elevation test.

[0084] According to some embodiments of the present disclosure, one or more parameters related to vascular function are calculated based on the image analysis.

[0085] According to some embodiments of the present disclosure, an estimate of the probability of impairment of vascular function is calculated based on one or more parameters.

[0086] According to some embodiments of the present disclosure, a prediction of when a blood vessel may be weakened is calculated based on one or more parameters.

[0087] According to some embodiments of the present disclosure, an estimate of the probability of impairment of vascular function is calculated based on the rate of change of one or more parameters.

[0088] According to some embodiments of the present disclosure, an estimate of the maturity of the VA is calculated based on the rate of change of one or more parameters.

[0089] According to some embodiments of the present disclosure, calculating the one or more parameters includes calculating a parameter indicative of development of one or more collateral vessels.

[0090] According to some embodiments of the present disclosure, calculating the one or more parameters includes calculating a number of collateral vessels.

[0091] According to some embodiments of the present disclosure, collateral veins are automatically detected by counting the number of veins in a particular image region in different images taken at different times.

[0092] According to some embodiments of the present disclosure, the location of a vascular access (VA) is automatically detected by detecting the intersection of a vein and an artery.

[0093] According to some embodiments of the present disclosure, the image analysis includes automatically detecting a location of a vascular access (VA) in at least one image.

[0094] According to some embodiments of the present disclosure, the image analysis includes automatically detecting a location of the fistula in at least one image.

[0095] According to some embodiments of the present disclosure, viewing the patient's vascular geometry includes capturing an image below the patient's skin that includes at least one artery and at least one vein.

[0096] According to some embodiments of the present disclosure, the patient's body is irradiated with near-infrared wavelengths.

[0097] According to some embodiments of the present disclosure, the illuminating includes using a digital light processing (DLP) projector.

[0098] According to some embodiments of the present disclosure, analyzing the vibrations of the patient's body includes analyzing light intensity at specific locations in an image of a location of the patient's body that includes the blood vessel.

[0099] According to some embodiments of the present disclosure, a spectrum is generated by generating a vector of light intensity at a particular location and converting the intensity vector to a frequency vector to generate a spectrum of vibrations.

[0100] According to some embodiments of the present disclosure, analyzing the vibrations includes analyzing a spectrum of the vibrations over a range of vibration frequencies. According to some embodiments of the present disclosure, the spectrum of the vibrations is in a range corresponding to frequencies that are audible to humans. According to some embodiments of the present disclosure, the spectrum of the vibrations is in a range corresponding to frequencies below audible to humans. According to some embodiments of the present disclosure, analyzing the vibrations of the body is in a range of frequencies below 1000 Hz.

[0101] According to some embodiments of the present disclosure, the step of analyzing the vibrations of the patient's body is performed by analyzing images captured at a frame rate of greater than 150 frames per second (FPS). According to some embodiments of the present disclosure, the step of analyzing the vibrations of the patient's body is performed by analyzing images captured at a frame rate of greater than 500 frames per second (FPS).

[0102] According to some embodiments of the present disclosure, the step of analyzing the vibrations of the patient's body is performed by analyzing selected pixels within the captured image.

[0103] According to some embodiments of the present disclosure, the pulse wave parameters are measured by detecting the location of the pulse wave in two images taken at different times and comparing the location of the pulse wave in the two images.

[0104] According to some embodiments of the present disclosure, pulse wave velocity is measured by detecting the location of the pulse wave in two images and dividing the distance along the centerline of the blood vessel in the two images by the time difference between capturing the two images.

[0105] According to aspects of some embodiments of the present disclosure, there is provided a method for replacing a physical examination performed by medical staff with monitoring of vascular function, the method comprising the steps of generating at least one image of an organ of a patient, analyzing the at least one image, and generating values ​​of a parameter related to the vascular function.

[0106] According to some embodiments of the present disclosure, the method further includes classifying the patient's condition as being one of suitable for dialysis or at risk for stenosis.

[0107] According to some embodiments of the present disclosure, one or more blood vessels are illuminated through the patient's skin, and analyzing at least one image includes calculating a parameter related to vascular function based on analysis of the images.

[0108] According to some embodiments of the present disclosure, this method is used instead of the physician performing a test that he or she sees, hears, and feels.

[0109] According to some embodiments of the present disclosure, the method is performed by an apparatus without contacting the patient's stoma. According to some embodiments of the present disclosure, the method is performed by an apparatus without contacting the patient's body.

[0110] According to some aspects of the present disclosure, there is provided a system for monitoring vascular function comprising an illumination unit configured to provide both a laser spot and structured light for laser speckle interferometry (LSI), a camera configured to image a location configured to be illuminated by the illumination unit, and a processor that processes images captured by the camera into extracted data regarding shape from the camera images obtained with the structured light and data regarding vibration from the camera images obtained with the LSI.

[0111] According to some embodiments of the present disclosure, there is further included a classifier that classifies the patient's condition as being one of suitable for dialysis or at risk for stenosis.

[0112] According to some embodiments of the present disclosure, the illumination portion includes a light source at near-infrared wavelengths.

[0113] According to some embodiments of the present disclosure, the illumination unit comprises a digital light processing (DLP) projector.

[0114] According to some embodiments of the present disclosure, the camera includes a camera capable of capturing images at a frame rate of greater than 150 frames per second (FPS).

[0115] According to some embodiments of the present disclosure, the camera has a resolution less than the maximum resolution of the camera and is capable of capturing images at a frame rate greater than 500 FPS.

[0116] According to some embodiments of the present disclosure, the support further comprises a support for the patient's limb, wherein the classifier classifies the patient's condition as one of a condition suitable for dialysis or a condition at risk of stenosis.

[0117] According to an aspect of some embodiments of the present disclosure, there is provided a method of calculating a number of collateral vessels, the method including imaging a patient's body to obtain vascular geometry and calculating the number of collateral vessels.

[0118] According to some embodiments of the present disclosure, calculating the number of collateral vessels includes automatically detecting collateral veins by counting the number of veins in a particular image region in different images taken at different times.

[0119] According to some embodiments of the present disclosure, the method further includes automatically detecting a location of a vascular access (VA) by detecting an intersection of a vein and an artery.

[0120] Unless otherwise defined, all technical and / or scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which the present invention pertains.Although methods and materials similar or equivalent to those described herein can be used in carrying out or testing embodiments of the present invention, exemplary methods and / or materials are described below.In case of conflict, the patent specification, including definitions, shall prevail.In addition, the materials, methods, and examples are illustrative only and are not necessarily intended to be limiting.

[0121] As will be appreciated by those skilled in the art, some embodiments of the present invention may be embodied as a system, a method, or a computer program product. Furthermore, some embodiments of the present invention may take the form of a computer program product embodied in one or more computer readable mediums having computer readable program code embodied thereon. Furthermore, some embodiments of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment (including firmware, resident software, microcode, etc.), or an embodiment combining software and hardware aspects, all of which may be generally referred to herein as a "circuit," "module," or "system." Implementation of the method and / or system of some embodiments of the present invention may include performing and / or completing selected tasks manually, automatically, or a combination thereof. Furthermore, according to the actual instrumentation and equipment of some embodiments of the method and / or system of the present invention, some selected tasks may be implemented by hardware, software, or firmware, and / or a combination thereof, for example using an operating system.

[0122] For example, hardware for performing selected tasks according to some embodiments of the present invention may be implemented as a chip or circuit. As software, selected tasks according to some embodiments of the present invention may be implemented as a number of software instructions executed by a computer using any suitable operating system. In an exemplary embodiment of the present invention, one or more tasks according to some exemplary embodiments of the methods and / or systems described herein are performed by a data processor, such as a computing platform for executing a number of instructions. Optionally, the data processor includes volatile memory for storing instructions and / or data, and / or non-volatile storage, such as a magnetic hard disk and / or removable media, for storing instructions and / or data. Optionally, a network connection is provided as well. A display and / or user input devices, such as a keyboard and / or mouse, are also optionally provided.

[0123] In some embodiments of the present invention, any combination of one or more computer readable media may be utilized. The computer readable media may be a computer readable signal medium or a computer readable storage medium. The computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples (non-exhaustive list) of computer readable storage media include electrical connections having one or more wires, portable computer diskettes, hard disks, random access memories, read only memories, erasable programmable read only memories, optical fibers, portable compact disk read only memories, optical storage devices, magnetic storage devices, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that contains or can store a program for use by or in connection with an instruction execution system, apparatus, or device.

[0124] A computer-readable signal medium may include a propagated data signal in which computer-readable program code is embodied, for example in baseband or as part of a carrier wave. Such a propagated signal may take any of a variety of forms, including but not limited to electromagnetic, optical, or any suitable combination thereof. A computer-readable signal medium is not a computer-readable storage medium, but may be any computer-readable medium that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, device, or apparatus.

[0125] The program code embodied on the computer readable medium and / or data used thereby may be transmitted using any suitable medium, including but not limited to wireless, wired, fiber optic cable, RF, etc., or any suitable combination of the foregoing.

[0126] Computer program code for carrying out operations for an embodiment of the present invention can be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as the "C" programming language or similar programming languages. The program code may be executed on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer, partially on a remote computer, or entirely on a remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet Service Provider).

[0127] Some embodiments of the present invention may be described below with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the present invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to generate a machine such that the instructions, executed via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions / acts specified in one or more blocks of the flowchart illustrations and / or block diagrams.

[0128] These computer program instructions may also be stored on a computer-readable medium that can direct a computer, other programmable data processing apparatus, or other device to function in a particular manner, such that the instructions stored on the computer-readable medium produce an article of manufacture that includes instructions that implement the functions / acts specified in one or more blocks of the flowcharts and / or block diagrams.

[0129] Computer program instructions may also be loaded into a computer, other programmable data processing apparatus, or other device and a series of operational steps executed on the computer, other programmable apparatus, or other device to generate a computer-implemented process such that the instructions executing on the computer or other programmable apparatus provide a process for implementing the functions / operations specified in one or more blocks of the flowcharts and / or block diagrams.

[0130] Some of the methods described herein are generally designed for computational use only and may not be feasible or practical for purely manual execution by a human expert. A human expert wishing to manually execute a similar task, such as monitoring a patient's blood vessels, is expected to use an entirely different method, e.g., leveraging the expertise and / or pattern recognition capabilities of the human brain, which is much more efficient than manually executing the steps of the methods described herein. [Brief description of the drawings]

