Ultrasonic diagnostic apparatus and control method of ultrasonic diagnostic apparatus

Abstract

In an ultrasonic diagnostic apparatus and a control method for the ultrasonic diagnostic apparatus, the accuracy of a blood vessel being an artery and the accuracy of the blood vessel being a vein are calculated respectively by analyzing an ultrasonic image. Based on the accuracy of the blood vessel being the artery and the accuracy of the blood vessel being the vein, it is determined whether the blood vessel is the artery or the vein or whether determination processing for determining whether the blood vessel is the artery or the vein is needed. In a case where it is determined that the determination processing is needed, the determination processing is executed, and based on the execution result of the determination processing, it is determined whether the blood vessel is the artery or the vein.

Description

Technical Field

[0001] This invention relates to an ultrasound diagnostic device with the function of determining the type of blood vessel (artery or vein) and a control method for the ultrasound diagnostic device. Background Technology

[0002] For example, when puncturing a patient's blood vessels, ultrasound imaging is used to determine the puncture site and needle thickness, thereby confirming the type, size, location, depth, course, and presence of obstructions such as nerves. In particular, since puncture errors in arteries and veins can directly lead to serious medical accidents, determining the type of blood vessel—whether it is an artery or a vein—is especially important.

[0003] Hereinafter, prior art documents that serve as references for this invention include, for example, Patent Document 1, Patent Document 2, etc.

[0004] Patent Document 1 describes a method for distinguishing between arteries and veins by detecting the direction and pulsation of blood flow in arteries and veins using color Doppler technology. Furthermore, Patent Document 1 also describes a method for distinguishing between arteries and veins by applying mechanical pressure to vascular tissue and then measuring and analyzing the absorption of two wavelengths based on the oxygen content in the blood, either by utilizing the compression of veins.

[0005] Patent document 2 describes how arteries and veins are identified by analyzing image data using prior information representing the locations of typical arteries and veins.

[0006] Previous technical documents

[0007] Patent documents

[0008] Patent Document 1: Japanese Patent Publication No. 2008-545502

[0009] Patent Document 2: Japanese Patent Application Publication No. 2018-202147 Summary of the Invention

[0010] The technical problem to be solved by the invention

[0011] As described in Patent Document 2, misidentification is possible when determining blood vessel type solely based on image data. As mentioned above, since misidentification of blood vessel type can directly lead to medical accidents, it is desirable to avoid determining blood vessel type solely based on image data.

[0012] On the other hand, as described in Patent Document 1, when the type of blood vessel is determined based on data other than image data, additional work is usually required to determine the type of blood vessel, which reduces the availability.

[0013] The purpose of this invention is to provide an ultrasound diagnostic device and a control method for the ultrasound diagnostic device that can prevent misidentification of blood vessel type and determine blood vessel type without reducing usability.

[0014] means for solving technical problems

[0015] To achieve the above objectives, the present invention provides an ultrasonic diagnostic device comprising:

[0016] Ultrasonic probe;

[0017] The image generation unit generates an ultrasonic image from the received signal obtained by transmitting and receiving ultrasonic beams on the subject using an ultrasonic probe.

[0018] The accuracy calculation unit analyzes ultrasound images and calculates the accuracy of identifying blood vessels in the ultrasound images as arteries and veins, respectively.

[0019] The vessel identification unit determines whether a vessel is an artery or a vein based on the accuracy of identifying it as an artery and the accuracy of identifying it as a vein, or determines whether further processing is needed to determine whether a vessel is an artery or a vein; and

[0020] The vessel identification unit, when it determines that identification processing is required, performs identification processing and, based on the result of the identification processing, determines whether the vessel is an artery or a vein.

[0021] Here, the accuracy calculation unit preferably detects a vascular region containing a prescribed shape of blood vessels within the ultrasound image when calculating the accuracy for arteries and the accuracy for veins.

[0022] Furthermore, the vascular region is either an arterial region containing arteries or a venous region containing veins.

[0023] The accuracy calculation unit preferably detects arterial regions containing blood vessels within the ultrasound image and calculates the accuracy of identifying blood vessels within the arterial region as arteries. It also detects venous regions containing the same blood vessels and calculates the accuracy of identifying the same blood vessels within the venous region as veins.

[0024] Furthermore, the accuracy calculation unit preferably detects a single blood vessel region containing a prescribed shape of blood vessels within the ultrasound image, and then calculates the accuracy of identifying the blood vessel within the single blood vessel region as an artery and the accuracy of identifying it as a vein.

[0025] Furthermore, preferably in the first case where the accuracy of one of the arteries and veins is above a first threshold and the accuracy of the other of the arteries and veins is less than a second threshold smaller than the first threshold, the vessel determination unit determines that the vessel is one of the arteries and veins. In the second case other than the first case, the vessel determination unit determines that a determination process is required.

[0026] Furthermore, the accuracy calculation unit preferably calculates the accuracy of each pixel in the ultrasound image as an artery pixel, the accuracy of each pixel as a vein pixel, and the accuracy of each pixel as a background pixel other than a blood vessel.

[0027] Furthermore, the blood vessel determination unit preferably determines whether a pixel is an artery pixel, a vein pixel, or a background pixel for each pixel in the ultrasound image based on the accuracy of the pixel being an artery pixel, the accuracy of the pixel being a vein pixel, and the accuracy of the pixel being a background pixel. Based on the artery pixel and the vein pixel, it determines the blood vessel region containing the blood vessel. If the ratio of the area of ​​one of the artery pixel and the area of ​​the vein pixel to the area of ​​the blood vessel in the blood vessel region is greater than or equal to a third threshold, it is determined that the blood vessel is either an artery or a vein. If the ratio is less than the third threshold, it is determined that further processing is required.

[0028] Furthermore, the vessel identification unit preferably prompts the operator to use an ultrasound probe to press on the examination site of the subject, calculate the aspect ratio of the vessel cross-section based on the ultrasound image generated under the condition that the examination site is pressed by the ultrasound probe, and determine whether the vessel is an artery or a vein based on the aspect ratio of the vessel cross-section.

[0029] Furthermore, the ultrasonic probe has a pressure sensor.

[0030] The preferred method for determining blood vessel location is to use pressure detected by a pressure sensor to determine whether the area being examined is being compressed.

[0031] Furthermore, the vessel identification unit preferably detects the movement of the examination site by analyzing multiple frames of ultrasound images, and determines whether the examination site is being compressed based on the movement of the examination site.

[0032] Furthermore, the vessel identification unit preferably determines whether the aspect ratio of the vessel cross-section changes within a specified time after prompting the operator to press the examination site with an ultrasound probe. Based on whether the aspect ratio of the vessel changes within the specified time, it determines whether the examination site is being compressed.

[0033] Furthermore, the vessel identification unit preferably prompts the operator to tilt the ultrasound probe at the examination site of the subject. In color Doppler mode, based on the direction of blood flow in the ultrasound image generated when the ultrasound probe is tilted at the examination site, it determines whether the vessel is an artery or a vein.

