Information processing apparatus, information processing method, and storage medium

Abstract

An information processing apparatus, an information processing method, and a storage medium that assist in determining arteries and veins. An information processing apparatus that performs processing of transmitting an ultrasonic beam (UB) from a transducer array (13) toward a living body (30) and causing an ultrasonic image (U) generated by receiving an ultrasonic echo generated in the living body (30) to be displayed in a display apparatus (21), the information processing apparatus including: a blood vessel aggregate detection section (72) that detects a blood vessel aggregate region (Ra) of a blood vessel aggregate including three or more blood vessels (B) aggregated from within the ultrasonic image (U); and an emphasized display section (54) that emphasizes the blood vessel aggregate region (Ra) within the ultrasonic image (U).

Description

TECHNICAL FIELD

[0001] The technology of the present application relates to an information processing apparatus, an information processing method, and a storage medium. BACKGROUND

[0002] Conventionally, as an apparatus that obtains an image of the inside of a subject, an ultrasonic diagnostic apparatus is known. The ultrasonic diagnostic apparatus generally has an ultrasonic probe provided with a transducer array in which a plurality of ultrasonic transducers are arranged. The ultrasonic probe, in a state in which the transducer array is in contact with the body surface of the subject, transmits an ultrasonic beam toward the inside of the subject from the transducer array, and receives an ultrasonic echo from the subject by the transducer array. Thereby, an electric signal corresponding to the ultrasonic echo can be acquired. In addition, the ultrasonic diagnostic apparatus generates an ultrasonic image of the portion of the subject by processing the acquired electric signal.

[0003] A procedure in which a so-called puncture needle is inserted into a blood vessel of a subject while observing the inside of the subject using an ultrasonic diagnostic apparatus (so-called echo-guided puncture) is known. In echo-guided puncture, generally, the operator needs to grasp the position and shape of a blood vessel included in an ultrasonic image and the like by confirming the ultrasonic image, but in order to accurately grasp these, a certain level of proficiency is required. Therefore, it is proposed to automatically detect a blood vessel included in an ultrasonic image and to present the detected blood vessel to the operator (for example, refer to Patent Literature 1).

[0004] Prior Art Documents

[0005] Patent Literature

[0006] Patent Literature 1: Japanese Patent Application Laid-Open No. 2017-524455 SUMMARY

[0007] Technical Problem to be Solved by the Invention

[0008] At the time of puncture, the operator needs to accurately determine which one of an artery and a vein the blood vessel is, based on the ultrasonic image. Hereinafter, this determination will be referred to as artery-vein determination.

[0009] It is also conceivable to perform artery-vein determination of a blood vessel based on an ultrasonic image and by information processing such as image analysis. However, in the case where the shape and the like of an artery and a vein are similar when performing artery-vein determination of a blood vessel alone, determination errors are likely to occur.

[0010] The technology of the present application aims to provide an information processing apparatus, an information processing method, and a program that can assist artery-vein determination of a blood vessel.

[0011] Means for Solving the Technical Problem

[0012] The information processing apparatus of the present application performs processing of causing a display apparatus to display an ultrasonic image generated by transmitting an ultrasonic beam from a transducer array toward a living body and receiving an ultrasonic echo generated in the living body, and includes: a blood vessel aggregate detection unit that detects a blood vessel aggregate region including a blood vessel aggregate formed by aggregation of three or more blood vessels from within the ultrasonic image; and an emphasized display unit that emphasizes the blood vessel aggregate region within the ultrasonic image.

[0013] The information processing apparatus of the present application performs processing of causing a display apparatus to display an ultrasonic image generated by transmitting an ultrasonic beam from a transducer array toward a living body and receiving an ultrasonic echo generated in the living body, and includes: a blood vessel aggregate detection unit that detects a blood vessel aggregate region including a blood vessel aggregate formed by aggregation of three or more blood vessels from within the ultrasonic image; and an emphasized display unit that emphasizes the blood vessel aggregate region within the ultrasonic image.

[0014] The information processing apparatus of the present application performs processing of causing a display apparatus to display an ultrasonic image generated by transmitting an ultrasonic beam from a transducer array toward a living body and receiving an ultrasonic echo generated in the living body, and includes: a blood vessel aggregate detection unit that detects a blood vessel aggregate region including a blood vessel aggregate formed by aggregation of three or more blood vessels from within the ultrasonic image; and an emphasized display unit that emphasizes the blood vessel aggregate region within the ultrasonic image.

[0015] The information processing apparatus of the present application performs processing of causing a display apparatus to display an ultrasonic image generated by transmitting an ultrasonic beam from a transducer array toward a living body and receiving an ultrasonic echo generated in the living body, and includes: a blood vessel aggregate detection unit that detects a blood vessel aggregate region including a blood vessel aggregate formed by aggregation of three or more blood vessels from within the ultrasonic image; and an emphasized display unit that emphasizes the blood vessel aggregate region within the ultrasonic image.

[0016] The information processing apparatus of the present application performs processing of causing a display apparatus to display an ultrasonic image generated by transmitting an ultrasonic beam from a transducer array toward a living body and receiving an ultrasonic echo generated in the living body, and includes: a blood vessel aggregate detection unit that detects a blood vessel aggregate region including a blood vessel aggregate formed by aggregation of three or more blood vessels from within the ultrasonic image; and an emphasized display unit that emphasizes the blood vessel aggregate region within the ultrasonic image.

[0017] The information processing apparatus of the present application performs processing of causing a display apparatus to display an ultrasonic image generated by transmitting an ultrasonic beam from a transducer array toward a living body and receiving an ultrasonic echo generated in the living body, and includes: a blood vessel aggregate detection unit that detects a blood vessel aggregate region including a blood vessel aggregate formed by aggregation of three or more blood vessels from within the ultrasonic image; and an emphasized display unit that emphasizes the blood vessel aggregate region within the ultrasonic image.

[0018] The information processing apparatus of the present application performs processing of causing a display apparatus to display an ultrasonic image generated by transmitting an ultrasonic beam from a transducer array toward a living body and receiving an ultrasonic echo generated in the living body, and includes: a blood vessel aggregate detection unit that detects a blood vessel aggregate region including a blood vessel aggregate formed by aggregation of three or more blood vessels from within the ultrasonic image; and an emphasized display unit that emphasizes the blood vessel aggregate region within the ultrasonic image.

[0019] The information processing apparatus of the present application performs processing of causing a display apparatus to display an ultrasonic image generated by transmitting an ultrasonic beam from a transducer array toward a living body and receiving an ultrasonic echo generated in the living body, and includes: a blood vessel aggregate detection unit that detects a blood vessel aggregate region including a blood vessel aggregate formed by aggregation of three or more blood vessels from within the ultrasonic image; and an emphasized display unit that emphasizes the blood vessel aggregate region within the ultrasonic image.

[0020] The information processing apparatus of the present application performs processing of causing a display apparatus to display an ultrasonic image generated by transmitting an ultrasonic beam from a transducer array toward a living body and receiving an ultrasonic echo generated in the living body, and includes: a blood vessel aggregate detection unit that detects a blood vessel aggregate region including a blood vessel aggregate formed by aggregation of three or more blood vessels from within the ultrasonic image; and an emphasized display unit that emphasizes the blood vessel aggregate region within the ultrasonic image.

[0021] The information processing apparatus of the present application performs processing of causing a display apparatus to display an ultrasonic image generated by transmitting an ultrasonic beam from a transducer array toward a living body and receiving an ultrasonic echo generated in the living body, and includes: a blood vessel aggregate detection unit that detects a blood vessel aggregate region including a blood vessel aggregate formed by aggregation of three or more blood vessels from within the ultrasonic image; and an emphasized display unit that emphasizes the blood vessel aggregate region within the ultrasonic image.