[0131] Some embodiments of the present invention are described herein, by way of example only, with reference to the accompanying drawings and images. With particular reference now to the drawings in detail, it is emphasized that the particulars shown are by way of example and for the purpose of illustrative discussion of the embodiments of the present invention. In this regard, the description with reference to the drawings will make apparent to those skilled in the art how the embodiments of the present invention may be implemented. [Figure 1] FIG. 1 is a graph showing the probability of vascular access thrombosis occurring within a three month period depending on flow rate and change in flow rate, as reported by Besarab, “Access Monitoring Is Worthwhile and Valuable, Blood Purification,” February 2006. [Diagram 2] 1 is a simplified diagram of a system for measuring blood vessels, according to an exemplary embodiment of the present invention. [Diagram 3] 1 is a simplified block diagram of a system for measuring blood vessels, in accordance with an exemplary embodiment of the present invention; [Figure 4A] 4 is a simplified flow chart of an algorithm according to an exemplary embodiment of the present invention. [Figure 4B] 4 is a simplified flow chart of an algorithm according to an exemplary embodiment of the present invention. [Figure 4C] 4 is a simplified flow chart of an algorithm according to an exemplary embodiment of the present invention. [Figure 4D]4 is a simplified flow chart of an algorithm according to an exemplary embodiment of the present invention. [Figure 4E] 4 is a simplified flow chart of an algorithm according to an exemplary embodiment of the present invention. [Figure 5A] 1 is a simplified diagram of a pulse wave traveling along a vein. [Figure 5B] 1 is a simplified diagram of a pulse wave traveling along a vein. [Figure 6] 1 is a simplified flowchart of a classification method according to an exemplary embodiment of the present invention. [Figure 7] 1 is a simplified block diagram of a system for measuring blood vessels, in accordance with an exemplary embodiment of the present invention; [Figure 8A] 1 is an image of optical components in a system constructed in accordance with an exemplary embodiment of the present invention. [Figure 8B] 1 is an image of optical components in a system constructed in accordance with an exemplary embodiment of the present invention. [Figure 9] 4 is a simplified flow chart of a method of segmentation according to an exemplary embodiment of the present invention. [Figure 10] 4 is a simplified flowchart of a registration method according to an exemplary embodiment of the present invention. [Figure 11] 1 is a simplified flow chart of a method according to an exemplary embodiment of the present invention. [Figure 12] 1 is a simplified flow chart of a method according to an exemplary embodiment of the present invention. [Figure 13] 1 is a simplified flow chart of a method according to an exemplary embodiment of the present invention. [Figure 14] 1 is a simplified flowchart of a classification method according to an exemplary embodiment of the present invention. [Figure 15] 1 shows three different images of the same patient's arm, according to an exemplary embodiment of the present invention. [Figure 16A] 1 is a table showing the steps a medical professional can take to examine a patient for vascular stenosis or thrombosis. [Figure 16B] 1 is a simplified flowchart of a method for testing a patient, according to an exemplary embodiment of the present invention. [Figure 17] 1 is a simplified block diagram of a method for testing a patient, according to an exemplary embodiment of the present invention. [Figure 18] 1 shows images of a patient's fistula taken at two different times. [Figure 19A] 1 is a simplified diagram of a system for monitoring vascular access (VA) and / or fistulas, according to two exemplary embodiments of the present invention. [Figure 19B] 1 is a simplified diagram of a system for monitoring vascular access (VA) and / or fistulas, according to two exemplary embodiments of the present invention. [Figure 20] 1 is an image of a system for monitoring a vascular access (VA) and / or fistula, according to an exemplary embodiment of the present invention. [Figure 21] Three different images of the same patient's arm are shown. [Figure 22A] 1 is a graph showing the power spectrum of vibrations measured by analysis of images produced by laser speckle imaging. [Figure 22B] 2 is a simplified flowchart illustration of a method for converting data from a stream of images to a frequency spectrum, according to an example embodiment of the present invention. [Figure 23] 1 is a simplified flowchart of a method for monitoring vascular function, according to an exemplary embodiment of the present invention. [Figure 24] 1 is a simplified flow chart of a method for replacing a physical exam performed by medical staff to monitor vascular function, according to an exemplary embodiment of the present invention. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0132] The present invention relates generally to the field of vascular monitoring of patients. Some aspects relate more particularly to early diagnosis of impaired vascular function, and more particularly to early detection of impaired vascular access in patients undergoing hemodialysis treatment. Some aspects relate more particularly to measurement of fistulas.

[0133] (Introduction) Surveillance by physical examination is a cost-effective and proven method for detecting VA abnormalities. However, nephrologists and HD staff generally have limited availability and are poorly informed. As a result, routine physical examinations of VA are not generally performed in HD units.

[0134] Moreover, due to the complex nature of the VA, surveillance strategies cannot consistently detect stenosis under different scenarios. Although low VA flow is associated with an increased risk of thrombosis, the association does not have sufficient accuracy in predicting thrombosis. In contrast, surveillance of VA flow and dynamic or static pressure was found to be inaccurate predictors of graft thrombosis, resulting in many unnecessary interventional procedures instead of preventing thrombosis. Moreover, PTA induces neointimal hyperplasia (NIH), mechanical trauma with associated risk of stenosis and impaired VA survival.

[0135] Both flow and pressure vary during dialysis and, more importantly, from patient to patient, making each single measurement a potentially inaccurate predictor of stenosis, and therefore thrombosis, and may go unnoticed as developing obstruction progresses.

[0136] If outflow were the only cause of stenosis, a hyperbolic relationship between flow pressure and access pressure would be expected to occur within a given access. However, this is not the case. Obstructions occur within the inflow and access body, and on average, a typical access has nearly two obstruction / access locations at reference. Obstructions change the relationship between flow and pressure. Because of these confounding factors due to anatomical factors and location of the stenosis, there is little, if any, correlation between single measurements of flow and pressure.

[0137] Reference is now made to FIG. 1, which is a graph showing the probability of vascular access thrombosis occurring within a three month period depending on flow rate and change in flow rate, as reported by Besarab, “Access Monitoring Is Worthwhile and Valuable,” Blood Purification, February 2006.

[0138] The graph in FIG. 1 includes a Y-axis 101 that shows the probability of vascular access thrombosis occurring within a three month period, a number of lines 103 that show flow rate in ml / min, and an X-axis 102 that shows the change in flow rate per month in ml / min.

[0139] Figure 1 shows that the probability of vascular access thrombosis occurring within a three-month period depends not only on the absolute flow rate at any given time, but also on the rate of change in flow rate, if there is a change in flow rate (Besarab, "Access Monitoring Is Worthwhile and Valuable," Blood Purification, February 2006).

[0140] An access with an initial flow rate of 600 ml / min and a decrease in flow rate of 20 ml / min per month had a lower probability of thrombosis (22%) than an access with an initial flow rate of 1200 ml / min and a decrease in flow rate of 100 ml / min (38%), even though the absolute flow rate was lower in the former (540 ml / min) than in the latter (900 ml / min) at the beginning of the observation period.

[0141] Therefore, there is a need for a monitoring solution that can detect stenosis formation early and predict thrombosis, and that overcomes at least some of the following shortcomings of existing monitoring practices:

[0142] There is poor adherence by dialysis centers to routine VA physical exams, as outlined in the following guidelines: Inherent inaccuracies associated with a single physical examination or VA pressure / flow measurement Inherent inaccuracies in a single parameter such as flow rate or pressure The results of routine measurements may be influenced by extraneous hemodynamic events. Measurements by different caregivers may lead to discrepancies.

[0143] (overview) An aspect of some embodiments of the present invention relates to replacing or supplementing physical exams performed by medical staff / nurses.

[0144] When nurses or doctors examine a patient's blood vessels, they typically perform a three-step test: seeing, listening and feeling.

[0145] An aspect of some embodiments relates to implementing seeing, hearing, and feeling through instrumental measurements and computerized analysis.

[0146] In some embodiments, the systems described herein perform seeing, hearing, and feeling based on illuminating and imaging a patient's limb and analyzing data collected from the imaging. In some embodiments, the system teaches how to predict fistula conditions, potentially allowing for early prevention of failure.

[0147] In some embodiments, the methods described herein perform the seeing, hearing, and feeling based on illuminating and imaging the patient's limb and analyzing the data collected from the imaging. In some embodiments, the system teaches how to predict fistula status, potentially allowing for early prevention of failure.

[0148] In some embodiments, blood flow is measured in a non-invasive manner based on image processing of images of blood vessels within the human body. Physiological parameters known to affect vascular access (VA) are measured, and the measurements are optionally used to determine whether the patient should be scheduled for a corrective procedure or proceed to undergo dialysis.

[0149] An aspect of some embodiments relates to performing sensing, as described herein, by instrumental measurements and computerized analysis.

[0150] In some embodiments, listening, as described herein, is performed by an appliance, optionally the same appliance.

[0151] In some embodiments, the viewing, as described herein, is performed by an instrument, optionally the same instrument.

[0152] An aspect of some embodiments of the present invention relates to the automated detection and / or monitoring of arteriovenous fistulas in vascular images.

[0153] In some embodiments, images of blood vessels are analyzed and the location where the artery connects to the vein is determined to be, optionally, the location of the arteriovenous fistula.

[0154] In some embodiments, images of blood vessels are analyzed and locations where arteries appear to connect to veins are optionally determined to be locations of arteriovenous fistulas.

[0155] In some embodiments, images of blood vessels are analyzed and arteriovenous fistulas are optionally measured to estimate geometric properties.

[0156] An aspect of some embodiments of the present invention relates to the automated, non-invasive measurement of parameters related to blood flow.

[0157] In some embodiments, the non-invasive measurements include imaging blood vessels through the skin using reflected and / or transmitted light.

[0158] In some embodiments, the probability of vascular access failure is optionally estimated, hi some embodiments, the estimation is based on one or more of the measured parameters.

[0159] In some embodiments, the probability of occlusion formation is optionally estimated, hi some embodiments, the estimation is based on one or more of the measured parameters.

[0160] In some embodiments, the probability of thrombus formation is optionally estimated, hi some embodiments, the estimation is based on one or more of the measured parameters.

[0161] In some embodiments, the grade of the stenosis is optionally estimated, hi some embodiments, the estimation is based on one or more of the measured parameters.

[0162] In some embodiments, the rate of stenosis formation is optionally estimated, hi some embodiments, the estimation is based on one or more of the measured parameters.

[0163] In some embodiments, the VA maturity grade is optionally estimated, hi some embodiments, the estimation is based on one or more of the measured parameters.

[0164] In some embodiments, the rate of VA maturation is optionally estimated, hi some embodiments, the estimation is based on one or more of the measured parameters.

[0165] An aspect of some embodiments of the present invention relates to providing visual reports to a caregiver.

[0166] Listed below are one or more attributes associated with some embodiments of the invention. 1. One or more patient-related parameters, including images, are readily available for measurement in a manner that is potentially cost-effective and / or non-invasive (optionally non-contact) and / or integrated into routine dialysis appointments. 2. Inputs to the algorithms described herein optionally include one or more patient-related parameters to estimate the probability of vascular access failure, each of which may be available on a single measurement basis or as multiple measurements along a time axis. 3. Some of the patient-related parameters are obtained using objective measurements and potentially do not require high competence from users such as patients and / or medical professionals. 4. Some of the patient-related parameters are optionally obtained from the patient's particular medical record and include elements such as demographics (e.g., age, sex, weight, and height), laboratory tests, imaging tests (e.g., x-ray, MRI), and physical exam results. It will be apparent to one skilled in the art that the parameters can be extracted in multiple ways, for example, by typing test results directly into a keyboard connected to a system as described herein, a computer process accessing electronic medical records using a particular patient ID, speech-to-text conversion, voice recognition algorithms applied to staff verbal analysis, and OCR of printouts / paper documents.

[0167] Measurement of VA Maturity: VAs have a unique tissue structure when compared to veins and arteries. This structure changes during the process of VA maturation and during the process of stenosis.

[0168] Structural changes affect the mechanical and optical properties of the VA and therefore monitoring of the changes can potentially be measured in some embodiments by one or more of the following: Imaging: by measuring changes in contrast or intensity of reflected and / or transmitted light, as a non-limiting example. Non-imaging: Intensity of reflected or transmitted light. Measurement of scattering and absorption coefficients (e.g., two-distance steady-state photon transfer measurements).

[0169] For example, in some embodiments, the system is configured to detect veins, and monitoring the VA during the maturation period potentially changes the detection results. In one example of optical sensing, the response of the VA to light (one or more of transmission, reflection, absorption, scattering) potentially changes over the maturation period. Monitoring the maturation is potentially beneficial to increase the success rate of VA maturation by suggesting timely preemptive correction. Measurement of vessel layers, or ratio between vessel layers, or change in ratio between layers, or change in absolute value of layers during the maturation or stenosis process.

[0170] The accuracy of estimating maturation (maturity level, stage, rate, completion) or the probability of vascular access failure, occlusion formation, and thrombus probability can be improved by using one or more parameters generated from non-invasive measurements. The parameters used can be measured directly or can be the result of pre-processing applied to the measurements. Such pre-processing can be the application of various algorithms as well as the combination of several parameters and the utilization of multiple measurements over time.

[0171] Below are examples of metrics or phenomena that are optionally extracted and used in some embodiments of the present invention.

[0172] 1. Pulse Wave Velocity - in some embodiments, detecting reflection or absorption of optical radiation from at least two points in an image frame. In some embodiments, the change in electrical impedance measured by electrodes placed between and / or along the vessel or tissue region. Optionally, the two points include a portion known to be prone to stenosis. More generally, at least one point is used to measure the shape of the pulse wave (e.g., pulse wave amplitude, Full-Width Half Max (FWHM), etc.).

[0173] In some embodiments, the pulse wave amplitude is optionally measured. An optional method for measuring the pulse wave amplitude includes measuring a first measurement of an area at a location along a vein identified as a dilation of the blood vessel due to a pulse wave. The area at the same location in another image when there is no pulse wave at that location is also measured in a second measurement. The difference between the first measurement and the second measurement is optionally related to the pulse wave amplitude. In some embodiments, the pulse wave amplitude is considered a feature corresponding to the mechanical properties of all and / or mature veins of the AV through which the pulse wave travels.

