Ultrasonic diagnostic apparatus

Abstract

The invention provides an ultrasonic diagnostic apparatus. The purpose of the present invention is to facilitate processing for displaying an appropriate Doppler waveform image in an ultrasonic diagnostic device. An information processing unit (28) provided in an ultrasound diagnostic device (100) executes: a process for generating a B-mode image on the basis of transmitting ultrasound waves to a subject (18) and receiving ultrasound waves reflected by the subject (18); generating a Doppler waveform image on the basis of transmitting ultrasonic waves to a subject (18) and receiving ultrasonic waves reflected by the subject; identifying a Doppler observation object in the subject (18) on the B-mode image; and generating an evaluation value for the Doppler waveform image on the basis of the Doppler waveform image and the reference Doppler waveform image corresponding to the Doppler observation object.

Description

Technical Field

[0001] The present invention relates to an ultrasonic diagnostic device, and in particular to a device for generating a B-mode image and a Doppler waveform image. Background Art

[0002] Ultrasonic diagnostic devices are widely used. Ultrasonic diagnostic devices generate a B-mode image representing a cross-sectional image of a subject or a Doppler waveform image representing blood flow velocity based on a reception signal obtained by transmitting ultrasonic waves from an ultrasonic probe to a subject and receiving ultrasonic waves reflected by the subject by the ultrasonic probe. As shown in the following patent document 1, an ultrasonic diagnostic device includes a device that displays a B-mode image of a subject and displays a Doppler waveform image for a blood vessel displayed in the B-mode image. Furthermore, as shown in patent documents 2 and 3, an ultrasonic diagnostic device includes a device that determines a part shown in the B-mode image based on the B-mode image of the subject.

[0003] Patent Document 1: Japanese Patent Application Publication No. 2018-082794

[0004] Patent Document 2: International Publication No. 2019 / 150715

[0005] Patent Document 3: International Publication No. 2017 / 033503

[0006] In an ultrasonic diagnostic apparatus, if the position or posture of the ultrasonic probe is inappropriate, an appropriate Doppler waveform image may not be displayed. Furthermore, since the appropriate position or posture of the ultrasonic probe varies depending on the part of the observation object, it may be difficult for the user to perform operations to display an appropriate Doppler waveform image. Summary of the invention

[0007] An object of the present invention is to facilitate processing for displaying an appropriate Doppler waveform image in an ultrasonic diagnostic apparatus.

[0008] The ultrasonic diagnostic device involved in the present invention is characterized in that it has an information processing unit, which performs the following processing: generating a B-mode image based on sending ultrasonic waves to a subject and receiving ultrasonic waves reflected by the subject; identifying a Doppler observation object in the subject on the B-mode image; generating a Doppler waveform image about the Doppler observation object based on sending ultrasonic waves to the subject and receiving ultrasonic waves reflected by the subject; and generating an evaluation value for the Doppler waveform image based on a reference Doppler waveform image corresponding to the Doppler observation object and the Doppler waveform image.

[0009] Preferably, the information processing unit specifies a test site as the Doppler observation target by being given the B-mode image, and constructs a machine learning model that outputs the evaluation value for the reference Doppler waveform image by being given information specifying the test site and the Doppler waveform image.

[0010] Preferably, the information processing unit performs the following processing: by referring to the B-mode image and an examined part database that establishes a correspondence between a reference B-mode image and each of the plurality of examined parts, identifying one of the plurality of examined parts as the Doppler observation target.

[0011] Preferably, the information processing unit calculates the degree of similarity between the B-mode image and baseline B-mode images for the multiple examined parts, determines the baseline B-mode image data having the greatest degree of similarity, and identifies the examined part correspondingly associated with the determined baseline B-mode image data as the Doppler observation object.

[0012] Preferably, the information processing unit is given information for determining the examined part and Doppler waveform image data to construct a disease determination model that outputs the type of disease, the disease possibility evaluation value for the disease, and the disease Doppler waveform image data, and takes the Doppler observation object as the examined part.

[0013] Preferably, the information processing unit performs processing for indicating a possibility of disease being confirmed in the Doppler observation target based on a disease Doppler waveform image indicating a Doppler waveform image when a disease is confirmed in the Doppler observation target and the Doppler waveform image.

[0014] Preferably, the information processing unit performs the following processing: displaying the evaluation value; and adjusting an operation parameter of the ultrasonic diagnostic apparatus based on the B-mode image or the Doppler waveform image according to a user operation when the evaluation value is displayed.

[0015] Preferably, the information processing unit performs a process of adjusting an operation parameter of the ultrasonic diagnostic apparatus based on the B-mode image or the Doppler waveform image when the evaluation value is smaller than a predetermined reference value.

[0016] Preferably, the information processing unit performs the following processing: by being given information for determining the examined part and the Doppler waveform image, a detail evaluation model is constructed to output details contained in the examined part, the reference Doppler waveform image for the details, and the evaluation value, and the Doppler observation object for which the evaluation value was previously generated is used as the examined part in the detail evaluation model.

[0017] Preferably, the information processing unit performs the following processing: based on the Doppler waveform image and the reference Doppler waveform image for the detail included in the examined part, identifying the detail included in the Doppler observation object for which the evaluation value was previously generated, and the processing for generating the evaluation value includes the following processing: generating the evaluation value based on the Doppler waveform image and the reference Doppler waveform image corresponding to the detail.

