Ultrasonic thickness measuring device and ultrasonic thickness measuring method

Abstract

The present invention discloses an ultrasonic thickness measuring device and an ultrasonic thickness measuring method. The ultrasonic thickness measuring device (100) comprises: an ultrasonic probe (60) having eight or fewer ultrasonic elements (1, 2, 3, 4, 5, 6, 7, 8) each having an ultrasonic transmitting element and a receiving element; and a control unit (33) for calculating the thickness of a target body tissue based on tomographic image data of a subject's body obtained based on a received signal received by each receiving element of each ultrasonic element (1, 2, 3, 4, 5, 6, 7, 8). The control unit (33) calculates the thickness based on the tomographic image based on each received signal received by each ultrasonic element (1, 2, 3, 4, 5, 6, 7, 8).

Description

Technical Field

[0001] The present invention relates to an ultrasonic thickness measurement device and an ultrasonic thickness measurement method for obtaining the thickness of a target body tissue from an ultrasonic cross-sectional image of a subject's body. Background Art

[0002] Conventionally, there is known a measuring device that uses ultrasonic waves to measure the thickness of a muscle layer or a fat layer of a body (Patent Document 1).

[0003] Prior art literature

[0004] Patent Literature

[0005] Patent Document 1: Japanese Patent Application Laid-Open No. 61-220634

[0006] Patent Document 1 estimates the thickness of the muscle layer or fat layer based on A-mode images of ultrasonic signals, but accuracy is insufficient. One possible method for improving accuracy is to increase the number of ultrasonic elements. However, this increases the amount of information processed by the thickness estimation processing unit, requiring high processing power for the circuit system, leading to an increase in the size of the device. Furthermore, this also increases the size of the probe. Summary of the Invention

[0007] To solve the above-mentioned problems, the ultrasonic thickness measurement device according to the present invention is characterized by comprising: an ultrasonic probe having eight or fewer ultrasonic elements, each of which includes an ultrasonic transmitting element and an ultrasonic receiving element; and a control unit for calculating the thickness of a target body tissue based on tomographic image data of a subject's body obtained based on received signals received by each of the receiving elements of each of the ultrasonic elements, wherein the control unit calculates the thickness based on the tomographic image data based on the received signals received by each of the ultrasonic elements.

[0008] In addition, the ultrasonic thickness measurement method involved in the present invention is characterized in that it is an ultrasonic thickness measurement method for calculating the thickness of the target body tissue based on tomographic image data of the subject's body obtained by each receiving element receiving the reflected waves of ultrasonic waves transmitted to the body from no more than eight ultrasonic elements having ultrasonic transmitting elements and receiving elements. In the ultrasonic thickness measurement method, the thickness is calculated based on the tomographic image data based on the individual reception signals received by each of the ultrasonic elements. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 This is a diagram showing a simplified overall configuration of an ultrasonic thickness measuring device according to Embodiment 1 of the present invention.

[0010] Figure 2 This is a simplified front view of the ultrasonic probe according to the first embodiment.

[0011] Figure 3 This is a front view of a state where the ultrasound probe according to the first embodiment is worn on the body.

[0012] Figure 4 This figure shows an A-mode image obtained by one ultrasonic element in the first embodiment and a corresponding one-line B-mode image.

[0013] Figure 5 (A) is a diagram showing input image data formed by 8 lines of B-mode images input to the control unit of the first embodiment in order to determine the target thickness. Figure 5 (B) is a diagram of output image data output from the control unit, in which the target thickness is estimated.

[0014] Figure 6 (A) is a diagram of input image data formed by 8 lines of B-mode images in the first embodiment. Figure 6 (B) is a diagram of the corresponding teaching data.

[0015] Figure 7 (A) is a diagram of input image data formed by a B-mode image obtained by an ultrasonic probe having 64 or more ultrasonic elements. Figure 7 (B) is a diagram of the corresponding teaching data.

[0016] Figure 8 The ultrasound probe is worn on the body. Figure 3 A simple main view of the status of the location.

[0017] Figure 9 Is worn on Figure 8 Figure 4. Position of the ultrasound probe to obtain a B-mode image.

[0018] Figure 10 It is the update system diagram of the learning model.