[0022] The computer-readable storage medium of the present application stores a program that causes a computer to execute a process of causing a display device to display an ultrasonic image generated by transmitting an ultrasonic beam from a transducer array toward a living body and receiving an ultrasonic echo generated in the living body, and the program causes the computer to execute a process of detecting, from the ultrasonic image, a blood vessel aggregate region including a blood vessel aggregate formed of three or more blood vessels, and emphasizing the detected blood vessel aggregate region in the ultrasonic image.

[0023] Effects of Invention

[0024] According to the technology of the present application, it is possible to provide an information processing apparatus, an information processing method, and a program that assist in determining arteriovenous of a blood vessel. BRIEF DESCRIPTION OF DRAWINGS

[0025] Figure 1 is an external view showing an example of the structure of an ultrasonic diagnostic apparatus according to the first embodiment.

[0026] Figure 2 is a view for explaining an example of echo-guided puncture.

[0027] Figure 3 is a block diagram showing an example of the structure of an ultrasonic diagnostic apparatus.

[0028] Figure 4 is a block diagram showing an example of the structure of a reception circuit.

[0029] Figure 5 is a block diagram showing an example of the structure of an image generation section.

[0030] Figure 6 is a block diagram showing an example of the structure of an image analysis section.

[0031] Figure 7 is a view for explaining an example of a blood vessel monad detection process.

[0032] Figure 8 is a view for explaining an example of a learning phase of a blood vessel monad detection model.

[0033] Figure 9 is a view for explaining an example of a blood vessel aggregate detection process.

[0034] Figure 10 is a view for explaining an example of a learning phase of a blood vessel aggregate detection model.

[0035] Figure 11 is a view for explaining an example of an arteriovenous determination process.

[0036] Figure 12is a diagram that more specifically describes an example of the arteriovenous determination processing.

[0037] Figure 13 is a diagram that describes an example of the correction processing.

[0038] Figure 14 is a diagram that represents an example of the emphasis display processing.

[0039] Figure 15 is a flowchart that represents an example of the operation of the ultrasonic diagnostic apparatus.

[0040] Figure 16 is a diagram that represents a modification example of the arteriovenous determination processing.

[0041] Figure 17 is a diagram that represents a modification example of the arteriovenous determination processing.

[0042] Figure 18 is a diagram that represents a modification example of the emphasis display.

[0043] Figure 19 is a diagram that represents an example of the display score.

[0044] Figure 20 is a diagram that represents an example of the display of the information that prompts the attention of the operator.

[0045] Figure 21 is a flowchart that represents an example of the threshold value setting processing.

[0046] Figure 22 is a diagram that represents an example of the threshold value set by the threshold value setting processing.

[0047] Figure 23 is a diagram that represents an example in which the blood vessel aggregate region is set to be not displayed.

[0048] Figure 24 is a diagram that represents a first modification example of the ultrasonic diagnostic apparatus.

[0049] Figure 25 is a diagram that represents a second modification example of the ultrasonic diagnostic apparatus. DETAILED DESCRIPTION

[0050] Hereinafter, an embodiment to which the technology of the present application pertains will be described with reference to the drawings. The description of the structural elements described below is based on a representative embodiment of the present application, but the technology of the present application is not limited to this embodiment.

[0051] [1st Embodiment]

[0052] Figure 1This illustrates an example of the structure of the ultrasound diagnostic apparatus 2 according to the present invention. The ultrasound diagnostic apparatus 2 according to this embodiment comprises an ultrasound probe 10 and an apparatus body 20. The ultrasound probe 10 is held by a surgeon and contacts the surface of the living body to be measured. The ultrasound probe 10 transmits and receives ultrasound beams relative to the interior of the living body.

[0053] The main body 20 of the device is, for example, a smartphone or tablet. The main body 20 performs tasks such as image processing of the signals output from the ultrasonic probe 10 by installing application software or other programs. The ultrasonic probe 10 and the main body 20 communicate wirelessly with each other, for example, via WiFi or Bluetooth (registered trademark). The main body 20 is not limited to mobile terminals such as smartphones or tablets, and can be a PC (Personal Computer). The main body 20 is an example of an "information processing device" according to the technology of this invention.

[0054] The ultrasonic probe 10 has a housing 11. The housing 11 consists of an array housing 11A and a handle 11B. The array housing 11A houses the transducer array 13 (reference). Figure 3 The handle 11B is connected to the array housing 11A and is held by the surgeon. For the sake of explanation, the direction from the handle 11B toward the array housing 11A is defined as the +Y direction, the width direction of the ultrasonic probe 10 orthogonal to the Y direction is defined as the X direction, and the direction orthogonal to both the X and Y directions (i.e., the thickness direction of the ultrasonic probe 10) is defined as the Z direction.

[0055] An acoustic lens is disposed at the +Y direction end of the array housing 11A. An acoustic matching layer (not shown) is disposed on the transducer array 13, and an acoustic lens is disposed on the acoustic matching layer. The plurality of transducers included in the transducer array 13 are arranged in a straight line along the X direction. That is, the ultrasonic probe 10 of this embodiment is linear, transmitting the ultrasonic beam UB in a linear manner. Alternatively, the ultrasonic probe 10 may be convex, with the transducer array 13 configured as a convex curved surface. In this case, the ultrasonic probe 10 transmits the ultrasonic beam UB radially. Furthermore, the ultrasonic probe 10 may be fan-shaped.

[0056] Furthermore, a linear guide mark M extending in the Y direction is provided on the outer periphery of the array housing 11A. The guide mark M is used as a reference when the operator brings the ultrasonic probe 10 into contact with the living body.

[0057] The device main body 20 has a display device 21 for displaying an ultrasonic image based on a signal transmitted from the ultrasonic probe 10. The display device 21 is, for example, a display device such as an organic EL (Organic Electro-Luminescence) display or a liquid crystal display. The display device 21 is equipped with a touch panel. The operator can perform various operations on the device main body 20 through the touch panel.

[0058] Figure 2 is a view for explaining an example of echo-guided puncture. As shown in Figure 2 , the ultrasonic probe 10 is used when the operator confirms an ultrasonic image displayed on the device main body 20 while puncturing a puncture needle 31 into a blood vessel B in a living body 30. The living body 30 is, for example, a wrist of a person. In the ultrasonic probe 10, for example, the ultrasonic probe 10 is brought into abutment with a surface of the living body 30 in a manner that the direction of travel of the blood vessel B is cut in the width direction (i.e., the X direction) of the ultrasonic probe 10. This procedure is called a short-axis method (or a cross method). A cross section of the blood vessel B is displayed in the ultrasonic image. The operator punctures, for example, a vein among one or more blood vessels B displayed in the ultrasonic image.

[0059] The device main body 20 performs an arteriovenous determination of the blood vessel after detecting the blood vessel from the ultrasonic image, displays the arteriovenous determination result in the ultrasonic image displayed in the display device 21, and thereby assists the puncture performed by the operator.

[0060] Figure 3 represents an example of the structure of the ultrasonic diagnostic apparatus 2. The ultrasonic probe 10 has a transducer array 13, a transceiver circuit 14, and a communication section 15. The transceiver circuit 14 includes a transmission circuit 16 and a reception circuit 17. The transmission circuit 16 and the reception circuit 17 are connected to the transducer array 13, respectively. In addition, the transceiver circuit 14 performs input and output of signals between the processor 25 of the device main body 20 via the communication section 15, respectively.