[0034] Furthermore, the vessel identification unit preferably searches for ultrasound images of past frames where the accuracy of identifying the same vessel as an artery or as a vein is at least a fourth threshold, and determines whether the vessel is an artery or a vein based on the accuracy of identifying the same vessel as an artery or as a vein in the searched ultrasound images of the frames.

[0035] Furthermore, the vessel identification unit preferably detects vessels in adjacent consecutive ultrasound images, and if the overlap ratio of vessels in consecutive ultrasound images is 4 or higher, they are determined to be the same vessels.

[0036] Furthermore, the preferred features include:

[0037] Displays; and

[0038] The display control unit, based on at least one of the determination result of whether a blood vessel is an artery or a vein and the confirmation result of whether a blood vessel is an artery or a vein, overlays a graphic containing a blood vessel with an ultrasound image and displays it on a monitor.

[0039] Furthermore, in addition to the graphics, the display control unit preferably displays the accuracy of identifying blood vessels as arteries and the accuracy of identifying them as veins on the display screen.

[0040] Furthermore, it is preferable that once it is determined whether a blood vessel is an artery or a vein, the display control unit displays the same graphic on the display for the same blood vessel.

[0041] Furthermore, preferably in cases where it is impossible to determine whether a blood vessel is an artery or a vein, the display control unit also displays the character for "blood vessel" on the screen in addition to the graphic.

[0042] Furthermore, the present invention provides a control method for an ultrasonic diagnostic device, wherein,

[0043] An ultrasonic image is generated from the received signal obtained by transmitting and receiving ultrasonic beams on the subject using an ultrasonic probe.

[0044] By analyzing ultrasound images, the accuracy of identifying blood vessels in the ultrasound images as arteries and veins is calculated.

[0045] Based on the accuracy of classifying a blood vessel as an artery or a vein, this determines whether a blood vessel is an artery or a vein, or whether further processing is needed to determine whether a blood vessel is an artery or a vein.

[0046] If it is determined that a specific action is required, the action is performed, and based on the result of the action, it is determined whether the blood vessel is an artery or a vein.

[0047] Invention Effects

[0048] This invention determines the type of blood vessel based on the accuracy of identifying it as an artery or a vein. When the type of blood vessel cannot be determined, a determining process is performed to confirm whether the vessel is an artery or a vein. Therefore, it can prevent misidentification of blood vessel type and significantly improve the accuracy of blood vessel type determination. Furthermore, this invention only performs the determining process when the type of blood vessel cannot be determined, thus greatly suppressing any reduction in usability. Attached Figure Description

[0049] Figure 1 This is a block diagram illustrating one embodiment of the structure of an ultrasound diagnostic device.

[0050] Figure 2 This is a block diagram illustrating one embodiment of the transceiver circuit structure.

[0051] Figure 3 This is a block diagram illustrating one embodiment of the structure of the image generation unit.

[0052] Figure 4 This is a block diagram illustrating one embodiment of the structure of the blood vessel processing unit.

[0053] Figure 5 This is a flowchart illustrating one embodiment of the operation of an ultrasound diagnostic device when capturing ultrasound images.

[0054] Figure 6 This is a flowchart illustrating one embodiment of the operation of an ultrasound diagnostic device when determining the type of blood vessels in an ultrasound image.

[0055] Figure 7 This is a flowchart illustrating another embodiment of the operation of an ultrasound diagnostic device when determining the type of blood vessels in an ultrasound image.

[0056] Figure 8 This is a conceptual diagram of one embodiment of an ultrasound image displayed by overlapping enclosing lines representing the region surrounding a blood vessel cross-section.

[0057] Figure 9 This is a conceptual diagram of another embodiment of an ultrasound image showing an overlapping of the enclosing lines of the region surrounding a blood vessel cross-section.

[0058] Figure 10 This is a conceptual diagram of one embodiment of an ultrasound image displayed by overlaying graphics representing a region showing a cross-section of a blood vessel.

[0059] Figure 11 This is a conceptual diagram of another embodiment of an ultrasound image displayed by overlaying graphics showing a cross-section of a blood vessel.

[0060] Figure 12This is a conceptual diagram of one embodiment of a message urging the operator to use an ultrasonic probe to press on the examination area of ​​the subject.

[0061] Figure 13A This is a conceptual diagram illustrating one embodiment of an ultrasound image taken when the area being examined is not compressed by the ultrasound probe.

[0062] Figure 13B This is a conceptual diagram illustrating one embodiment of an ultrasound image taken when the area being examined is compressed by an ultrasound probe.

[0063] Figure 14 This is a conceptual diagram of one embodiment of a message urging the operator to tilt the ultrasonic probe at the examination site of the subject. Detailed Implementation

[0064] Hereinafter, the ultrasonic diagnostic apparatus and its control method according to the present invention will be described in detail based on the preferred embodiments shown in the accompanying drawings.

[0065] Figure 1 This is a block diagram illustrating one embodiment of the structure of the ultrasonic diagnostic device of the present invention. Figure 1 The ultrasonic diagnostic device 20 shown includes: an ultrasonic probe 1 and a device body 3 connected to the ultrasonic probe 1.

[0066] Ultrasonic probe 1 scans the examination area of ​​the subject using an ultrasonic beam and outputs an acoustic signal corresponding to the ultrasonic image of that examination area. For example... Figure 1 As shown, the ultrasonic probe 1 includes a transducer array 11 and a transceiver circuit 14. The transducer array 11 and the transceiver circuit 14 are bidirectionally connected. Furthermore, the device control unit 36 ​​of the device body 3, which will be described later, is connected to the transceiver circuit 14.

[0067] The transducer array 11 has multiple ultrasonic transducers arranged in one or two dimensions. These transducers transmit ultrasonic waves according to the drive signal supplied from the transceiver circuit 14, and receive reflected waves from the subject to output analog received signals.

[0068] Each oscillator is constructed using, for example, the following components: electrodes are formed at both ends of a piezoelectric material composed of piezoelectric ceramics such as PZT (Lead Zirconate Titanate), polymer piezoelectric elements such as PVDF (Poly Vinylidene Di Fluoride), and piezoelectric single crystals such as PMN-PT (Lead Magnesium Niobate-Lead Titanate solid solution).

[0069] Under the control of the device control unit 36, the transceiver circuit 14 transmits ultrasonic waves from the transducer array 11, and performs reception focus processing on the received signal output from the transducer array 11 that receives the ultrasonic echo, thereby generating an acoustic signal. Figure 2 As shown, the transceiver circuit 14 includes: a pulse generator 51 connected to the oscillator array 11, an amplification unit 52 connected in series from the oscillator array 11, an AD (Analog to Digital) conversion unit 53, and a beam shaper 54.

[0070] The pulse generator 51, for example, includes multiple pulse generators. Based on the transmission delay mode selected by the device control unit 36, it adjusts the delay amount and supplies each drive signal to multiple oscillators so that the ultrasonic waves transmitted from the multiple oscillators of the oscillator array 11 form an ultrasonic beam. Thus, when a pulsed or continuous wave voltage is applied to the electrodes of the oscillators of the oscillator array 11, the piezoelectric element expands and contracts to generate pulsed or continuous wave ultrasonic waves from each oscillator, and the composite wave of these ultrasonic waves forms an ultrasonic beam.