[0019] Description of Reference Numerals

[0020] 1, 2, 3, 4, 5, 6, 7, 8…Ultrasonic element, 9…Wiring, 10…Casing, 11…Transmitting element, 12…Receiving element, 13…Belt, 14…Base member, 15…Drive pulse generating circuit, 16…Transmitting circuit, 17…Signal processing circuit, 18…Receiving circuit, 19…Multiplexer, 20…Microcomputer, 21…Transmitting element, 22…Receiving element, 23…Communication unit, 24…A-mode image, 25…Tablet computer, 26…B-mode image, 27…Learning model, 28…Monitor, 30…Tomographic image, 31…Transmitting element, 32…Receiving element, 3 3…control unit, 34…muscle layer thickness, 35…subcutaneous fat thickness, 36…skin surface, 37…learning model generation center, 38…visceral fat thickness, 39…rectus abdominis muscle, 41…transmitting element, 42…receiving element, 43…portable echo probe, 44…laptop computer, 45…conventional ultrasonic probe, 50…teaching image data, 51…transmitting element, 52…receiving element, 60…ultrasonic probe, 61…transmitting element, 62…receiving element, 71…transmitting element, 72…receiving element, 81…transmitting element, 82…receiving element, 100…ultrasonic thickness measuring device DETAILED DESCRIPTION

[0021] Hereinafter, the present invention will be briefly described.

[0022] To solve the above-mentioned problems, a first embodiment of the present invention provides an ultrasonic thickness measurement device, comprising: an ultrasonic probe having eight or fewer ultrasonic elements, each of which includes an ultrasonic transmitting element and an ultrasonic receiving element; and a control unit for calculating the thickness of a target body tissue based on tomographic image data of a subject's body obtained based on received signals received by each of the receiving elements of each of the ultrasonic elements, wherein the control unit calculates the thickness based on the tomographic image data based on the received signals received by each of the ultrasonic elements.

[0023] Here, the term "thickness" is not limited to the thickness of the muscle layer and fat layer of the body, but also includes the thickness used to determine the thickness of an organ with a layer structure, the thickness used to determine an abnormal part, and the like.

[0024] According to this embodiment, the control unit calculates the thickness based on the tomographic image data based on the received signals received by no more than eight ultrasonic elements. The tomographic image data based on the received signals received by no more than eight ultrasonic elements is tomographic image data in a state where no more than eight lines of tomographic image data are arranged from the skin surface in the depth direction.

[0025] In other words, the amount of information processed by the control unit to determine the thickness is the amount of information obtained by arranging the eight or fewer lines of tomographic image data, thus reducing the amount of information. This eliminates the need for high processing power in the circuitry that constitutes the control unit, enabling device miniaturization. Furthermore, the size of the ultrasonic probe can be reduced.

[0026] The ultrasonic thickness measurement device according to the second aspect of the present invention is characterized in that the ultrasonic probe includes: a base member wearable on the body; and eight or less ultrasonic elements arranged on the base member.

[0027] According to this aspect, since the number of ultrasonic elements included in the ultrasonic probe is 8 or less, the size of the ultrasonic probe can be reduced. In addition, the ultrasonic probe can be worn on the body via the base member, and thus has excellent usability.

[0028] The ultrasonic thickness measuring device according to a third aspect of the present invention is characterized in that, in the first aspect or the second aspect, the tomographic image data inputted and used by the control unit to determine the thickness is data obtained by arranging B-mode images generated based on A-mode images in correspondence with the configuration of eight or fewer ultrasonic elements, wherein each A-mode image is an image generated by processing received signals received by the eight or fewer ultrasonic elements.

[0029] Each B-mode image generated from each A-mode image exhibits varying brightness in the depth direction away from the skin, but maintains constant brightness in the width direction of each row, which intersects the depth direction. In other words, a tomographic image composed of up to eight rows of B-mode images appears to have brightness that varies in a block-like manner with respect to the depth direction, row by row.

[0030] According to this embodiment, the input tomographic image data used by the control unit to determine the thickness is tomographic image data obtained by arranging the eight or fewer lines of B-mode images, and the brightness of each line varies in a block-like manner relative to the depth direction. Consequently, the amount of information processed by the control unit to determine the thickness is reduced, as the amount is the block-like varying tomographic image data. Consequently, the circuitry constituting the control unit does not require high processing power, enabling device miniaturization.