[0018] Preferably, the information processing unit performs a process of providing an instruction on operation of the ultrasonic probe to a user through a human-machine interface based on the evaluation value.

[0019] Effects of the Invention

[0020] According to the present invention, it is possible to facilitate the process of displaying an appropriate Doppler waveform image in an ultrasonic diagnostic apparatus. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 It is a diagram showing the configuration of an ultrasonic diagnostic apparatus according to an embodiment of the present invention.

[0022] Figure 2 It is a diagram showing an example of a Doppler waveform image.

[0023] Figure 3 This is a flowchart of the Doppler waveform determination process.

[0024] Figure 4 It is a figure which shows the Doppler waveform image of the position where stenosis occurs.

[0025] Figure 5 It is a figure which shows the Doppler waveform image on the upstream side of a stenosis.

[0026] Figure 6 It is a figure which shows the Doppler waveform image on the downstream side of a stenosis.

[0027] Explanation of symbols

[0028] 10-beam control unit, 12-transmitting unit, 14-ultrasonic probe, 16-vibrating element, 18-subject, 20-receiving unit, 22-control unit, 24-operating unit, 26-memory, 28-information processing unit, 30-phase addition unit, 32-B-mode image generating unit, 34-image processing unit, 36-Doppler processing unit, 38-Doppler image generating unit, 40-display unit, 52-baseline. DETAILED DESCRIPTION

[0029] The embodiments of the present invention are described with reference to the drawings. The same components shown in multiple drawings are marked with the same symbols, and their descriptions are omitted. In addition, in this specification, the term "A image" in which the term "image" is connected to a specific name "A" means an image represented by "A image data". In addition, the expression "generating A image data" is sometimes simplified to "generating A image".

[0030] exist Figure 1 2 shows the structure of the ultrasonic diagnostic apparatus 100 according to the embodiment of the present invention. The ultrasonic diagnostic apparatus 100 includes a beam control unit 10, a transmitting unit 12, an ultrasonic probe 14, a receiving unit 20, a control unit 22, an operating unit 24, a memory 26, an information processing unit 28, and a display unit 40. The information processing unit 28 may be composed of one or more processors that realize the functions of the phasing and adding unit 30, the B-mode image generating unit 32, the image processing unit 34, the Doppler processing unit 36, and the Doppler image generating unit 38 by executing a program. The control unit 22 performs overall control of the ultrasonic diagnostic apparatus 100. The operating unit 24 includes a keyboard, a mouse, a lever, a button, etc., and outputs information related to the user's operation to the control unit 22. The operating unit 24 may include a touch panel in the display screen of the display unit 40. The control unit 22 may control the ultrasonic diagnostic apparatus 100 according to the operation in the operating unit 24.

[0031] The operation of the ultrasonic diagnostic apparatus 100 will be described in general. The ultrasonic diagnostic apparatus 100 transmits ultrasonic waves from the ultrasonic probe 14 to the subject 18, and receives the ultrasonic waves reflected by the subject 18 by the ultrasonic probe 14. The ultrasonic diagnostic apparatus 100 performs each measurement based on the B mode and the Doppler mode. In the B mode operation, the ultrasonic diagnostic apparatus 100 generates a B mode image based on the ultrasonic waves received from the subject 18, and displays it on the display unit 40. In the Doppler mode operation, the ultrasonic diagnostic apparatus 100 generates a Doppler waveform image in the subject 18 based on the Doppler frequency shift of the ultrasonic waves received from the subject 18, and displays it on the display unit 40. Only one of the B mode operation and the Doppler mode operation may be performed, or the measurement based on these two modes may be performed in a time-division manner.

[0032] The specific structure of the ultrasonic diagnostic apparatus 100 and the specific processing performed by the ultrasonic diagnostic apparatus 100 are described. The ultrasonic probe 14 is set to a state of contact with the surface of the subject 18. The ultrasonic probe 14 has a plurality of vibrating elements 16. The transmitting unit 12 outputs a transmission signal to each vibrating element 16 of the ultrasonic probe 14 based on the control of the beam control unit 10. As a result, ultrasonic waves are transmitted from the ultrasonic probe 14. The beam control unit 10 forms a transmission beam in the ultrasonic probe 14 by controlling the transmitting unit 12, and scans the transmission beam on the subject 18. That is, the transmitting unit 12 adjusts the delay time or level of each transmission signal according to the control of the beam control unit 10, forms a transmission beam in the ultrasonic probe 14, and scans the transmission beam on the subject 18.

[0033] When each vibration element 16 of the ultrasonic probe 14 receives the ultrasonic wave reflected in the subject 18, each vibration element 16 outputs an electrical signal corresponding to the received ultrasonic wave to the receiving unit 20. The receiving unit 20 performs amplification, detection, band limiting and other processing on the reception signal output from each vibration element 16 according to the control of the beam control unit 10, and outputs it to the phasing and adding unit 30.

[0034] The phasing and adding unit 30 generates a phased reception signal by phasing and adding a plurality of reception signals output from the receiving unit 20 to the plurality of vibration elements 16. Thus, a phased reception signal is generated in which the phases are adjusted and added so that the reception signals based on the ultrasound waves received from a specific direction are mutually enhanced and a reception beam is formed in the specific direction. When the phasing and adding unit 30 operates in the B mode, the phased reception signal is output to the B mode image generating unit 32, and when the phasing and adding unit 30 operates in the Doppler mode, the phased reception signal is output to the Doppler processing unit 36.