[0174] In some embodiments, Pulse Wave Analysis (PWA) is optionally performed to assess variances related to vascular stiffness associated with additional risk factors such as cardiovascular disease or atherosclerosis, which may affect VA survival over time. In some embodiments, pulse quality is optionally scored, and changes over time and between different segments are optionally included in the analysis.

[0175] 2. The appearance and development of collateral veins and their characteristics, such as density, size, distance from the VA, orientation, filling, etc., by imaging and / or other detection methods, for example, measuring contrast by absorption of light at visible or NIR wavelengths, or by emission at far infrared wavelengths. Other measurement options include measuring the amount of change in absorption in the visible and near infrared, and the amount of emission in the far infrared. Another optional method for measuring the development of collateral circulation is, optionally, measuring the temperature change around the VA. In some embodiments, the detection of the appearance and development of collateral veins optionally uses reference images or measurements obtained from previous examinations. In some embodiments, optional trend analysis of the rate of collateral vein development uses frequent examinations. Examinations are optionally performed daily, every dialysis session, weekly, biweekly, or monthly.

[0176] In some embodiments, collateral veins are detected by comparing a new image with a previous image and counting the veins, and an increase in the number of veins is optionally taken to mean that the new vein is a collateral vein.

[0177] In some embodiments, the appearance and / or development of collateral veins is detected by extracting features from a single image or measurement.

[0178] Rationale: Detection of collateral vessels potentially indicates a flow-limiting (hemodynamically significant) disorder. Collateral vessels can develop, enlarge, and dissipate increased intra-access pressures in the setting of outflow stenosis.

[0179] 3. Minimum diameter of blood vessel (area of ​​stenosis) determined by image processing. 4. Detection of stenosis points by estimation of mechanical reflected waves or local pressure / flow changes, for example by measuring electrical impedance changes. 5. Maximum diameter of blood vessel by image processing (appearance and size of aneurysm). 6. Detection of vascular collapse when the arm or leg is elevated. 7. Use of near infrared (NIR) (700-1000 nm) reflectance and / or displacement spectroscopy to measure the amount of oxygenated and deoxygenated hemoglobin (Hb). 8.Spectroscopic analysis of oxygenated and deoxygenated hemoglobin (Hb). 9. Audible VA noise. 10. Palpable pulsation (tremor) in VA. 11. Analysis of electrical impedance changes in the VA using signal processing methods known in the art. 12. In some embodiments where multiple measurements of the same parameter are taken over time, the measurements may be synchronized according to the detected respiratory cycle and sorted for the detection algorithm with respect to their relative time along the respiratory cycle. Such synchronization and sorting is potentially beneficial, for example, when assessing changes in oxygen mixture over time, but may also improve the accuracy of other measurements, such as pulse wave velocity.

[0180] The output of a system as described herein may be in the form of an audible alarm, a visual alarm, an image, a sequence of images, or a video that provides guidance to the medical practitioner for rapid and accurate intervention (e.g., giving recommendations to the medical practitioner regarding the best location for intervention). The system may recommend treatment (PTA, no intervention, thrombectomy) for the patient. The recommendation is optionally based on information collected by the system.

[0181] According to an aspect of some embodiments of the present invention, the output of the system during the test is optionally analyzed and / or optionally used to guide the patient through the test in order to perform the test correctly. As a non-limiting example, the elevation test verifies that the limb height / position is correct. In some embodiments, there is also an alert to the nurse / technologist if the patient is not performing the test correctly or needs help.

[0182] In some embodiments, the above-mentioned outputs are optionally used to support a remote physical examination performed by the patient, while the system provides feedback regarding the correct performance of the examination and / or alerts remote support personnel, such as a nurse or technician, that additional guidance is required.

[0183] In some embodiments, system outputs are optionally provided differently to different consumers of the data: for example, a dialysis nurse is optionally provided with a general interpretation regarding the likelihood of clinically meaningful stenosis formation, and an interventional radiologist is optionally alerted with annotated images and / or a report that optionally highlights parameters such as the location, severity, and rate of stenosis formation.

[0184] According to an aspect of some embodiments of the present invention there is provided a system and method for measuring parameters associated with a fistula.

[0185] In some embodiments, a system is provided that includes an optical device for acquiring one or more images of a fistula in the same patient along a surveillance period.

[0186] In some embodiments, one or more measurements and / or features are optionally extracted from the images and their changes over time are optionally monitored, in some embodiments the features are timeline derivatives of parameters measured or estimated in the images, by way of non-limiting examples changes in number, branching, and size of collateral veins over a period of days / weeks / months, etc.

[0187] In some embodiments, machine learning derived methods are used to identify patterns within the above changes that could potentially lead to significant clinical endpoints (e.g., fistula stenosis) before there are clinical signs or symptoms that a human nurse can identify.

[0188] In some embodiments, a system is provided for measuring a parameter associated with a stoma by optical means.

[0189] In some embodiments, structured light is projected onto a patient's body or limb and the body is imaged. In some embodiments, the structured light can include horizontal and / or vertical stripes of equal or different widths, and / or various light patterns other than stripes.

[0190] In some embodiments, structured light imaging is used to provide information about the extent of the fistula, e.g., the length of the long axis of the fistula along the body, the width of the short axis of the fistula along the body, the shape of the fistula as it appears in the image, segmentation of the perimeter of the fistula, the eccentricity and / or aspect ratio of each segment, the smoothness and / or roughness of the fistula contour.

[0191] In some embodiments, a pattern of structured light is projected onto the patient's body or limb and the body is imaged, providing information about the three-dimensional shape of the stoma or organ.

[0192] In some embodiments, the system identifies changes in the shape of the fistula and / or the organ near the fistula. In some embodiments, a projector is used to project one or more light patterns (e.g., structured light). In some embodiments, the method measures and / or estimates how the pattern deforms on the patient's organ to measure how the organ's shape and geometry change over time.

[0193] In some embodiments, a pattern of structured light is projected onto the patient's body or limb and the body is imaged to provide information regarding the three-dimensional shape of the fistula, characteristics and / or variance of curvature, changes in shape and / or volume of the underlying arm / organ section near the fistula, and three-dimensional surface characteristics such as smoothness and / or roughness, as some non-limiting examples of the entire fistula or a segment portion of the fistula (e.g., needle insertion point).

[0194] In some embodiments, laser speckle interferometry (LSI) is used. In some embodiments, LSI is used to record and observe the vibrations of the fistula surface that correlate with the internal blood flow and turbulence. Changes in blood flow and turbulence typically correlate with stenotic events and the potential occurrence of clinical conditions.

[0195] In some embodiments, imaging speckle light is used to provide information about dynamic effects within the fistula, e.g., heart rate, blood flow turbulence, and optionally generate a spectrogram of fistula vibrations.

[0196] In some embodiments, images of the body are taken at intervals and the differences between the images are optionally used to determine differences in stoma shape.

[0197] In some embodiments, images are taken days, weeks, months, or years apart, and the differences between the images are optionally used to measure and / or monitor changes in size or shape of the fistula.

[0198] In some embodiments, images are taken seconds or minutes apart, for example with the hand held horizontally and then with the hand held vertically, and the difference between the images is optionally used to measure and / or monitor one or more of: whether at least a portion of the blood in the fistula is able to drain the fistula, the rate of blood drainage, the extent of blood drainage from the fistula, and / or a particular portion of the fistula, and collapse of one or more needle insertion points.

[0199] In some embodiments, images are taken at second intervals as a video clip or movie, and the differences between image frames are optionally used to measure and / or monitor dynamic parameters associated with the fistula, such as heart rate, blood flow turbulence, etc., optionally generating a spectrogram of the fistula vibrations.

[0200] In some embodiments, the spectrogram is optionally generated by selecting one or more pixels in the image frame that show large, or even the largest, variations in intensity over time. In some embodiments, the number of pixels selected is optionally in the range of 1 to 100 pixels. In some implementations, the pixel intensity values ​​of this or these pixels are used to calculate a function of time light intensity. In some embodiments, the frequency spectrum of light intensity is optionally generated by converting from the time domain to the frequency domain, for example by a Fast Fourier Transform (FFT).

[0201] In some embodiments, analysis of changes in dynamic parameters associated with the fistula between imaging sessions is performed to monitor changes in the fistula and patient condition.

[0202] In some embodiments, implementing the above in conjunction with near infrared imaging potentially allows for the collection of data that correlates with tests required to be performed by nurses and / or physicians and has already been clinically proven to have predictive value for identifying stenosis events.

[0203] In accordance with an aspect of some embodiments of the present invention, systems and methods are provided for performing and recording two or more techniques or modalities, such as one or more of structured light, laser speckle interferometry, image analysis, and near-infrared imaging modalities, using a single imaging device.

[0204] In some embodiments, the system includes a processor and an imaging device including a digital light processing (DLP) projector and a near-infrared camera.

[0205] According to an aspect of some embodiments of the present invention there is provided a system and method for analyzing vibrations of light reflected from a patient's body.

[0206] In some embodiments, cardiac pulsatility is monitored.

[0207] In some embodiments, analyzing the pattern of vibrations caused by flow through or near the fistula is optionally to detect complete or partial obstruction of either the inflow or outflow pathways.

[0208] In some embodiments, applying localized pressure to either the inflow or outflow pathways while analyzing the pattern of vibrations caused by flow through or near the fistula is, optionally, to detect complete or partial obstruction of either the inflow or outflow pathways.

[0209] In some embodiments, analyzing the vibrations is optionally to detect the onset of flow through the fistula associated with normal cardiac activity (diastole or systole of the cardiac cycle).

[0210] In some embodiments, analyzing the vibrations is to detect the initiation of flow through the fistula, which optionally corresponds to a sudden release (partial or complete collapse or dilation of the fistula).

[0211] In some embodiments, analyzing the vibrations is optionally to detect periods of blood flowing into the fistula, followed by a sudden opening of the obstruction that allows blood to flow out of the fistula. Such an opening may occur during high pressures during systole. In some cases, the sudden opening is referred to as hammering. In some embodiments, hammering is detected by measuring the amplitude of the vibrations, optionally relative to the amplitude at other times, for example, during a heartbeat.

[0212] In some embodiments, analyzing the oscillations associated with flow onset for any or all types of onset is optionally measuring a parameter value, or a change in a parameter value, or a change in a characteristic parameter value, or a variance in a parameter value. The parameters can be one or more of intensity, energy, onset steepness (derivative of value), relaxation time, time width, duty cycle, spectral content, spectral width, or any combination thereof.

[0213] In some embodiments, analyzing the oscillations associated with the onset of flow optionally involves measuring a parameter value associated with a time delay or phase delay between onsets associated with sudden release and onsets associated with normal cardiac activity.

[0214] In some embodiments, analyzing the oscillations associated with the initiation of the flow optionally comprises measuring a parameter value related to the regularity or self-similarity of a series of initiations of the same source.

[0215] Before describing at least one embodiment of the invention in detail, it is to be understood that the invention is not necessarily limited in its application to the details of construction and the arrangement of components and / or methods set forth in the following description and / or illustrated in the drawings and / or examples, as the invention is capable of other embodiments or of being practiced or carried out in various ways.

[0216] Reference is now made to FIG. 2, which is a simplified diagram of a system for measuring blood vessels in accordance with an exemplary embodiment of the present invention.

[0217] FIG. 2 shows a high-level overview of an exemplary system 200 for measuring blood vessels.

[0218] In some embodiments, the system 200 may include at least one illumination source 202 and at least one detector 204, such as a camera.

[0219] In some embodiments, the system 200 may further include a control unit 206 that optionally activates the illumination source 202 and the camera 204, and an optional processor 208 that optionally receives and analyzes images generated by the camera 202.

[0220] In some embodiments, images and / or data generated following analysis of the images may be displayed on an optional display 210 connected to the processor 208, either wirelessly or via a wired connection.

[0221] In some embodiments, the processor 208 and the display 210 may be implemented in a single device, such as a laptop, tablet, or smartphone. In some embodiments, a scanning system may be applied that optionally moves the detection unit (automatically or manually) and optionally scans the organ at multiple points. Figure 2 illustrates the system 200 applied to an arm 212.

[0222] The systems and methods can be implemented with other organs, including but not limited to.