[0031] The ultrasonic thickness measuring device according to a fourth embodiment of the present invention is characterized in that, in any one of the first to third embodiments, the control unit is capable of accessing a learning model having parameters for obtaining attribute information corresponding to the thickness of the target body tissue based on input tomographic image data, the control unit uses the tomographic image data of the subject's body as input image data, performs processing to obtain attribute information corresponding to the thickness using the learning model, and obtains the thickness based on the obtained attribute information.

[0032] According to this embodiment, the control unit uses the learning model to obtain attribute information corresponding to the thickness using tomographic image data of the subject's body as input image data, and then obtains the thickness based on the obtained attribute information. This allows the thickness of the target body tissue to be automatically and accurately obtained.

[0033] The ultrasonic thickness measuring device according to the fifth embodiment of the present invention is characterized in that, in the fourth embodiment, the learning model uses as one set of data tomographic image data based on individual reception signals received by no more than eight ultrasonic elements from the target body tissue and teaching image data corresponding to the tomographic image data and indicating the thickness of the target body tissue, and performs learning on the plurality of sets of data, thereby setting parameters for obtaining attribute information corresponding to the thickness of the target body tissue based on the input tomographic image data.

[0034] According to this method, the parameters of the learning model used to obtain attribute information corresponding to the thickness of the target body tissue from the input tomographic image data are set by learning the tomographic image data obtained by arranging the eight or fewer B-mode images, similar to the input tomographic image data. Therefore, as described above, the parameters of the learning model can be set using tomographic image data with a small amount of information.

[0035] The ultrasonic thickness measuring device according to the sixth aspect of the present invention is characterized in that, in the fourth aspect or the fifth aspect, the control unit is connected to the learning model via a wireless or wired communication unit, and the learning model is capable of updating the parameters using new tomographic image data and teaching image data corresponding to the new tomographic image data.

[0036] According to this aspect, the learning model can update the parameters using new tomographic image data and teaching image data corresponding to the new tomographic image data. This allows accurate acquisition of attribute information corresponding to the thickness of the target body tissue from the input tomographic image data.

[0037] The ultrasonic thickness measurement method involved in the seventh embodiment of the present invention is characterized in that it is an ultrasonic thickness measurement method for calculating the thickness of the target body tissue based on tomographic image data of the subject's body obtained by each receiving element receiving the reflected waves of ultrasonic waves transmitted to the body from no more than 8 ultrasonic elements having ultrasonic transmitting elements and receiving elements. In the ultrasonic thickness measurement method, the thickness is calculated based on the tomographic image data based on the respective received signals received by each of the ultrasonic elements.

[0038] According to this aspect, the same effects as those of the first aspect can be obtained.

[0039] The ultrasonic thickness measuring device according to the eighth embodiment of the present invention is characterized in that, in the seventh embodiment, a learning model having parameters for obtaining attribute information corresponding to the thickness of the target body tissue based on input tomographic image data is accessed, the tomographic image data of the subject's body is used as an input image, and processing is performed using the learning model to obtain the attribute information corresponding to the thickness, and the thickness is obtained based on the obtained attribute information.

[0040] According to this aspect, the same effects as those of the fourth aspect can be obtained.

[0041] Implementation Method 1

[0042] The following is based on Figures 1 to 7 The ultrasonic thickness measuring device according to the first embodiment of the present invention will be described in detail.

[0043] like Figure 1 As shown, the ultrasonic thickness measuring device 100 comprises: an ultrasonic probe 60 having an ultrasonic element for emitting and receiving ultrasonic waves; and a control unit 33 for controlling the functions of the ultrasonic probe 60 and performing signal processing. The control unit 33 is housed in the housing 10 ( Figure 3 ).

[0044] Ultrasonic probe

[0045] like Figure 1 and Figure 2 As shown in FIG. 1 , in this embodiment, the ultrasonic probe 60 includes eight ultrasonic elements 1, 2, 3, 4, 5, 6, 7, and 8. Figure 1 In the figure, the six ultrasonic elements 2, 3, 4, 5, 6, and 7 other than the ultrasonic element 1 and the ultrasonic element 8 are omitted. Figure 1 As shown, the ultrasonic element 1 includes an ultrasonic transmitting element 11 and a receiving element 12, and the ultrasonic element 8 includes an ultrasonic transmitting element 81 and a receiving element 82. Figure 2As shown, the other six ultrasonic elements 2, 3, 4, 5, 6, and 7 also have ultrasonic transmitting elements 21, 31, 41, 51, 61, and 71 and receiving elements 22, 32, 42, 52, 62, and 72, respectively.

