Ultrasound image analysis device and ultrasound image analysis program

Abstract

To provide an ultrasound image analysis device that can easily analyze muscle movement. [Solution] An ultrasound image analysis device 12 having a transceiver 20 connected to an ultrasound probe 11 that converts reflected waves generated by irradiating ultrasound onto a subject into signals and outputs them, and a processor 17 that processes signals obtained from the ultrasound probe 11 to generate two-dimensional ultrasound images, wherein the processor 17 is configured to perform a first process of generating multiple ultrasound images of the subject's muscles in motion, a second process of setting a region of interest in a single ultrasound image selected from the multiple ultrasound images, a third process of extracting specified points within the region of interest, and a fourth process of determining the amount of muscle movement by automatically tracking each specified point on ultrasound images other than the selected ultrasound image.

Description

[Technical Field]

[0001] The present disclosure relates to an ultrasound image analyzer and an ultrasound image analysis program that analyze ultrasound images of muscles obtained by irradiating a subject with ultrasound. [Background technology]

[0002] An example of an ultrasound diagnostic device as an ultrasound image analyzer that analyzes ultrasound images of muscles obtained by irradiating a subject with ultrasound is described in Patent Document 1. The ultrasound diagnostic device described in Patent Document 1 is an ultrasound diagnostic device configured to be connectable to an ultrasound probe, and includes a transmitter that controls the supply of a transmission electrical signal for transmitting ultrasound from the ultrasound probe to the subject, a receiver that acquires a received signal based on reflected ultrasound received by the ultrasound probe, an ultrasound image generator that generates tomographic image data of the subject based on the received signal, a motion receiver that acquires motion information of the subject, a dynamic schematic data generator that generates schematic image data that schematically represents the subject's motion based on the motion information, and a display processor that generates composite image data by combining the tomographic image data and the schematic image data based on time information.

[0003] Patent Document 1 also states that the receiving unit acquires a received signal including a cross section of the subject's muscles or bones, and the ultrasound image generating unit generates tomographic image data including a cross section of the subject's muscles or bones based on the received signal. Patent Document 1 also states that the subject's movement is a movement that involves movement of the subject's muscles or bones. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent No. 6206155 Summary of the Invention [Problem to be solved by the invention]

[0005] The inventors of the present application have recognized that the ultrasonic diagnostic device described in Patent Document 1 has difficulty in analyzing muscle movements.

[0006] An object of this embodiment is to provide an ultrasound image analysis device and an ultrasound image analysis program that make it easy to analyze muscle movement. [Means for solving the problem]

[0007] This embodiment is an ultrasound image analysis device having a transmitting / receiving device connected to an ultrasound probe that irradiates ultrasound onto a subject, converts the reflected waves generated into signals, and outputs the signals, and a processor that processes the signals obtained from the ultrasound probe to generate two-dimensional ultrasound images.The processor is configured to perform the following steps: a first process of generating multiple ultrasound images of the subject's muscles moving; a second process of setting a region of interest in a single ultrasound image selected from the multiple ultrasound images; a third process of extracting specified points within the region of interest; and a fourth process of determining the amount of movement of the muscle by automatically tracking each of the specified points on the ultrasound images other than the selected ultrasound image. [Effects of the Invention]

[0008] According to the ultrasound image analyzing device of this embodiment, it is possible to obtain the effect of facilitating analysis of muscle movement. [Brief explanation of the drawings]

[0009] [Figure 1] 1 is a schematic diagram showing the configuration of an ultrasound image analysis system including an ultrasound image analysis device. [Figure 2] 1 is a flowchart showing an example of use of the ultrasound image analysis system. [Figure 3] FIG. 1 is a schematic diagram showing an example of a screen of a display device of an ultrasound image analysis device; [Figure 4] FIG. 4(A) is a partial schematic diagram of the screen of the display device, and FIG. 4(B) is a graph showing the amount of movement of the specified point. [Figure 5]10 is a flowchart illustrating another example of use of the ultrasound image analysis system. DETAILED DESCRIPTION OF THE INVENTION

