Endothelium function examination device of arterial blood vessel

Abstract

To provide an endothelium function examination device of an arterial blood vessel which allows even an operator who is unskilled in determining a muscle tissue in a short axis image, to easily position the muscle tissue between the arterial blood vessel and an ultrasonic probe.SOLUTION: A muscle tissue region image generation part 94 generates a muscle tissue region image GKN which indicates a muscle tissue KN in an actual short axis image from image information which is present in the actual short axis image, using a learned model LM obtained by learning in advance the muscle tissue region image GKN which is present in the short axis image and stored, and a display control part 92 displays the muscle tissue region image GKN in a state of being overlapped with short axis images of a first short axis image display region G1 and a second short axis image display region G2 by the display control part 92. Thereby, it is possible to easily set an arrangement of an ultrasonic probe 24 on an upper arm 16 and a twisted position of the upper arm 16 so that the muscle tissue KN is positioned between an arterial blood vessel 20 and the ultrasonic probe 24.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to an endothelial function inspection device for an arterial blood vessel, which displays an area of ​​muscle tissue within an ultrasound image showing a cross-section of the arterial blood vessel based on changes in arterial diameter that appear in the ultrasound image, so that the muscle tissue can be easily interposed between the ultrasound probe and the arterial blood vessel. [Background technology]

[0002] There is known an endothelial function testing device for arterial blood vessels that brings an ultrasonic probe into contact with the epidermis of a living body, generates a cross-sectional image showing a cross section of an arterial blood vessel located under the epidermis from an ultrasonic reflection signal from under the epidermis, measures a change in the vascular diameter of the arterial blood vessel from the cross-sectional image, and tests the endothelial function of the arterial blood vessel based on the amount of change in the vascular diameter. For example, the endothelial function testing device for arterial blood vessels described in Patent Document 1 is such an example.

[0003] In the arterial endothelial function testing device described in Patent Document 1, ultrasonic cross-sectional images are synthesized based on reflected waves detected by an ultrasonic array, and a transverse cross-sectional image (short-axis image) or a longitudinal cross-sectional image (long-axis image) of the arterial blood vessel, which is an ultrasonic cross-sectional image of the arterial blood vessel under the skin, is generated, and the diameter of the arterial blood vessel or the endothelial diameter (intima diameter) is calculated from the image. In addition, in order to evaluate the vascular endothelial function, the rate of change (%) of the vascular endothelial diameter (intima diameter) that indicates FMD (flow-mediated vasodilation) after ischemia reactive hyperemia [=100×(dmax -d) / d] (where d is the vascular endothelial diameter at rest, and dmax is the maximum vascular endothelial diameter after release from ischemia) is calculated. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] JP 2011-177571 A Summary of the Invention [Problem to be solved by the invention]

[0005] In the above-mentioned endothelial function testing device, if muscle tissue, which attenuates ultrasound less than other tissues such as fat, is present in the propagation path between the ultrasound probe and the arterial blood vessel, the blood vessel image is displayed relatively clearly in the cross-sectional image of the arterial blood vessel, which is an ultrasound image, and therefore accuracy in blood vessel diameter measurement can be achieved. Therefore, an experienced operator reads the area of ​​muscle tissue from the cross-sectional image of the arterial blood vessel, and determines the placement of the ultrasound probe on the arm and the twisting position of the arm so that the area of ​​muscle tissue is located in the ultrasound propagation path between the epidermis on which the ultrasound probe is placed and the blood vessel.

[0006] However, cross-sectional images of arterial blood vessels generated based on weak and noisy ultrasonic reflection signals are unclear, and a great deal of skill is required to read muscle tissue in the ultrasound images. For this reason, it can be difficult for an unskilled operator to accurately grasp the muscle tissue area, obtain a clear blood vessel image, and ensure the accuracy of blood vessel diameter measurement.

[0007] The present invention has been made in light of the above circumstances, and an object of the present invention is to provide an apparatus for testing endothelial function of arterial blood vessels, which enables even an operator who is not skilled in determining muscle tissue in a cross-sectional image of an arterial blood vessel to easily locate muscle tissue between the epidermis on which the ultrasound probe is placed and the arterial blood vessel.

[0008] The present inventors have conducted various studies in light of the above circumstances, and have found that by inputting image information about a cross-sectional image of an arterial blood vessel, which is an ultrasound image, into a neural network, and repeatedly having an experienced operator teach the neural network the area of ​​muscle tissue in the cross-sectional image of the arterial blood vessel to create a machine learning model that has been trained, and then clearly displaying the area of ​​muscle tissue in the cross-sectional image of the arterial blood vessel using the machine learning model, even an unskilled operator can accurately grasp the area of ​​muscle tissue and easily position the area of ​​muscle tissue between the skin on which the ultrasound probe is placed and the arterial blood vessel. The present invention has been made based on such findings.