[0071] The transmitted ultrasonic beam is reflected by an object such as a part of the subject being examined and propagates toward the transducer array 11 of the ultrasonic probe 1. Each transducer constituting the transducer array 11 expands and contracts by receiving the ultrasonic echoes propagating toward the transducer array 11 as described above, generating received signals as electrical signals, and outputting these received signals to the amplification unit 52.

[0072] The amplification unit 52 amplifies the signals input from each oscillator constituting the oscillator array 11 and sends the amplified signals to the AD conversion unit 53. The AD conversion unit 53 converts the analog signals sent from the amplification unit 52 into digital received data and outputs this received data to the beam shaper 54.

[0073] The beam shaper 54 assigns a delay to each received data converted by the AD converter 53 and adds them together according to the sound velocity or sound velocity distribution set based on the receiving delay mode selected by the device control unit 36, thereby performing so-called receiving focus processing. Through this receiving focus processing, the received data converted by the AD converter 53 are phase-integrated and added together, and an ultrasonic echo signal with a reduced focus is generated.

[0074] Next, the main body 3 of the device generates an ultrasonic image of the examination site of the subject based on the acoustic signal generated by the ultrasonic probe 1, and displays the ultrasonic image of the examination site of the subject. For example... Figure 1 As shown, the main body 3 of the device includes: an image generation unit 31, an image memory 32, a blood vessel processing unit 35, a display control unit 33, a display (show unit) 34, an input device 37, and a device control unit 36.

[0075] The image generation unit 31 is connected to the transceiver circuit 14. A display control unit 33 and a display 34 are connected in series within the image generation unit 31. Furthermore, an image memory 32 and a blood vessel processing unit 35 are connected to the image generation unit 31, and the display control unit 33 is connected to both the image memory 32 and the blood vessel processing unit 35. A device control unit 36 ​​is connected to the transceiver circuit 14, the image generation unit 31, the display control unit 33, the image memory 32, and the blood vessel processing unit 35. An input device 37 is connected to the device control unit 36.

[0076] Under the control of the device control unit 36, the image generation unit 31 generates an ultrasonic image (ultrasonic image signal) of the examination area of ​​the subject from the received signal obtained by transmitting and receiving an ultrasonic beam at the examination site of the subject using an ultrasonic probe 1 (more precisely, using a transducer array 11), and further from the acoustic signal generated from the received signal by the transceiver circuit 14. Figure 3 As shown, the image generation unit 31 has a structure in which the signal processing unit 16, the DSC (Digital Scan Converter) 18 and the image processing unit 17 are connected in series.

[0077] The signal processing unit 16 generates image information data corresponding to the ultrasound image based on the acoustic signal generated by the transceiver circuit 14. More specifically, after performing signal processing on the acoustic signal generated by the beam shaper 54 of the transceiver circuit 14, the signal processing unit 16 performs envelope detection processing, for example, after correcting for attenuation caused by propagation distance based on the depth of the location where the ultrasound is reflected, thereby generating image information data representing tomographic image information related to the tissue in the examined body.

[0078] DSC18 converts the image information data generated by the signal processing unit 16 into an image signal scanned in the manner of a conventional television signal.

[0079] The image processing unit 17 performs various image processing operations on the image signal input from the DSC18, such as brightness correction, grayscale correction, sharpness correction, image size correction, refresh rate correction, scanning frequency correction, and color correction according to the display format of the display 34, to generate an ultrasound image (ultrasound image signal), and outputs the image-processed ultrasound image to the image memory 32, the blood vessel processing unit 35, and the display control unit 33.

[0080] The image memory 32 is a memory that holds a series of multiple frames of ultrasonic images (ultrasonic image signals) generated by the image generation unit 31 during each inspection, under the control of the device control unit 36. The image memory 32 can be a recording medium such as flash memory, HDD (Hard Disk Drive), SSD (Solid State Drive), FD (Flexible Disc), MO (Magneto-Optical Disc), MT (Magnetic Tape), RAM (Random Access Memory), CD (Compact Disc), DVD (Digital Versatile Disc), SD card (Secure Digital Card), USB memory (Universal Serial Bus memory), or an external server.

[0081] Under the control of the device control unit 36, the vascular processing unit 35 performs various processing steps to determine the type of blood vessels in the ultrasound image of the examination site of the subject, that is, to determine whether the blood vessel is an artery or a vein. For example... Figure 4 As shown, the blood vessel processing unit 35 includes an accuracy calculation unit 61, a blood vessel determination unit 62, and a blood vessel determination unit 63. In the accuracy calculation unit 61, the blood vessel determination unit 62 and the blood vessel determination unit 63 are connected in series.

[0082] The accuracy calculation unit 61 analyzes the ultrasound image of the examination site of the subject and calculates the accuracy of the blood vessels in the ultrasound image as arteries and the accuracy of the blood vessels as veins.

[0083] Regarding the accuracy calculation unit 61, there are no particular limitations. It can analyze ultrasound images and calculate the accuracy of blood vessels as arteries and the accuracy of blood vessels as veins by using at least one of the following image analysis techniques: machine learning models learned using machine learning techniques such as deep learning, template matching, and image analysis techniques using features such as Adaboost (Adaptive Boosting), SVM (Support Vector Machine), or SIFT (Scale-Invariant Feature Transform).

[0084] The vessel determination unit 62 determines whether a vessel is an artery or a vein based on the accuracy of its identification as an artery or a vein, or whether additional determination processing is needed to determine whether the vessel is an artery or a vein. In other words, the vessel determination unit 62 determines whether the type of vessel can be determined solely based on the accuracy of its identification as an artery or a vein.

[0085] Furthermore, the specific details regarding the determined treatment will be described later.

[0086] If the vessel determination unit 62 determines that a determination process is required, the vessel determination unit 63 performs the determination process and determines whether the vessel in the ultrasound image is an artery or a vein based on the execution result of the determination process.

[0087] Under the control of the device control unit 36, the display control unit 33 displays various information on the display 34. For example, the display control unit 33 performs prescribed processing on the ultrasound image stored in the image memory 32 and displays the processed ultrasound image on the display 34. Furthermore, the display control unit 33 displays the determination results of whether a blood vessel is an artery or a vein on the display 34.

[0088] Under the control of the display control unit 33, the display 34 displays the aforementioned information. Examples of the display 34 include LCD (Liquid Crystal Display) and organic EL (Electro-Luminescence) displays.

[0089] Input device 37 accepts various commands input by the operator (inspector) of the ultrasound diagnostic device. Input device 37 is not specifically limited to any particular type and may include various buttons or touch panels where the operator inputs commands via touch.

[0090] The device control unit 36 ​​controls the ultrasonic probe 1 and the device body 3 based on pre-stored programs and operator commands input from the input device 37.

[0091] The terminal-side processor 39 consists of an image generation unit 31, a blood vessel processing unit 35, a display control unit 33, and a device control unit 36.

[0092] Next, refer to Figure 5 The flowchart illustrates the operation of the ultrasound diagnostic device when capturing ultrasound images.