[0035] The operation in the B mode will be described. The phase adjustment and addition unit 30 generates each phase-adjusted reception signal based on the ultrasound waves received from each direction of the reception beam scanned in the subject 18, and outputs it to the B-mode image generation unit 32. The B-mode image generation unit 32 generates B-mode image data based on the phase-adjusted reception signal obtained for each reception beam direction, and outputs it to the image processing unit 34. The B-mode image data based on one scan of the transmission beam and the reception beam is one frame of image data, corresponding to one B-mode image.

[0036] The beam control unit 10, the transmission unit 12, the ultrasonic probe 14, the reception unit 20, the phase adjustment and addition unit 30, and the B-mode image generation unit 32 sequentially generate B-mode image data as the transmission beam and the reception beam are repeatedly scanned, and output each B-mode image data to the image processing unit 34. The image processing unit 34 generates an image signal for displaying a B-mode image based on the B-mode image data, and outputs it to the display unit 40. The display unit 40 displays the B-mode image based on the image signal.

[0037] Next, the operation in Doppler mode is described. Doppler mode includes PW Doppler mode (pulsed wave Doppler mode) that transmits ultrasonic pulses at a repetition frequency PRF and CW Doppler mode (continuous wave Doppler mode) that continuously transmits ultrasonic waves. The user can select to operate in PW Doppler mode or in CW Doppler mode.

[0038] The Doppler processing unit 36 ​​sequentially performs fast Fourier transform processing on the phased received signals divided within a predetermined time length, sequentially generates spectrum data of Doppler shift as time passes, and outputs it to the Doppler image generating unit 38. Here, the Doppler shift refers to the frequency indicating the deviation of the frequency of the received signal from the frequency of the transmitted signal.

[0039] The Doppler image generation unit 38 generates Doppler waveform image data based on a plurality of sets of spectrum data sequentially outputted over time. Figure 2 An example of a Doppler waveform image represented by Doppler waveform image data is shown in . The Doppler waveform image has the horizontal axis direction as time and the vertical axis direction as the Doppler frequency shift (blood flow velocity). The brightness of multiple images arranged vertically at a certain moment on the time axis represents the spectrum corresponding to that moment. The baseline 52 extending in a straight line in the horizontal direction indicates that the Doppler frequency shift is 0. The Doppler image generation unit 38 generates Doppler waveform image data sequentially as time passes, and outputs it to the image processing unit 34. The image processing unit 34 generates an image signal displaying the Doppler waveform image based on the Doppler waveform image data, and outputs it to the display unit 40. The display unit 40 displays the Doppler waveform image based on the image signal.

[0040] The ultrasonic diagnostic apparatus 100 according to this embodiment performs Figure 3 The Doppler waveform determination process is a process for determining the appropriateness of a Doppler waveform image. Figure 3The flowchart of FIG. 1 shows the processing when the Doppler mode is the PW Doppler mode. In the Doppler waveform determination processing, the user first performs an image freezing operation (S101) to freeze the image displayed on the display unit 40, and the B-mode image data generated immediately before the image freezing operation is performed is used as the processing object. The B-mode image of the processing object can be displayed on the display unit 40.

[0041] The image processing unit 34 recognizes the examined part such as an organ appearing in the B-mode image as a Doppler observation target ( S102 ) Specifically, the image processing unit 34 performs the following processing referring to the examined part database stored in the memory 26 .

[0042] The examination site database contains data for constructing an examination site determination model as a machine learning model. The examination site determination model outputs information that determines the examination site as a Doppler observation object by assigning B-mode image data of the processing object. Here, the information that determines the examination site is, for example, character information representing the name of the examination site, an ID (Identification) pre-set for the examination site, etc. The examination site determination model is constructed, for example, based on multiple sets of teacher data obtained through measurements performed on multiple different examination sites in the past. The teacher data can be, for example, data that establishes a corresponding association between the B-mode image data of the processing object and the information that determines the examination site as a Doppler observation object. The examination site determination model can be constructed using machine learning algorithms such as CNN, AdaBoost, and SVN. The machine learning model described below is also constructed using machine learning algorithms such as CNN, AdaBoost, and SVN. The machine learning algorithm may include a deep learning algorithm.

[0043] The examined part may be, for example, the heart, carotid artery, liver, kidney, uterus, prostate, upper limbs, lower limbs, etc. The plurality of reference B-mode image data may be a plurality of image data showing tomographic images at different positions of the examined part.

[0044] The image processing unit 34 constructs an examination site identification model by referring to the examination site database. The image processing unit 34 obtains information identifying the examination site by assigning the B-mode image data of the processing target to the examination site identification model, thereby identifying the Doppler observation target.

[0045] In addition, the examined part database may include an examined part table that establishes a corresponding association between information determining the examined part and a plurality of reference B-mode image data about the examined part. In this case, the image processing unit 34 may perform the following template matching processing. That is, the image processing unit 34 obtains an approximate evaluation value of the degree of approximation between the B-mode image data representing the processing object and each reference B-mode image data correspondingly associated with each examined part in the examined part database, and determines the reference B-mode image data with the largest approximate evaluation value. Then, the examined part correspondingly associated with the determined reference B-mode image data is identified as a Doppler observation object appearing in the B-mode image of the processing object, i.e., a Doppler observation object on the B-mode image. In addition, the degree of approximation of two image data may be a correlation value about two images represented by the two image data.