[0009] That is, the gist of the present invention is (a) an endothelial function testing device for arterial blood vessels that brings an ultrasonic sensor into contact with the epidermis of a living body, generates a cross-sectional image showing a cross-section of an arterial blood vessel located under the epidermis from an ultrasonic reflection signal from under the epidermis, and measures changes in the vascular diameter of the arterial blood vessel appearing in the cross-sectional image, comprising: (b) a short-axis image display device that displays a short-axis image of the arterial blood vessel; (c) a muscle tissue region image generation unit that generates a muscle tissue region image showing the region of muscle tissue located in the actual short-axis image from image information appearing in the actual short-axis image using a learned model that has been previously learned and stored about the region of muscle tissue appearing in the short-axis image; and (d) a display control unit that superimposes the muscle tissue region image on the short-axis image and displays it on the image display device. Effect of the Invention

[0010] In the thus configured arterial endothelial function testing device, a muscle region display control unit uses a learned model that has previously learned and stored the muscle tissue region appearing in the short-axis image to generate a muscle tissue region image showing the muscle tissue region in the actual short-axis image from image information appearing in the actual short-axis image, and the display control unit displays the muscle tissue region image superimposed on the short-axis image. This allows even an operator who is not skilled in determining muscle tissue in a short-axis image to accurately and easily grasp the muscle tissue region in the short-axis image, and can easily set the position of the ultrasound probe on the arm or the twist position of the arm so that the muscle tissue region is located in the propagation path between the ultrasound probe and the blood vessel. This allows a clear blood vessel image to be generated, improving the accuracy of blood vessel diameter measurement.

[0011] Preferably, the trained model is a machine learning model that has been repeatedly subjected to supervised learning using training data in which a predetermined short-axis image is used as input data and an area of ​​muscle tissue identified by a skilled operator in the short-axis image is used as output data, thereby clearly identifying the area of ​​muscle tissue in the short-axis image.

[0012] Preferably, the machine learning model is a multi-layered neural network that has undergone deep learning, in which weight coefficients between nodes belonging to adjacent layers are successively updated when the input data is input to nodes of an input layer and output data indicating the area of ​​muscle tissue identified by an experienced operator in the short-axis image is repeatedly taught to nodes of an output layer, thereby more clearly identifying the area of ​​muscle tissue in the short-axis image.

[0013] Preferably, in the multi-layer neural network, brightness information for each pixel constituting the predetermined short-axis image is input as the input data to an input layer, and output data indicating pixels that indicate the muscle tissue area is output from an output layer, thereby more clearly identifying the muscle tissue area in the short-axis image.

[0014] Preferably, in the output data output from the output layer of the multilayer neural network, image recognition is performed on a pixel-by-pixel basis constituting the short-axis image, the texture of the region to which the pixel belongs is characterized from information on each pixel and its adjacent pixels, and a meaningful region division is estimated for each pixel, whether it belongs to a muscle tissue region or other tissue, based on the texture. This reduces the number of nodes constituting the output layer of the multilayer neural network, making the configuration of the multilayer neural network compact. [Brief description of the drawings]

[0015] [Figure 1] 1 is a perspective view showing the overall configuration of an endothelial function testing device for arterial blood vessels according to one embodiment of the present invention; [Diagram 2] 2 is a diagram for explaining XYZ orthogonal coordinate axes used in the present embodiment for positioning an ultrasound probe in the endothelial function testing apparatus of FIG. 1. FIG. [Diagram 3] FIG. 2 is an enlarged view showing a schematic configuration of blood vessel layers that is the measurement target of the endothelial function testing device of FIG. 1. [Figure 4]3 is a diagram illustrating an example of an ultrasound image of an arterial blood vessel displayed on an image display device during a positioning operation of an ultrasound probe by the endothelial function inspection device of FIG. 1. FIG. [Diagram 5] 4 is a time chart illustrating the change in vascular lumen diameter after release from blood flow in an arterial blood vessel FMD evaluation using the endothelial function testing device of FIG. 1. [Figure 6] 13 is a photograph showing a muscle tissue region image superimposed on a short axis image. [Figure 7] 2 is a functional block diagram illustrating the configuration of a muscle tissue region image generating unit provided in the endothelial function inspection device of FIG. 1. FIG. [Figure 8] 2 is a flowchart illustrating a main part of the control operation of the electronic control device of FIG. 1, showing a muscle tissue region image generating routine. [Figure 9] 2 is a flowchart illustrating a main part of the control operation of the electronic control device of FIG. 1, showing an FMD measurement routine. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0016] In the present invention, the endothelial function testing device is preferably adapted to measure the brachial artery, which is an artery beneath the epidermis of the upper arm of a living body, but is also applicable to detection of vascular endothelial function of other arteries, such as the forearm and phaco arteries, which can be measured from the epidermal surface of the body.

[0017] The ultrasonic probe provided in the endothelial function testing device in the present invention is preferably an H-shaped probe having two parallel rows of a first short-axis ultrasonic array probe and a second short-axis ultrasonic array probe, and a long-axis ultrasonic array probe connecting the longitudinal center of the first short-axis ultrasonic array probe and the second short-axis ultrasonic array probe, on one plane. However, the present invention can be similarly applied and effective to an endothelial function testing device provided with other probes, such as one having a single short-axis ultrasonic array probe, or one having two parallel rows of a first short-axis ultrasonic array probe and a second short-axis ultrasonic array probe without a long-axis ultrasonic array probe.