[0093] First, with the ultrasonic probe 1 in contact with the examination area of ​​the subject, the ultrasonic wave is transmitted through the transceiver circuit 14 under the control of the device control unit 36, thereby generating an acoustic signal (step S1).

[0094] That is, according to the drive signal from the pulse generator 51, multiple transducers of the transducer array 11 send ultrasonic beams to the examination site of the subject.

[0095] Each oscillator of the oscillator array 11 receives ultrasonic echoes from the inspection site based on ultrasonic beams sent from the pulse generator 51, and outputs received signals as analog signals from each oscillator of the oscillator array 11 that receives the ultrasonic echoes.

[0096] The amplification unit 52 amplifies the received signal output from each oscillator of the oscillator array 11, and the AD conversion unit 53 performs AD conversion to obtain the received data.

[0097] The received data is processed by the beam shaper 54 to generate an acoustic signal.

[0098] Next, under the control of the device control unit 36, the image generation unit 31 generates an ultrasonic image (ultrasonic image signal) of the examination area of ​​the subject based on the acoustic signal generated by the beam shaper 54 of the transceiver circuit 14 (step S2).

[0099] That is, the signal processing unit 16 performs various signal processing on the acoustic signal generated by the beam shaper 54 to generate image information data representing tomographic image information related to the tissue in the subject body.

[0100] The image information data generated by the signal processing unit 16 is converted by the DSC18 grating, and then various image processing is performed by the image processing unit 17 to generate an ultrasonic image (ultrasonic image signal).

[0101] The ultrasonic image generated by the image processing unit 17 is stored in the image memory 32.

[0102] Next, under the control of the device control unit 36, the display control unit 33 performs the prescribed processing on the ultrasonic image stored in the image memory 32 and displays it on the display 34 (step S3).

[0103] Next, the operation of the ultrasound diagnostic device in determining the type of blood vessels in an ultrasound image will be explained. First, refer to... Figure 6The flowchart describes the operation of an ultrasound diagnostic device when calculating the accuracy as an artery and the accuracy as a vein, detecting a vascular region (artery region, vein region) of a specified shape, such as a rectangle, circle, or polygon, containing blood vessels within an ultrasound image, and determining the type of blood vessel within that vascular region.

[0104] First, the accuracy calculation unit 61 detects the vascular region in the ultrasound image and calculates the accuracy of the blood vessels in the vascular region as arteries and the accuracy of them as veins (step S11).

[0105] The vascular region is either the arterial region, which contains arteries, or the venous region, which contains veins.

[0106] The accuracy calculation unit 61, for example, uses a machine learning model to detect arterial regions containing blood vessels in an ultrasound image and calculates the accuracy of identifying blood vessels within those regions as arteries. Furthermore, the accuracy calculation unit 61 detects venous regions containing the same blood vessels and calculates the accuracy of identifying blood vessels within those regions as veins. In other words, the accuracy calculation unit 61 performs the following processing twice for the same blood vessel: calculating the accuracy of identifying the blood vessel as an artery and calculating the accuracy of identifying it as a vein.

[0107] Here, the mechanical learning model for arteries is a learning-complete model that uses the learning ultrasound image and the correct data on the accuracy of identifying arteries in the arterial region and the blood vessels in the arterial region as arteries as teacher data, and learns the relationship between the learning ultrasound image and the correct data on the accuracy of identifying arteries in the arterial region and the blood vessels in the arterial region as arteries based on multiple teacher data.

[0108] In this case, the ultrasound image of the examination site of the subject during the examination is used as input through the mechanical learning model of the artery. The output is a prediction result that infers the arterial region and the accuracy of the blood vessels in the arterial region as arteries.

[0109] Then, the accuracy calculation unit 61 detects the arterial region in the ultrasound image based on the inference results made by the machine learning model of the artery, and calculates the accuracy of the blood vessels in the arterial region as arteries.

[0110] Furthermore, the machine learning model for veins is a learning-complete model that uses learning ultrasound images and vein regions in those learning ultrasound images, as well as correct data representing the accuracy of veins, as teacher data, and learns the relationship between learning ultrasound images and vein regions in those learning ultrasound images, as well as correct data representing the accuracy of veins, based on multiple teacher data.

[0111] In this case, the ultrasound image of the examination site of the subject during the examination is used as input by the machine learning model of veins. The output of the ultrasound image is the inferred vein region and the inferred result as the accuracy of the vein.

[0112] Then, the accuracy calculation unit 61 detects the vein region in the ultrasound image based on the inference results made by the machine learning model of the vein, and calculates the accuracy of the blood vessels in the vein region as veins.

[0113] Alternatively, the accuracy calculation unit 61 can also use a machine learning model to detect a single blood vessel region containing a prescribed shape of blood vessels within the ultrasound image, and then calculate the accuracy of the blood vessels within that single blood vessel region as arteries and as veins. A single blood vessel region refers to a region that contains blood vessels without distinguishing between arterial and venous regions. That is, the accuracy calculation unit 61 calculates the accuracy of the blood vessels as arteries and as veins in one operation.

[0114] Here, the machine learning model is a learning-complete model that uses a learning ultrasound image and a single blood vessel region containing a blood vessel of a specified shape within the learning ultrasound image, as well as the correct data on the accuracy of the blood vessels within the single blood vessel region as arteries and as veins, as teacher data, and learns the relationship between the learning ultrasound image and the single blood vessel region within the learning ultrasound image, as well as the correct data on the accuracy of the blood vessels within the single blood vessel region as arteries and as veins, based on multiple teacher data.

[0115] In this case, the machine learning model takes the ultrasound image of the examination site of the subject during the examination as input and outputs the prediction results of a single blood vessel region in the ultrasound image, the accuracy of the blood vessel in the single blood vessel region as an artery, and the accuracy of the blood vessel as a vein.

[0116] Then, based on the prediction results made by the machine learning model, the accuracy calculation unit 61 detects a single blood vessel region in the ultrasound image and calculates the accuracy of identifying the blood vessel in the single blood vessel region as an artery and the accuracy of identifying it as a vein.

[0117] Next, the vessel determination unit 62 determines whether the vessel is an artery or a vein based on the accuracy of the vessel being identified as an artery or a vein, or determines whether a determination process is required (step S12).

[0118] Here, in the first case where the accuracy of one of the arteries or veins is above the first threshold and the accuracy of the other of the arteries or veins is less than the second threshold which is smaller than the first threshold (Yes in step S12), the vessel determination unit 62 determines that the vessel is one of the arteries or veins (step S13).

[0119] When it is determined that the blood vessel is either an artery or a vein, the display control unit 33, based on the determination result, overlays a graphic containing the blood vessel onto the ultrasound image and displays it on the display 34 (step S14). For example, as Figure 8 As shown, as a graphic representation, the rectangular enclosing line of the region surrounding the blood vessel cross-section overlaps with the ultrasound image and is displayed on the display 34. Furthermore, in addition to this enclosing line, the accuracy of the blood vessel as an artery and the accuracy as a vein are also displayed on the display 34.

[0120] Furthermore, in this invention, the accuracy of a blood vessel as an artery and the accuracy of it as a vein do not necessarily have to be displayed on the display 34. That is, the accuracy of a blood vessel as an artery and the accuracy of it as a vein may or may not be displayed on the display 34.