[0046] Here, "having an ultrasonic transmitting element and a receiving element" refers to an element described in terms of function. In terms of structure, one ultrasonic element has the function of a "transmitting element" and the function of a "receiving element". Figure 2 , reference numeral 9 denotes wiring.

[0047] like Figure 2 As shown, the ultrasonic probe 60 includes a flat base member 14 ( Figure 2 ) and eight ultrasonic elements 1, 2, 3, 4, 5, 6, 7, and 8 arranged in a row at equal intervals on the base member 14.

[0048] like Figure 3 As shown in the embodiment, the ultrasonic probe 60 of the ultrasonic thickness measuring device 100 and the housing 10 containing the control unit 33 are mounted on the belt 13. That is, the ultrasonic probe 60 and the control unit 33 are partially wound around the abdomen of the body and fixed with the belt 13. Specifically, the belt 13 is configured to be able to be fixed to the body by Figure 3 The device is worn on a target part of the body to measure the thickness of the target muscle layer, etc.

[0049] Control Department

[0050] The control unit 33 obtains tomographic image data ( Figure 5 ) to determine the thickness of the target body tissue.

[0051] That is, the control unit 33 generates data of a tomographic image 30 (described later) based on the respective reception signals sequentially received by the eight ultrasonic elements 1, 2, 3, 4, 5, 6, 7, and 8. Figure 4 、 Figure 5 ) to find the thickness.

[0052] like Figure 1 As shown, the control unit 33 includes a drive pulse generating circuit 15, a transmitting circuit 16, a signal processing circuit 17, a receiving circuit 18, a multiplexer 19, a microcomputer 20, and a communication unit 23. The control unit 33 is configured to be able to access a tablet computer 25 via the communication unit 23. The tablet computer 25 is equipped with a learning model 27 described later.

[0053] When transmitting ultrasonic waves, the drive pulse generating circuit 15 generates a pattern of a specified drive frequency and wave number, and the transmitting circuit 16 outputs a transmission waveform of a specified drive voltage, and ultrasonic waves are transmitted from each transmitting element 11, 21, 31, 41, 51, 61, 71, and 8 of the ultrasonic elements 1, 2, 3, 4, 5, 6, 7, and 8.

[0054] When receiving ultrasound, the reception signals of the receiving elements 12, 22, 32, 42, 52, 62, 72, and 82 of the ultrasonic elements 1, 2, 3, 4, 5, 6, 7, and 8 are amplified by the receiving circuit 18, and then subjected to envelope processing and LOG compression by the signal processing circuit 17 to generate tomographic images 30 of the eight ultrasonic elements 1, 2, 3, 4, 5, 6, 7, and 8, i.e., A-mode images 24. Figure 4 , an A-mode image 24 generated from a reception signal of one ultrasonic element is shown.

[0055] The control of the operations of the circuits 15, 16, 17, and 18 is performed via a microcomputer 20. Furthermore, the microcomputer 20 is configured to sequentially switch the transmission and reception operations of the eight ultrasonic elements 1, 2, 3, 4, 5, 6, 7, and 8 using a multiplexer 19. In other words, the eight ultrasonic elements 1, 2, 3, 4, 5, 6, 7, and 8 are configured to sequentially receive the reception signals.

[0056] In this embodiment, the data of eight A-mode images 24 of the eight ultrasonic elements 1, 2, 3, 4, 5, 6, 7, and 8 are transmitted to a tablet computer 25 equipped with a learning model 27 via a communication unit 23 under the control of a microcomputer 20. The communication unit 23 is composed of a wireless LAN circuit in this embodiment, but may also be composed of a wired circuit.

[0057] The tablet computer 25 includes a GPU and generates data for eight B-mode images 26 based on the data of the eight A-mode images 24 that have been sent. Figure 4 , one B-mode image 26 corresponding to one A-mode image 24 is shown.