[0018] In the present invention, the trained model is preferably a machine learning model based on a machine learning algorithm. The machine learning algorithm is a nearest neighbor method, a naive Bayes method, a support vector machine, or the like. In addition, deep learning is used, which uses a neural network to generate features and connection weighting coefficients for learning. In addition, the teacher data is training data, and is composed of a pair of input data and output data.

[0019] DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. EXAMPLES

[0020] FIG. 1 is a perspective view illustrating the overall configuration of an endothelial function testing device 22 that uses a probe unit 12 supported by a sensor support 10 to non-invasively test the endothelial function of an arterial blood vessel 20 located from above the skin 18 (strictly speaking, the epidermis) to below the skin 18 in the upper arm 16 of a living body 14.

[0021] The probe unit 12 functions as a sensor for inspecting biological information related to the arterial blood vessel 20, i.e., the endothelial function of the arterial blood vessel 20, and includes an H-shaped ultrasonic probe 24 having a pair of parallel first short-axis ultrasonic array probe 24a and second short-axis ultrasonic array probe 24b, and a long-axis ultrasonic array probe 24c connecting the longitudinal center of the first short-axis ultrasonic array probe 24a and the second short-axis ultrasonic array probe 24b on one plane, i.e., a flat probe surface 25. The probe unit 12 also includes a multi-axis driving mechanism (positioning mechanism) 26 for positioning the ultrasonic probe 24 in the XYZ directions and for positioning the rotation angles around the X-axis and Z-axis, and a driving device 27 including an XYZ motor for driving the multi-axis driving mechanism in the XYZ directions. The first short-axis ultrasonic array probe 24a, the second short-axis ultrasonic array probe 24b, and the long-axis ultrasonic array probe 24c are, for example, a number of ultrasonic transducers a1 to a2 made of piezoelectric ceramics, as shown in FIG. 2 described later. n are linearly arranged to form an elongated shape.

[0022] Fig. 2 is a diagram for explaining the XYZ orthogonal coordinate axes used in this embodiment for positioning the ultrasonic probe 24. With respect to the XYZ orthogonal coordinate axes as shown in Fig. 2, the ultrasonic probe 24 is translated in the X-axis direction by, for example, the multi-axis driving mechanism 26. It is also rotated around the X-axis and Z-axis.

[0023] 3 is an enlarged view showing a schematic diagram of the vascular wall structure of an arterial blood vessel 20 in the upper arm, which is the subject of measurement by the endothelial function testing device 22. The arterial blood vessel 20 has a three-layer structure consisting of a tunica intima L1, a tunica media L2, and a tunica adventitia L3. Since ultrasonic waves are generally reflected at areas with different acoustic impedances, an image of the arterial blood vessel 20 taken using ultrasonic waves shows the interface between the blood in the vascular lumen and the tunica intima L1, and the interface between the tunica media L2 and the tunica adventitia L3 in white, the vascular lumen in black, and tissue in black and white mottling.

[0024] 1, the endothelial function inspection device 22 includes an electronic control device 28 configured by a so-called microcomputer, an image display device 30, an ultrasound drive control circuit 32, and a three-axis drive motor control circuit 34. In measuring a blood vessel state using the endothelial function inspection device 22, when a drive signal is supplied from the ultrasound drive control circuit 32 by the electronic control device 28, beam-shaped ultrasound is sequentially emitted from the first short-axis ultrasound array probe 24a, the second short-axis ultrasound array probe 24b, and the long-axis ultrasound array probe 24c of the ultrasound probe 24 in the probe unit 12 by well-known beamforming drive. Then, ultrasonic reflection signals are detected by the first short-axis ultrasonic array probe 24a, the second short-axis ultrasonic array probe 24b, and the long-axis ultrasonic array probe 24c, and the detected ultrasonic reflection signals are processed in the electronic control device 28 to generate a first short-axis image, a second short-axis image, and a long-axis image, which are ultrasonic images of the arterial blood vessels 20 under the skin 18, and are displayed in the first short-axis image display area G1, the second short-axis image display area G2, and the long-axis image display area G3 of the image display device 30.

[0025] In FIG. 1, the electronic control device 28 functionally comprises an ultrasound drive control unit 80, a detection processing unit 82, an ultrasound image generation unit 84, a three-axis drive motor control unit 86, a cuff pressure control unit 88, a vascular condition evaluation unit 90, a display control unit 92, and a muscle tissue region image generation unit 94.

[0026] 4 is a diagram showing the positional relationship between the arterial blood vessel 20 and the ultrasound probe 24 positioned at a predetermined measurement position when an ultrasound image of the arterial blood vessel 20 is generated in the measurement of the blood vessel condition by the endothelial function inspection device 22, and also showing an example of an ultrasound image of the blood vessel displayed on the image display device 30 in that positional relationship. In the image display device 30, for example, as shown in FIG. 4(a), the first short-axis image display area G1, the second short-axis image display area G2, and the long-axis image display area G3 have a common vertical axis indicating the depth dimension from the skin 18. Note that "ImA, ImB" in FIG. 4(a) each indicate a cross section of the arterial blood vessel 20.