[0046] After the Doppler observation object is identified, the image processing unit 34 determines whether a Doppler gate can be set on the B-mode image based on the B-mode image data of the processing object (S103). Here, the Doppler gate refers to the range for measuring the blood flow velocity by the action of the Doppler mode on the transmission beam and the reception beam, and is set in the image of the blood vessel appearing in the B-mode image. When the blood vessel is identified in the B-mode image, the image processing unit 34 determines that the Doppler gate can be set, and the process proceeds to step S104. When the blood vessel is not identified in the B-mode image by image recognition technology, etc., the image processing unit 34 determines that the Doppler gate cannot be set, and the process proceeds to step S108.

[0047] Whether the Doppler gate can be set may be determined by the user referring to the image displayed on the display unit 40. In this case, the process executed by the ultrasonic diagnostic apparatus 100 proceeds to step S104 or step S108 according to the user's operation.

[0048] In steps S104 and S108, the image is unfrozen by performing an operation to unfreeze the image. Alternatively, the control unit 22 automatically unfreezes the image. Thus, as time passes, the B-mode image data is sequentially output from the B-mode image generating unit 32 to the image processing unit 34. Furthermore, as time passes, the Doppler waveform image data is sequentially output from the Doppler image generating unit 38 to the image processing unit 34. After step S108, the processing performed by the ultrasonic diagnostic apparatus 100 returns to step S101.

[0049] In addition, when the Doppler mode is the CW Doppler mode, step S103 and step S108 may not be executed.

[0050] The examination site database includes data for constructing a Doppler waveform evaluation model as a machine learning model. The Doppler waveform evaluation model outputs a Doppler waveform evaluation value and standard reference Doppler waveform image data about the blood flowing through the examination site by being assigned information for determining the examination site and Doppler waveform image data. The Doppler waveform evaluation value may be, for example, an evaluation value indicating the degree of approximation between the reference Doppler waveform image data and the assigned Doppler waveform image data. The Doppler waveform evaluation model may be constructed, for example, based on a plurality of sets of teacher data obtained by measurements performed in the past on a plurality of different examination sites. The teacher data may be, for example, data that establishes a correspondence association between information for determining the examination site and Doppler waveform image data obtained for the examination site.

[0051] The image processing unit 34 constructs a Doppler waveform evaluation model by referring to the examination site database. The image processing unit 34 obtains a Doppler waveform evaluation value by assigning information that specifies the examination site to be observed by Doppler and Doppler waveform image data to the Doppler waveform evaluation model, and acquires reference Doppler waveform image data (S105 and S106). The image processing unit 34 performs a determination result display process described later based on the Doppler waveform evaluation value and the reference Doppler waveform image data (S107).

[0052] In addition, when the inspection site table is used, the reference Doppler waveform image data about the blood flowing through each inspection site can also be associated with the information that specifies each inspection site in the inspection site table. In this case, after executing step S104, the image processing unit 34 refers to the inspection site database and obtains the reference Doppler waveform image data associated with the inspection site identified as the object of Doppler observation (S106). The image processing unit 34 obtains the Doppler waveform evaluation value as the degree of similarity between the reference Doppler waveform image data and the Doppler waveform image data output from the Doppler image generation unit 38 (S105). The image processing unit 34 performs the following determination result display processing based on the Doppler waveform evaluation value (S107).

[0053] The image processing unit 34 generates determination result information indicating whether the Doppler waveform image data is appropriately generated, etc. The image processing unit 34 generates a video signal showing the determination result information, and outputs it to the display unit 40. The display unit 40 displays the determination result information based on the video signal.

[0054] The determination result information may include, for example, the following information (i) to (iii). The information included in the determination result information is not limited to the following information (i) to (iii), and the determination result information may include other arbitrary information.

[0055] (i) Name of the examined part identified as the Doppler observation target based on the B-mode image

[0056] (ii) Doppler waveform evaluation value

[0057] (iii) A Doppler waveform image acquired by the ultrasonic diagnostic apparatus and a reference Doppler waveform image of the inspection site identified as the object of Doppler observation

[0058] The information (i) to (iii) above may be updated sequentially over time based on Doppler waveform image data that is sequentially generated over time, or may be displayed in real time on the display unit 40. Furthermore, the Doppler waveform evaluation value may be replaced by text indicating the magnitude of the Doppler waveform evaluation value, such as "large", "normal", or "small".

[0059] In this way, the information processing unit 28 included in the ultrasonic diagnostic apparatus 100 performs processing for generating a B-mode image based on transmitting ultrasonic waves to the subject 18 and receiving ultrasonic waves reflected by the subject 18. Furthermore, the information processing unit 28 performs processing for identifying the Doppler observation target in the subject 18 on the B-mode image. This processing may be processing for obtaining information for identifying the subject site to be observed by assigning the B-mode image data of the processing target to the subject site identification model.