[0223] Reference is now made to FIG. 3, which is a simplified block diagram of a system for measuring blood vessels in accordance with an exemplary embodiment of the present invention.

[0224] FIG. 3 illustrates a top-level block diagram of an exemplary system.

[0225] In some embodiments, the system may include at least two main units: a detection unit 302 and a software unit 306 .

[0226] The system may include additional units such as a workstation 304 and an optional cloud infrastructure 308.

[0227] In some embodiments, the software unit 306 includes at least two sub-units: an embedding unit 330 and an algorithmic unit 334. The software unit 306 may include additional blocks, such as a graphical user interface unit 332.

[0228] (Detection unit) In some embodiments, the detection unit 302 optionally uses: 1. Visual / optical detection to obtain an image containing information that can be further analyzed. 2.Speckle Imaging - When an object is illuminated with laser light, the backscattered light forms an interference pattern consisting of dark and bright areas. This pattern is called the speckle pattern. If the object being illuminated is static, the speckle pattern is stationary. If there is movement of objects such as red blood cells in tissue, the speckle pattern changes with time. The speckle image contains information related to the changes in the blood vessels, which can be optionally analyzed and extracted by image processing. 3. Dark field side illumination a. Specular light that does not reach the camera b. Only diffuse scattered light captured by the camera c. Reduction of surface reflection d. The contrast profile changes with changing source and detector angles. 4. Trans-illumination - Illuminating the backside of the sample. The sample is placed between the illumination source and the sensor device. Trans-illumination potentially improves image contrast and / or potentially increases the depth at which blood vessels can be imaged. 5. Photoacoustic imaging potentially enhances contrast between different media due to differences in the changes in the optical properties of different media. Photoacoustic imaging potentially reduces scattering in tissue due to averaging of refractive index gradients in tissue components, potentially resulting in greater penetration depth of light.

[0229] In some embodiments, the detection unit 302 optionally includes one or more of the following components: 1. One or more detectors / sensors / cameras 310 (e.g., CCD or CMOS, InGaAs sensors, microbolometers) are sensitive to one or more of visible, near infrared, and short wavelength infrared (SWIR) light. In some embodiments, the sensor frame rate can range from a single frame to a high frame rate. The sensor frame rate optionally ranges, for example, from 5, 10, 16, 24, 30, 50, 60, 100, 165, 200, and even up to 300 frames per second (fps). 2. One or more lenses 312 (zoom or fixed focal length) and / or filters 3. One or more illuminators 314 or emitters (e.g., coherent or non-coherent, narrow spectrum or broadband, UV, visible, SWIR, far infrared, near infrared - e.g., near infrared induction or green (532 nm) laser). The emitters may be coaxial or at different angles to the detector 310 and VA. The mode of operation can be still or video. 4. One or more polarizing filters (elliptical and / or linear) 5. One or more optical bandpass filters 6. The detection unit optionally includes a scanning system or a moving bar scanner.

[0230] In some embodiments, the detection unit 302 optionally uses an audio / sound detection sensor 316 instead of or in addition to visual / optical detection, and the detection unit 302 may optionally include one or more audio sensors.

[0231] In some embodiments, the detection unit 302 may include a vital signs sensor.

[0232] (Software Unit) In some embodiments, the software unit 306 may include one or more of the following components: 1. GUI - A graphic user interface / application 332 for one or more of operating the examination procedure, displaying images and / or results, and / or inserting or importing patient clinical information. 2. Embedder 330 - for controlling the detection unit 302. 3. Algorithm Unit 334 - The algorithm unit optionally contains algorithms or software modules for image processing, machine learning (ML).

[0233] In some embodiments, the input of the ML algorithm is optionally images and / or data captured by the detection unit 302.

[0234] In some embodiments, the input may also include the patient's clinical information and / or vital signs.

[0235] In some embodiments, the workstation 304 optionally includes a computer, a screen, a keyboard, one or more knob controls, a mechanical interface for an imaging unit, and an interface to a power source or electrical power. In some embodiments, the workstation 304 may also include an "organ fixation surface."

[0236] In some embodiments, the workstation 304 optionally includes one or more of the following: a control unit 320 for controlling the operation of the detection unit 302 and / or one or more components of the detection unit 302; Computer 320 Display 324 Optionally, an organ fixation surface or device 326 for positioning the organ in a specific position relative to the illuminator 314 and / or detector 310. A stand 328 for positioning the components of the system in specific positions relative to the patient's organs.

[0237] In some embodiments, the cloud infrastructure 308 optionally includes one or more of the following cloud services: Virtual memory (database) server 340 Web Application Server 336 Computing services for machine learning, such as improved algorithm(s) based on new data, and / or for analytics, to provide users with measurements of features and metrics, and / or for insights, to provide metrics related to the current or predicted future clinical state of the VA.

[0238] The machine learning algorithms can be supervised or unsupervised, learning based on images and / or patient parameters generated by embodiments of the present invention, and / or databases of patients, diseases, vital signs, parameters from the dialysis machine, and / or other data available in the electronic medical record, optionally including the patient's previous interventions, additional risk factors, comorbidities, etc.

[0239] The steps include one or more of the following: 1. Extracting features from images 2. Feature trend calculation 3. Performing ML on feature vectors and / or feature vector trends

[0240] In some embodiments, the result of the ML is a statistical classifier model that distinguishes between AV patency less than or greater than 50%.

[0241] In some embodiments, analytics and insights are performed on the metadata and patient records to calculate AV failure statistics based on the patient profile (metadata and medical health records).

[0242] In some embodiments, an analysis is optionally performed on the performance of the clinic, for example, how many stenosis events there are per year.

[0243] Reference is now made to Figures 4A-4E, which are simplified flow charts of an algorithm according to an exemplary embodiment of the present invention.

[0244] 4A-4E show, by way of non-limiting example, flow charts illustrating exemplary algorithms that may be implemented in the software unit 306 or cloud unit 308 of the system.

[0245] Fig. 4A shows a procedure flow for vascular access as an example.

[0246] First, an organ of the subject (e.g., an arm) is placed inside the fixation sleeve under the detection unit (402). In some embodiments, the organ is an arm or a leg, and all measurements are taken when the organ is approximately perpendicular to the ground (pointing up or down). In some embodiments, some measurements are taken when the organ is approximately parallel to the ground, and some measurements are taken when the organ is perpendicular to the ground (pointing up or down). In some embodiments, some measurements are taken when the organ is lower than the patient's heart, and some measurements are taken when the organ is higher than the patient's heart.

[0247] Next, a region of interest (ROI) is detected 404. In some embodiments, the ROI is the vascular access body and / or the periphery of the vascular access body. Detection can be done automatically by the system or manually by the physician / user.

[0248] The next step is to obtain one or more measurements, eg, images, of the ROI (406).

[0249] The images are passed through a processing algorithm (408), for example an image processing algorithm, and then optionally stored in a database 410.

[0250] The next step is to extract features (414) from the current inspection measurement, e.g., an image, and from the previous inspection measurement (412), e.g., an image.

[0251] The features are fed into a statistical model (416) that can classify the vascular access body between "early detection of failure" (418) and a "stable" state (420).

[0252] FIG. 4B illustrates an exemplary algorithm flow for extracting features of the “Pulse Wave Velocity” phenomenon.

[0253] The first step is pre-processing (422) to detect the image scale, for example in mm.

[0254] The second step is to subtract the first image from the second image 424. The result contains two bright spots.

[0255] The next step is to find (426) the centers of the bright spots and calculate (428) the distance along the path along the vessel between the centers of the bright spots.

[0256] The next step is to divide the calculated path by the time period between the two images to generate a pulse wave velocity result (430).

[0257] FIG. 4C illustrates an exemplary algorithm flow for extracting features of collateral vein phenomenon.

[0258] The first step is pre-processing to detect the image scale, for example in mm (434).

[0259] The second step is to detect vascular pathways and / or branches (436).

[0260] The next step is to calculate the length of each branch along the venous pathway from the fistula and its distance (438).

[0261] The above method is also described in more detail below under the heading "Vascular Access (VA) Detection Body Algorithm" and in several locations where segmentation is described.

[0262] A further step includes calculating parameters describing the collateral venous phenomenon (442), including one or more parameters such as: 1. Multiple Branches 2. Total length of branches 3. Center of gravity of branch 4. Centroid distance from fistula 5. Oval block 6. Detect the diameter of the branch and, optionally, the blood filling the lumen of the vessel.

[0263] FIG. 4D illustrates an exemplary algorithm flow for extracting features of aneurysms and stenosis events.

[0264] The first step is pre-processing to detect the image scale, for example in mm (446).

[0265] The next step is to detect the venous and / or arterial pathways (448).

[0266] The next step is to segment the venous and / or arterial pathways (450).

[0267] The next step is to find and calculate the narrowest and widest widths along the venous and / or arterial pathways (452).

[0268] 4E shows an exemplary algorithm flow for extracting features for an arm elevation test. It should be understood that the algorithm flow is applicable to other target organs and is not limited to the arm.

[0269] In some embodiments, two images are obtained after the arm is elevated to track the change in outflow, which is translated into a short-term change in the volume of the fistula. In a normal outflow state, the fistula empties "quickly" (over a few seconds) and the difference in shape / area between the two images is detected and / or measured. In a blocked outflow state, the fistula does not empty fast enough and smaller changes, if any, in the shape / area of ​​the fistula are detected / measured. By tracking such changes over time, changes in the patency of the fistula can be tracked.

[0270] In some embodiments, the arm elevation test may be applied when the arm is elevated (pointing up, pointing down, perpendicular to the ground, and / or pointing above heart level).

[0271] In some embodiments, the first step is pre-processing to detect the image scale (456), for example in mm.

[0272] The next step is to detect vascular accesses (fistulas) in the images (458).

[0273] The next step is to segment 460 the vascular access (fistula) in the image and, optionally, cut out the fistula from the rest of the image.

[0274] The next step is to calculate the vascular access area in the image (462).

[0275] In some embodiments, the arm elevation test begins by taking a first image above heart level when the arm is parallel to the ground and a second image when the arm is perpendicular to the ground (pointing up or down).

[0276] After acquiring the first and second images, the next step is pre-processing, for example to detect the image scale in both images, for example in mm.

[0277] The next step is to detect the vascular access in both images.

[0278] The next step is to calculate the vascular access area in both images.

[0279] The next step is to subtract the first vascular access area from the second vascular access area.

[0280] In some embodiments, the arm elevation test begins by moving the arm (or any other target organ) from a first position where the arm is approximately parallel to the ground, to a second position where the arm is approximately perpendicular to the ground (pointing up or down).

[0281] The next step is to take two images of the elevated arm.

[0282] The next step is pre-processing to detect the image scale, e.g. in mm, in both images.

[0283] The next step is to detect the vascular access in both images.

[0284] The next step is to calculate the vascular access area in both images.

[0285] The next step is to subtract the first vascular access area from the second vascular access area.

[0286] The next step is to divide the calculated difference by the time period between the two images.

[0287] Reference is now made to Figures 5A and 5B, which are simplified illustrations of a pulse wave traveling along a vein.

[0288] FIG. 5A shows a first image, and FIG. 5B shows a second image taken a short time later.

[0289] The images in FIGS. 5A and 5B show an arm 502, a vein 504, an artery 506, and a fistula 508 where vein 504 connects to artery 506.

[0290] FIG. 5A shows a first location 510 where the vein is enlarged by the pressure of the pulse wave at time t0.

[0291] FIG. 5A shows a second location 512 where the vein is enlarged by the pressure of the pulse wave at time t1.

[0292] The second location 512 is further into the vein 504 relative to the first location 510 .

[0293] Pulse wave velocity is optionally measured by measuring the distance between the first location 510 and the second location 512, divided by the time difference between the capture of the first and second images.

[0294] In some embodiments, the time difference is a fraction of a second. By way of non-limiting example, imaging of pressure waves traveling along a blood vessel is optionally performed at a frame rate greater than 120 fps, e.g., 165 fps, where the image frames are approximately 15-30 centimeters wide.

[0295] In some embodiments, for both positions described above with an image frame having a field of view of 160 mm, the time difference is less than 6 ms for a pulse wave velocity of about 20 m / sec. Such a time difference applies to all pulse wave velocities less than 20 m / sec.