[0027] The endothelial function testing device 22 evaluates FMD (Flow-Mediated Dilation) to measure the diameter, intimal thickness, plaque, blood flow velocity, etc. of the arterial blood vessel 20 based on the reflected signal of the ultrasound output from the ultrasound probe 24 to the arterial blood vessel 20. In this FMD evaluation, the image display device 30 displays the rate of change in the diameter of the intima in the arterial blood vessel 20, i.e., the expansion rate R of the lumen diameter, in a time series. When evaluating FMD and generating an ultrasound image of the arterial blood vessel 20, the ultrasound probe 24 is automatically positioned at a predetermined measurement position P with respect to the arterial blood vessel 20, which is the measurement target, by driving the multi-axis drive mechanism 26 to which a drive signal is supplied from the three-axis drive motor control circuit 34 by the three-axis drive motor control unit 86 provided in the electronic control device 28. The predetermined measurement position P is a position where the first short-axis ultrasonic array probe 24a and the second short-axis ultrasonic array probe 24b are perpendicular to the arterial blood vessel 20 and the long-axis ultrasonic array probe 24c is parallel to the arterial blood vessel 20. Explaining with reference to Fig. 4, the predetermined measurement position P is a position where "a=b, c=d, e=f" in Fig. 4. That is, it is a measurement position where the distance from the first short-axis ultrasonic array probe 24a to the center of the arterial blood vessel 20 and the distance from the second short-axis ultrasonic array probe 24b to the center of the arterial blood vessel 20 are equal to each other, and the image of the arterial blood vessel 20 is positioned at the center in the width direction in both the first short-axis image display region G1 and the second short-axis image display region G2.

[0028] When measuring blood vessel conditions using the endothelial function testing device 22, the sensor support 10 holds the probe unit 12 in a fixed position so as to lightly contact the arterial blood vessel 20 located directly below the skin 18 of the upper arm 16 of the living body 14 from above the skin 18 without deforming the blood vessel.

[0029] As shown in FIG. 1, the sensor support 10 includes, for example, a base 36 fixed to a pedestal (not shown), a unit fixture 38 to which the probe unit 12 is fixed so that it can be pressed toward the upper arm 16 by a pressing actuator 37, a first arm 40 whose base end is connected to the base 36 via a flexible fixture, and a flexible arm 44 having a second arm 42 whose tip end is connected to the unit fixture 38 via a flexible fixture and is connected to the tip of the first arm 40 so as to be rotatable around one axis.

[0030] The multi-axis driving mechanism 26 is configured to include an X-axis rotation (yawing) mechanism fixed to the unit fixture 38 for positioning the rotation position of the ultrasonic probe 24 about the x-axis by an x-axis rotation actuator, an X-axis translation mechanism for positioning the translation position of the ultrasonic probe 24 in the X-axis direction by an X-axis rotation actuator, and a Z-axis rotation mechanism for positioning the rotation position of the ultrasonic probe 24 about the Z-axis by a Z-axis actuator. With this configuration, the multi-axis driving mechanism 26 positions the ultrasonic probe 24 by a drive unit 27 operating according to a command from an electronic control device 28.

[0031] The ultrasonic drive control circuit 32 controls the emission of ultrasonic waves from the ultrasonic probe 24 to the arterial blood vessel 20 according to a command from an ultrasonic drive control unit 80 provided in the electronic control unit 28. For example, among the many ultrasonic transducers a1 to an arranged in a row in the first short-axis ultrasonic array probe 24a, a certain number of ultrasonic transducers, for example, 15 ultrasonic transducers a1 to a15, are simultaneously driven at a frequency of about 10 MHz while giving a predetermined phase difference from the end ultrasonic transducer a1, thereby sequentially emitting convergent ultrasonic beams toward the arterial blood vessel 20 in the direction of the arrangement of the ultrasonic transducers. Then, the ultrasonic transducers are shifted one by one to scan the ultrasonic beam, and the reflected waves for each emission are received and input to the electronic control unit 28. The reflected wave signal input to the electronic control unit 28 is detected by the detection processing unit 82 and processed by the ultrasonic image generating unit 84 as information that can be used for image synthesis, which will be described in detail below.

[0032] The electronic control device 28 generates cross-sectional images of the arterial blood vessel 20 under the skin 18 based on the ultrasonic reflected waves received by the ultrasonic probe 24, i.e., a cross-sectional image (short-axis image) of the arterial blood vessel 20 in a direction intersecting the longitudinal direction, and a cross-sectional image (long-axis image) of the arterial blood vessel 20 in the longitudinal direction, and displays them on the image display device 30. The vascular state evaluation unit 90 calculates the diameter of the arterial blood vessel 20 or the endothelial diameter (lumen diameter) d1, which is the diameter of the endothelium 70, from the short-axis image or long-axis image of the arterial blood vessel 20 thus generated. In addition, in order to evaluate the endothelial function of the arterial blood vessel 20, the expansion rate (change rate) R (%) [= 100 × (d1 - da) / da] of the vascular lumen diameter, which indicates FMD (flow-mediated dilation response) after ischemia reactive hyperemia, is calculated. In this formula, "da" indicates the vascular lumen diameter (base diameter, resting diameter) at rest.