[0061] The transducer array 13 has a plurality of transducers (not shown) arranged one-dimensionally or two-dimensionally. These transducers transmit an ultrasonic beam UB according to a drive signal supplied from the transmission circuit 16, respectively, and receive an ultrasonic echo from the living body 30. The transducers output a signal based on the received ultrasonic echo. The transducers are constituted, for example, by forming electrodes at both ends of a piezoelectric body. The piezoelectric body is constituted by a piezoelectric ceramic typified by PZT (Lead Zirconate Titanate), a high molecular piezoelectric element typified by PVDF (Poly Vinylidene Di Fluoride), a piezoelectric single crystal typified by PMN-PT (Lead Magnesium Niobate-Lead Titanate), and the like.

[0062] The transmission circuit 16 includes, for example, a plurality of pulse generators. The transmission circuit 16 adjusts the amount of delay of a drive signal supplied to the plurality of transducers included in the transducer array 13 based on a transmission delay pattern selected in accordance with a control signal transmitted from the processor 25 of the device main body 20. The drive signal is adjusted in the amount of delay by the transmission circuit 16 so that the ultrasonic waves transmitted from the plurality of transducers form the ultrasonic beam UB. The drive signal is a voltage signal that is pulsed or continuous wave. The transducers transmit the ultrasonic waves that are pulsed or continuous wave by stretching and contracting when the drive signal is applied. The ultrasonic beam UB that is a resultant wave is formed by synthesizing the ultrasonic waves transmitted from the plurality of transducers.

[0063] The ultrasonic beam UB transmitted into the living body 30 is reflected at a site such as a blood vessel B in the living body 30, thereby becoming an ultrasonic echo and propagating toward the transducer array 13. In this way, the ultrasonic echo propagating toward the transducer array 13 is received by the plurality of transducers constituting the transducer array 13. The transducers generate an electric signal by receiving the ultrasonic echo and stretching and contracting. The electric signal generated by the transducers is output to the reception circuit 17.

[0064] The reception circuit 17 generates an acoustic line signal by processing the electric signal output from the transducer array 13 in accordance with a control signal transmitted from the processor 25 of the device main body 20. As an example, as shown in FIG. 4, the reception circuit 17 is configured by connecting in series an amplification section 41, an A / D (analog / digital) conversion section 42, and a beam former 43. Figure 4

[0065] The amplification section 41 amplifies the signal input from the plurality of transducers constituting the transducer array 13 and transmits the amplified signal to the A / D conversion section 42. The A / D conversion section 42 converts the signal transmitted from the amplification section 41 into digital reception data and transmits the converted reception data to the beam former 43. The beam former 43 imparts a delay to each of the reception data converted by the A / D conversion section 42 and adds them in accordance with a distribution of the speed of sound or the acoustic velocity set based on a reception delay pattern selected in accordance with a control signal transmitted from the processor 25 of the device main body 20. This addition process is called reception focus processing. By the reception focus processing, the acoustic line signal in which each of the reception data converted by the A / D conversion section 42 is added in phase and the focus of the ultrasonic echo is reduced is obtained.

[0066] The device main body 20 has a display device 21, an input device 22, a communication section 23, a storage device 24, and a processor 25. The input device 22 is, for example, a touch panel or the like attached to the display device 21. In the case where the device main body 20 is a PC or the like, the input device 22 can be a keyboard, a mouse, a trackball, a touch pad, or the like. The communication section 23 performs wireless communication with the communication section 15 of the ultrasonic probe 10.

[0067] ​An input device 22 and a storage device 24 are connected to the processor 25. In addition, the processor 25 and the storage device 24 are connected in a manner capable of mutually bidirectionally transferring information.

[0068] The storage device 24 is a device that stores a program 26 that causes the ultrasonic diagnostic apparatus 2 to operate, and the like, and is, for example, a flash memory, an HDD (Hard Disc Drive), or an SSD (Solid State Drive). In the case of the device main body 20 being a PC or the like, as the storage device 24, a recording medium such as an FD (Flexible Disc), an MO (Magneto-Optical) disc, a magnetic tape, a CD (Compact Disc), a DVD (Digital Versatile Disc), an SD (Secure Digital) card, a USB (Universal Serial Bus) memory, or the like, or a server or the like can be used.

[0069] The processor 25 is, for example, a CPU (Central Processing Unit). The processor 25 functions as a main control section 50, an image generation section 51, a display control section 52, an image analysis section 53, and an emphasis display section 54 by performing processing in cooperation with a RAM (Random Access Memory) (not shown) or the like in accordance with the program 26.

[0070] In addition, the processor 25 is not limited to a CPU, and can be configured using an FPGA (Field Programmable Gate Array), a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), a GPU (Graphics Processing Unit), another IC (Integrated Circuit), or the like, or can be configured in combination of these.

[0071] The main control section 50 performs control of each section of the ultrasonic diagnostic apparatus 2 in accordance with an input operation by a doctor in charge via the input device 22. The main control section 50 transmits the above-described control signal to the ultrasonic probe 10 via the communication section 23. An acoustic line signal generated by the reception circuit 17 from the ultrasonic probe 10 is input to the processor 25 via the communication section 23.

[0072] The image generation section 51 acquires the acoustic line signals input from the ultrasonic probe 10 under the control of the main control section 50, and generates an ultrasonic image U from the acquired acoustic line signals. As an example, as shown in FIG. 1, the image generation section 51 is configured by connecting the signal processing section 61, a DSC (Digital Scan Converter) 62, and an image processing section 63 in series. Figure 5

[0073] The signal processing section 61 generates the B-mode image signals, which are the tomographic image information related to the tissues in the subject, by performing envelope detection processing after performing correction of the distance-caused attenuation according to the depths of the reflection positions of the ultrasonic waves on the acoustic line signals generated by the reception circuit 17.

[0074] The DSC 62 converts the B-mode image signals generated by the signal processing section 61 into image signals according to the scanning method of a general television signal (so-called raster conversion). The image processing section 63 performs various image processing such as gradation processing on the B-mode image signals input from the DSC 62, and outputs the B-mode image signals to the display control section 52 and the image analysis section 53. Hereinafter, the B-mode image signals on which the image processing has been performed by the image processing section 63 are simply referred to as the ultrasonic image U.

[0075] In addition, the transceiving circuit 14 of the ultrasonic probe 10 and the image generation section 51 are controlled by the main control section 50 so that the ultrasonic image U is periodically generated at a prescribed frame rate. The transceiving circuit 14 and the image generation section 51 function as an image acquisition section that acquires the ultrasonic image U.

[0076] The display control section 52 performs prescribed processing on the ultrasonic image U generated by the image generation section 51 under the control of the main control section 50, and displays the ultrasonic image U on which the processing has been performed on the display device 21.

[0077] The image analysis section 53 generates blood vessel detection information DB by performing image analysis on the ultrasonic image U input from the image generation section 51 under the control of the main control section 50, and outputs the generated blood vessel detection information DB to the emphasis display section 54. The blood vessel detection information DB includes, for example, the detection results of the blood vessel regions included in the ultrasonic image U and the arteriovenous determination results of the detected blood vessels. Also, the blood vessel regions include "vessel monomer regions" that indicate regions of vessel monomers and "vessel aggregate regions" that indicate regions of vessel aggregates in which three or more blood vessels are aggregated. The vessel aggregate is, for example, a complex of an artery and a concomitant vein. The vessel aggregate mainly exists in anatomically stable portions.