[0121] exist Figure 8 In the example shown, in the center of the ultrasound image, the bounding line 71 of the rectangle containing the artery is displayed overlapping with the ultrasound image, and in addition, characters such as "80%" are displayed as the accuracy of the artery. Furthermore, in the lower center of the ultrasound image, the bounding line 72 of the rectangle containing the vein is displayed overlapping with the ultrasound image, and in addition, characters such as "70%" are displayed as the accuracy of the vein.

[0122] like Figure 8 As shown, the accuracy of identifying a blood vessel in the central part of the ultrasound image as an artery is 80%, and the accuracy as a vein is 0%. For example, let the first threshold be 80% and the second threshold be 20%. In this case, since the accuracy of identifying the blood vessel as an artery is 80% or more of the first threshold and the accuracy of identifying it as a vein is 0% or less than the second threshold of 20%, the blood vessel determination unit 62 determines that the blood vessel is an artery.

[0123] In addition, Figure 8 In the diagram, solid lines represent the enclosing lines 71 containing arteries, and dashed lines represent the enclosing lines 72 containing veins. However, there are no particular limitations on the brightness, chromaticity, line type, and shape of the enclosing lines 71 and 72.

[0124] On the other hand, in the second case other than the first case mentioned above (no in step S12), that is, when the accuracy of the blood vessel as an artery or vein is above the first threshold and the accuracy of the blood vessel as the other artery or vein is less than the second threshold which is smaller than the first threshold, the blood vessel determination unit 62 determines whether additional determination processing is required (step S15).

[0125] For example, in Figure 9 In the example shown, in the blood vessel in the central part of the ultrasound image, the bounding line 71 of the rectangle representing the artery is displayed overlapping with the ultrasound image. In addition, characters such as "80%" are displayed as the accuracy of the artery. Furthermore, in the same blood vessel, the bounding line 72 of the rectangle representing the vein is displayed overlapping with the ultrasound image. In addition, characters such as "90%" are displayed as the accuracy of the vein.

[0126] like Figure 9 As shown, the accuracy of identifying blood vessels in the central part of the ultrasound image as arteries is 80%, and as veins is 90%. Figure 8 Similarly, in the case of the example, the first threshold is set to 80% and the second threshold is set to 20%. In this case, since the accuracy of the blood vessel as an artery is 80% or more of the first threshold, but the accuracy as a vein is 90% or less than the second threshold of 20%, the blood vessel determination unit 62 determines that it needs to be determined.

[0127] in addition, Figure 9 The ultrasound image shown is a conceptual diagram illustrating a state where the accuracy of identifying the same blood vessel as an artery and the accuracy of identifying it as a vein are both not 0%, and is not displayed on display 34.

[0128] When it is determined that a determination process is required, the determination process is performed by the blood vessel determination unit 63 (step S16), and the type of blood vessel, i.e., whether the blood vessel is an artery or a vein, is determined based on the execution result (step S17).

[0129] When it is determined whether a blood vessel is an artery or a vein, the display control unit 33, based on the determination result, overlays a graphic containing the blood vessel onto the ultrasound image and displays it on the display 34 (step S18). For example, as Figure 8 Similarly, in the example shown, as a graphic, the bounding line of the rectangle surrounding the region of the blood vessel cross-section is superimposed on the ultrasound image and displayed on the display 34.

[0130] In addition, the aforementioned actions are repeated for each frame of the ultrasound image and for each blood vessel region.

[0131] Next, refer to Figure 7The flowchart describes how, for each pixel in an ultrasound image, a pixel is determined to be either an artery pixel or a vein pixel, and based on this result, the operation of the ultrasound diagnostic device when determining the type of blood vessel is explained.

[0132] First, the accuracy calculation unit 61 calculates the accuracy of each pixel in the ultrasound image as an artery pixel, the accuracy as a vein pixel, and the accuracy as a background pixel other than a blood vessel (step S21). The accuracy calculation unit 61 uses, for example, a machine learning model for accuracy estimation to calculate the accuracy of each pixel as an artery pixel, the accuracy as a vein pixel, and the accuracy as a background pixel other than a blood vessel.

[0133] Here, the machine learning model is a learning-complete model that uses a learning ultrasound image and the correct data for each pixel of the learning ultrasound image, indicating whether the pixel is an artery pixel, a vein pixel, or a background pixel, as teacher data, and learns the relationship between the learning ultrasound image and the correct data for each pixel of the learning ultrasound image, indicating whether the pixel is an artery pixel, a vein pixel, or a background pixel, based on multiple teacher data.

[0134] In this case, the machine learning model takes the ultrasound image of the examination site of the subject during the examination as input and outputs the prediction results for each pixel of the ultrasound image, predicting the accuracy of the pixel as an artery pixel, the accuracy of the pixel as a vein pixel, and the accuracy of the pixel as a background pixel.

[0135] Then, based on the prediction results made by the machine learning model, the accuracy calculation unit 61 calculates the accuracy of each pixel in the ultrasound image as an artery pixel, the accuracy as a vein pixel, and the accuracy as a background pixel.

[0136] Next, the blood vessel determination unit 62 determines the type of a pixel—whether it is an artery pixel, a vein pixel, or a background pixel—based on the accuracy of the pixel as an artery pixel, the accuracy as a vein pixel, and the accuracy as a background pixel for each pixel in the ultrasound image (step S22).

[0137] For example, the blood vessel determination unit 62 determines the pixel as the type of pixel with the highest accuracy for the same pixel. That is, if the accuracy is highest for an artery pixel, the pixel is determined to be an artery pixel. Similarly, if the accuracy is highest for a vein pixel, the pixel is determined to be a vein pixel, and if the accuracy is highest for a background pixel, the pixel is determined to be a background pixel.

[0138] Next, the vessel determination unit 62 determines the vessel region containing the vessel based on the artery pixels and vein pixels (step S23). For example, the vessel determination unit 62 determines the region represented by the collection (block) of artery pixels and vein pixels as the vessel region.

[0139] Next, the vessel determination unit 62 determines whether the vessel in the vessel region is an artery or a vein based on the area of ​​the artery pixel and the area of ​​the vein pixel relative to the area of ​​the vessel in the vessel region, or determines whether a determination process is required (step S24).

[0140] Here, if the ratio of the area of ​​an artery pixel to the area of ​​a vein pixel relative to the area of ​​the blood vessel in the blood vessel region is a third threshold or higher (yes in step S24), the blood vessel determination unit 62 determines that the blood vessel is an artery or a vein (step S25).

[0141] When it is determined that the blood vessel is an artery or a vein, the display control unit 33, based on the determination result, overlays a graphic containing the blood vessel onto the ultrasound image and displays it on the display 34 (step S26). For example, as Figure 10 As shown, a graphic representing the region of the blood vessel cross-section is superimposed on the ultrasound image and displayed on the monitor 34.

[0142] exist Figure 10 In the example shown, the graphic 73 representing the region of arterial pixels is superimposed on the ultrasound image in the center. Furthermore, the graphic 74 representing the region of vein pixels is superimposed on the ultrasound image in the lower left of the center of the ultrasound image, and the graphic 73 representing the region of arterial pixels is superimposed on the ultrasound image in the right.