[0010] (Overview of ultrasound image analysis system) Several specific examples of ultrasound image analysis devices and ultrasound image analysis programs are described with reference to the drawings. FIG. 1 shows an ultrasound image analysis system including an ultrasound image analysis device. The ultrasound image analysis system 10 is a device that irradiates ultrasound onto a subject, processes the reflected ultrasound to generate an image, and processes and analyzes the generated image. The ultrasound image analysis system 10 includes an ultrasound probe 11, an ultrasound image analysis device 12, and an external device 13. The ultrasound image analysis system 10 is operated and used by a user. The user includes medical professionals and researchers. Medical professionals include doctors, physical therapists, nurses, etc.

[0011] (Explanation of the ultrasound probe) The ultrasonic probe 11 is composed of elements such as a main body, an acoustic lens, an acoustic matching layer, a vibrator (piezoelectric element), and a damper (packing material). The ultrasonic probe 11 is connected to the ultrasonic image analyzer 12 via a communication system 14 so as to enable mutual communication between the ultrasonic probe 11 and the ultrasonic image analyzer 12. The communication system 14 is composed of one or more systems selected from a wireless communication system and a wired communication system.

[0012] The ultrasonic probe 11 is used while being in contact with the surface of a subject, for example, the skin 15C of a human arm 15. The ultrasonic probe 11 is configured to irradiate ultrasonic waves toward the muscles 16 inside the arm 15 upon receiving a control signal from the ultrasonic image analyzer 12. The ultrasonic probe 11 is also configured to receive reflected waves generated by irradiating the muscles 16 with ultrasonic waves, convert them into electrical signals, and transmit the electrical signals to the ultrasonic image analyzer 12. The specific structure and function of the ultrasonic probe 11 are publicly known, as described in Japanese Patent Nos. 4945326, 5192921, 540141, etc., and therefore a description of the specific structure and function will be omitted.

[0013] (Explanation of ultrasound image analysis device) The ultrasound image analyzer 12 is a device that generates an ultrasound image by processing the reflected waves obtained by irradiating an object with ultrasound, and analyzes the generated ultrasound image. The ultrasound image analyzer 12 is a computer that includes a main body (casing), a processor 17, a main memory 18, an auxiliary memory 19, a transmitting / receiving device 20, an operating device 21, a display device 22, a communication device 23, etc. The computer may be configured as either a portable computer or a fixed computer.

[0014] Portable computers include smartphones, tablet terminals, and notebook computers. Fixed computers include tower computers and desktop computers. The processor 17 is provided inside the main body and is composed of a central processing unit (CPU (Central Processing Unit)) that integrates an arithmetic unit (arithmetic circuit) and a control unit (control circuit). The processor 17 is communicably connected to a main memory 18, an auxiliary memory 19, a transmission / reception device 20, an operation device 21, a display device 22, a communication device 23, etc. via a bus 24.

[0015] Processor 17 comprehensively controls other devices and circuits provided inside the main body as well as devices and circuits provided outside the main body. In addition to a central processing unit, processor 17 also includes arithmetic processing circuits such as a digital signal processor, an application-specific integrated circuit (ASIC), and a GPU. GPU stands for Graphics Processing Unit, and is a graphics controller that performs arithmetic processing necessary for image processing of 3D graphics, etc. Furthermore, the GPU is configured to perform machine learning, specifically deep learning, in the process of processing and analyzing ultrasound images.

[0016] When the processor 17 runs a non-transitory program stored in the auxiliary memory 19, the program executes various processes. The various processes executed by the program include the processing itself performed within the processor 17, judgment, analysis, inference, control and instruction of other elements, acquisition of information and signals from other elements, storage of information in the auxiliary memory 19, etc. The various processing targets handled by the program include signals, information, data, ultrasound images, graphs, maps, charts, etc.