[0078] ​The emphasis display section 54 emphasizes display of the blood vessel individual region and the blood vessel aggregate region in the ultrasonic wave image U displayed on the display device 21 under the control of the main control section 50 based on the blood vessel detection information DB input from the image analysis section 53. Also, the emphasis display section 54 displays the blood vessel individual region so that it is possible to identify whether the blood vessel included in the blood vessel individual region is an artery or a vein based on the artery-vein determination result.

[0079] As an example, as shown in FIG. 6, the image analysis section 53 is composed of a blood vessel individual detection section 71, a blood vessel aggregate detection section 72, an artery-vein determination section 73, and a correction section 74. The ultrasonic wave image U generated by the image generation section 51 is input to the blood vessel individual detection section 71 and the blood vessel aggregate detection section 72. Figure 6

[0080] The blood vessel individual detection section 71 determines the blood vessel individual region by individually detecting each blood vessel included in the ultrasonic wave image U, and performs artery-vein determination of the blood vessel included in the blood vessel individual region. The blood vessel individual detection section 71 inputs information indicating the detection result of the blood vessel individual region and the artery-vein determination result of each blood vessel individual region to the correction section 74 as blood vessel individual detection information Dl.

[0081] The blood vessel aggregate detection section 72 detects a blood vessel aggregate region in which three or more blood vessels are aggregated based on the ultrasonic wave image U, and outputs information indicating the detected blood vessel aggregate region to the artery-vein determination section 73 as blood vessel aggregate detection information D2.

[0082] The artery-vein determination section 73 performs artery-vein determination of each blood vessel in the blood vessel aggregate region included in the blood vessel aggregate detection information D2, and outputs information indicating the artery-vein determination result to the correction section 74 as artery-vein determination information D3.

[0083] The correction section 74 corrects the artery-vein determination result included in the blood vessel individual detection information Dl based on the artery-vein determination information D3. The correction section 74 outputs information including the corrected blood vessel individual detection information Dl, the blood vessel aggregate detection information D2, and the artery-vein determination information D3 to the emphasis display section 54 as the above-mentioned blood vessel detection information DB.

[0084] Figure 7 An example of the blood vessel individual detection processing based on the blood vessel individual detection section 71 is shown. The blood vessel individual detection section 71 performs processing of detecting a blood vessel individual region Rs including a blood vessel individual using a known algorithm from the ultrasonic wave image U and artery-vein determination. In the example shown in FIG. 7, the blood vessel individual detection section 71 detects a blood vessel individual region Rs including a blood vessel individual 71a in the ultrasonic wave image U, and performs artery-vein determination of the blood vessel individual 71a. Figure 7 ​In the present embodiment, symbols B1 to B5 indicate blood vessels. Hereinafter, when blood vessels do not need to be distinguished, they are simply labeled as blood vessels B. The blood vessel monomer region Rs indicated by a broken line indicates a region including blood vessels B determined to be arteries. The blood vessel monomer region Rs indicated by a solid line indicates a region including blood vessels B determined to be veins.

[0085] A "label" indicating the arteriovenous determination result and a "score" indicating the reliability (i.e., certainty) of the arteriovenous determination result are assigned to the blood vessel monomer region Rs. The label indicates which of "artery" and "vein" the blood vessels B included in the blood vessel monomer region Rs are. The score is a value in the range of 0 or more and 1 or less, and the closer to 1, the higher the reliability is indicated. The blood vessel monomer region Rs to which the label and the score are assigned corresponds to the above-described blood vessel monomer detection information D1.

[0086] In the present embodiment, the blood vessel monomer detection unit 71 performs a blood vessel monomer detection process using a learning end model, i.e., a blood vessel monomer detection model 71A (see FIG. 2) generated by machine learning. Figure 8 ) performs a blood vessel monomer detection process. The blood vessel monomer detection model 71A is, for example, an algorithm for object detection using deep learning. As the blood vessel monomer detection model 71A, for example, an object detection model composed of R-CNN (Regional CNN: Region-based Convolutional Neural Network), which is one of convolutional neural networks (CNNs), can be used.

[0087] The blood vessel monomer detection model 71A detects a region including a blood vessel monomer as an object from within the ultrasonic image U and determines a label for the detected region. Then, the blood vessel monomer detection model 71A outputs information indicating the detected blood vessel monomer region Rs together with the label and the score.

[0088] Figure 8 is a diagram illustrating an example of a learning stage in which the blood vessel monomer detection model 71A is learned by machine learning. The blood vessel monomer detection model 71A is learned using teacher data TD1. The teacher data TD1 includes a plurality of teacher images P to which correct labels L are assigned. The teacher images P included in the teacher data TD1 are sample images of blood vessel monomers (arteries and veins). The teacher data TD1 includes various teacher images P different in shape, size, and the like of blood vessels.

[0089] In the learning stage, the teacher images P are input to the blood vessel monomer detection model 71A. The blood vessel monomer detection model 71A outputs a determination result A for the teacher images P. Based on this determination result A and the correct labels L, a loss operation using a loss function is performed. Then, based on the result of the loss operation, update settings of various coefficients of the blood vessel monomer detection model 71A are performed, and the blood vessel monomer detection model 71A is updated based on the update settings.

[0090] In the learning stage, the series of processes of inputting the teacher image P to the blood vessel monomer detection model 71A, outputting the determination result A from the blood vessel monomer detection model 71A, loss calculation, update setting, and update of the blood vessel monomer detection model 71A are repeated. The repetition of the series of processes ends in a case where the detection accuracy reaches a predetermined set level. In this way, the blood vessel monomer detection model 71A whose detection accuracy reaches the set level is stored in the storage device 24 and is used by the blood vessel monomer detection unit 71 in the application stage, that is, the blood vessel monomer detection process.

[0091] Figure 9 An example of the blood vessel aggregate detection process based on the blood vessel aggregate detection unit 72 is shown. The blood vessel aggregate detection unit 72 performs a process of detecting a blood vessel aggregate region Ra containing a blood vessel aggregate from within the ultrasonic image U using a known algorithm.

[0092] In the present embodiment, the blood vessel aggregate detection unit 72 performs the blood vessel aggregate detection process using a learning end model, that is, a blood vessel aggregate detection model 72A (refer to FIG. 8) generated through machine learning. Figure 10 The blood vessel aggregate detection model 72A is, for example, an algorithm of object detection using deep learning. As the blood vessel aggregate detection model 72A, for example, an object detection model constituted by R-CNN which is one of CNNs can be used.

[0093] The blood vessel aggregate detection unit 72 detects a blood vessel aggregate region Ra containing a blood vessel aggregate as an object from within the ultrasonic image U. Information indicating the blood vessel aggregate region Ra corresponds to the above-described blood vessel aggregate detection information D2.

[0094] Figure 10 is a diagram illustrating an example of a learning stage in which the blood vessel aggregate detection model 72A is learned through machine learning. The blood vessel aggregate detection model 72A is learned using teacher data TD2. The teacher data TD2 contains a plurality of teacher images P to which correct labels L are assigned. The teacher images P contained in the teacher data TD2 are sample images of blood vessel aggregates. The teacher data TD2 contains various teacher images P different in the number of blood vessels constituting a blood vessel aggregate, the shape of the blood vessels, the size of the blood vessels, the arrangement (positional relationship) of a plurality of blood vessels, and the like.