[0296] One or more of the following algorithms may be implemented in the systems described herein.

[0297] (Predictor / Classifier Method) Reference is now made to FIG. 6, which is a simplified flow chart of a classifier method according to an exemplary embodiment of the present invention.

[0298] FIG. 6 illustrates the input of one or more feature descriptors, such as a collateral vein descriptor 602, a pulse wave velocity descriptor 604, an arm elevation descriptor 606, and an aneurysm and / or stenosis descriptor 608.

[0299] In some embodiments, the inputs 602 , 604 , 606 , 608 are provided to a threshold calculation unit 612 .

[0300] In some embodiments, the trend calculation unit 614 optionally accepts input of history and / or trend descriptors 610, optionally from a local or remote database.

[0301] In some embodiments, the trend calculation unit 614 generates a trend data output.

[0302] In some embodiments, the threshold calculation unit 612 generates a threshold data output.

[0303] In some embodiments, one or more of the above outputs are provided to a statistics unit 616 .

[0304] In some embodiments, the output of the statistics unit 616 is input to a decision unit 618 .

[0305] The decision unit 618 optionally generates a decision that the VA is determined to be “stable” (622) or that a fault is detected (620).

[0306] FIG. 6 illustrates an exemplary classification algorithm that can be based on machine learning (supervised or unsupervised) tools or heuristic rules that perform the following steps: 1. Image processing and other data analysis 2. Extracting features from a single image or a set of consecutive images such as collateral vessel development, VA zone, etc. Some examples of features include the minimum radial size of the VA body, pulse wave velocity, size and density of collateral veins, distance of collateral veins from the AV or fistula, etc. The feature may also be the change in the feature between successive images and / or the rate of change of the feature between successive images. 3. Classifying the VA status based on the extracted features The classification can be based on ground rules, thresholds, and / or statistical models, which can be based on machine learning algorithms such as Support Vector Machines (SVMs), logistic regression, neural networks, decision trees, decision forests, "k-means", etc.

[0307] The classification can be between two levels (intervention required or not) or between three or more levels.

[0308] Non-limiting examples of methods used for prediction and / or classification include one or more of: Parameter Value Table Regression of patient-related parameter values K Nearest Neighbors (KNN) applied to parameter values Support Vector Machine (SVM) Deep Learning Neural network(s)

[0309] In some embodiments, the machine learning uses a training set. A non-limiting example of generating and using a training data set includes repeatedly measuring parameters as described herein for N patients over a period of time.

[0310] Over time, record which patients had vascular insufficiency and / or which patients were examined by additional techniques such as human examination, ultrasound, x-ray imaging, and what the determination of the additional techniques was. The parameters and determinations potentially generate a training dataset that can be used to train the machine learning methods described above or to generate a KNN dataset.

[0311] In some embodiments, some or all of the parameters measured for the above datasets are also measured for the patient for prediction and / or classification purposes.

[0312] It should be noted that the time-collected parameters optionally include measurements, parameters calculated from measurements, first derivatives of the parameter values, and second derivatives of the parameter values.

[0313] It should be noted that a nurse or doctor performing a vascular exam by sight, hearing and feeling methods typically provides a decision or classification based on the values ​​of one or two parameters, whereas the systems and methods described herein potentially use more parameters and potentially arrive at a more accurate decision or classification based on more data of the patient and / or group of patients used to generate the training set.

[0314] (Scaling algorithm) The scaling algorithm calculates the image scale (e.g., scaling pixels to mm). The scaling may be used to calculate absolute or relative values ​​for one or more of the vessel radius, pulse wave velocity, collateral vessel size, collateral vessel density, and collateral vessel distance from the VA.

[0315] (Registration Algorithm) The registration algorithm can perform an automatic or semi-automatic registration between two or more consecutive images.

[0316] The registration algorithm may align and / or scale two or more images containing the same object to different positions, or different fields of view, or different fields of view.

[0317] In some embodiments, the input to the registration algorithm includes at least two images and, in the case of semi-automatic registration, optionally one or more points marked by a user on the two images.

[0318] The registration algorithm potentially allows the system to measure the variation between at least two exams, no matter how the arm or another examined organ is positioned during different exams.

[0319] In some embodiments, alignment of at least two images of the same patient containing VA objects is optionally performed by detection (e.g., segmentation) of VAs and fitting the VA image in the first image by a geometric transformation to the VA image in the second image.

[0320] (Vascular Access (VA) Body Algorithm Detection) In some embodiments, an automatic or semi-automatic detection of the location of the vascular access body in the image is performed.

[0321] In some embodiments, the input for the algorithm for detection of a vascular access body includes at least one image including a vascular access body within an image frame.

[0322] In some embodiments, the optional input is a set of one or more points along the blood vessel containing the VA body, optionally marked by a doctor / nurse on an image containing the VA body.

[0323] The algorithm output may be a set of pixels of the vascular access body in the image.

[0324] In some embodiments, the computerized detection of the VA body is based on the unique VA shape, size, orientation, position, and the like.

[0325] In some embodiments, a device such as the "ELY-1000 Vascular Imaging Instrument for Arterial Puncture" developed by ELYNNSH MEDICAL is used as a non-limiting example, which, according to the manufacturer, can assist medical staff in identifying subcutaneous arteries during arterial puncture and display the exact location and direction of the artery conveniently and quickly.

[0326] In some embodiments, locations are detected in the image where arteries and veins appear to be connected or joined.

[0327] In some embodiments, the blood vessels that provide blood to the VA are surgically elevated toward the skin surface. Due to the difference in depth of the vascular site, an image covering a field of view (FOV) that includes the VA, the VA often appears as a closed contour centroid. The tissue surrounding the VA body is often deeper under the skin than the VA body.

[0328] In some embodiments, the difference in depth is optionally detected by the VA body potentially appearing as areas darker than the natural or surrounding blood vessels. For example, if near-infrared light is used, it is absorbed in blood Hgb, causing blood vessels closer to the surface to appear darker than deeper blood vessels.

[0329] (Pulse Wave Velocity Algorithm) Reference is again made to Figures 5A and 5B, which illustrate an exemplary method for measuring pulse wave velocity.

[0330] Pulse wave velocity is also a general indicator of vascular stiffness and can be obtained by measuring the distance between two points on a blood vessel and the pulse wave transit time. Pulse wave velocity can be measured locally, regionally or systemically.

[0331] The term localized is used to mean along the fistula and nearby associated vascular structures.

[0332] Physiologically, there is a relationship between pulse rate, blood flow, and pressure within the blood vessels.

[0333] A pulse wave (created by the heartbeat) travels from the heart to the arteries and from the veins to the heart. As the pulse wave travels, it temporarily deforms the blood vessels (e.g., veins) at moving discrete points in time.

[0334] For example, the vein radius can be temporarily expanded at a particular point along the vein, which can be detected by measuring the absorption of light by the blood flowing within the vein, with the location of the expanded vein showing up as a darker or lighter spot along the vein (depending on the measurement method, such as reflection or transmission).

[0335] By detecting points associated with dilated blood vessels in two or more consecutive images, while the time between image captures is known, the pulse wave velocity can be calculated: the pulse wave velocity is equal to the distance between the two points divided by the time between the two image captures.

[0336] (Example - System Description) The system may measure one or more of the following exemplary phenomena: vascular diameter, pulse wave velocity, near-infrared (e.g., 700-1000 nm) reflectance spectroscopy, status of collateral veins, and their characteristics such as density, size, distance from the vascular access, and oxygen concentration at the vascular access.

[0337] In some embodiments, the near-infrared spectral range is used for vascular imaging. The spectral window lies from about 700 nm to about 900 nm, where light can penetrate deep into tissue and where more radiation is absorbed by venous blood vessels than by surrounding tissue.

[0338] Reference is now made to FIG. 7, which is a simplified block diagram of a system for measuring blood vessels in accordance with an exemplary embodiment of the present invention.

[0339] 7 shows a top-level block diagram of an example embodiment of a system 700. The system 700 can include an imaging / detection unit 702 and a software / computation unit 706.

[0340] The imaging / detection unit 702 optionally includes one or more sensors 710 , one or more lenses 712 , one or more filters 713 , and one or more illuminators 714 , 716 .

[0341] In some embodiments, the sensor(s) 710 may be a CMOS sensor.

[0342] In some embodiments, the sensor 710 may be a multispectral camera and / or a hyperspectral camera.

[0343] In some embodiments, the sensor 710 may be a near-infrared sensor or a camera.

[0344] In some embodiments, lens 712 may optionally be a fixed focal length lens.

[0345] In some embodiments, lens 712 may optionally be a zoom lens.

[0346] In some embodiments, the filter 713 may optionally include a bandpass filter or a longpass filter.

[0347] In some embodiments, the illuminator(s) 714, 716 may optionally include near infrared LEDs in the 700-1200 nm spectral range.

[0348] In some embodiments, the illuminator(s) 714, 716 may optionally include broadband near-infrared LEDs.

[0349] In some embodiments, the illuminator(s) 714, 716 may optionally include one or more laser sources in the near infrared spectral range of 850 nm and 910 nm.

[0350] In some embodiments, the illuminator(s) 714, 716 can optionally include narrowband illumination in the 900 nm spectral range.

[0351] In some embodiments, the illuminator(s) 714, 716 may optionally include an array of illuminators.

[0352] In some embodiments, the software / computation unit 706 optionally includes one or more of a GUI 734, an image processing unit 735, a computer vision unit 736, and a machine learning algorithm unit 737.

[0353] In some embodiments, the algorithm unit 737 optionally includes one or more of an image processing algorithm, a vein segmentation algorithm, a sub-vein detection and / or segmentation algorithm, a pulse wave detection algorithm, and a classifier algorithm or algorithms, optionally a machine learning algorithm.

[0354] The system 700 may include additional units such as a workstation 704 and an optional cloud infrastructure 708.

[0355] In some embodiments, the cloud infrastructure 708 optionally includes one or more of a web application 738 , a database 740 (optionally including big data analytics capabilities), and an analytics unit 742 .

[0356] In some embodiments, the workstation 704 optionally includes one or more of a control unit 720 for controlling the operation of the imaging / detection unit 702 and / or one or more components of the imaging / detection unit 702, a computer 722, a display 724, and optionally an organ fixation surface or device 726 for optionally positioning the organ in a specific position relative to the illuminators 714, 716 and / or sensors 710, and a stand 728 for positioning the components of the system in specific positions relative to the patient's organ.

[0357] Reference is now made to Figures 8A and 8B, which are images of optical components in a system configured in accordance with one embodiment of the present invention.

[0358] 8A and 8B show some of the optical channels of an exemplary system as shown in FIG. 8A. Camera 802, optionally a hyperspectral sensor (camera). Lens 802 is optionally a fixed focal length lens. Optional Filter Mount 806. Filter 808, in some embodiments, is an optical long pass filter, and in some embodiments, a filter with a cutoff wavelength of 670 nm. Illumination source 812.

[0359] In some embodiments, the system includes an optional mechanical adapter 810 for connecting an illumination source 812 to the body of the camera 802 .

[0360] FIG. 8B shows an assembly unit 814 that includes the components of FIG. 8A.

[0361] In some embodiments, the exemplary vascular condition classification algorithm may be divided into three blocks: image processing, feature extraction, and statistical classifier.

[0362] The high-level flow of an exemplary algorithm may be similar to that shown in FIG. 4A.

[0363] Image Processing: The image processing block can include several steps. Image quality improvements such as contrast and illumination enhancement, sharpness, multi-polarization state imaging, multi-wavelength imaging (intensity ratio imaging), multiple exposures, optional High Dynamic Range (HDR) and Contrast Limited Adaptive Histogram Equalization (CLAHE).

[0364] In some embodiments, the intensity ratio image represents the pixel-by-pixel ratio between images captured at different wavelengths, as described by the following formula:

[0365]

number

[0366] Rij is the pixel at position (i,j) in the ratio image, IM1ij is the pixel at position (i,j) in the first image, and IM2ij is the pixel at position (i,j) in the second image.

[0367] Image segmentation – to locate vascular access (VA) structures, vessel boundaries and collateral structures.

[0368] Reference is now made to FIG. 9, which is a simplified flow chart of a segmentation method according to an exemplary embodiment of the present invention.