[0033] In measuring vascular condition using endothelial function testing device 22, the measurement site on living body 14, for example upper arm 16, is compressed by a pressure device such as cuff 62 to block blood flow, and a part of living body 14 (the part distal to the part of blood flow obstructed) is put into an ischemic state. After that, the blood flow is suddenly released, and blood flow in arterial blood vessel 20 at the measurement site is rapidly increased. This causes nitric oxide (NO) to be produced from the endothelium due to increased shear stress on the endothelium of the vascular wall, and endothelial function is assessed by examining the relaxation state of smooth muscle that depends on this nitric oxide.

[0034] 5 is a time chart showing an example of the change in vascular lumen diameter d1 after release from blood vessel obstruction (avascularization) in the FMD evaluation of the arterial blood vessel 20 by the endothelial function testing device 22. In FIG. 5, time t1 represents the time when blood vessel obstruction is released, and the vascular lumen diameter d1 starts to expand from time t2, and reaches its maximum value d at time t3. MAX Therefore, the expansion rate R of the blood vessel lumen diameter calculated by the electronic control device 28 reaches a maximum at time t3.

[0035] As shown in FIG. 1, the cuff pressure control unit 88 in the electronic control unit 28 controls the air pump 58, the pressure control valve 60, and the like to perform the occlusion for FMD evaluation of the arterial blood vessel 20. For example, in accordance with a command from the electronic control unit 28, the original pressure from the air pump 58 is controlled by the pressure control valve 60 and supplied to the cuff 62 wrapped around the upper arm 16. Specifically, the pressure (cuff pressure) of the cuff 62 is increased to a predetermined occlusion cuff pressure that exceeds the systolic blood pressure of the living body 14, for example, to perform the occlusion for FMD evaluation. At this time, the cuff pressure control unit 88 detects the cuff pressure in response to a signal from a pressure sensor 64 that detects the pressure (cuff pressure) of the cuff 62. In FIG. 5, for example, the cuff pressure control unit 88 maintains the cuff pressure at the occlusion cuff pressure for a predetermined time before the release of the occlusion, i.e., a predetermined time before time t1, and immediately reduces the cuff pressure to atmospheric pressure when the occlusion is released (time t1). As a result, blood flow in the arterial blood vessel 20 at the measurement site P is rapidly initiated, and the endothelial function testing device 22 measures the blood vessel diameter d MAX is measured.

[0036] The ultrasonic image generating unit 84 generates a first short-axis image representing a cross section of the arterial blood vessel 20 based on the ultrasonic reflection signal detected by the first short-axis ultrasonic array probe 24a, generates a second short-axis image representing a cross section of the arterial blood vessel 20 based on the ultrasonic reflection signal detected by the second short-axis ultrasonic array probe 24b, and generates a long-axis image representing a longitudinal section of the arterial blood vessel 20 based on the ultrasonic reflection signal detected by the long-axis ultrasonic array probe 24c.

[0037] The display control unit 92 displays the first short axis cross-sectional image, the second short axis cross-sectional image, and the long axis cross-sectional image generated by the ultrasound image generation unit 84 in the first short axis image display area G1, the second short axis image display area G2, and the long axis image display area G3, respectively, on the image display device 30.

[0038] Generally, short-axis cross-sectional images obtained using ultrasound have a lot of speckle noise, as shown in Fig. 6 showing the actual first short-axis cross-sectional image or the second short-axis cross-sectional image, and skill is required to determine the muscle tissue KN. For this reason, the endothelial function inspection device 22 of this embodiment is equipped with a muscle tissue region image generating unit 94 that generates a muscle tissue region image GKN showing the muscle tissue KN located in the first short-axis image display region G1 and the second short-axis image display region G2 from image information of the first short-axis image and the second short-axis image displayed in the actual first short-axis image display region G1 and the second short-axis image display region G2, using a learned model LM that has been learned and stored in advance for the muscle tissue KN appearing in the short-axis image.

[0039] As shown in Fig. 7, the muscle tissue region image generating unit 94 includes a learned model unit 96 that stores a learned model LM that has been previously learned and stored for the muscle tissue KN appearing in the first short-axis image and the second short-axis image, and a muscle tissue region image synthesizing unit 98 that uses the learned model LM to generate a muscle tissue region image GKN showing the muscle tissue KN located in the actual first short-axis image and the second short-axis image from the image information appearing in the actual first short-axis image and the second short-axis image. The display control unit 92 displays the muscle tissue region image GKN showing the muscle tissue KN in the first short-axis image display area G1 and the second short-axis image display area G2 of the image display device 30, for example, as shown in Fig. 6, by superimposing the muscle tissue region image GKN on the first short-axis image and the second short-axis image, respectively. In the case of Fig. 6, the muscle tissue region image GKN is displayed in a state surrounded by a curved image LKN showing the outer edge of the muscle tissue KN, and the muscle tissue region image GKN may be an image displayed with diagonal lines or colors showing the entire region of the muscle tissue KN.

[0040] The trained model LM is a machine learning model MLM that has been repeatedly subjected to supervised learning using training data in which the image information of the entire first and second short-axis images displayed in the first and second short-axis image display areas G1 and G2 is used as input data, and a muscle tissue region image GKN specified by an experienced operator drawing in the short-axis image displayed on an input display device (not shown) using a mouse or pen is used as output data. The image display device 30 may be used as the input display device.