[0095] In the learning stage, the teacher image P is input to the blood vessel aggregate detection model 72A. The blood vessel aggregate detection model 72A outputs a determination result A with respect to the teacher image P. Based on the determination result A and the correct label L, loss calculation using a loss function is performed. Then, update setting of various coefficients of the blood vessel aggregate detection model 72A is performed based on the result of the loss calculation, and the blood vessel aggregate detection model 72A is updated based on the update setting.

[0096] In the learning stage, the series of processes of inputting the teacher image P to the blood vessel aggregate detection model 72A, outputting the determination result A from the blood vessel aggregate detection model 72A, loss calculation, update setting, and update of the blood vessel aggregate detection model 72A are repeated. The repetition of the series of processes ends when the detection accuracy reaches a predetermined set level. In this way, the blood vessel aggregate detection model 72A whose detection accuracy reaches the set level is stored in the storage device 24 and is used by the blood vessel aggregate detection unit 72 in the application stage, that is, the blood vessel aggregate detection process.

[0097] Figure 11 An example of the arteriovenous determination process based on the arteriovenous determination unit 73 is shown. The arteriovenous determination unit 73 performs arteriovenous determination on each blood vessel B included in the blood vessel aggregate region Ra based on the blood vessel aggregate detection information D2, and generates arteriovenous determination information D3 by calculating a label and a score for each blood vessel B. The arteriovenous determination unit 73 uses the feature amount of the anatomical blood vessel within the blood vessel aggregate region Ra in the arteriovenous determination. The arteriovenous determination unit 73 calculates a score for each of "artery" and "vein" as labels for the blood vessel B, and selects the label with the higher score.

[0098] Figure 12 is a diagram that explains an example of the arteriovenous determination process in more detail. First, the arteriovenous determination unit 73 calculates a feature amount for each blood vessel B included in the blood vessel aggregate region Ra. The feature amount is the diameter (hereinafter referred to as the blood vessel diameter) D of each blood vessel B within the blood vessel aggregate region Ra, the displacement amount K of the blood vessel B from the center C of the blood vessel aggregate region Ra, the circularity of each blood vessel B, and the like. The displacement amount K is, for example, the distance from the center C of the blood vessel aggregate region Ra to the center of each blood vessel B. The arteriovenous determination unit 73 determines which of an artery and a vein each blood vessel B is using at least one or more of the feature amounts of the blood vessel diameter D, the displacement amount K, and the circularity. The arteriovenous determination unit 73 performs arteriovenous determination using, for example, an algorithm based on machine learning such as AdaBoost, SVM (Support Vector Machine), or the like.

[0099] An artery is usually located at the center of a blood vessel aggregate, and thus the displacement amount K is small. Also, since the internal pressure of an artery is high, the blood vessel diameter is large and the circularity is high. In contrast, a vein is displaced from an artery, and thus the displacement amount K is large. Also, since the internal pressure of a vein is low, the blood vessel diameter is small and the circularity is low. The arteriovenous determination unit 73 performs arteriovenous determination on each blood vessel B based on these feature amounts, and performs calculation of a score and determination of a label. For example, the arteriovenous determination unit 73 calculates a score as an artery and a score as a vein for each blood vessel B, and selects the label with the higher score. In this way, by using anatomical feature amounts as a blood vessel aggregate to perform determination, arteriovenous determination can be performed with high accuracy.

[0100] Figure 13 An example of the correction processing based on the correction section 74 is shown. For the corresponding blood vessel B, the correction section 74 compares the score included in the arteriovenous determination information D3 and the score included in the blood vessel monomer detection information Dl, and selects the label of which score is higher. For example, in the example shown in Figure 13 the score (0.90) included in the arteriovenous determination information D3 is higher than the score (0.75) included in the blood vessel monomer detection information Dl. Therefore, the correction section 74 selects the label (artery) included in the arteriovenous determination information D3 instead of the label (vein) included in the blood vessel monomer detection information Dl as the label of the blood vessel B3. Similarly, for the blood vessels B4 and B5, the correction section 74 also selects the label of which score is higher. That is, in the example shown in Figure 13 the labels of the blood vessels B1 to B5 included in the blood vessel monomer detection information Dl, only the label of the blood vessel B3 is corrected. In this way, the labels included in the blood vessel monomer detection information Dl are corrected.

[0101] The correction section 74 outputs information including the corrected blood vessel monomer detection information Dl, the blood vessel aggregate detection information D2, and the arteriovenous determination information D3 in which the labels are corrected, to the emphasis display section 54 as the above-described blood vessel detection information DB. The blood vessel detection information DB includes the position information of the blood vessel monomer regions Rs and the blood vessel aggregate regions Ra within the ultrasonic image U, and the labels and the scores for the blood vessel monomer regions Rs.

[0102] Figure 14 An example of the emphasis display processing based on the emphasis display section 54 is shown. The emphasis display section 54 displays the blood vessel monomer regions Rs and the blood vessel aggregate regions Ra within the ultrasonic image U displayed on the display device 21 of the device main body 20 according to the blood vessel detection information DB using rectangular frames. Also, the emphasis display section 54 displays the blood vessel monomer regions Rs in a recognizable manner as to whether the blood vessels included in the blood vessel monomer regions Rs are arteries or veins according to the arteriovenous determination result. In the example shown in Figure 14 the blood vessel monomer regions Rs including veins are represented by solid lines, and the blood vessel monomer regions Rs including arteries are represented by dashed lines. Also, the blood vessel aggregate regions Ra are represented by double-dot chain lines. Note that the emphasis display section 54 is not limited to the line types, and can display the blood vessel monomer regions Rs and the blood vessel aggregate regions Ra in a recognizable manner according to the thickness of the lines, the colors of the lines, the brightness of the lines, and the like.

[0103] Next, the use of the blood vessel monomer detection information Dl and the blood vessel aggregate detection information D2 is described. Figure 15The flowchart shown illustrates an example of the operation of the ultrasonic diagnostic apparatus 2. First, the main control section 50 determines whether a start operation has been performed using the input device 22 or the like and by the operator (step S10). In the case where the main control section 50 determines that a start operation has been performed (step S10: YES), an ultrasonic image U is generated by causing the transceiving circuit 14 of the ultrasonic probe 10 to operate in conjunction with the image generation section 51 (step Sll). The generated ultrasonic image U is displayed on the display device 21 by the display control section 52.

[0104] At this time, as shown in Figure 2 , the operator causes the ultrasonic probe 10 to be brought into contact with the surface of the living body 30. The ultrasonic beam UB is transmitted from the transducer array 13 into the living body 30 in accordance with a drive signal input from the transmission circuit 16. Ultrasonic echoes from within the living body 30 are received by the transducer array 13, and the received signals are output to the reception circuit 17. The received signals received by the reception circuit 17 become acoustic ray signals via the amplification section 41, the A / D conversion section 42, and the beamformer 43. The acoustic ray signals are output to the apparatus main body 20 via the communication section 15.

[0105] The apparatus main body 20 receives the acoustic ray signals output from the ultrasonic probe 10 via the communication section 23. The acoustic ray signals received by the apparatus main body 20 are output to the image generation section 51. The acoustic ray signals become B-mode image signals by envelope detection processing performed in the signal processing section 61 in the image generation section 51, and are output to the display control section 52 as an ultrasonic image U after passing through the DSC 62 and the image processing section 63. Also, the ultrasonic image U is output to the image analysis section 53.

[0106] In the image analysis section 53, the above-described blood vessel monomer detection processing (refer to Figure 7 ) is performed by the blood vessel monomer detection section 71 (step S12). The blood vessel monomer detection information Dl generated by this blood vessel monomer detection processing is output to the correction section 74.