[0017] The main memory 18 is a volatile storage device that functions as a work area and a buffer area when the processor 17 executes processing. The auxiliary memory 19 is a non-volatile storage device, i.e., a non-transitory storage medium. Non-transitory programs are stored in the auxiliary memory 19. The auxiliary memory 19 also stores various types of information used by the processor 17 to execute various processes, various types of information resulting from the execution of various processes by the processor 17, etc. The various types of information stored in the auxiliary memory 19 include information itself, data, graphs, maps, charts, etc.

[0018] The auxiliary memory 19 has a larger capacity than the main memory 18, and operates in response to input and output instructions from the processor 17. The auxiliary memory 19, which is a non-transitory storage medium, is composed of, for example, a magnetic disk, an optical disk, a flash memory, etc. An example of a magnetic disk is a hard disk drive. An example of an optical disk is a compact disk, a digital video disk, a Blu-ray disk, etc.

[0019] Flash memory is a type of semiconductor memory, and examples of flash memory include SD memory cards, USB flash drives, solid state drives, etc. One or more elements included in auxiliary memory 19 can be defined as storage media 19A that can be attached to and detached from the main body.

[0020] The transmitting / receiving device 20 is configured to be connected to the ultrasound probe 11 via a communication system 14. The transmitting / receiving device 20 is configured with a communication cable, a communication circuit, a communication antenna, etc. The transmitting / receiving device 20 may be configured as either a wireless communication system or a wired communication system.

[0021] The operation device 21 is operated by a user. The operation device 21 is composed of elements such as operation buttons, operation levers, operation knobs, a keyboard, a mouse, a liquid crystal display, and an organic electroluminescence display. The operation device 21 may be either a structure that is directly attached to the main body or a structure that is connected to the main body via a communication interface. The communication interface includes a wireless communication system or a wired communication system. The structure and function of the operation device 21 are selected depending on whether the computer that constitutes the ultrasound image analysis device 12 is a portable computer or a fixed computer.

[0022] The operation device 21 is operated when inputting various types of information to the ultrasound image analyzer 12, when causing the processor 17 to execute various processes, when using the ultrasound probe 11, when displaying information on the display device 22, when sending information to the external device 13, etc. The user can adjust the brightness of the ultrasound image, the brightness of the entire screen of the display device 22, the depth at which the ultrasound image is generated, etc. The depth at which the ultrasound image is generated is, for example, the depth from the surface of the arm 15.

[0023] The user can also input auxiliary information by operating the operation device 21. The auxiliary information includes the type of subject, the subject's identification number, the part of the subject from which the ultrasound image is acquired, the cross-sectional direction of the muscle from which the ultrasound image is acquired, the identification of the superficial and deep layers of the muscle, whether the muscle is subjected to an external force, and if so, the direction and value of the external force. The type of subject is, for example, a human, an animal, etc., and animals include dogs, cats, pigs, horses, etc. The subject's identification number is a number that distinguishes multiple subjects from each other and may include a symbol.

[0024] The parts of the subject from which ultrasound images are acquired include the right arm, left arm, right leg, left leg, torso, tail, etc. These parts can also be further subdivided and input. The cross-sectional direction of the muscle from which ultrasound images are acquired includes, for example, the cross-sectional direction along the skin, the direction intersecting the skin, the depth direction of the muscle, the direction along the bone inside the muscle, the direction intersecting the bone inside the muscle, etc. The auxiliary information input by the user operating the operation device 21 is stored in the auxiliary memory 19 in association with the subject's identification number.