[0143] For example, Figure 10 In the ultrasound image shown, the area of ​​the blood vessel in the central vascular region is 100, the area of ​​the artery pixel in this vascular region is 100, the area of ​​the vein pixel is 0, and the third threshold is set to 0.8. In this case, relative to the area of ​​the blood vessel in the vascular region being 100, the area of ​​the artery pixel being 100 is 100 / 100 = 1, which is greater than or equal to the third threshold of 0.8. Therefore, the vascular determination unit 62 determines that the blood vessel is an artery.

[0144] In addition, Figure 10 In Figures 73 and 74, a defined shaded line is applied to the area of ​​the artery pixel and the area of ​​the vein pixel, but this is not limited to this; for example, it can be colored with a semi-transparent color, or it can be represented by a diagonal line. Alternatively, the aforementioned enclosing line can be displayed, or only the enclosing line can be displayed. Figure 8 The same applies to the example shown.

[0145] On the other hand, if the ratio of the area of ​​the artery pixel to the area of ​​the vein pixel relative to the area of ​​the blood vessel in the blood vessel region is less than the third threshold (no in step S24), the blood vessel determination unit 62 determines that additional determination processing is required (step S27).

[0146] For example, in Figure 11 In the example shown, in the vascular region of the central part of the ultrasound image, the graphic 73 representing the artery pixels in the central part in the left-right direction is superimposed on the ultrasound image and displayed, while the graphic 74 representing the vein pixels on both sides are superimposed on the ultrasound image and displayed. That is, both artery pixels and vein pixels coexist in the same vascular region.

[0147] For example, Figure 11 In the ultrasound image shown, the area of ​​the blood vessels in the central vascular region is 100, the area of ​​the artery pixels in this vascular region is 40, the area of ​​the vein pixels is 60, and the third threshold is set to 0.8. In this case, relative to the area of ​​the blood vessels in the vascular region of 100, the area of ​​the artery pixels of 40 is 40 / 100 = 0.4, and the area of ​​the vein pixels of 60 is 60 / 100 = 0.6, neither of which is greater than the third threshold of 0.8. Therefore, the blood vessel determination unit 62 determines that it needs to be processed.

[0148] in addition, Figure 11 The ultrasound image shown is a conceptual diagram illustrating a state where neither the area of ​​the arterial pixel nor the area of ​​the vein pixel in the same vascular region is 0, and is not displayed on the monitor 34.

[0149] When it is determined that a determination process is required, the determination process is performed by the blood vessel determination unit 63 (step S28), and the type of blood vessel, i.e., whether the blood vessel is an artery or a vein, is determined based on the execution result (step S29).

[0150] When it is determined whether a blood vessel is an artery or a vein, the display control unit 33, based on the determination result, overlays a graphic containing the blood vessel onto the ultrasound image and displays it on the display 34 (step S30). For example, with Figure 10 Similarly, in the example shown, the graphic representing the region of the blood vessel cross-section is superimposed on the ultrasound image and displayed on the monitor 34.

[0151] Similarly, the aforementioned actions are repeated for each frame of the ultrasound image and for each blood vessel region.

[0152] Next, the determination process will be explained. There are no particular limitations on the determination process; examples include methods such as pressing the examination site, using color Doppler mode, and using ultrasound images from past frames.

[0153] First, the method of pressing the examination site will be explained.

[0154] In this situation, the vessel identification unit 63 prompts the operator to use the ultrasound probe 1 to compress the examination site of the subject. For example, as Figure 12 As shown, the message from the blood vessel determination unit 63 to urge the operator is displayed on the display 34 via the display control unit 33. Figure 12 In the right part of the ultrasound image, a diagram showing the pressing of the ultrasound probe is displayed, and below it, the words "Press!" are displayed. Alternatively, a speaker can be provided in the blood vessel identification unit 63 to output a voice to urge the operator, or both messages and sounds can be used to urge the operator.

[0155] Next, the vessel determination unit 63 calculates the aspect ratio of the vessel profile based on the ultrasound image generated when the examination site is compressed by the ultrasound probe 1.

[0156] Here, it should be from such Figure 13A The examination area shown is no longer compressed, and the condition changes as follows: Figure 13B When the examination site is compressed, the artery represented by enclosing line 71 is almost not compressed due to high internal pressure, while the vein represented by enclosing line 72 is significantly compressed due to low internal pressure, causing a change in the aspect ratio of the vein's cross-section. For example... Figure 13B As shown, for example, the horizontal length / vertical length increases.

[0157] Then, the vessel identification unit 63 determines whether the vessel is an artery or a vein based on the aspect ratio of the vessel cross-section. That is, if the aspect ratio of the vessel cross-section does not change, it means that the vessel is not compressed, and therefore the vessel identification unit 63 determines that the vessel is an artery. Conversely, if the aspect ratio of the vessel cross-section changes, it means that the vessel is compressed, and the vessel identification unit 63 determines that the vessel is a vein.

[0158] In addition, by providing a pressure sensor in the ultrasound probe 1 to detect the pressure applied to the contact surface with the examination site of the subject, the blood vessel determination unit 63 can determine whether the examination site is compressed based on the pressure detected by the pressure sensor.

[0159] Furthermore, the vessel determination unit 63 can detect the movement of the examination site by analyzing multiple frames of ultrasound images that are sequential in time, such as optical flow, and determine whether the examination site is compressed based on the movement of the examination site.

[0160] Furthermore, the vessel identification unit 63 can also prompt the operator to apply pressure to the examination site using the ultrasonic probe 1, and within a specified time, determine whether there is a change in the aspect ratio of the vessel cross-section, and based on whether the aspect ratio of the vessel changes within the specified time, determine whether the examination site is compressed. With this determination method, image analysis such as the aforementioned pressure sensor and motion detection is not required.

[0161] In this case, it is expected that the vessel determination unit 63, through the display control unit 33, will display the remaining time of the aforementioned predetermined time, i.e., the time for determining whether the aspect ratio of the vessel cross-section has changed, on the display 34. Thus, the operator can determine the duration of pressure applied to the examination site using the ultrasound probe 1, in other words, the moment when pressure applied to the examination site using the ultrasound probe 1 ends.

[0162] Next, the method of using color Doppler modes will be explained.

[0163] In this situation, the vascular identification unit 63 prompts the operator to tilt the ultrasound probe 1 towards the peripheral or central side of the examination site on the subject. For example, as Figure 14 As shown, the message from the blood vessel determination unit 63 to urge the operator is displayed on the display 34 via the display control unit 33. Figure 14 In the middle, on the right side of the ultrasound image, a schematic diagram showing the tilted ultrasound probe is displayed, and below it, the characters "Tilted!" are displayed. Similarly, the vessel identification unit 63 can output a voice to urge the operator from a speaker, or it can use both messages and voice.