[0107] Also, step S13 and step S14 are performed in parallel with step S12. In step S13, the above-described blood vessel aggregate detection processing (refer to Figure 9 ) is performed by the blood vessel aggregate detection section 72. The blood vessel aggregate detection information D2 generated by this blood vessel aggregate detection processing is output to the arteriovenous determination section 73. In step S14, the above-described arteriovenous determination processing (refer to Figure 11 and Figure 12 ) is performed by the arteriovenous determination section 73. The arteriovenous determination information D3 generated by this arteriovenous determination processing is output to the correction section 74.

[0108] Further, in the image analysis section 53, the above-described correction processing (refer to Figure 13) (step S15). In this correction processing, the labels of the vessel monomer regions Rs included in the vessel monomer detection information Dl are corrected based on the artery-vein determination information D3. As a result of this correction processing, the vessel detection information DB is output to the emphasis display section 54.

[0109] Then, the above-described emphasis display processing is performed by the emphasis display section 54 (refer to FIG. 6) (step S16). By this emphasis display processing, the vessel monomer regions Rs and the vessel aggregate region Ra are emphasized and displayed within the ultrasonic image U displayed on the display device 21. Also, the vessel monomer regions Rs are displayed in a manner in which it is possible to identify whether the vessels included therein are arteries or veins. In this way, by performing the emphasis display, the doctor in charge is able to accurately grasp the vessel aggregate present within the ultrasonic image U, and is also able to accurately grasp whether the vessel monomers are arteries or veins. Figure 14

[0110] Next, the main control section 50 determines whether or not an end operation has been performed using the input device 22 or the like and by the doctor in charge (step S17). The main control section 50 returns the processing to step Sll in a case in which it is determined that the end operation has not been performed (step S17: No). By this, a new ultrasonic image U is generated. On the other hand, the main control section 50 ends the operation of the ultrasonic diagnostic apparatus 2 in a case in which it is determined that the end operation has been performed (step S17: Yes).

[0111] In the past, vessels were detected by the vessel monomer detection processing, and artery-vein determination was performed on the vessels detected individually. In such a method, errors occur frequently in the artery-vein determination of the vessels that constitute the vessel aggregate, and there are cases in which the artery-vein determination changes for each frame. When the doctor in charge performs a puncture based on such an artery-vein determination result, the vessel of the puncture target can sometimes be mistaken.

[0112] In contrast to this, according to the technology of the present application, the vessel aggregate region Ra is detected from the ultrasonic image U, and the detected vessel aggregate region Ra is emphasized and displayed within the ultrasonic image U, and thus the artery-vein determination of the vessels performed by the doctor in charge can be assisted. Also, according to the technology of the present application, since the artery-vein determination is performed based on the vessel feature amount within the vessel aggregate region Ra, the artery-vein determination can be performed with high accuracy even for the vessels that constitute the vessel aggregate. By this, the doctor in charge is able to accurately grasp the vessel of the puncture target (for example, a vein).

[0113] [Modified Example]

[0114] Hereinafter, various modified examples of the ultrasonic diagnostic apparatus 2 related to the above-described first embodiment will be described.

[0115] In the first embodiment, the artery-vein determination section 73 performs the artery-vein determination processing (refer to FIG. 5) on the vessel aggregate region Ra detected from the ultrasonic image U (step S14). In this artery-vein determination processing, the artery-vein determination is performed on the vessel aggregate region Ra based on the vessel feature amount. Figure 11 and​Figure 12 ), scores are calculated for "artery" and "vein" as labels for the blood vessel B, and the label with the higher score is selected. Alternatively, for example, as shown in Figure 16 , a score threshold value can be set, and the label with a score above the threshold value is selected.

[0116] Also, for example, as shown in Figure 17 , there can be a case where scores are calculated for "artery" and "vein" as labels for the blood vessel B, and either of the scores is less than a threshold value. In this case, the artery-vein determination unit 73 can also consider that determination of the label (i.e., artery-vein determination) is difficult, and stop the artery-vein determination. In this way, in the case where artery-vein determination is difficult, the emphasis display unit 54 can display the blood vessel single region Rs in the ultrasound image U without distinguishing which of "artery" and "vein" the blood vessel single region Rs is. In this case, for example, as shown in Figure 18 , the emphasis display unit 54 can simply display the blood vessel single region Rs as "blood vessel".

[0117] Also, for example, as shown in Figure 19 , the emphasis display unit 54 can display the score of the label selected by the correction unit 74 (i.e., the reliability of the determination result selected by the correction unit 74) in association with the blood vessel single region Rs. Thereby, the surgeon can grasp the reliability of the artery-vein determination for each blood vessel.

[0118] Also, for example, as shown in Figure 20 , in the case where the score of the label selected by the correction unit 74 (i.e., the reliability of the determination result selected by the correction unit 74) is less than a certain value, the emphasis display unit 54 can display information that calls attention to the surgeon. Thereby, the surgeon can reliably grasp the case where the reliability of the artery-vein determination is low, and attention is required at the time of puncture.

[0119] Also, the artery-vein determination unit 73 can change the criterion for artery-vein determination for each blood vessel aggregate region Ra. The reason for this is that, for example, in the case where the pattern of the blood vessel aggregate within the blood vessel aggregate region Ra is a pattern that is typical anatomically, the determination result is likely to be correct even if the score of the artery-vein determination is low. The pattern of the blood vessel aggregate is information represented by the relative positions of the plurality of blood vessels of the blood vessel aggregate, the number of blood vessels, the size of each blood vessel, and the like.

[0120] Before the artery-vein determination unit 73 performs artery-vein determination on the blood vessel aggregate region Ra, for example, the artery-vein determination unit 73 can perform Figure 21The threshold setting processing is shown. First, the arteriovenous determination section 73 analyzes the pattern of the blood vessel aggregate within the blood vessel aggregate region Ra (step S20), and determines whether the blood vessel aggregate is a typical pattern (step S21). When the arteriovenous determination section 73 determines that the blood vessel aggregate is a typical pattern (step S21: Yes), the threshold for arteriovenous determination is set to "first threshold" (step S22). On the other hand, when the arteriovenous determination section 73 determines that the blood vessel aggregate is not a typical pattern (step S21: No), the threshold for arteriovenous determination is set to "second threshold" (step S23). Here, the first threshold is a value smaller than the second threshold.

[0121] As shown in Figure 22 , when the pattern of the blood vessel aggregate within the blood vessel aggregate region Ra is typical, the threshold serving as a basis for arteriovenous determination is set low. On the other hand, when the pattern of the blood vessel aggregate is not typical, the threshold serving as a basis for arteriovenous determination is set high. In this way, when the pattern of the blood vessel aggregate is not typical, the basis for arteriovenous determination is set high, and thus more reliable determination is performed. Note that the basis for arteriovenous determination is not limited to the score threshold, and the basis for arteriovenous determination can be changed by changing the algorithm for arteriovenous determination.

[0122] Also, as shown in Figure 23 , the emphasis display section 54 can not display the blood vessel aggregate region Ra after the arteriovenous determination section 73 performs arteriovenous determination.

[0123] Also, in the first embodiment, the blood vessel monomer detection section 71 and the blood vessel aggregate detection section 72 are each constituted by a separate object detection model, but the blood vessel monomer detection section 71 and the blood vessel aggregate detection section 72 can be constituted by one object detection model. In this case, the object detection model can be learned using teacher data including teacher images of blood vessel monomers and teacher images of blood vessel aggregates. Also, the blood vessel monomer detection section 71, the blood vessel aggregate detection section 72, and the arteriovenous determination section 73 can be constituted by one object detection model. Further, the blood vessel monomer detection section 71, the blood vessel aggregate detection section 72, the arteriovenous determination section 73, and the correction section 74 can be constituted by one object detection model.