[0025] The display device 22 is attached directly to the main body or connected to the main body via a cable. The display device 22 is a display that is visually viewed by the user, and the display may include a liquid crystal display, an organic electroluminescence display, or the like. The connection structure of these displays to the main body is appropriately selected depending on whether the computer constituting the ultrasound image analysis device 12 is a portable computer or a fixed computer. The display may also be defined as a monitor. Various information is displayed on the screen of the display device 22. The display device 22 may also be configured to display operation buttons, operation tabs, etc. on the screen. In other words, the display device 22 can also function as the operation device 21.

[0026] The communication device 23 includes devices, equipment, and standards that connect the ultrasound image analysis device 12 to the external device 13 via the network 25. The communication device 23 includes a communication circuit, a cable, an antenna, a communication port, a communication connector, a communication hub, etc. The network 25 is configured by at least one of a wireless communication system and a wired communication system.

[0027] The following is a specific description of the configuration of the processor 17. The processor 17 is configured to function as a signal processing unit 26, an ultrasound image processing unit 27, a specified point extraction unit 28, a movement amount determination unit 29, an information processing unit 30, and an artificial intelligence unit 33 by running a non-transitory program stored in the auxiliary memory 19.

[0028] The signal processing unit 26 is configured to process control signals sent from the ultrasound image analyzer 12 to the ultrasound probe 11 and to process electrical signals received from the ultrasound probe 11. The ultrasound image processing unit 27 is configured to generate ultrasound images by processing the electrical signals received from the ultrasound probe 11. The ultrasound image processing unit 27 is configured to generate multiple two-dimensional ultrasound images continuously in time series. The two-dimensional ultrasound images are cross-sectional images including the muscles 16 and membranes of the arm 15. The ultrasound image processing unit 27 is also configured to process, analyze, judge, modify, etc. the ultrasound images.

[0029] The designated point extraction unit 28 is configured to automatically extract multiple designated points within the regions of interest A1 and B1 for a single (one) ultrasound image 32 shown in Fig. 3, for example. The ultrasound image 32 shown in Fig. 3 is selected by a user operating the operation device 21. Examples of the designated points A2 and B2 include boundaries of contrast (light and dark) that exist within the regions of interest A1 and B1, edges of muscle fibers (bending points), etc. The technical meaning of the regions of interest A1 and B1 will be described later.

[0030] The movement amount determination unit 29 determines the amount of movement, or in other words, the amount of movement, of the muscle 16 by continuously and automatically tracking the positions of the specified points A2 and B2 for multiple ultrasound images 32 generated consecutively in time series. The process of continuously and automatically tracking the positions of specified points within an ultrasound image for multiple ultrasound images can be realized, for example, by the Lucas-Kanade method. The Lucas-Kanade method is well known, as shown in the following information examples 1 and 2, and therefore a detailed description thereof will be omitted.

[0031] Example 1: "About the Lucas Kanade method https: / / www.slideshare.net / slideshow / lucas-kanade / 75287273 [Accessed September 18, 2024]" Information example 2: "Lucas Kanade Law - Overview - http: / / www.thothchildren.com / chapter / 5bcc763e51d9305189030e26 [Accessed September 18, 2024]" Furthermore, processing for automatically and continuously tracking the position of a specified point on an ultrasound image across multiple ultrasound images is also disclosed in Japanese Patent Nos. 3688562 and 4598260, among others.

[0032] The information processing unit 30 is configured to process information input by operating the operation device 21, process information sent from the ultrasound image analysis device 12 to the external device 13, process information received from the external device 13, etc. The information processing unit 30 also stores the information input by operating the operation device 21 and the information received from the external device 13 in the auxiliary memory 19.

[0033] The artificial intelligence unit 33 is configured to create history data and update data for the various information stored in the auxiliary memory 19 based on the various information acquired by the processor 17, the various information stored in the auxiliary memory 19, and learning data, and to store the created data in the auxiliary memory 19. The artificial intelligence unit 33 is configured to process the ultrasound image 32 in cooperation with the signal processing unit 26, the ultrasound image processing unit 27, the specified point extraction unit 28, the movement amount determination unit 29, and the information processing unit 30.