[0164] Next, in color Doppler mode, the vessel determination unit 63 determines whether a vessel is an artery or a vein based on the direction of blood flow in the ultrasound image generated when the ultrasound probe 1 is tilted at the examination site. For example, if the ultrasound probe 1 is tilted to the peripheral side, and the direction of blood flow is closer to the ultrasound probe 1, the vessel determination unit 63 determines that the vessel is an artery; if the direction of blood flow is away from the ultrasound probe 1, it determines that the vessel is a vein. On the other hand, if the ultrasound probe 1 is tilted to the central side, the vessel determination unit 63 determines the opposite result to that when the ultrasound probe 1 is tilted to the peripheral side.

[0165] In addition, since it is only necessary to determine the direction of blood flow, it is not necessary to display the direction of blood flow in color in the ultrasound image.

[0166] Then, after determining whether the blood vessel is an artery or a vein in the vessel identification section 63, the color Doppler mode ends.

[0167] Next, the method of using ultrasound images from past frames will be explained.

[0168] In this case, the vessel identification unit 63 searches for frames of ultrasound images in the image memory 32 where the accuracy of identifying the same vessel as the vessel in the ultrasound image at the time of examination as an artery or as a vein is at least a fourth threshold. For example, the vessel identification unit 63 searches for the frame of ultrasound images in the past frames where the accuracy of identifying the same vessel as an artery or as a vein is the highest.

[0169] In addition, the blood vessel determination unit 63 can detect blood vessels in adjacent ultrasound images of consecutive frames, and if the overlap ratio of blood vessels in the ultrasound images of consecutive frames is 4 or higher, it can determine that they are the same blood vessels.

[0170] Then, the vessel identification unit 63 determines whether the vessel in the ultrasound image at the time of examination is an artery or a vein based on the accuracy of identifying the same vessel as an artery or a vein in the ultrasound images of frames searched from past frames. That is, the accuracy of identifying the same vessel as an artery or a vein in the current frame's ultrasound image is directly used from the accuracy of identifying the same vessel as an artery or a vein in the ultrasound images of past frames.

[0171] As described above, the ultrasound diagnostic device determines the type of blood vessel based on the accuracy of identifying it as an artery or a vein. When the type of blood vessel cannot be determined, a determination process is performed to identify whether the vessel is an artery or a vein. Therefore, misidentification of blood vessel type can be prevented, and the accuracy of blood vessel type determination can be significantly improved. Furthermore, since the ultrasound diagnostic device only performs the determination process when the type of blood vessel cannot be determined, it can significantly suppress any reduction in usability.

[0172] Furthermore, when using an ultrasound diagnostic device to perform punctures into blood vessels, the operator needs to be proficient in scanning the examination site and interpreting the ultrasound images. For inexperienced operators, scanning the examination site and interpreting the ultrasound images is not easy. Therefore, as described above, by determining the area containing blood vessels and the type of blood vessels, and displaying the determination result on the display 34, the operator can be supported in mastering the scanning of the examination site and interpreting the ultrasound images.

[0173] Furthermore, the display control unit 33 can overlay a graphic containing a blood vessel onto an ultrasound image and display it on the display 34 based on at least one of the determination result of whether the blood vessel is an artery or a vein and the confirmation result of whether the blood vessel is an artery or a vein. That is, the graphic containing a blood vessel can be overlaid onto the ultrasound image and displayed on the display 34 based on both the determination result and the confirmation result.

[0174] In this case, the accuracy calculation unit 61 calculates a score, for example, based on the aspect ratio of the blood vessel cross-section in the ultrasound image generated when the examination site is compressed by the ultrasound probe 1. Then, the accuracy calculation unit 61 weights and averages the accuracy of the blood vessel as an artery and the accuracy as a vein with the aforementioned score of the aspect ratio of the blood vessel cross-section, thereby calculating the final score of the blood vessel as an artery and the final score as a vein.

[0175] Then, the display control unit 33 replaces the accuracy of the blood vessel as an artery and the accuracy as a vein, and displays the final score of the blood vessel as an artery and the final score as a vein on the display 34 by superimposing them on the ultrasound image. Thus, the operator can know the final score of the blood vessel as an artery and the final score as a vein, which is more accurate than the accuracy of the blood vessel as an artery and the accuracy of the blood vessel as a vein.

[0176] Similarly, the vessel determination unit 62 can replace the accuracy of the vessel as an artery and the accuracy of the vessel as a vein, and determine whether the vessel is an artery or a vein based on the final score of the vessel as an artery and the final score of the vessel as a vein, or determine whether a determination process is required.

[0177] Furthermore, once the display control unit 33 determines whether a blood vessel is an artery or a vein, it displays the same graphic on the display 34 for the same blood vessel. As a result, the processing required to determine the type of blood vessel can be significantly reduced.

[0178] Furthermore, if the determination process fails to identify whether a blood vessel is an artery or a vein, the display control unit 33 can display characters such as "blood vessel" on the display 34 in addition to the graphic. This allows the operator to recognize the presence of a blood vessel within the graphic area.

[0179] Furthermore, in the determination process, such as the method of pressing the aforementioned examination site, the method of using color Doppler mode, and the method of using ultrasound images from past frames, two or more determination processes can be used in combination.

[0180] Here, in the method of pressing the examination site, the operator uses the ultrasound probe 1 to press the examination site. In the method using color Doppler mode, the operator needs to tilt the ultrasound probe 1 at the examination site. However, in the method using past frame ultrasound images, the operator does not need to do so. Therefore, it is desirable to first execute the method using past frame ultrasound images. If the type of blood vessel cannot be determined based on the execution result, the method of pressing the examination site and the method using color Doppler mode are executed sequentially, and the determination process is performed in stages.

[0181] Furthermore, this invention is not limited to fixed ultrasound diagnostic devices; it is also applicable to portable ultrasound diagnostic devices where the main body 3 is implemented using a laptop terminal device, and to handheld ultrasound diagnostic devices where the main body 3 is implemented using a handheld terminal device such as a smartphone or tablet PC. The ultrasound probe 1 and the main body 3 can be connected via a wired connection or a wireless connection. Additionally, the entire image generation unit 31 or only the signal processing unit 16 can be located on the ultrasound probe 1 side, or they can be located on the main body 3 side.

[0182] In the device of the present invention, the hardware structure of the processing unit that performs various processes such as the transceiver circuit 14, the image generation unit 31, the display control unit 33, the blood vessel processing unit 35, and the device control unit 36 ​​can be dedicated hardware or various processors or computers that execute programs.

[0183] Various processors include: common processors that execute software (programs) to perform the functions of various processing units, namely CPUs (Central Processing Units); FPGAs (Field Programmable Gate Arrays), which can change their circuit structure after manufacturing, namely Programmable Logic Devices (PLDs); and processors with circuit structures specifically designed to perform specific processes, such as ASICs (Application Specific Integrated Circuits), namely dedicated circuits.

[0184] A processing unit can be constructed from one of these various processors, or it can be constructed from a combination of two or more processors of the same or different types, such as a combination of multiple FPGAs or a combination of an FPGA and a CPU. Furthermore, multiple processing units can be constructed from one of various processors, or two or more processing units can be combined and constructed using a single processor.