[0058] The input tomographic image 30 data used by the control unit 33 to determine the thickness is data obtained by arranging the B-mode images 26 generated based on the A-mode images 24 generated by processing the reception signals sequentially received by the eight ultrasonic elements 1, 2, 3, 4, 5, 6, 7, and 8 in correspondence with the arrangements of the eight ultrasonic elements 1, 2, 3, 4, 5, 6, 7, and 8.

[0059] Figure 5Figure (A) shows eight B-mode images 26 arranged in correspondence with the positions of the eight ultrasonic elements 1, 2, 3, 4, 5, 6, 7, and 8. Specifically, eight lines of tomographic image data are arranged along the depth direction (below the figure) from the skin surface 36. These eight lines of B-mode image data 26 serve as input image data used to determine the thickness.

[0060] As described above, the control unit 33 can access the learning model 27 having parameters for obtaining attribute information corresponding to the thickness of the target body tissue from the input tomographic image 30 data.

[0061] The control unit 33 is configured to convert the 8-line B-mode image 26 ( Figure 5 (A)) is used as input image data, and a learning model 27 mounted on a tablet computer 25 is used to obtain attribute information corresponding to the thickness, and the thickness is obtained from the obtained attribute information. The obtained thickness is displayed as output image data on a monitor 28 ( Figure 5 (B)).

[0062] It should be noted that the learning model 27 may be installed in a computer such as a notebook computer instead of being installed in the tablet computer 25 .

[0063] Here, "attribute information corresponding to thickness" can include, for example, information on the location of the boundary between the fat layer and the muscle layer, obtained by utilizing the fact that ultrasound waves transmitted are significantly reflected at the boundary between the fat layer and the muscle layer, but are substantially not reflected in the muscle layer or the fat layer. If one surface of a muscle layer is in contact with a fat layer and the other surface is in contact with another fat layer, the locations of "one boundary" corresponding to the one surface of the muscle layer and "another boundary" corresponding to the other surface of the muscle layer can be determined using ultrasound. The distance between the "one boundary" and the "another boundary" represents the calculated thickness of the muscle layer.

[0064] Alternatively, when calculating the thickness of subcutaneous fat, if the position of the boundary between the subcutaneous fat and the muscle layer located inside it is calculated using ultrasound as "attribute information", the distance between the calculated boundary and the skin surface becomes the thickness of the subcutaneous fat.

[0065] Figure 5 (B) is output image data displayed on the monitor 28 of the tablet computer 25. In this embodiment, the muscle layer is blanked and image data representing the muscle layer thickness 34 and the subcutaneous fat thickness 35 are displayed.

[0066] Learning model parameters

[0067] In this embodiment, the learning model 27 is constructed as follows.

[0068] like Figure 6 As shown, the data of the tomographic image 30 based on the respective reception signals sequentially received by the eight ultrasonic elements 1, 2, 3, 4, 5, 6, 7, and 8 from the body tissue at a specific location, namely, the eight lines of B-mode images 26 ( Figure 6 (A)), and obtain the teaching image data 50 ( Figure 6 (B)) is used as one set of data, and multiple sets, for example, 100 or more, are prepared. Then, machine learning is performed on the prepared multiple sets of data, and parameters are set for obtaining attribute information corresponding to the thickness of the target body tissue from the input image data.

[0069] The method for generating a learning model takes the U-Net convolution processing method for the purpose of regional segmentation of medical images as an example. Specifically, Figure 6 The 8-line B-mode image 26 of (A) is subjected to the usual convolution processing in the neural network of machine learning and also subjected to pooling processing. The output image data based on this processing is compared with Figure 6 The training image data 50 of (B) is compared and the error is minimized by calculation, that is, the cross entropy error function and the gradient descent method are used to calculate and set the parameters. This setting is performed for more than 100 sets to optimize the parameters.

[0070] In this embodiment, if Figure 1 As shown, the tablet computer 25 is connected to the learning model generation center 37 via a communication line. The parameters are set by the learning model generation center 37, and each time the estimation accuracy improves, the result is sent to the tablet computer 25 to update the learning model 27.

[0071] The learning model 27 can also be constructed in the following manner.

[0072] Figure 7 (A) is input image data formed of a tomographic image 30 of a B-mode image obtained by using an ultrasonic probe having 64 or more ultrasonic elements and receiving 64 or more reception signals from all the ultrasonic elements. Figure 7 (B) is the teaching image data 50 corresponding to the input image data.