[0034] The artificial intelligence unit 33 is an artificial intelligence (AI) that includes transformers including GPT (Generative Pre-trained Transformer), BERT (Bidirectional Encoder Representations from Transformers), etc., and language models such as recurrent neural networks, and is capable of performing processing as generative artificial intelligence.

[0035] The language model is an example of a learning model based on a machine learning algorithm. Specific examples of machine learning algorithms include nearest neighbor methods, naive Bayes methods, decision trees, support vector machines, and deep learning using neural networks. The artificial intelligence unit 33 can apply the above algorithms as appropriate.

[0036] The machine learning performed by the artificial intelligence unit 33 includes three types: supervised learning, unsupervised learning, and reinforcement learning. In supervised learning, machine learning is performed using training data including supervised data. The supervised data is a method of training a machine using input data for training and output data including correct answer data, forming a predictive model based on a dataset (sample data). In unsupervised learning, a machine is trained using data that does not have correct answer information attached, forming a predictive model based on the regularity and similarity of the dataset. Reinforcement learning is a method of training a machine by trial and error to maximize a set target "score."

[0037] The artificial intelligence unit 33 performs machine learning by analyzing and processing various information and data stored in the auxiliary memory 19, information input via the operation device 21, and information and data processed or determined by the signal processing unit 26, ultrasound image processing unit 27, designated point extraction unit 28, and movement amount determination unit 29. In machine learning, for example, deep learning using a neural network is performed to generate a trained model. The generated trained model can output a correct answer even for unknown data. The generated trained model is stored in the auxiliary memory 19. The trained model generated by the artificial intelligence unit 33 includes the subject's body part, the cross-sectional direction of the muscle, the direction and value of the external force applied to the muscle, the identification of the superficial layer 16A and deep layer 16B of the muscle 16, the amount of movement of the superficial layer 16A of the muscle 16 in response to the external force, the amount of movement of the deep layer 16B of the muscle 16 in response to the external force, the positions of the designated points A2 and B2, the positions of the representative designated points A3 and B3, etc. The trained model generated by the artificial intelligence unit 33 is stored in the auxiliary memory 19 in association with the type and identification number of the subject.

[0038] (External device description) The external device 13 includes a printer, various computers, etc. The printer can print images, graphs, data, etc. showing the movement amount of the muscle 16 onto a paper medium. The various computers include computers such as a workstation, a supercomputer, a mainframe, etc.

[0039] (Example of use of ultrasound image analysis system) An example of how to use the ultrasound image analysis system 10 is shown in the flowchart of Figure 2. In S10, a process is performed to acquire an ultrasound image (image frame) 32 using the ultrasound probe 11. Specifically, the user touches the tip of the ultrasound probe 11 to the surface of the subject, for example, the skin 15C of a human arm 15. Next, pulsed ultrasound is emitted, i.e., irradiated, from the transducer of the ultrasound probe 11 toward the muscle 16 inside the arm 15.

[0040] Furthermore, the transducer of the ultrasonic probe 11 receives reflected waves generated by irradiating the muscle with ultrasonic waves, and the received signals are sent from the ultrasonic probe 11 to the ultrasonic image analyzer 12. In step S10, the processor 17 of the ultrasonic image analyzer 12 runs a program stored in the auxiliary memory 19 and processes the signals received from the ultrasonic probe 11 to generate two-dimensional ultrasonic images (cross-sectional images) 32. The processor 17 can continuously generate, for example, several tens of ultrasonic images 32 per second, and can display them on the display device 22 as moving or still images.