[0060] The information processing unit 28 performs processing for generating a Doppler waveform image of a Doppler observation target based on transmitting ultrasonic waves to the subject 18 and receiving ultrasonic waves reflected by the subject 18. The information processing unit 28 can also obtain reference Doppler waveform image data by assigning information specifying the subject site as the Doppler observation target and the Doppler waveform image generated by the Doppler image generating unit 38 to a Doppler waveform evaluation model to obtain a Doppler waveform evaluation value.

[0061] In the ultrasonic diagnostic apparatus 100 according to the present embodiment, based on the Doppler waveform evaluation value, instructions on the operation of the ultrasonic probe 14 are provided to the user through the operation unit 24 and the display unit 40 as a human-machine interface. For example, when the Doppler waveform evaluation value is less than a predetermined threshold value, a text, a graphic, etc. that prompts the user to adjust the position or posture of the ultrasonic probe 14 may be displayed. In this case, the image processing unit 34 may sequentially obtain the Doppler waveform evaluation value as time passes based on the Doppler waveform image data sequentially generated as time passes, and display the instructions that change in real time on the display unit 40. The user can adjust the position and posture of the ultrasonic probe 14 by referring to the Doppler waveform image and the reference Doppler waveform image displayed on the display unit 40.

[0062] In addition, an acceleration sensor may be provided in the ultrasonic probe 14. The acceleration detection value based on the acceleration sensor is output to the control unit 22, and the Doppler waveform evaluation value is output from the image processing unit 34 to the control unit 22. For example, when the acceleration detection value is greater than a predetermined threshold value and the Doppler waveform evaluation value is less than the predetermined threshold value, the control unit 22 outputs an instruction to the image processing unit 34 to make the ultrasonic probe 14 still. The image processing unit 34 displays the instruction on the display unit 40.

[0063] Instructions can be generated by a machine learning model. For example, data corresponding to B-mode image data, Doppler waveform image data, Doppler waveform evaluation values, acceleration detection values, etc. acquired in the past are stored in the memory 26 as teacher data. The control unit 22 constructs an instructor as a machine learning model in the control unit 22 based on the instructor data stored in the memory 26. The instructor generates instructions containing information on how to move the ultrasonic probe 14 by assigning the B-mode image data, Doppler waveform image data, Doppler waveform evaluation values, etc. at the current moment. The control unit 22 displays the instructions generated by the instructor on the display unit 40.

[0064] Generally speaking, the standard Doppler waveform image of the blood vessel that appears in the B-mode image is different depending on the examined part. Therefore, even if the B-mode image and the Doppler waveform image are displayed on the display unit 40 for a certain examined part, it is difficult for the user to understand whether the Doppler waveform image is appropriate, whether the position or posture of the ultrasonic probe 14 in contact with the subject 18 is appropriate, etc. According to the ultrasonic diagnostic apparatus 100 involved in this embodiment, the appropriateness of the Doppler waveform image is represented by the Doppler waveform evaluation value. In addition, by displaying the instruction on the display unit 40, the user can easily understand whether the position or posture of the ultrasonic probe 14 in contact with the subject 18 is appropriate, etc.

[0065] In the ultrasonic diagnostic apparatus 100, the disease determination result display process can be executed instead of the determination result display process (S107) or together with the determination result display process (S107). The disease determination result display process is a process for determining whether a disease is confirmed in the subject 18 based on the Doppler waveform image data by a machine learning model described below.

[0066] The examination site database contains data for constructing a disease determination model as a machine learning model. The disease determination model outputs the category of the disease, the disease possibility evaluation value for the disease, and the disease Doppler waveform image data by being assigned information for determining the examination site and Doppler waveform image data. For example, in the case where the examination site is the carotid artery, there is stenosis of the carotid artery as a disease. The disease Doppler waveform image data includes reference Doppler waveform image data of the location where the stenosis occurs, reference Doppler waveform image data on the upstream side of the stenosis, and reference Doppler waveform image data on the downstream side of the stenosis. The disease possibility evaluation value can be, for example, an evaluation value indicating the degree of approximation between the disease Doppler waveform image data corresponding to the determined disease category and the assigned Doppler waveform image data.

[0067] As explained above Figure 2 This is a Doppler waveform image of a normal artery. Figure 4 The Doppler waveform image of the location where the stenosis occurs is shown in FIG. Figure 5 The Doppler waveform image of the upstream side of the stenosis is shown in FIG. Figure 6 A Doppler waveform image of the downstream side of the stenosis is shown in FIG.

[0068] The disease determination model is constructed based on, for example, multiple sets of teacher data obtained through past measurements of multiple different examined parts. The teacher data may be, for example, data that establishes a correspondence between information that identifies the examined part, information that identifies the type of disease, and Doppler waveform image data obtained for the disease at the examined part.

[0069] The image processing unit 34 constructs a disease determination model by referring to the examination site database. The image processing unit 34 acquires information for determining the type of disease, a disease possibility evaluation value for the disease, and disease Doppler waveform image data by assigning information for determining the examination site and Doppler waveform image data to the disease determination model.

[0070] When multiple diseases are determined for the examined part identified as the object of Doppler observation, the image processing unit 34 obtains information on the type of the determined disease, the disease possibility evaluation value, and the disease Doppler waveform image data for each of the multiple diseases. The image processing unit 34 performs the following disease determination result display processing based on the acquired information, data, etc.