[0369] FIG. 9 shows an example segmentation flow including input of a first image 902, segmentation 904 of the first image 902 to generate a second image 906 with optional segmentation lines 907, optional separation 908 of organs appearing in the second image 906, and generation of a third image 910 including only images of the separated organs.

[0370] One or more of the following methods may be used: K-means algorithm, histogram-based methods, edge detection, region growing methods, Mumford and Shah segmentation, CNN (Convolutional Neural Network), etc.

[0371] Alignment between images from a previous examination and images from a subsequent examination. The alignment step optionally scales and / or aligns the new image(s) to the reference image(s), optionally the image(s) from the previous examination.

[0372] Reference is now made to FIG. 10, which is a simplified flowchart of a registration method according to an exemplary embodiment of the present invention.

[0373] FIG. 10 shows a first image 1002A and a second image 1006A.

[0374] In some embodiments, a point detection operation 1004 is optionally performed on the two images.

[0375] In some embodiments, the point detection criteria is optionally one or more of corner points, intensity-based criteria such as blob detection, speed up robust features (SURF), and the like.

[0376] In some embodiments, the similarity of two points is measured by a feature metric difference between one or more feature metrics of each of the two points.

[0377] The first image 1002A is marked by the specific points detected in the first image 1002A to generate a first new image 1002B having specific points marked thereon. The second image 1006A is marked by the specific points detected in the second image 1006A according to the same criteria used to detect the points in the first image 1002A to generate a second new image 1006B having specific points marked thereon.

[0378] FIG. 10 shows several lines 1007 connecting corresponding particular points in a first new image 1002B and a second new image 1006B.

[0379] In some embodiments, one or both of the first new image 1002B and the second new image 1006B are optionally transformed 1008 using detection of corresponding marked points to perform a transformation and, optionally, generate a new combined image 1010. In some implementations, the transformation 1008 includes one or more of image normalization, image scaling, image rotation, and an affine transformation performed on one or both of the first new image 1002B and the second new image 1006B.

[0380] In some embodiments, registration is performed to align and / or scale a first image, e.g., a current inspection image, to a second image, e.g., a previous inspection image. One or more of the following methods may be used for registration: Scale Invariant Feature Transform (SIFT), speeded up robust features (SURF) algorithm, optionally interest point detection, automatic feature detection and matching, and affine transformation calculation.

[0381] · Feature Extraction: The Feature Extraction block may contain several sub-blocks that analyze the data and extract features from the image.

[0382] In some embodiments, the feature extraction optionally generates a feature vector.

[0383] In some embodiments, feature extraction is optionally performed after the image processing step that produces the standardized image.

[0384] A feature vector is a mathematical representation used to characterize data, such as an image. There are several ways to characterize data, some of which are listed below.

[0385] Feature extraction from pre-trained DNNs (A. Krizhevsky, I. Sutskever, GE Hinton: ImageNet Classification with Deep Convolutional Neural Networks. NIPS 2012:1106-1114).

[0386] One method involves passing the images through a neural network trained on a large image dataset and using the descriptor layer.

[0387] Another approach is to develop specific descriptors for each phenomenon.

[0388] Vessel length and minimum diameter Reference is now made to FIG. 11, which is a simplified flowchart of a method according to an exemplary embodiment of the present invention.

[0389] FIG. 11 illustrates a method for generating descriptors for the length and / or minimum diameter of a vessel.

[0390] FIG. 11 shows a first image 1102 as input, a conversion 1104 of the first image 1102 into a binary image 1106, a location 1114 of the narrowest passage in the organ (blood vessel), a tracing 1108 of the centerline of the organ (blood vessel) appearing in the binary image 1106, and the generation of a third image 1110 having the centerline 1112 of the organ (blood vessel) marked on the third image 1110.

[0391] Similar methods can optionally be used to generate "Pulse Wave Velocity", "Collateral Development", and "Aneurysms and Stenosis" descriptors.

[0392] In the above method, the "distance transform" and "local maximum" methods can be used on the binary image to detect the centerline and diameter of the vessel.

[0393] Other methods that may be useful are path finding algorithms - Dijkstra's algorithm, the A* search algorithm.

[0394] Arterial and venous mixed oxygen concentration during VA Reference is now made to FIG. 12, which is a simplified flow chart illustration of a method according to an exemplary embodiment of the present invention.

[0395] FIG. 12 illustrates a method for generating a descriptor of arterial and / or venous oxygen concentration during VA.

[0396] FIG. 12 shows a first image 1202 as input, a histogram unit 1204 for generating a histogram 1206 of the first image 1202, and a computation unit 1210 for generating a feature(s) vector 1212 associated with the first image 1202.

[0397] The absorption of deoxyHb is higher than that of oxyHb in the range of 740 nm to 760 nm; therefore, in this range, veins absorb optical radiation and arteries become relatively transparent.

[0398] In the 850nm to 1000nm range, veins become relatively transparent and arteries absorb more radiation.

[0399] Blood in the VA, especially when stenosis occurs, mixes arterial and venous blood, resulting in blood recirculation.

[0400] As long as VA functionality is good, a higher rate of arterial blood should flow through the VA, which is indicated by darker gray levels when illuminated at 850 nm to 1000 nm. By calculating a histogram of an intensity "normalized" image, such as the first image 1202 shown in Figure 12, and comparing the histogram to a "reference" image, the system can create a feature vector that describes the change in blood mixture within the VA, or the rate of change of blood mixture within the VA.

[0401] pulse wave velocity Reference is now made to FIG. 13, which is a simplified flowchart of a method according to an exemplary embodiment of the present invention.

[0402] FIG. 13 shows how the pulse wave velocity is calculated.

[0403] FIG. 13 shows a first image 1302 obtained as input at time t0, a second image 1304 obtained as input at time t1, and a computation unit 1306 for generating a third image 1308.

[0404] FIG. 13 illustrates an exemplary method for pulse wave velocity feature extraction.

[0405] In some embodiments, two consecutive image frames, such as images 1302, 1304 in FIG. 13, optionally after alignment and / or segmentation (standardized images), are fused to generate a fused image, such as the third image 1308.

[0406] In some embodiments, the fused image is generated by subtracting one of the images from the other.

[0407] In some embodiments, the fused image is generated by adding one of the images to the other.

[0408] In some embodiments, the center of mass of the two brightest spots 1312, 1314 is calculated and the length of the path 1312 between the center of mass of the two brightest spots 1312, 1314 along the path 1312 is measured.

[0409] In some embodiments, the path 1312 is optionally a centerline of a blood vessel.

[0410] Statistical Classifier Models Reference is now made to FIG. 14, which is a simplified flowchart of a classifier method according to an exemplary embodiment of the present invention.

[0411] FIG. 14 illustrates input of one or more feature descriptors, such as a collateral vein descriptor 1402, a pulse wave velocity descriptor 1404, an aneurysm and / or stenosis descriptor 1406, and an arterial and venous blood mixture descriptor 1408.

[0412] In some embodiments, the inputs 1402, 1404, 1406, 1408 are provided to a trend calculation unit 1412. In some embodiments, the trend calculation unit 1412 optionally accepts inputs of history and / or trend descriptors 1410, optionally from a local or remote database.

[0413] In some embodiments, the trend calculation unit 1412 generates a trend feature vector 1414 .

[0414] In some embodiments, the trend feature vector 1414 is optionally stored in a database (local or remote).

[0415] In some embodiments, the trend feature vector 1414 is input to a classifier 1416 .

[0416] The results of the classifier 1416 are optionally input to a decision unit 1418, which generates a decision that the VA is determined to be "stable" 1420 or that a fault is detected (1422).

[0417] In some embodiments, detecting the fault may include estimating a high probability of imminent failure of the VA.

[0418] Classification into "stable" or "early fault detection" can be done by statistical classifier models such as SVM, logistic regression, and neural networks.

[0419] In some embodiments, the extracted features 1402 , 1404 , 1406 , 1408 of every phenomenon are optionally collected into one “feature” vector 1414 .

[0420] In some embodiments, the feature vector 1414 is optionally stored in a database.

[0421] In some embodiments, the feature vector 1414 and the 'historical feature vector' 1410 are optionally sent to a 'trend calculation' unit 1412 .

[0422] In some embodiments, the output of the 'Trend Calculation' unit 1412 is a 'New Trend Feature Vector' 1414 , which is optionally stored in a database and / or sent to a classifier unit 1416 .

[0423] In some embodiments, the output from the classifier unit 1416 may be detected as "early fault detection" or "stable."

[0424] In some embodiments, the classification is made on the level of maturation or rate of maturation after VA surgery has been performed.

[0425] Fistula maturity may be expressed as X% maturity after Y days.

[0426] Reference is now made to Figures 15A-C, which show three different images of the same patient's arm, in accordance with an exemplary embodiment of the present invention.

[0427] FIG. 15A shows an image of a patient's arm at wavelengths visible to humans, taken at a distance of approximately 40 centimeters from the arm.

[0428] Figure 15B shows an image of a patient's arm at near-infrared wavelengths, illustrating that the use of near-infrared imaging improves the visibility of blood vessels, such as superficial veins 1512.

[0429] FIG. 15C shows an image of a patient's arm with a point of interest 1522 that has been automatically generated (by image analysis) at the location of a blood vessel.

[0430] When nurses or doctors examine a patient's blood vessels, they typically perform a three-step test: seeing, listening and feeling.

[0431] In some embodiments, the systems described herein perform the seeing, hearing and feeling based on illuminating and imaging the patient's limb and analyzing the data collected from the imaging.

[0432] In some embodiments, the methods described herein perform the seeing, hearing, and feeling based on illuminating and imaging the patient's limb and analyzing the data collected from the imaging.

[0433] Reference is now made to FIG. 16A, which is a table illustrating the steps a medical professional should take to screen a patient for vascular stenosis or thrombosis.

[0434] Figure 16A is intended to show what a human would be instructed to do, however it is recognized that differences between humans are expected to affect such testing.

[0435] It should be noted that automated testing can potentially provide better reproducibility for such testing.

[0436] It is noted that automated testing may provide faster testing with less involvement of medical staff.

[0437] Reference is now made to FIG. 16B, which is a simplified flowchart of a method for testing a patient in accordance with an exemplary embodiment of the present invention.

[0438] The method of FIG. 16 includes a device that views (1622) a patient's body by capturing one or more images of the body and using image analysis on the images, the device that hears (1624) the patient's body by capturing vibrations of the body and analyzing the vibrations at human audible frequencies, and the device that feels (1626) the patient's body by analyzing the vibrations of the body at frequencies below human audible frequencies.

[0439] In some embodiments, capturing one or more images of the body is optionally performed by capturing images at near-infrared wavelengths.

[0440] In some embodiments, capturing the vibrations of the body is optionally performed by laser speckle imaging, as described elsewhere herein.

[0441] In some embodiments, capturing the body vibrations is optionally performed by a microphone in contact with the patient's body and / or by a microphone attached to a stethoscope in contact with the patient's body.

[0442] It should be noted that in some embodiments, automated testing can potentially provide such testing without human contact with the patient, potentially being usable in situations where medical distancing is desirable, such as when a patient may be carrying a contagious disease.

[0443] In some embodiments, the systems and methods described herein optionally "see", i.e., analyze images of blood vessels; "hear", i.e., analyze vibrations of the patient's body at frequencies audible to humans; and "feel", i.e., analyze vibrations of the patient's body at low frequencies, reaching below typical audible frequencies.

[0444] In some embodiments, a non-contact surveillance tool is provided to complement and / or replace vascular access (VA) physical examination, potentially allowing earlier detection of stenosis than human examination.

[0445] In some embodiments, the surveillance tool does not contact the patient's stoma and / or the patient's limb, while the limb is optionally positioned within the device that allows the stoma to be located within the field of view of the device.

[0446] In some embodiments, recording and monitoring parameters measured by surveillance potentially allows for earlier detection and / or prediction of stenosis than human examination.

[0447] In some embodiments, monitoring is enabled without human contact, for example at distances greater than 10, 20, 30, 40, 50 centimeters from the location of the VA.

[0448] In some embodiments, the systems and methods optionally allow obtaining all parameters that are normally obtained by human physical examination by seeing, feeling and hearing.

[0449] In some embodiments, it may be easier to train a person to operate the monitoring of a VA using the embodiments described herein than using human senses.