[0041] Preferably, the machine learning model MLM is a multi-layered neural network that has undergone deep learning in which weight coefficients between nodes belonging to adjacent layers are sequentially updated when the input data is input to the nodes of the input layer and output data is taught to the nodes of the output layer as pixels indicating muscle tissue KN identified by an experienced operator in the short-axis image.

[0042] In the above multilayer neural network, preferably, the brightness information Pin(x,y) for each pixel constituting the predetermined short-axis image is input to the input layer as input data, and the output layer outputs output data Pout(x,y,t) indicating a pixel indicating muscle tissue KN. The t of the output data is a texture indicating whether or not the pixel indicated by the output data Pout(x,y) is within the area of ​​muscle tissue KN (if t=1, it is within the area of ​​muscle tissue KN, and if t=0, it is a feature indicating other tissue).

[0043] That is, in the output data output from the output layer of the multilayer neural network, image recognition is performed on a pixel-by-pixel basis constituting the short-axis image, and the texture t of the region (tissue) to which the pixel belongs is characterized from the information of each pixel and its adjacent pixels, and a meaningful region division, whether it belongs to muscle tissue KN or other tissue, is estimated for each pixel P(x, y) based on the texture t.

[0044] 8 and 9 are flow charts for explaining the main part of the control operation of the electronic control device 28, which are repeatedly executed at a predetermined cycle. Fig. 8 shows a muscle tissue region image display control routine that enables the muscle tissue region KN to be easily positioned between the ultrasonic probe 24 and the arterial blood vessel 20 by displaying the muscle tissue region image GKN superimposed on the short-axis images of the first short-axis image display region G1 and the second short-axis image display region G2 prior to FMD measurement. Fig. 9 shows an FMD measurement routine that performs FMD evaluation to measure the diameter, intima thickness, plaque, blood flow velocity, etc. of the arterial blood vessel 20 based on the reflected signal of the ultrasonic wave output from the ultrasonic probe 24 to the arterial blood vessel 20.

[0045] 8 (hereinafter, step will be omitted), it is judged whether or not an ultrasound image display start operation has been performed prior to FMD evaluation, for example, based on whether any screen of the image display device 30 has been touched. If the judgment in S1 is negative, the device is put on standby, but if positive, in S2 corresponding to the ultrasound image generating unit 84, a first short-axis image representing a cross section of the arterial blood vessel 20 is generated based on an ultrasound reflection signal detected by the first short-axis ultrasound array probe 24a, a second short-axis image representing a cross section of the arterial blood vessel 20 is generated based on an ultrasound reflection signal detected by the second short-axis ultrasound array probe 24b, and a long-axis image representing a longitudinal section of the arterial blood vessel 20 is generated based on an ultrasound reflection signal detected by the long-axis ultrasound array probe 24c, and the first short-axis image display area G1, the second short-axis image display area G2, and the long-axis image display area G3 are displayed, respectively.

[0046] Next, in S3, it is determined whether or not a control activation operation for generating and displaying a muscle tissue region image GKN has been performed, for example, based on whether or not the screen of either the first short-axis image display region G1 or the second short-axis image display region G2 in which the short-axis image of the image display device 30 is displayed has been touched. If the determination in S3 is negative, S1 and subsequent steps are repeated, but if positive, in S4 corresponding to the muscle tissue region image generating unit 94, the learned model LM is used to generate muscle tissue region images GKN showing muscle tissue KN located in the first short-axis image display region G1 and the second short-axis image display region G2, respectively, from the image information of the first short-axis image and the second short-axis image displayed in the actual first short-axis image display region G1 and the second short-axis image display region G2. Then, in S5 corresponding to the display control unit 92, the muscle tissue region image GKN is clearly displayed superimposed on the first short axis cross-sectional image and the second short axis cross-sectional image in the first short axis image display area G1 and the second short axis image display area G2 where the first short axis cross-sectional image and the second short axis cross-sectional image are displayed, respectively. Fig. 6 shows this state.

[0047] While checking the first short axis cross-sectional image and the second short axis cross-sectional image as well as the muscle tissue region image GKN superimposed on the first short axis cross-sectional image and the second short axis cross-sectional image as shown in FIG. 6, the operator can easily determine the position of the ultrasonic probe 24 on the upper arm 16 and the twist position of the upper arm 16 so that the muscle tissue KN shown in the muscle tissue region image GKN is located as close as possible between the skin 18 on which the ultrasonic probe 24 is placed and the arterial blood vessel 20.