[0071] In addition, when the inspection site table is used, in the inspection site table, the reference Doppler waveform image data about the blood flowing through each inspection site is associated with each inspection site, and in addition, the disease Doppler waveform image data representing the Doppler waveform image when a disease is confirmed in the inspection site can be associated with each inspection site. In this case, the image processing unit 34 refers to the inspection site database and obtains the disease Doppler waveform image data associated with the inspection site identified as the object of Doppler observation. The image processing unit 34 obtains the disease possibility evaluation value indicating the degree of similarity between the disease Doppler waveform image data and the Doppler waveform image data output from the Doppler image generation unit 38.

[0072] The image processing unit 34 generates disease possibility information indicating the possibility of disease confirmation, etc. The image processing unit 34 generates a video signal showing the disease possibility information, and outputs it to the display unit 40. The display unit 40 displays the disease possibility information based on the video signal.

[0073] The disease possibility information may include, for example, the following information (iv) to (vi). The information included in the disease possibility information is not limited to the following information (iv) to (vi), and the disease possibility information may include other arbitrary information.

[0074] (iv) Name of the examined part identified as the Doppler observation target based on the B-mode image

[0075] (v) Disease type and disease likelihood evaluation value for the disease

[0076] (vi) Doppler waveform image acquired by the ultrasonic diagnostic apparatus 100 and a disease Doppler waveform image of a part of the body identified as a target for Doppler observation

[0077] The information (i) to (vi) above can be updated sequentially over time based on Doppler waveform image data that is sequentially generated over time, and can also be displayed in real time on the display unit 40. In addition, the disease possibility evaluation value can also be replaced by text indicating the magnitude of the disease possibility evaluation value, such as "found" or "not found".

[0078] The examination site database includes data for constructing a detail evaluation model as a machine learning model. The detail evaluation model outputs details contained in the determined examination site, detail reference Doppler waveform image data, and detail evaluation values ​​by being assigned information for determining the examination site and Doppler waveform image data. In the case where the examination site is the lower limb of the subject 18, the details may be, for example, peripheral blood vessels. The detail reference Doppler waveform image data is data representing a standard Doppler waveform image regarding the details. The detail evaluation value represents the degree of approximation between the detail reference Doppler waveform image data and the assigned Doppler waveform image data. The detail evaluation model is constructed, for example, based on multiple sets of teacher data obtained by measurements performed on multiple different examination sites in the past. The teacher data may be, for example, data that establishes a corresponding association between information for determining the examination site and Doppler waveform image data obtained for the examination site and information for determining the details contained in the examination site.

[0079] The image processing unit 34 first identifies the examined part as the Doppler observation target on the B-mode image, and then builds a detail evaluation model by referring to the examined part database. The image processing unit 34 acquires detail-determining information, detail reference Doppler waveform image data, and detail evaluation value by assigning information for determining the examined part and Doppler waveform image data to the detail evaluation model.

[0080] The detail included in the inspection part previously identified as the Doppler observation object on the B-mode image is re-identified as the Doppler observation object by the detail evaluation model. The determination result display processing and disease determination result display processing for the detail identified as the Doppler observation object are the same as when the inspection part is identified as the Doppler observation object.

[0081] In addition, when the inspection part table is used, a plurality of detail reference Doppler waveform image data about the details included in each inspection part may be associated with each inspection part in the inspection part table. The image processing unit 34 first identifies the inspection part as the Doppler observation object on the B-mode image, and then refers to the inspection part database to obtain the detail reference Doppler waveform image data associated with the inspection part identified as the Doppler observation object. The image processing unit 34 obtains a detail evaluation value indicating the degree of similarity between the detail reference Doppler waveform image data and the Doppler waveform image data output from the Doppler image generation unit 38. The image processing unit 34 obtains the detail evaluation value for each of the plurality of detail reference Doppler waveform images through the same processing. In this case, the image processing unit 34 determines the detail reference Doppler waveform image data with the largest detail evaluation value. Then, the detail associated with the determined detail reference Doppler waveform image data is identified as the Doppler observation object on the B-mode image. Thus, the detail included in the inspection site previously identified as the Doppler observation target on the B-mode image is re-identified as the Doppler observation target. The determination result display processing and disease determination result display processing for the detail identified as the Doppler observation target are the same as when the inspection site is identified as the Doppler observation target.

[0082] The image processing unit 34 that performs the determination result display processing generates determination result information indicating whether the Doppler waveform image data is properly generated, etc. The image processing unit 34 generates a video signal that displays the determination result information, and outputs it to the display unit 40. The display unit 40 displays the determination result information based on the video signal.

[0083] The determination result information may include, for example, the following information (a) to (c).

[0084] (a) Name of detail identified as a Doppler observation target from the B-mode image (information identifying the detail)

[0085] (b) Detail evaluation value

[0086] (c) A Doppler waveform image acquired by the ultrasonic diagnostic apparatus and a reference Doppler waveform image of the inspection site identified as the object of Doppler observation

[0087] The image processing unit 34 that performs the disease determination result display processing generates disease possibility information indicating the possibility of disease confirmation, etc. The image processing unit 34 generates a video signal that displays the disease possibility information and outputs it to the display unit 40. The display unit 40 displays the disease possibility information based on the video signal.

[0088] The disease possibility information may include, for example, the following information (d) to (f).