[0073] Alternatively, Figure 7 (A) The data of the tomographic image 30 and Figure 7The teaching image data 50 (B) is cut out of eight lines of tomographic image data and teaching data at each sensor arrangement interval. For example, 100 or more sets of these are prepared. The same machine learning is performed as described above to set parameters for obtaining attribute information corresponding to the thickness of the target body tissue from the input image data. B-mode images based on 64 or more ultrasonic elements have the advantage of facilitating muscle layer identification and creation of teaching data.

[0074] In addition, in this embodiment, the control unit 33 is connected to the learning model 27 via the wireless communication unit 23, and the learning model 27 can be connected to the learning model 27 by the equivalent Figure 6 The data of the new tomographic image 30 of (A) and the data of the new tomographic image 30 corresponding to the data of the new tomographic image 30 are equivalent to Figure 6 The parameters are updated using the teaching image data 50 of (B).

[0075] Specifically, ultrasound is first used to obtain new tomographic image data 30 of tissue at a specific site in the body, and the thickness of the target tissue is determined. This new tomographic image data 30 is then transmitted from the tablet computer 25 to the learning model generation center 37. The learning model 27 parameters are updated based on the set of teaching image data 50 corresponding to this image. If the estimated accuracy improves, the result is transmitted to the tablet computer 25, and the parameters of the learning model 27 are updated.

[0076] Description of the Effect of Implementation Method 1

[0077] Next, a step of obtaining the thickness of the target body tissue using the ultrasonic thickness measurement device 100 according to the first embodiment is performed.

[0078] First, the ultrasonic probe 60 and the control unit 33 of the ultrasonic thickness measuring device 100 of this embodiment are as follows: Figure 3 As shown, the device is wrapped around the abdomen of the subject and fixed with a belt 13. Then, eight ultrasonic elements 1, 2, 3, 4, 5, 6, 7, and 8 sequentially transmit and receive ultrasonic waves, and eight A-mode images 24 are generated based on the eight received signals. In addition, a tablet computer 25 generates eight B-mode images 26 based on the eight A-mode images 24, that is, eight rows of B-mode images 26 are generated. Figure 5 (A)) data.

[0079] Next, the 8-line B-mode image 26 ( Figure 5 (A)) is used as input image data and the learning model 27 is used to obtain the attribute information corresponding to the thickness, and the thickness ( Figure 5 (B)), and display it on monitor 28.

[0080] It should be noted that the information related to the thickness displayed on the monitor 28 is not limited to Figure 5 The form of (B) may be, for example, a numerical value or a comparable graph.

[0081] Description of the Effects of Embodiment 1

[0082] (1) According to the present embodiment, the control unit 33 calculates the thickness of the target body tissue based on the tomographic image data based on the reception signals sequentially received by the eight ultrasonic elements 1, 2, 3, 4, 5, 6, 7, and 8. The tomographic image data based on the reception signals sequentially received by the eight ultrasonic elements 1, 2, 3, 4, 5, 6, 7, and 8 are tomographic image data obtained by arranging the data of the eight tomographic images 30 along the depth direction from the skin surface 36 ( Figure 5 (A)).

[0083] That is, the amount of information processed by the control unit 33 to obtain the thickness is the amount of information obtained by arranging the data of the 8 lines of each tomographic image 30 ( Figure 5 (A)), so the amount of information is reduced. As a result, the circuit portion constituting the control unit 33 is not required to have high processing power, and the device 100 can be miniaturized. In addition, the size of the ultrasonic probe 60 can also be reduced.

[0084] (2) In this embodiment, the ultrasonic probe 60 includes eight ultrasonic elements, which can reduce the size of the ultrasonic probe 60 compared to conventional ultrasonic probes. Furthermore, the ultrasonic probe 60 can be worn on the body using the base member 14, thus providing excellent usability.

[0085] (3) In addition, Figure 4 As shown, the B-mode image 26 generated from the A-mode image 24 is an image with varying brightness in a line in the depth direction away from the skin surface 36, but the brightness is constant in the direction intersecting the depth direction, that is, in the width direction of the line. In other words, the brightness in the line varies in a block-like manner with respect to the depth direction. Figure 5 As shown in FIG. 1A , a tomographic image 30 in which eight lines of B-mode images are arranged becomes an image in which the brightness appears to change in a block-like manner for each line in the depth direction.