[0450] The embodiments described herein can be used to potentially add value by recording, using, and tracking changes to the same patient's historical data.

[0451] Use of the embodiments described herein may enable pre-session and / or post-session testing in a clinic without physical contact.

[0452] Use of the embodiments described herein potentially aids in medical care during COVID-19.

[0453] Using embodiments as described herein potentially enables care in a home set-up, possibly operated by the patient.

[0454] Reference is now made to FIG. 17, which is a simplified block diagram of a method for studying a patient according to one embodiment of the present invention.

[0455] FIG. 17 illustrates a method that includes the following. Admission of patients for testing (1702) Measuring a Patient Using an Embodiment of the Invention (1704) Data collection from sensors (1706) Data Analysis (1708) Optionally, providing a determination regarding the patient's fistula status (1710)

[0456] The status of the patient's fistula optionally includes a determination of the medical condition and / or patency of the patient's fistula. The medical condition is optionally determined to be healthy and / or functioning, or to have a potential for deterioration. In some embodiments, a probability of deterioration above a certain threshold optionally generates a recommendation to send the patient for additional testing, such as a Doppler ultrasound or an x-ray angiogram.

[0457] Reference is now made to Figures 18A and 18B, which are images of a patient's fistula taken at two different times.

[0458] Figure 18A shows an ink marking of the outline of the fistula 1802. Figure 18A also shows physical features 1804 that are visible on the patient's skin.

[0459] Figure 18B is an image of the fistula taken at a different time. Figure 18B shows that the ink marking 1802 changes shape due to a change in the shape and / or size of the fistula. Figure 18B also shows that the physical feature 1804 appears to have moved relative to the outline of the fistula or relative to the ink marking 1802.

[0460] 18A and 18B are images of a 36 year old male with a right brachiocephalic artery fistula created in 2004. The fistula has several aneurysms 1801A, 1801B.

[0461] Reference is now made to Figures 19A and 19B, which are simplified illustrations of systems for monitoring vascular access (VA) and / or fistulas, according to two exemplary embodiments of the present invention.

[0462] 19A shows a system 1900 including a head 1902 and a base 1906. The head 1902 optionally includes a light projector and an imaging system. In some embodiments, the base 1906 optionally includes a shape configured to support an arm or leg in a particular position relative to the head 1902. In some embodiments, the base 1906 optionally includes a strap configured to support an arm or leg in a particular position relative to the head 1902.

[0463] 19A shows a system 1910 including a projector 1912 and an imager 1914. In some embodiments, the projector 1912 includes an optional cover 1916. In some embodiments, the cover 1916 may be desirable and / or required for safety, particularly if the projector includes a laser.

[0464] In some embodiments, the image capture device 1914 can optionally capture frames at rates greater than standard video rates, optionally at rates greater than 60 frames per second (FPS), greater than 60 FPS, greater than 100 FPS, greater than 150, 200, 300, 400, 500, and 600 FPS.

[0465] A high frame rate allows for detection of high frequency vibrations of the patient's body (Shannon's Law), as is known in the art.

[0466] In some embodiments, a near-infrared high speed camera is optionally used, optionally with a frame rate of 150 FPS or greater.

[0467] In some embodiments, off-the-shelf cameras are optionally used, such as a FLIR FL3 U3 camera capable of capturing images at 1.3 megapixel full frame size with a frame rate of 150 FPS.

[0468] In some embodiments, the camera is used to capture frame rates greater than 160 FPS, up to 600 FPS, 620 FPS or higher.

[0469] In some embodiments, off-the-shelf cameras capable of capturing images with frame sizes ranging from 1.3 to 2 megapixels or greater are optionally used.

[0470] In some embodiments, commercially available cameras are optionally used to image at higher frame rates while imaging at lower frame sizes. As some non-limiting examples, the cameras optionally image at sizes of 10x20 pixels, 10x10 pixels, etc.

[0471] In some embodiments, the imaging device captures small frames less than the maximum frame size, optionally up to the small frame size mentioned above, at a particular location of interest on the patient's body at the location of the fistula or the location of the VA point of interest.

[0472] In some embodiments, the projector optionally projects light onto a location of interest to allow a user to precisely locate a location on the patient's body.

[0473] In some embodiments, the location of interest is a fistula in a patient.

[0474] In some embodiments, two or more spots are illuminated simultaneously.

[0475] In some embodiments, one location of interest at which a spot is applied is a fistula of the patient, and another location of interest at which a spot is applied is a location adjacent to the fistula of the patient but not the fistula.

[0476] In some embodiments, one location of interest at which a spot is irradiated is the fistulous aneurysm, and another location of interest at which a spot is irradiated is a location adjacent to, but not at, the fistulous aneurysm.

[0477] In some embodiments, the projector is a digital light processing (DLP) projector.

[0478] In some embodiments, the projector is a laser projector.

[0479] In some embodiments, a location of interest, such as a fistula, aneurysm, or bulging area of ​​the body, is optionally identified by using structured light and image analysis, and a projector is controlled, optionally automatically controlled, to illuminate the location of interest. In embodiments, a DLP and / or laser projector is optionally controlled to illuminate the location of interest.

[0480] In some embodiments, the doctor or nurse controls the lighting to the location of interest.

[0481] In some embodiments, a doctor or nurse controls the laser delivery to the location of interest.

[0482] In some embodiments, the projector can optionally project light in multiple modes, including two or more of: projecting uniform (or nearly uniform) illumination over an area or limited spot on the patient's body, potentially sufficient to image collateral veins, projecting structured light, optionally including stripes of specific width, equal width, or widths different from a programmed or other pattern, and projecting one or more spots of coherent laser light, potentially useful for measuring one or more of vibrations, micro-vibrations, and pulse waves, e.g., by laser speckle interferometry.

[0483] In some embodiments, the projector can be switched between any one of three different illumination modes: uniform, structured, and spot.

[0484] In some embodiments, the projector can provide a spot size on the patient's limb ranging from 0.5 mm to 5 mm in diameter, for example a spot size of about 1 mm.

[0485] In some embodiments, the projector includes one or more LED and / or laser light sources, optionally at near-infrared wavelengths.

[0486] In some embodiments, the projector is optionally a digital light processing (DLP) projector.

[0487] In some embodiments, the projector optionally includes nano-mirrors to shape the light.

[0488] In some embodiments, the projector optionally includes Micro Electro Mechanical System (MEMS) mirrors to shape the light.

[0489] In some embodiments, the projector optionally includes a Digital Mirror Driver (DMD).

[0490] In some embodiments, the projector and the camera are packed in one package.

[0491] Reference is now made to FIG. 20, which is an image of a system for monitoring vascular access (VA) and / or fistulas, according to an exemplary embodiment of the present invention.

[0492] FIG. 20 shows a system including a projector 2004 , an imager 2006 , and an optional processor 2002 .

[0493] Reference is now made to Figures 21A-C, which show three different images of the same patient's arm.

[0494] The image in Figure 21A shows a patient's arm held below the patient's heart level. Two inflated needle insertion tips 2102, 2104 are shown over the stoma in the patient's arm.

[0495] The image in Figure 21B shows a patient's arm held above the level of the patient's heart, with the image captured immediately after the patient has raised the arm to a raised position. A first one of the inset points 2102 is shown contracted, while a second one of the inset points 2104 is still inflated.

[0496] The image in Figure 21C shows the patient's arm elevated, and the image is captured a short time later than the image in Figure 21B. Both needle insertion points 2102, 2104 are shown in a retracted, folded state.

[0497] Testing by altitude test In some embodiments, the systems and methods described herein are optionally used to measure and quantitate in an elevation test, i.e., measurement and quantification is performed one or more times with the body or limb held below heart level and one or more times with the body or limb held in an elevated position above heart level.

[0498] 21A-C show, in some instances, the fistula may not drain when held in one position and drain when held in one or more other positions. In some instances, the fistula may not drain when held in one position and drain when held in one or more other positions.

[0499] The difference between the locations correlates with the medical condition of the fistula, such as the ratio between inflow and outflow velocities and / or pressures.

[0500] The rate and manner in which the fistula drains, as well as the differences between drainage patterns at different lifts, correlate with the medical condition of the fistula. In some embodiments, the drainage rate and / or pattern is optionally measured by generating a 3D shape and / or one or more 3D curves that describe the contours of the fistula and / or by tracking the changes between the curves along a set.

[0501] In some embodiments, the drainage rate and pattern is optionally estimated by assessing the volume encapsulated by the 3D shape and / or by one or more curves and by tracking the change in total volume over time, potentially providing the level and rate of drainage.

[0502] In some embodiments, the spatial curvature of the curve can be estimated and the drainage pattern can be characterized by analyzing the change in the time curvature.

[0503] In some embodiments, the smoothness of the curvature of each curve, and the change in the smoothness of the curvature over time during drainage, can be used to estimate the drainage pattern.

[0504] In some embodiments, correlations between any flow-related parameters estimated from analysis of the measured vibrations and any parameters estimated from drainage patterns or flow rates based on 3D or curvilinear shapes are optionally used to estimate the health of the fistula.

[0505] Reference is now made to FIG. 22A, which is a graph illustrating the power spectrum of vibration measured by analysis of an image produced by laser speckle imaging.

[0506] FIG. 22A shows a graph 220 where the X-axis 2202 shows the frequency ranges or bins and the Y-axis 2204 shows the relative power spectrum in the units in which it is measured.

[0507] To create this graph, two groups of patients were sampled: the first group 2206 had a blood flow velocity (FV) greater than 500 mL / min, and the second group 2208 had an FV less than 500 mL / min.

[0508] Graph 2200 shows that the maximum in the power spectrum is located at approximately 140 Hz for both groups. This raises the question that listening to the pitch of the blood flow in both groups may not be a good way to distinguish between them. However, differences are seen when analyzing the power spectra of both groups.

[0509] The first group 2206 appears to have a higher amplitude maximum than the second group 2208.

[0510] The second group 2208 appears to have a flatter or wider curve than the first group 2206.

[0511] As shown in FIG. 22A, the oscillations resolved in the power spectrum are caused by blood flow and / or turbulence through the blood vessels.

[0512] Blood flow and turbulence change over time and are influenced by the local physical conditions in and around the vessel in which the blood flow occurs, potentially including pressure gradients, vessel diameter, vessel wall compliance, vessel inner surface properties, etc.

[0513] The power spectrum of blood flow measured at VA / fistula locations is potentially related to the physical and / or clinical blood flow status at these locations. Changes in such power spectrum features over time potentially correlate with deterioration in fistula health. Analyzing changes in power spectra obtained from VA / fistula locations potentially predicts fistula deterioration at an early stage.

[0514] With reference to the early stage predictions described herein, it is noted that such predictions potentially allow for percutaneous transluminal angioplasty (PTA) to be performed sooner than would be performed based on the pre-existing condition of a medical test.

[0515] In some embodiments, the power spectrum is measured by measuring the intensity of light reflected from the patient's body, which is expected to vary with frequencies related to the frequency of the body's vibrations.

[0516] In some embodiments, the power spectrum is measured by measuring the intensity of light reflected from an illuminated spot on the patient's body, in such embodiments, the vibrations are measured specifically at the illuminated spot.

[0517] In some embodiments, the power spectrum is measured by measuring the difference between successive images of the body, for example, small shifts in a pattern on the body. The pattern may be a mole on the skin, structured light, moving spots of light, moving laser speckles, and similar movements.

[0518] Reference is now made to FIG. 22B, which is a simplified flow chart illustration of a method for converting data from image streams to frequency bands according to one embodiment of the present invention.

[0519] The method of FIG. 22B includes receiving (2222) a stream of images of a patient's body, optionally selecting (2224) one or more pixels having a high variance in intensity over a period of the image stream, and generating (2226) an intensity vector over the period of time. Converting a vector of intensities into a vector of frequency spectra (2228).

[0520] In some embodiments, the transformation is performed by a Fast Fourier Transform.

[0521] In some embodiments, the power spectrum is optionally normalized before it is analyzed. As some non-limiting examples, a normalization factor is optionally calculated from the total spectral energy, the peak value, the peak-to-baseline ratio, the energy within a particular bandwidth, etc.

[0522] In some embodiments, a reference spectrum measured at a remote location (e.g., far from the fistula) is used as a reference. Both spectra may or may not be normalized, and the measured spectrum is replaced by the difference between the spectra at the different locations.