[0089] (d) Name of the detail identified as the Doppler observation target based on the B-mode image

[0090] (e) Disease type and disease likelihood evaluation value for the disease

[0091] (f) Doppler waveform image acquired by the ultrasonic diagnostic apparatus 100 and a disease Doppler waveform image of a detail identified as a Doppler observation target

[0092] In this way, the information processing unit 28 included in the ultrasonic diagnostic apparatus 100 performs processing for identifying details in the Doppler observation target in the subject 18 on the B-mode image. This processing may include the following processing: assigning information identifying the subject part and the Doppler waveform image data to the detail evaluation model, and acquiring details included in the identified subject part and detail reference Doppler waveform image data, and detail evaluation values.

[0093] In the determination result display process in step S107, when the Doppler waveform evaluation value is less than a predetermined reference value, the image processing unit 34 may execute an automatic optimization function (Auto Optimizer). The automatic optimization function is a function for adjusting the operation parameters of the ultrasonic diagnostic apparatus 100 based on the B-mode image data. The operation parameters of the B-mode include, for example, the depth of the observation range, the gain for the received signal, the time gain control (a control value for adjusting the state of increasing the gain as the receiving time passes), and the focusing (the degree to which the ultrasonic beam is converged). By executing the automatic optimization function, the image processing unit 34 adjusts the image quality of the B-mode image of the processing object to an image quality that is easy for the user to visually recognize.

[0094] The operation parameters of the Doppler mode also include the repetition frequency PRF (velocity range), baseline, etc. By executing the automatic optimization function, the image processing unit 34 tracks the Doppler waveform appearing in the Doppler waveform image, and adjusts the range of the Doppler frequency shift, that is, the velocity range, the position of the baseline, etc. based on the tracked Doppler waveform. The control unit 22 executes the automatic optimization function, and the control unit 22 adjusts the operation parameters of the beam control unit 10, the transmitting unit 12, the receiving unit 20, and the information processing unit 28.

[0095] When the Doppler waveform evaluation value is less than a preset reference value, the determination result information may include information prompting the user to execute the automatic optimization function. The user may perform an operation to execute the automatic optimization function according to the information displayed. The control unit 22 executes the automatic optimization function according to the user's operation.

[0096] When the Doppler waveform evaluation value is smaller than a preset reference value, the control unit 22 may execute the automatic optimization function without any operation by the user.

[0097] [Structure of the present invention]

[0098] Structure 1:

[0099] An ultrasonic diagnostic device, characterized in that it comprises an information processing unit,

[0100] The information processing unit performs the following processing:

[0101] generating a B-mode image based on transmitting ultrasonic waves to a subject and receiving ultrasonic waves reflected by the subject;

[0102] identifying a Doppler observation object in the subject on the B-mode image;

[0103] generating a Doppler waveform image of the Doppler observation object based on transmitting ultrasonic waves to the subject and receiving ultrasonic waves reflected by the subject; and

[0104] An evaluation value for the Doppler waveform image is generated based on a reference Doppler waveform image corresponding to the Doppler observation target and the Doppler waveform image.

[0105] Structure 2:

[0106] The ultrasonic diagnostic apparatus according to configuration 1 is characterized in that:

[0107] The information processing unit specifies a test site to be observed by Doppler by being given the B-mode image, and constructs a machine learning model that outputs the evaluation value for the reference Doppler waveform image by being given information specifying the test site and the Doppler waveform image.

[0108] Structure 3:

[0109] The ultrasonic diagnostic apparatus according to configuration 1 is characterized in that:

[0110] The information processing unit performs the following processing:

[0111] By referring to the B-mode image and an examination site database that establishes a correspondence between a reference B-mode image and each of the plurality of examination sites, one of the plurality of examination sites is identified as the Doppler observation target.

[0112] Structure 4:

[0113] The ultrasonic diagnostic apparatus according to configuration 3 is characterized in that:

[0114] The information processing unit calculates the degree of similarity between the B-mode image and reference B-mode images for the plurality of examined parts, determines the reference B-mode image data having the greatest degree of similarity, and identifies the examined part correspondingly associated with the determined reference B-mode image data as the Doppler observation object.

[0115] Structure 5:

[0116] The ultrasonic diagnostic apparatus according to any one of Structures 1 to 4 is characterized in that:

[0117] The information processing unit is given information that determines the Doppler observation inspection site and Doppler waveform image data to construct a disease determination model that outputs the type of disease, the disease possibility evaluation value for the disease, and the disease Doppler waveform image data, and uses the Doppler observation object as the Doppler observation inspection site.

[0118] Structure 6:

[0119] The ultrasonic diagnostic apparatus according to any one of Structures 1 to 5, characterized in that

[0120] The information processing unit performs the following processing:

[0121] The possibility that a disease is confirmed in the Doppler observation target is indicated based on a disease Doppler waveform image representing a Doppler waveform image when a disease is confirmed in the Doppler observation target and the Doppler waveform image.

[0122] Structure 7:

[0123] The ultrasonic diagnostic apparatus according to any one of Structures 1 to 6, characterized in that

[0124] The information processing unit performs the following processing:

[0125] Display the rating value; and

[0126] According to a user's operation when the evaluation value is displayed, an operation parameter of the ultrasonic diagnostic apparatus is adjusted based on the B-mode image or the Doppler waveform image.