[0086] According to the present embodiment, the input tomographic image 30 data used by the control unit 33 to determine the thickness is tomographic image data in which eight lines of B-mode images 26 are arranged ( Figure 5(A)), and the tomographic image data is tomographic image data whose brightness varies in a block-like manner for each line relative to the depth direction. Therefore, the amount of information processed by the control unit 33 to determine the thickness is the data of the tomographic image 30 that varies in a block-like manner, and this amount of information is reduced. Consequently, the circuitry constituting the control unit 33 does not require high processing power, allowing for a more compact device 100.

[0087] (4) In this embodiment, the control unit 33 uses the tomographic image 30 of the subject's body as input image data, performs processing to determine attribute information corresponding to the thickness using the learning model 27, and determines the thickness based on the determined attribute information. This allows the thickness of the target body tissue to be determined automatically and accurately.

[0088] (5) In addition, in this embodiment, the parameters of the learning model 27 used to obtain the attribute information corresponding to the thickness of the target body tissue from the input tomographic image 30 data are the same as the input tomographic image 30 data, which is the tomographic image data of the state in which 8 lines of B-mode images are arranged ( Figure 6 Therefore, as described above, the parameters of the learning model 27 can be set using the data of the tomographic image 30 having a small amount of information.

[0089] (6) In addition, in this embodiment, the learning model 27 can be used to learn the new tomographic image 30 ( Figure 6 (A)) and the teaching image data ( Figure 6 Thus, attribute information corresponding to the thickness of the target body tissue can be obtained with high accuracy from the input tomographic image 30 data.

[0090] Implementation Method 2

[0091] Then, based on Figure 8 and Figure 9 An ultrasonic thickness measuring device 100 according to a second embodiment of the present invention will be described.

[0092] The ultrasonic thickness measuring device 100 of this embodiment is a device for determining the thickness of visceral fat. Figure 8 As shown in FIG, the ultrasound probe 60 and the control unit 33 are worn on the chest area of the body for use. Figure 8 The belt 13 is omitted in the figure. Figure 9 This is a tomographic image 30 of the thoracic cavity portion of the body. Figure 9The tomographic image 30 is a B-mode image obtained using an ultrasonic probe having 64 or more ultrasonic elements and 64 or more received signals received by all the ultrasonic elements. Since the rectus abdominis muscle 39 is absent in the thoracic region of the body, images of subcutaneous fat thickness 35 and images of visceral fat thickness 38 can be obtained.

[0093] Therefore, by measuring the thoracic region using the ultrasonic thickness measurement device 100 of this embodiment, a learning model 27 having parameters for determining visceral fat thickness can be created in the same manner as in the first embodiment, and the visceral fat thickness of the subject can be determined using this learning model 27 in the same manner as described above.

[0094] Implementation 3

[0095] Then, based on Figure 10 Embodiment 3 of the present invention will be described.

[0096] Figure 10 The diagram shows a state in which four ultrasonic thickness measuring devices are independently used by user A, user B, user C, and user D, and are connected wirelessly or wired around a learning model generation center 37 .

[0097] User A and User D are both individuals, using the ultrasonic thickness measurement device 100 of this embodiment. User B is a gym worker, using a portable echo probe 43 and a laptop computer 44 with a learning model to visually identify abdominal muscle or fat thickness. User C is a healthcare institution, using an ultrasonic thickness measurement device 300 comprised of an ultrasonic diagnostic device connected to a conventional ultrasonic probe 45.

[0098] The data of the tomographic images 30 obtained by the users A, B, C, and D are sent to the learning model generation center 37. The learning model generation center 37 determines the body tissue to be the target of the collected data of each tomographic image 30, that is, the muscle layer or the fat layer, and creates the teaching image data 50 ( Figure 6 (B) Figure 7 (B)) generates the learning model 27 and parameters for the determined body tissue. These are performed on the data of each transmitted tomographic image 30 to improve the accuracy of the learning model 27 and parameters.

[0099] It can be said that the more data on the collected tomographic images 30 increases, the higher the accuracy of the learning model 27. Whenever the parameters of the learning model 27 are updated and the accuracy is improved, the latest parameters are transmitted from the learning model generation center 37 to the tablet computer 25 or laptop computer on which the learning model 27 is installed, thereby updating the learning model 27.