[0124] Also, in the first embodiment, the blood vessel monomer detection section 71 and the blood vessel aggregate detection section 72 are constituted by an object detection model including a CNN, but the object detection model is not limited to a CNN, and can be a separator or another general detection model.

[0125] Further, the object detection models that constitute the blood vessel single detection section 71 and the blood vessel aggregate detection section 72 can be constituted by a recognizer that performs object recognition based on image feature amounts such as AdaBoost or SVM. In this case, the recognizer can be learned based on a feature amount vector after a teacher image is converted into the feature amount vector. As the feature amount of the blood vessel aggregate, the distance between blood vessels (the distance between the centers of blood vessels, the distance between the outer circumferential portions of blood vessels, etc.) can be used. The recognizer recognizes as a blood vessel aggregate when the distance between blood vessels is equal to or less than a certain value and the number of blood vessels is three or more.

[0126] Further, the blood vessel single detection section 71 and the blood vessel aggregate detection section 72 are not limited to object detection models based on mechanical learning, and can perform object detection by template matching. In this case, the blood vessel single detection section 71 stores typical pattern data of a blood vessel single as a template in advance, searches the ultrasonic image U using the template, and calculates the similarity to the pattern data. Then, the blood vessel single detection section 71 determines the position at which the similarity is equal to or more than a predetermined value and becomes the maximum as a blood vessel single region Rs. Further, the blood vessel aggregate detection section 72 stores typical pattern data of a blood vessel aggregate as a template in advance, searches the ultrasonic image U using the template, and calculates the similarity to the pattern data. Then, the blood vessel aggregate detection section 72 determines the position at which the similarity is equal to or more than a predetermined value and becomes the maximum as a blood vessel aggregate region Ra. In addition, the template can be a part of an actual ultrasonic image, or an image in which a blood vessel or a blood vessel aggregate is patterned.

[0127] Further, in calculating the similarity, in addition to simple template matching, for example, a machine learning method using Csurka et al.: Visual Categorization with Bags of Keypoints, Proc. of ECCV Workshop on Statistical Learning in Computer Vision, pp. 59-74 (2004) or a general image recognition method of deep learning using Krizhevsky et al.: ImageNet Classification with Deep Convolutional Neural Networks, Advances in Neural Information Processing Systems 25, pp. 1106-1114 (2012) can be used.

[0128] In the first embodiment, the ultrasonic probe 10 is connected to the device main body 20 by wireless communication, but instead, the ultrasonic probe 10 can be connected to the device main body 20 by wire.

[0129] Further, in the first embodiment, the image generation section 51 that generates the ultrasonic image U from the acoustic ray signal is provided in the device main body 20, but instead, the image generation section 51 can be provided in the ultrasonic probe 10. In this case, the ultrasonic probe 10 generates the ultrasonic image U and outputs it to the device main body 20. The processor 25 of the device main body 20 performs image analysis and the like based on the ultrasonic image U input from the ultrasonic probe 10.

[0130] Further, in the first embodiment, the display device 21, the input device 22, and the ultrasonic probe 10 are directly connected to the processor 25, but the display device 21, the input device 22, and the ultrasonic probe 10 can be indirectly connected to the processor 25 through a network.

[0131] As an example, Figure 24In the ultrasonic diagnostic apparatus 2A shown, the display device 21, input device 22, and ultrasonic probe 10A are connected to the apparatus main body 20A via a network NW. In the apparatus main body 20A, the display device 21 and input device 22 are removed from the apparatus main body 20 according to the first embodiment, and a transceiver circuit 14 is added, thus constituting the apparatus with the transceiver circuit 14, storage device 24, and processor 25. In the ultrasonic probe 10A, the transceiver circuit 14 is removed from the ultrasonic probe 10 according to the first embodiment.

[0132] Thus, in the ultrasound diagnostic device 2A, the display device 21, input device 22, and ultrasound probe 10A are connected to the device body 20A via a network NW, allowing the device body 20A to be used as a so-called remote server. Consequently, for example, the surgeon can have the display device 21, input device 22, and ultrasound probe 10A readily available, improving convenience. Furthermore, the convenience is further enhanced by using a mobile terminal such as a smartphone or tablet to configure the display device 21 and input device 22.

[0133] As another example, in Figure 25 In the ultrasound diagnostic device 2B shown, the display device 21 and the input device 22 are mounted on the device body 20B, and the ultrasound probe 10A is connected to the device body 20B via a network NW. In this case, the device body 20B can be configured as a remote server. Furthermore, the device body 20B can also be configured as a mobile terminal such as a smartphone or tablet.

[0134] In the first embodiment, the hardware structure of the processing unit, which performs various processes such as the main control unit 50, the image generation unit 51, the display control unit 52, the image analysis unit 53, and the emphasis display unit 54, can use various processors as shown below. These processors include general-purpose processors (CPUs) that execute software (program 26) as described above to function as various processing units, as well as processors such as FPGAs (programmable logic devices, PLDs) whose circuit structure can be changed after manufacturing, and processors such as ASICs (dedicated circuits) with circuit structures specifically designed for performing specific processes.

[0135] A processing unit can consist of one of these various processors, or it can consist of a combination of two or more processors of the same or different types (e.g., a combination of multiple FPGAs and / or a combination of a CPU and an FPGA). Furthermore, multiple processing units can be composed of a single processor.

[0136] As an example of a case where a plurality of processing sections are constituted by one processor, first, there is a manner in which one processor constituted by a combination of one or more CPUs and software, like a computer such as a user terminal and a server, functions as a plurality of processing sections. Second, there is a manner in which a processor that realizes the functions of the entire system including a plurality of processing sections by one IC chip, like a System On Chip (SoC), is used. In this way, various processing sections are constituted by using one or more of the above-described various processors as a hardware structure.

[0137] In addition, as the hardware structure of these various processors, more specifically, a circuit (circuitry) constituted by combining circuit elements such as semiconductor elements can be used.

[0138] From the above, the technologies described in the following supplementary items 1 to 9 can be grasped.

[0139] [Supplementary item 1]

[0140] An information processing apparatus that performs processing of causing a display apparatus to display an ultrasonic image generated by transmitting an ultrasonic beam from a transducer array toward an inside of a living body and receiving an ultrasonic echo generated in the inside of the living body, the information processing apparatus comprising a processor,

[0141] The processor detects a blood vessel cluster region in which a blood vessel cluster including three or more blood vessels is gathered from within the ultrasonic image, and emphasizes display of the detected blood vessel cluster region within the ultrasonic image.

[0142] [Supplementary item 2]

[0143] The information processing apparatus according to supplementary item 1, wherein

[0144] The processor determines which one of an artery and a vein each blood vessel included in the blood vessel cluster region is, based on a feature amount of each blood vessel within the blood vessel cluster region.

[0145] [Supplementary item 3]

[0146] The information processing apparatus according to supplementary item 2, wherein

[0147] The processor determines based on at least one or more of a blood vessel diameter, a displacement amount of a blood vessel from a center of the blood vessel cluster region, and a circularity of a blood vessel.

[0148] [Supplementary item 4]

[0149] The information processing apparatus according to supplementary item 2 or supplementary item 3, wherein

[0150] The processor detects a blood vessel monomer region containing a blood vessel monomer from within the ultrasonogram, and determines which of an artery and a vein a blood vessel contained in the detected blood vessel monomer region is.