[0127] Structure 8:

[0128] The ultrasonic diagnostic apparatus according to any one of Structures 1 to 7, characterized in that

[0129] The information processing unit performs a process of adjusting an operation parameter of the ultrasonic diagnostic apparatus based on the B-mode image or the Doppler waveform image when the evaluation value is smaller than a predetermined reference value.

[0130] Structure 9:

[0131] The ultrasonic diagnostic apparatus according to any one of Structures 1 to 8, characterized in that

[0132] The information processing unit performs the following processing:

[0133] The detail evaluation model is constructed by receiving information specifying the detail observation inspection site and the Doppler waveform image, and outputting the detail included in the detail observation inspection site, the reference Doppler waveform image for the detail, and the evaluation value.

[0134] The Doppler observation object for which the evaluation value has been generated in advance is used as the detailed observation examination site in the detailed evaluation model.

[0135] Structure 10:

[0136] The ultrasonic diagnostic apparatus according to any one of Structures 1 to 8, characterized in that

[0137] The information processing unit performs processing to identify a detail included in the Doppler observation target for which the evaluation value has been previously generated, based on the Doppler waveform image and the reference Doppler waveform image for the detail included in the examined part;

[0138] The process of generating the evaluation value includes a process of generating the evaluation value based on the Doppler waveform image and the reference Doppler waveform image corresponding to the detail.

[0139] Structure 11:

[0140] The ultrasonic diagnostic apparatus according to any one of Structures 1 to 10 is characterized in that

[0141] The information processing unit performs the following processing:

[0142] Based on the evaluation value, instructions on the operation of the ultrasound probe are provided to the user through the human-machine interface.

Claims

1. An ultrasonic diagnostic device, characterized in that: Equipped with information processing department, The information processing unit performs the following processing: generating a B-mode image based on transmitting ultrasonic waves to a subject and receiving ultrasonic waves reflected by the subject; identifying a Doppler observation object in the subject on the B-mode image; generating a Doppler waveform image regarding the Doppler observation object based on transmitting ultrasonic waves to the subject and receiving ultrasonic waves reflected by the subject; and An evaluation value for the Doppler waveform image is generated based on a reference Doppler waveform image corresponding to the Doppler observation target and the Doppler waveform image.

2. The ultrasonic diagnostic apparatus according to claim 1, wherein: The information processing unit specifies a test site to be observed by Doppler by being given the B-mode image, and constructs a machine learning model that outputs the evaluation value for the reference Doppler waveform image by being given information specifying the test site and the Doppler waveform image.

3. The ultrasonic diagnostic apparatus according to claim 1, wherein: The information processing unit performs the following processing: By referring to the B-mode image and an examination site database that establishes a correspondence between a reference B-mode image and each of the plurality of examination sites, one of the plurality of examination sites is identified as the Doppler observation object.

4. The ultrasonic diagnostic apparatus according to claim 3, wherein: The information processing unit calculates the degree of similarity between the B-mode image and reference B-mode images for the plurality of examined parts, determines the reference B-mode image data having the greatest degree of similarity, and identifies the examined part correspondingly associated with the determined reference B-mode image data as the Doppler observation object.

5. The ultrasonic diagnostic apparatus according to claim 1, wherein: The information processing unit is given information identifying an inspection site and Doppler waveform image data to construct a disease determination model that outputs a disease category, a disease possibility evaluation value for the disease, and disease Doppler waveform image data, with the Doppler observation object being the inspection site.

6. The ultrasonic diagnostic apparatus according to claim 1, wherein: The information processing unit performs the following processing: The possibility that a disease is confirmed in the Doppler observation target is indicated based on a disease Doppler waveform image representing a Doppler waveform image when a disease is confirmed in the Doppler observation target and the Doppler waveform image.

7. The ultrasonic diagnostic apparatus according to claim 1, wherein: The information processing unit performs the following processing: Display the rating value; and According to a user's operation when the evaluation value is displayed, an operation parameter of the ultrasonic diagnostic apparatus is adjusted based on the B-mode image or the Doppler waveform image.

8. The ultrasonic diagnostic apparatus according to claim 1, wherein: The information processing unit performs a process of adjusting an operation parameter of the ultrasonic diagnostic apparatus based on the B-mode image or the Doppler waveform image when the evaluation value is smaller than a predetermined reference value.

9. The ultrasonic diagnostic apparatus according to claim 1, wherein: The information processing unit performs the following processing: The detail evaluation model is constructed by receiving information specifying the examined part and the Doppler waveform image, and outputting the detail included in the examined part, the reference Doppler waveform image for the detail, and the evaluation value. The Doppler observation object for which the evaluation value has been generated in advance is used as the examination site in the detailed evaluation model.

10. The ultrasonic diagnostic apparatus according to claim 1, wherein: The information processing unit performs processing to identify a detail included in the Doppler observation target for which the evaluation value has been previously generated, based on the Doppler waveform image and the reference Doppler waveform image for the detail included in the examined part; The process of generating the evaluation value includes a process of generating the evaluation value based on the Doppler waveform image and the reference Doppler waveform image corresponding to the detail.

11. The ultrasonic diagnostic apparatus according to claim 1, wherein: The information processing unit performs the following processing: Based on the evaluation value, instructions on the operation of the ultrasound probe are provided to the user through the human-machine interface.

Images