[0185] For example, in computers such as servers and clients, there exist processors that consist of a combination of one or more CPUs and software, and that processor functions as multiple processing units. Furthermore, in systems-on-chips (SoCs), there exist processors that use a single integrated circuit (IC) chip to implement the overall functionality of a system including multiple processing units.

[0186] Furthermore, more specifically, the hardware architecture of these various processors is a circuit composed of circuit elements such as semiconductor components.

[0187] Furthermore, the method of the present invention can be implemented, for example, by a program for causing a computer to perform its various steps. Also, a computer-readable recording medium containing the program can be provided.

[0188] The present invention has been described in detail above, but the present invention is not limited to the above embodiments. It is self-evident that various improvements or modifications can be made without departing from the spirit of the present invention.

[0189] Symbol Explanation

[0190] 1-Ultrasound probe, 3-Device body, 11-Vortex array, 14-Transceiver circuit, 16-Signal processing unit, 17-Image processing unit, 18-DSC, 31-Image generation unit, 32-Image memory, 33-Display control unit, 34-Display, 35-Vessel processing unit, 36-Device control unit, 37-Input device, 39-Processor, 51-Pulse generator, 52-Amplification unit, 53-AD conversion unit, 54-Beam shaper, 61-Accuracy calculation unit, 62-Vessel determination unit, 63-Vessel identification unit, 71, 72-Enclosure line, 73, 74-Graphics.

Claims

1. An ultrasonic diagnostic device, comprising: Ultrasonic probe; The image generation unit generates an ultrasonic image from the received signal obtained by transmitting and receiving an ultrasonic beam on the subject using the ultrasonic probe. The accuracy calculation unit analyzes the ultrasound image and calculates the accuracy of identifying blood vessels in the ultrasound image as arteries and the accuracy of identifying them as veins, respectively. The vessel determination unit determines that the vessel is either an artery or a vein in a first case where the accuracy of identifying the vessel as either an artery or a vein is greater than or equal to a first threshold, and the accuracy of identifying the vessel as either an artery or a vein is less than a second threshold smaller than the first threshold. In a second case other than the first case, it determines that a determination process for determining whether the vessel is an artery or a vein is required. The vessel identification unit performs the identification process when it determines that the identification process is required, and determines whether the vessel is an artery or a vein based on the result of the identification process.

2. The ultrasonic diagnostic device according to claim 1, wherein, When calculating the accuracy for the artery and the accuracy for the vein, the accuracy calculation unit detects a vascular region containing a prescribed shape of blood vessel within the ultrasound image.

3. The ultrasonic diagnostic device according to claim 2, wherein, The vascular region is either an arterial region containing the artery or a venous region containing the vein. The accuracy calculation unit detects the arterial region containing the blood vessel within the ultrasound image, calculates the accuracy of identifying the blood vessel within the arterial region as the artery, and detects the vein region containing the same blood vessel, calculates the accuracy of identifying the same blood vessel within the vein region as the vein.

4. The ultrasonic diagnostic device according to claim 2, wherein, The accuracy calculation unit detects a single blood vessel region containing a prescribed shape of blood vessels within the ultrasound image, and then calculates the accuracy of identifying the blood vessel within the single blood vessel region as an artery and the accuracy of identifying it as a vein.

5. The ultrasonic diagnostic device according to claim 1, wherein, The accuracy calculation unit calculates the accuracy of each pixel in the ultrasound image as an artery pixel, an artery pixel, and a background pixel other than the blood vessel.

6. The ultrasound diagnostic apparatus according to any one of claims 1 to 5, wherein, The vessel identification unit enables the operator to use the ultrasound probe to press on the examination site of the subject, calculate the aspect ratio of the vessel section based on the ultrasound image generated under the pressure of the ultrasound probe on the examination site, and determine whether the vessel is an artery or a vein based on the aspect ratio of the vessel section.

7. The ultrasonic diagnostic device according to claim 6, wherein, The ultrasonic probe has a pressure sensor. The blood vessel determination unit determines whether the examination site is being compressed based on the pressure detected by the pressure sensor.

8. The ultrasonic diagnostic device according to claim 6, wherein, The blood vessel determination unit detects the movement of the examination site by analyzing multiple frames of the ultrasound images, and determines whether the examination site is being compressed based on the movement of the examination site.

9. The ultrasonic diagnostic device according to claim 6, wherein, The vessel identification unit determines whether the aspect ratio of the vessel cross-section changes within a specified time from the time the operator is prompted to use the ultrasonic probe to compress the examination site. Based on whether the aspect ratio of the vessel changes within the specified time, it determines whether the examination site is being compressed.

10. The ultrasonic diagnostic device according to claim 1, wherein, The vessel identification unit prompts the operator to tilt the ultrasound probe at the examination site of the subject. In color Doppler mode, based on the direction of blood flow in the ultrasound image generated when the ultrasound probe is tilted at the examination site, the vessel is determined to be either an artery or a vein.

11. The ultrasonic diagnostic device according to claim 1, wherein, The vessel identification unit searches for frames of ultrasound images in the past to determine whether the same vessel is an artery or a vein, based on the accuracy of identifying the same vessel as an artery or a vein in the searched frames of ultrasound images.

12. The ultrasonic diagnostic apparatus according to claim 11, wherein, The blood vessel determination unit detects the blood vessels in adjacent consecutive ultrasound images. If the overlap ratio of the blood vessels in the consecutive ultrasound images is greater than or equal to the fourth threshold, the blood vessels are determined to be the same.

13. The ultrasonic diagnostic device according to claim 1, wherein, The ultrasound diagnostic device includes: Displays; and The display control unit, based on at least one of the determination result that the blood vessel is the artery or the vein and the confirmation result that the blood vessel is the artery or the vein, overlays a graphic containing the blood vessel onto the ultrasound image and displays it on the display.

14. The ultrasonic diagnostic apparatus according to claim 13, wherein, In addition to the graphic, the display control unit also displays the accuracy of identifying the blood vessel as an artery and the accuracy of identifying it as a vein on the display screen.

15. The ultrasonic diagnostic apparatus according to claim 13, wherein, Once it is determined whether the blood vessel is an artery or a vein, the display control unit displays the same graphic on the display for the same blood vessel.

16. The ultrasonic diagnostic apparatus according to claim 13, wherein, In cases where it is impossible to determine whether the blood vessel is an artery or a vein, the display control unit also displays the character for "blood vessel" on the display in addition to the graphic.

17. A control method for an ultrasound diagnostic device, wherein, An ultrasonic image is generated from the received signal obtained by transmitting and receiving ultrasonic beams on the subject using an ultrasonic probe. By analyzing the ultrasound images, the accuracy of identifying blood vessels in the ultrasound images as arteries and the accuracy of identifying them as veins are calculated. In a first case, where the accuracy of identifying the blood vessel as either an artery or a vein is greater than a first threshold, and the accuracy of identifying the blood vessel as either an artery or a vein is less than a second threshold smaller than the first threshold, the blood vessel is determined to be either an artery or a vein. In a second case other than the first case, it is determined that a determination process is needed to determine whether the blood vessel is an artery or a vein. If it is determined that the determination process is required, the determination process is executed, and based on the execution result of the determination process, it is determined whether the blood vessel is the artery or the vein.

Images