[0048] 9, an arterial blood vessel 20 is identified from the lumen of a plurality of tubular organs in a short-axis cross-sectional image obtained based on a reflected signal received by the ultrasonic probe 24. For example, a video of short-axis cross-sectional images consisting of a plurality of frames synchronized with the diastole of the pulse is continuously calculated within a section in which the ultrasonic probe 24 applies pressure to the biological tissue directly below the ultrasonic probe 24 until the vein in the short-axis cross-sectional image is sufficiently compressed by the pressing actuator 37, and then the pressure is released. Next, the compressed and released states of the biological tissue directly below the ultrasonic probe 24 are determined from the video consisting of a plurality of consecutive frames of the short-axis cross-sectional images using a movement vector indicating the movement of a pixel or a local region consisting of a group of pixels between frames. Next, the short-axis cross-sectional image in the compressed state is subjected to a smoothing process, and the smoothed short-axis cross-sectional image is binarized to a binarized short-axis cross-sectional image, which is subjected to a predetermined number of expansion processes and then a predetermined number of contraction processes. Next, a plurality of lumens are generated in the closed short-axis cross-sectional image, and a labeling process is performed to label the lumens in the closed short-axis cross-sectional image, and a short-axis cross-sectional image in the compressed state in which the lumens are superimposed is generated. Next, the lumen of the arterial blood vessel 20 is determined from among the plurality of lumens generated in the short-axis cross-sectional image in the compressed state based on whether or not a preset arterial blood vessel lumen determination condition is satisfied. When any of the lumens displayed in the short-axis cross-sectional image in the compressed state is determined to be the lumen of the arterial blood vessel 20, a template of a local region including the entire arterial blood vessel 20 is created, and the template is used to track the movement of the arterial blood vessel 20 during the process in which the short-axis cross-sectional image transitions from the compressed state to the released state, and the arterial blood vessel is identified in the short-axis cross-sectional image in the released state. FIG. 6 shows a schematic image of an arterial blood vessel 20 that is thus identified as a perfect circle.

[0049] Using the arterial blood vessel 20 obtained in S11, the FMD of the arterial blood vessel 20 is evaluated in S12-S18 corresponding to the blood vessel condition evaluation unit 90. First, in S12, the sensor support 10 is in light contact with the arterial blood vessel 20 located directly below the skin 18 of the upper arm 16 of the living body 14 from above the skin 18 without deforming the arterial blood vessel 20. The probe unit 12 is positioned by the three-axis drive motor control unit 86 so that the position of the ultrasonic probe 24 in three-dimensional space is the measurement position shown in FIG. 4(b) with respect to the arterial blood vessel 20. Next, in S13, the lumen diameter da, which is the diameter of the endothelium 70 of the artery 20, is measured in the resting section. The period before t0 in FIG. 5 shows this state. After that, in S14, the upper arm 16 is compressed by the cuff 62 to stop the bleeding of the arterial blood vessel 20 in the upper arm 16. The period from t0 to t1 in FIG. 5 shows this state. Next, in S15, after a predetermined time has elapsed since hemostasis, for example, 5 minutes, the pressure applied by the cuff 62 is released, and the blood flow in the arterial blood vessel 20 is suddenly released and blood flow in the blood vessel 20 at the measurement site is resumed, and this state is shown for the period from time t1 in Fig. 5. This causes a sudden increase in blood flow, which increases the shear stress on the endothelium of the vascular wall of the arterial blood vessel 20, causing the production of nitric oxide (NO) from the endothelium, and the relaxation of smooth muscle dependent on this nitric oxide causes a temporary increase in the endothelial diameter of the arterial blood vessel 20.

[0050] In S16, the lumen diameter d of the arterial blood vessel 20 after the release of hemostasis reaches a maximum value d as shown at time t4 in FIG. MAX The measurement is repeated until it is determined that the maximum value d MAX When it is determined that the maximum value d MAX Based on the lumen diameter da, which is the diameter of the endothelium 70 of the artery 20 at rest obtained in S3, the expansion rate (change rate) R (%) of the vascular lumen diameter, which represents the FMD (flow-mediated vasodilation response) after ischemia reactive hyperemia to evaluate the endothelial function of the arterial blood vessel 20 [= 100 × (d MAX −da) / da] is calculated and displayed on the image display device 30 by the display control unit 92.

[0051] As described above, according to the endothelial function inspection device 22 of this embodiment, the muscle tissue region image generating unit 94 generates a muscle tissue region image GKN showing the muscle tissue KN in the actual short-axis image from image information appearing in the actual short-axis image using the learned model LM that has previously learned and stored the muscle tissue region image GKN appearing in the short-axis image, and the display control unit 92 displays the muscle tissue region image GKN superimposed on the short-axis images in the first short-axis image display area G1 and the second short-axis image display area G2. As a result, even an operator who is not skilled in determining the muscle tissue KN in the short-axis image can accurately and easily grasp the muscle tissue KN in the short-axis image, and can easily set the position of the ultrasound probe 24 on the upper arm 16 and the twist position of the upper arm 16 so that the muscle tissue KN is located between the ultrasound probe 24 and the arterial blood vessel 20. As a result, a clear blood vessel image can be generated, and the accuracy of blood vessel diameter measurement can be improved.

[0052] According to the endothelial function testing device 22 of this embodiment, the learned model LM is a machine learning model MLM that has been repeatedly subjected to supervised learning using learning data in which a predetermined short-axis image is used as input data and the area of ​​muscle tissue KN identified by a skilled operator in the short-axis image is used as output data. This allows the area of ​​muscle tissue KN to be clearly identified in the short-axis image.