[0151] [Para 5]

[0152] The information processing apparatus according to Para 4, wherein

[0153] The processor corrects the determination result of the blood vessel in the blood vessel monomer region based on the determination result of each blood vessel in the blood vessel aggregate region.

[0154] [Para 6]

[0155] The information processing apparatus according to Para 5, wherein

[0156] The processor compares the reliability of the determination of the blood vessel in the blood vessel monomer region with the reliability of the determination of each blood vessel in the blood vessel aggregate region, and selects a determination result with higher reliability.

[0157] [Para 7]

[0158] The information processing apparatus according to Para 6, wherein

[0159] The processor displays each blood vessel contained in the blood vessel aggregate region as distinguishable between an artery and a vein based on the correction result.

[0160] [Para 8]

[0161] The information processing apparatus according to Para 7, wherein

[0162] The processor displays the reliability with respect to the selected determination result in the display device.

[0163] [Para 9]

[0164] The information processing apparatus according to Para 8, wherein

[0165] The processor displays a message for attention on the display device in a case where the reliability with respect to the selected determination result is lower than a certain value.

[0166] The technology of the present application can also be appropriately combined with the above-described various embodiments and / or various modifications. Also, various structures can of course be employed as long as they do not depart from the gist, without being limited to the above-described embodiments.

[0167] The above-described contents and drawings are detailed descriptions of a part of the technology of the present application, and are only one example of the technology of the present application. For example, the descriptions related to the above-described structure, function, action, and effect are descriptions related to one example of the structure, function, action, and effect of the part of the technology of the present application. Therefore, the above-described contents and drawings can of course delete unnecessary parts, or add or replace new elements, within the scope of the gist of the technology of the present application. Also, in order to avoid complicated situations, and to easily understand the part of the technology of the present application, the descriptions related to technical common knowledge and the like which are not particularly necessary to enable the technology of the present application are omitted in the above-described contents and drawings.

[0168] In the present specification, the meaning of "A and / or B" is the same as "at least one of A and B". That is, the meaning of "A and / or B" is that only A can be included, only B can be included, or both of A and B can be included.

[0169] All of the literature, patent applications and technical standards cited in the present specification are, to the extent that they are each specifically and individually denoted by reference to be incorporated herein by reference, incorporated by reference in the present specification to the same extent as the individual literature, patent application and technical standard is denoted to be incorporated by reference.

[0170] Symbol Explanation

[0171] 2, 2A, 2B - ultrasonic diagnostic apparatus, 4 - reception circuit, 10, 10A - ultrasonic probe, 11 - housing, 11A - array housing portion, 11B - handle portion, 13 - transducer array, 14 - transceiver circuit, 15 - communication portion, 16 - transmission circuit, 17 - reception circuit, 20, 20A, 20B - apparatus main body, 21 - display apparatus, 22 - input apparatus, 23 - communication portion, 24 - storage apparatus, 25 - processor, 26 - program, 30 - living body, 31 - puncture needle, 41 - amplification portion, 42 - A / D conversion portion, 43 - beam shaper, 50 - main control portion, 51 - image generation portion, 52 - display control portion, 53 - image analysis portion, 54 - emphasis display portion, 61 - signal processing portion, 62 - DSC, 63 - image processing portion, 71 - blood vessel monomer detection portion, 71A - blood vessel monomer detection model, 72 - blood vessel aggregate detection portion, 72A - blood vessel aggregate detection model, 73 - arteriovenous determination portion, 74 - correction portion, A - determination result, B, B1-B5 - blood vessel, C - center, D - blood vessel diameter, K - displacement amount, D1 - blood vessel monomer detection information, D2 - blood vessel aggregate detection information, D3 - arteriovenous determination information, DB - blood vessel detection information, L - correct label, M - guide mark, NW - network, P - teacher image, Ra - blood vessel aggregate region, Rs - blood vessel monomer region, TD1, TD2 - teacher data, U - ultrasonic image, UB - ultrasonic beam.

Claims

1. An information processing apparatus that performs processing of causing a display apparatus to display an ultrasonic wave image generated by transmitting an ultrasonic wave beam from a transducer array toward an inside of a living body and receiving an ultrasonic wave echo generated in the inside of the living body, the information processing apparatus comprising: a blood vessel aggregate detection section that detects a blood vessel aggregate region including a blood vessel aggregate formed by aggregation of three or more blood vessels from within the ultrasonic wave image; an emphasis display section that emphasizes the blood vessel aggregate region within the ultrasonic wave image; and an artery-vein determination section that determines, for each blood vessel included in the blood vessel aggregate region, which one of an artery and a vein the blood vessel is, based on a feature amount of each blood vessel within the blood vessel aggregate region. 2.The information processing apparatus according to claim 1, wherein the artery-vein determination section determines based on at least one or more of a blood vessel diameter, a displacement amount of a blood vessel from a center of the blood vessel aggregate region, and a circularity of a blood vessel. 3.The information processing apparatus according to claim 1 or 2, wherein the information processing apparatus further comprises a blood vessel monomer detection section that detects a blood vessel monomer region including a blood vessel monomer from within the ultrasonic wave image and determines which one of an artery and a vein a blood vessel included in the detected blood vessel monomer region is. 4.The information processing apparatus according to claim 3, wherein the information processing apparatus further comprises a correction section that corrects a determination result of the blood vessel monomer detection section based on a determination result of the artery-vein determination section. 5.The information processing apparatus according to claim 4, wherein the correction section compares a reliability of the determination of the blood vessel monomer detection section and a reliability of the determination of the artery-vein determination section and selects a determination result with a higher reliability. 6.The information processing apparatus according to claim 5, wherein the emphasis display section displays each blood vessel included in the blood vessel aggregate region so that an artery and a vein can be distinguished based on a correction result of the correction section. 7.The information processing apparatus according to claim 6, wherein the emphasis display section displays a reliability of the determination result selected by the correction section on the display apparatus. 8.The information processing apparatus according to claim 7, wherein the emphasis display section displays a message for calling attention on the display apparatus in a case where the reliability of the determination result selected by the correction section is lower than a certain value. 9.An information processing method that performs processing of causing a display apparatus to display an ultrasonic wave image generated by transmitting an ultrasonic wave beam from a transducer array toward an inside of a living body and receiving an ultrasonic wave echo generated in the inside of the living body, in the information processing method, a blood vessel aggregate region including a blood vessel aggregate formed by aggregation of three or more blood vessels is detected from within the ultrasonic wave image, and the detected blood vessel aggregate region is emphasized within the ultrasonic wave image, For each of the blood vessels included in the blood vessel aggregate region, it is determined which of an artery and a vein each blood vessel within the blood vessel aggregate region is according to a feature amount of each blood vessel within the blood vessel aggregate region.

10. A storage medium readable by a computer, the storage medium storing a program causing a computer to execute processing that causes a display device to display an ultrasonic image generated by transmitting an ultrasonic beam from a transducer array toward a living body and receiving an ultrasonic echo generated in the living body, The program causes the computer to execute the following processing: A blood vessel aggregate region including a blood vessel aggregate of three or more blood vessels is detected from within the ultrasonic image, and the detected blood vessel aggregate region is emphasized and displayed within the ultrasonic image; and For each of the blood vessels included in the blood vessel aggregate region, it is determined which of an artery and a vein each blood vessel within the blood vessel aggregate region is according to a feature amount of each blood vessel within the blood vessel aggregate region.

Images