[0100] Other implementations

[0101] The ultrasonic thickness measurement device 100 according to the embodiment of the present invention basically has the above-described configuration, but it is of course possible to modify or omit some of the configurations without departing from the spirit of the present invention.

[0102] (1) In the above embodiment, the ultrasonic probe 60 is described as having eight ultrasonic elements 1, 2, 3, 4, 5, 6, 7, and 8. However, the number is not limited to eight. Alternatively, the number may be four, which is less than eight, and four lines of tomographic image data may be arranged. Furthermore, the number of ultrasonic elements may be 16 or 32, which is greater than eight, as long as reception is achieved by eight or fewer of the ultrasonic elements and the number of received signals is eight or fewer.

[0103] (2) In the above embodiment, the ultrasonic probe 60 and the control unit 33 are partially wrapped around the abdomen of the body and fixed with the belt 13. However, this is not the only option. The ultrasonic probe 60 may be a commonly used ultrasonic echo probe.

[0104] (3) In the above embodiment, the control unit 33 and the learning model 27 are separated from each other. However, the control unit 33 may be provided with the learning model 27 and the communication unit 23.

Claims

1. An ultrasonic thickness measuring device, characterized in that: have: An ultrasonic probe having eight or less ultrasonic elements, each of which has an ultrasonic transmitting element and an ultrasonic receiving element; and The control unit obtains the thickness of a target body tissue based on tomographic image data of the subject's body obtained based on the reception signals received by the reception elements of the ultrasonic elements. The control unit arranges data of each B-mode image generated from each A-mode image generated by processing each reception signal sequentially received by each ultrasonic element in correspondence with the arrangement of each ultrasonic element, and calculates the thickness based on the data of the B-mode image arranged along the arrangement.

2. The ultrasonic thickness measuring device according to claim 1, characterized in that: The ultrasonic probe has: a base member capable of being worn on the body; and No more than eight ultrasonic elements are arranged on the base member.

3. The ultrasonic thickness measuring device according to claim 1 or 2, characterized in that: The input tomographic image data used by the control unit to determine the thickness is data obtained by arranging B-mode images generated from A-mode images in correspondence with the arrangement of the eight or less ultrasonic elements. Each of the A-mode images is an image generated by processing reception signals received by eight or less of the ultrasonic elements.

4. The ultrasonic thickness measuring device according to claim 1, wherein: The control unit is capable of accessing a learning model having parameters for obtaining attribute information corresponding to the thickness of the target body tissue based on the input tomographic image data. The control unit uses the learning model to perform processing for obtaining attribute information corresponding to the thickness using tomographic image data of the subject's body as input image data, and obtains the thickness based on the obtained attribute information.

5. The ultrasonic thickness measuring device according to claim 4, characterized in that: The learning model uses as one set of data the tomographic image data of each reception signal received by less than eight ultrasonic elements from the target body tissue and the teaching image data corresponding to the tomographic image data and calculating the thickness state, and performs learning on multiple sets of data, setting parameters for obtaining attribute information corresponding to the thickness of the target body tissue based on the input tomographic image data.

6. The ultrasonic thickness measuring device according to claim 4 or 5, characterized in that: The control unit is connected to the learning model via a wireless or wired communication unit. The learning model can update the parameters using new tomographic image data and teaching image data corresponding to the new tomographic image data.

7. An ultrasonic thickness measurement method, characterized in that: This ultrasonic thickness measurement method determines the thickness of target body tissue based on tomographic image data of a subject's body obtained by receiving, at each receiving element, reflected waves of ultrasonic waves transmitted to the body from eight or fewer ultrasonic elements having ultrasonic transmitting and receiving elements. In the ultrasonic thickness measurement method, data of each B-mode image generated based on each A-mode image generated by processing each reception signal sequentially received by each ultrasonic element is arranged corresponding to the configuration of each ultrasonic element, and the thickness is calculated based on the data of the B-mode images arranged along the configuration.

8. The ultrasonic thickness measurement method according to claim 7, characterized in that: accessing a learning model having parameters for obtaining attribute information corresponding to the thickness of the target body tissue based on input tomographic image data, The tomographic image data of the subject's body is used as an input image, and a process of obtaining attribute information corresponding to the thickness is performed using the learning model, and the thickness is obtained based on the obtained attribute information.

Images