[0053] Moreover, according to the endothelial function testing device 22 of this embodiment, the machine learning model MLM is a multi-layered neural network in which deep learning is performed, in which weight coefficients between nodes belonging to adjacent layers are sequentially updated when the input data is input to the nodes of the input layer, and output data indicating pixels indicating muscle tissue KN identified by a skilled operator in the short-axis image is repeatedly taught to the nodes of the output layer. This allows the area of ​​muscle tissue KN to be more clearly identified in the short-axis image.

[0054] Furthermore, according to the endothelial function inspection device 22 of this embodiment, in the multi-layer neural network, brightness information for each pixel constituting a given short-axis image is input as the input data to the input layer, and output data indicating pixels that indicate muscle tissue KN in the given short-axis image is output from the output layer. This allows the muscle tissue region image GKN indicating muscle tissue KN to be more clearly identified in the short-axis image.

[0055] Moreover, according to the endothelial function testing device 22 of this embodiment, in the output data sequentially output from the output layer of the multilayer neural network, image recognition is performed on a pixel-by-pixel basis constituting the predetermined short-axis image, the texture of the brachial region to which the pixel belongs is characterized from the information of each pixel and its adjacent pixels, and a meaningful region division is estimated for each pixel, whether it belongs to muscle tissue KN or other tissue, based on the texture. This reduces the number of nodes constituting the output layer of the multilayer neural network, making the configuration of the multilayer neural network more compact.

[0056] Although a preferred embodiment of the present invention has been described in detail above with reference to the drawings, the present invention is not limited to this embodiment, and various modifications can be made without departing from the spirit of the present invention. [Explanation of symbols]

[0057] 10: sensor support, 12: probe unit, 14: living body, 16: upper arm (living body), 18: skin, 20: arterial blood vessel, 22: endothelial function test device, 24: ultrasonic probe, 24a: first short-axis ultrasonic array probe, 24b: second short-axis ultrasonic array probe, 24c: long-axis ultrasonic array probe, 25: probe surface, 26: multi-axis drive mechanism, 27: drive device, 28: electronic control device, 30: image display device, 32: ultrasonic drive control circuit, 34: three-axis drive motor control circuit, 36: base, 37: pressure actuator (living body compression device), 38: unit fixing device, 4 0: first arm, 42,: second arm, 44: flexible arm, 58: air pump, 60: pressure control valve, 62: cuff, 64: pressure sensor, 70: endothelium, 80: ultrasonic drive control unit, 82: detection processing unit, 84: ultrasonic signal processing unit, 86: 3-axis drive motor control unit, 88: cuff pressure control unit, 90: blood vessel state evaluation unit, 92: display control unit, 94: muscle tissue region image generation unit, 96: trained model unit, 98: muscle tissue region image synthesis unit, G1: first short axis image display area, G2: second short axis image display area, G3: long axis image display area, L1: intima, L2: media, L3: adventitia, KN: muscle tissue, GKN: muscle tissue region image, LKN: curve image, LM: learning model, MLM: machine learning model

Claims

1. 1. An apparatus for testing endothelial function of an arterial blood vessel, comprising: an ultrasonic sensor that is in contact with the epidermis of a living body; a cross-sectional image that shows a cross section of an arterial blood vessel located under the epidermis based on an ultrasonic reflection signal from under the epidermis; and a measurement of a change in a diameter of the arterial blood vessel that appears in the cross-sectional image, a short-axis image display device that displays a short-axis image of the arterial blood vessel; a muscle tissue region image generating unit that generates a muscle tissue region image showing muscle tissue located in the actual short-axis image from image information shown in the actual short-axis image using a learned model that has been previously learned and stored for the muscle tissue region shown in the short-axis image; a display control unit that displays the muscle tissue region image on the image display device by superimposing the muscle tissue region image on the short axis image. An apparatus for testing endothelial function of arterial blood vessels.

2. The trained model is a machine learning model that has been repeatedly subjected to supervised learning using training data in which a predetermined short-axis image is used as input data and an area of ​​muscle tissue identified by an experienced operator in the short-axis image is used as output data.

2. The apparatus for inspecting endothelial function of arterial blood vessels according to claim 1.

3. The machine learning model is a multi-layered neural network in which deep learning is performed, in which the weight coefficients between nodes belonging to adjacent layers are sequentially updated when the input data is input to the nodes of the input layer and the output data is repeatedly taught to the nodes of the output layer, which indicates the area of ​​muscle tissue identified by an experienced operator in the short-axis image.

3. The apparatus for testing endothelial function of arterial blood vessels according to claim 2.

4. In the multilayer neural network, the brightness information for each pixel constituting the predetermined short-axis image is input to an input layer as the input data, and output data indicating pixels that indicate the muscle tissue area is output from an output layer.

4. The apparatus for inspecting endothelial function of arterial blood vessels according to claim 3.

5. In the output data output from the output layer of the multi-layered neural network, image recognition is performed on a pixel-by-pixel basis that constitutes the short-axis image, and the texture of the brachial region to which the pixel belongs is characterized from the information of each pixel and its neighboring pixels, and a meaningful region division is estimated for each pixel based on the texture, indicating whether the pixel belongs to a muscle tissue region or to other tissues.

3. The apparatus for testing endothelial function of arterial blood vessels according to claim 2.

Images