[0523] In some embodiments, the skewness or kurtosis of the measured power spectrum or differential power spectrum is optionally used to estimate flow rate.

[0524] In some embodiments, the measured power spectrum is first fitted to a model, in some embodiments assuming, by way of non-limiting example, one or more hidden model mixtures, and the model parameters are used as correlators to the flow rate.

[0525] In some embodiments, energy in a particular frequency range is used to estimate flow rate.

[0526] Seeing, hearing and feeling We further describe some aspects of the invention with respect to a "see, hear and feel" procedure used by medical staff.

[0527] In some embodiments, the "seeing, hearing and feeling" procedure is optionally performed by the system embodiments described herein.

[0528] In some embodiments, the systems described herein perform the seeing, hearing and feeling based on illuminating and imaging the patient's limb and analyzing the data collected from the imaging.

[0529] In some embodiments, the methods described herein perform the seeing, hearing, and feeling based on illuminating and imaging the patient's limb and analyzing the data collected from the imaging.

[0530] A fistula murmur, also called a bruit, is an indicator of how the dialysis access is functioning.

[0531] An AV fistula is an access type formed by connecting an artery to a vein under the skin (usually in the upper or lower arm or leg). (i) More blood flow from the artery through the vein allows the fistula to grow larger and stronger. A healthy AV fistula has murmur (a buzzing sound that humans can hear), tremor (a buzzing sensation that humans can feel), and good blood flow velocity.

[0532] In some embodiments, the "seeing" aspect is optionally performed by imaging the body or limb and analyzing one or more images to quantify vascular and / or fistula structures.

[0533] In some embodiments, the "seeing" aspect is optionally performed by imaging the body or limb using structured light to generate a 3D shape of the stoma.

[0534] In some embodiments, the "listening" aspect is optionally performed by measuring body or limb vibrations and analyzing the vibrations to quantify parameter values ​​related to the medical condition of the stoma. In some embodiments, the "listening" aspect includes analyzing vibrations within a frequency range within the human hearing range.

[0535] In some embodiments, the "sensing" aspect is optionally performed by measuring body or limb vibrations and analyzing the vibrations to quantify parameter values ​​related to the fistula pathology. In some embodiments, the "sensing" aspect includes optionally analyzing vibrations in a frequency range extending above and / or below the range of human hearing.

[0536] In some embodiments, analyzing the vibrations is optionally performed in a frequency range below 1,000 Hz. In some embodiments, analyzing the vibrations is optionally performed in a frequency range smaller than a typical human voice, for example below 4,000 Hz.

[0537] As some non-limiting examples, “sensory” aspects include one or more of the following:

[0538] To measure a human's pulse, typically in the range of 40 beats per minute or higher. Such measurements require the analysis of vibrations at a frequency of 1 Hertz or even slightly less. If such an analysis is carried out by analyzing image frames of a video sequence, it is sufficient to analyze the image frames at about twice the rate of the frequency to be measured, i.e., for example, at about 2 frames per second or more.

[0539] Measuring tremor, which is typically in the range of 50 to 250 hertz or 50 to 750 hertz. Where such an analysis is performed by analysing image frames of a video sequence, it is sufficient to analyse the image frames at about twice the rate of the frequency to be measured, ie for example at about 100 frames per second or more.

[0540] For example, the power spectrum of the vibrations is analyzed and quantified as described above with reference to Figures 22A and 22B.

[0541] In some embodiments, "seeing, hearing and feeling" is performed without physically touching the patient, by image analysis and / or by using specific lighting modes.

[0542] Reference is now made to FIG. 23, which is a simplified flowchart of a method for monitoring vascular function according to an exemplary embodiment of the present invention.

[0543] The method of FIG. 23 includes illuminating one or more blood vessels through a patient's skin (2302), capturing at least one image of the blood vessels (2304), analyzing the at least one image (2306), and calculating a parameter related to vascular function based on the image analysis (2308).

[0544] Referring now to FIG. 24, there is shown a simplified flowchart of a method for replacing physical exams performed by medical staff to monitor vascular function, in accordance with an exemplary embodiment of the present invention.

[0545] The method of FIG. 24 includes generating (2402) at least one image of a patient organ, analyzing (2404) the at least one image, and generating (2406) a parameter value related to vascular function.

[0546] Although certain embodiments have been disclosed in detail herein, this has been done by way of example for illustrative purposes only and is not intended to be limiting with respect to the scope of the following claims. It is specifically contemplated that various substitutions, changes, and modifications can be made without departing from the spirit and scope of the present disclosure as defined by the claims. Other aspects, advantages, and modifications are contemplated to be within the scope of the following claims. The claims presented are representative of the implementations and features disclosed herein. Other unclaimed implementations and features are also contemplated. Accordingly, other embodiments are within the scope of the following claims.

[0547] It is expected that many related image processing algorithms will be developed during the life of the patent which matures from this application, and the scope of the term image processing is intended to include a priori all such new techniques.

[0548] As used herein in reference to an amount or value, the term "approximately" means "within ±15%."

[0549] The terms "comprise," "include," "have," and their conjugations mean "including but not limited to."

[0550] The term "consisting of" is intended to mean "including" and "limited to."

[0551] The term "consisting essentially of" means that a composition, method, or structure may include additional components, steps, and / or moieties, but only if the additional components, steps, and / or moieties do not materially alter the basic and novel characteristics of the claimed composition, method, or structure.

[0552] As used herein, the singular forms "a," "an," and "the" include plural references unless the context clearly dictates otherwise. For example, the term "a unit" or "at least one unit" can include a plurality of units, including combinations thereof.

[0553] The words "example" and "exemplary" are used herein to mean "serving as an example, instance, or illustration." Any embodiment described as "example" or "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments and / or as excluding the incorporation of features from other embodiments.

[0554] The term "optionally" is used herein to mean "is provided in some embodiments and is not provided in other embodiments." Any particular embodiment of the invention may include multiple "optional" features unless such features are inconsistent.

[0555] Throughout this application, various embodiments of the invention may be presented in a range format. It should be understood that the description in range format is merely for convenience and brevity and should not be construed as an inflexible limitation on the scope of the invention. Thus, the description of a range should be considered as specifically disclosing all possible subranges as well as individual numerical values ​​within that range. For example, the description of a range such as 1-6 should be considered as having specifically disclosed subranges such as 1-3, 1-4, 1-5, 2-4, 2-6, 3-6, etc., as well as individual numbers within that range, such as 1, 2, 3, 4, 5, and 6. This applies regardless of the breadth of the range.

[0556] Whenever a numerical range is given herein (e.g., any pair of numbers linked by "10 to 15," "10 to 15," or another such range designation), it is meant to include any number (fractional or integer) within the indicated range limits, inclusive, unless the context clearly dictates otherwise. Ranges / rangings / ranges between a first designated number and a second designated number and ranges / rangings / ranges from a first designated number to a second designated number (to, up to, until, through, or another such range designation term) are used interchangeably herein and are meant to include the first designated number and the second designated number, and all fractional and integer numbers therebetween.

[0557] Unless otherwise indicated, numbers used herein, and any numerical ranges based thereon, are approximations within the accuracy of reasonable measurement and rounding errors, as will be understood by one of ordinary skill in the art.

[0558] It will be understood that certain features of the invention that are, for clarity, described in the context of separate embodiments, may also be provided in combination in a single embodiment. Conversely, for brevity, various features of the invention that are described in the context of a single embodiment may also be provided separately or in any suitable subcombination or as appropriate with any other described embodiment of the invention. Certain features described in the context of various embodiments are not to be regarded as essential features of those embodiments, unless the embodiment is inoperable without those elements.

[0559] While this disclosure has been described in conjunction with specific embodiments thereof, it is evident that many alternatives, modifications, and variations will be apparent to those skilled in the art. Accordingly, the present invention is intended to embrace all such alternatives, modifications, and variations that fall within the spirit and broad scope of the appended claims.

[0560] All publications, patents, and patent applications mentioned in this specification are incorporated herein by reference in their entirety as if each individual publication, patent, or patent application was specifically and individually indicated to be incorporated herein by reference. Furthermore, citation or identification of any reference in this application should not be construed as an admission that such reference is available as prior art to the present invention. To the extent that section headings are used, they should not be construed as necessarily limiting. Additionally, the priority documents of this application are incorporated herein by reference in their entirety.

Claims

1. 1. A system for monitoring vascular function, comprising: an illumination unit configured to switch projected light between at least two of three modes of projecting light: uniform illumination, structured illumination, and spot illumination; a camera configured to capture an image of a position that the illumination unit is configured to illuminate; a processor for processing images captured by the camera to extract shape data from the camera images and vibration data derived from the camera images; Equipped with The processor, By analyzing vibrations captured by image analysis at human audible frequencies, the system listens to the patient's body and Sensing the patient's body by analyzing vibrations acquired by image analysis at frequencies extending below the human audible frequency; It is configured as follows: system.

2. The camera has a camera capable of capturing images at a frame rate of greater than 150 frames per second (FPS). The system of claim 1 .

3. The illumination unit has a light source of near-infrared wavelength. The system of claim 1 .

4. 1. A system for monitoring vascular access in a patient undergoing hemodialysis treatment by automated seeing, hearing and feeling testing, comprising: a camera configured to image the patient's body to obtain a geometry of the blood vessels; a processor configured to receive an image from the camera; Including, The system comprises: acquiring a shape of a body organ at a location of a vascular access (VA) of the patient's body using image analysis; analyzing vibrations of the patient's body at a location on the patient's body that includes the blood vessel using image analysis; configured to: The system comprises: Performing viewing by image analysis of the image acquired by imaging; By image analysis of the image acquired by the imaging, the vibration is analyzed at a human audible frequency to perform listening; By analyzing the image acquired by the imaging, the vibration is analyzed at a frequency ranging from a frequency lower than a human audible frequency, thereby performing sensing; and programmed to automatically perform a visual, hearing, and feeling examination of the patient's body by system.

5. A classifier configured to classify the state of the VA by combining two or more features extracted from seeing, hearing, and feeling. The system of claim 4.

6. obtaining the shape includes calculating a three-dimensional (3D) shape of the patient's stoma; A system according to claim 4 or claim 5.

7. configured to record the characteristics measured along a surveillance period and predict the likelihood of stenosis based on changes along the surveillance period. The system of claim 5.

8. and performing said listening by analyzing vibrations of the patient's body includes analyzing vibrations at frequencies above 80 Hz. A system according to any one of claims 4 to 7.

9. analyzing the vibrations of the patient's body includes analyzing movement of a pattern at a particular location in an image of a location of the patient's body that includes the blood vessel. The system of claim 4.

10. Analyzing the vibrations of the patient's body is performed by analyzing images captured at a frame rate of greater than 150 frames per second (FPS). The system of claim 4.

11. an illumination unit configured to switch projected light between at least two of three modes of projecting light: uniform illumination, structured illumination, and spot illumination; A system according to any one of claims 4 to 10.

12. having a camera capable of capturing images at a frame rate greater than 150 frames per second (FPS); A system according to any one of claims 4 to 11.

13. The lighting unit includes a digital light processing (DLP) projector. The system of claim 11.

14. configured to calculate a drainage rate of the patient's fistula based on a change in 3D shape of the patient's fistula; A system according to any one of claims 4 to 13.

15. The method of claim 1, wherein the calculation is performed during an elevation test. The system of claim 14.

16. and configured to calculate one or more parameters indicative of development of one or more collateral vessels based on said image analysis. A system according to any one of claims 4 to 15.

17. The system is configured to provide feedback to support the remote physical examination. A system according to any one of claims 4 to 16.

18. and calculating one or more parameters based on the image analysis, and calculating an estimate of VA maturity calculated based on a rate of change of the one or more parameters. A system according to any one of claims 4 to 17.

19. configured to calculate one or more parameters based on passing an image through a trained neural network and using a descriptor layer of the trained neural network. A system according to any one of claims 4 to 18.

20. The monitoring includes classifying a maturation level of the patient's body VA. The system of claim 4.

21. Used instead of a doctor to perform tests that can be seen, heard, and felt The system of claim 4.

22. one or more parameters related to vascular function are calculated based on the image analysis; an estimate of the probability of impairment of vascular function is calculated based on said one or more parameters; The system of claim 4.

Images