[0041] FIG. 3 is a cross-sectional view of muscle 16 taken along line III-III in FIG. 1. The cross-sectional view of FIG. 3 is a cross-sectional view along the length of bones 15A and 15B of arm 15 shown in FIG. 1. Bone 15A is the radius, and bone 15B is the ulna. FIG. 3 is an example of an ultrasound image 32 displayed on screen 31 of display device 22. Ultrasound image 32 is displayed as a quadrangle, e.g., a rectangle or a square, within screen 31. Ultrasound image 32 shows a superficial layer 16A and a deep layer 16B of muscle 16. Superficial layer 16A is located between skin 15C and deep layer 16B of arm 15. Fascia 16C is also displayed between superficial layer 16A and deep layer 16B. A scale 31A is displayed on the outside of ultrasound image 32 on screen 31. Scale 31A is displayed along one side of ultrasound image 32. The scale 31A is marked at intervals of several millimeters (mm) corresponding to the actual size of the muscle 16, for example.

[0042] The ultrasound image 32 is displayed with gradations of light and dark according to the reflection intensity of each point in the muscle 16. In addition, during the process of generating the ultrasound image 32, the arm 15 can be moved or an external force can be applied to the arm 15. Furthermore, during the process of generating the ultrasound image 32, the ultrasound probe 11 is kept in contact with the skin 15C at the same position and does not move. In this way, multiple consecutive ultrasound images 32 are acquired in chronological order.

[0043] In step S20, the user operates the operation device 21 to select one of the ultrasound images 32 acquired in step S10, the ultrasound image 32 being taken before moving the arm 15 or before applying an external force to the arm 15. The user also operates the operation device 21 to set regions of interest (ROI) A1, A2 at predetermined locations on the selected ultrasound image 32. The peripheral shape of the region of interest A1 shown in FIG. 3 is, for example, a substantially rectangular shape. In FIG. 3, the region of interest A1 is set in the superficial layer 16A, and the region of interest B1 is set in the deep layer 16B.

[0044] In step S30, processor 17 automatically extracts a large number of designated points A2 within region of interest A1, and also automatically extracts a large number of designated points B2 within region of interest B1. Examples of designated points include boundaries of contrast (light and dark) within regions of interest A1 and B1, edges of muscle fibers (bending points), etc. The extracted large number of designated points A2 and B2 are displayed as colored marks within ultrasound image 32. The color of designated point A2 is different from the color of designated point B2. The user can visually confirm the positions and movements of designated points A2 and B2 displayed on screen 31.

[0045] The processor 17 processes the plurality of consecutive ultrasound images 32 in step S40 to When the arm 15 is moved or when an external force is applied to the arm 15 It determines the amount of movement (amount of movement) of the muscle 16. Details of the process performed by the processor 17 in step S40 are as follows.

[0046] In step S41, the processor 17 performs automatic tracking processing on a plurality of consecutive ultrasound images 32 to determine the amount of movement of each of the designated points A2 and B2. In step S42, the processor 17 compares two ultrasound images 32 positioned one after the other in time series, and deletes designated points that are displayed in later ultrasound images 32 in time series and have a relatively large amount of movement compared to designated points displayed in earlier ultrasound images 32. For example, the processor 17 deletes the top 10% of designated points with relatively large amounts of movement, that is, excludes them from tracking targets.

[0047] In step S43, processor 17 averages the amounts of movement of the top 10% of the remaining designated points that have the largest relative amounts of movement, to obtain an average value. Processor 17 can treat the obtained average value as the amount of movement of muscle 16 as a whole. Furthermore, processor 17 can determine representative designated points A3 and B3 from the many designated points A2 and B2, as shown in FIG. 4(A), and display them on display device 22. Representative designated point A3 is designated point A2 located at the center of region of interest A1. Representative designated point B3 is designated point B2 located at the center of region of interest B1.

[0048] Furthermore, processor 17 can calculate the amount of movement of the representative designated point relative to the reference position of the representative designated point before an external force is applied to arm 15 or when arm 15 is stopped, and display this on display device 22. Figure 4(B) shows the amount of movement of the representative designated point in a graph 40. In graph 40, the horizontal axis shows time, and the vertical axis shows the amount of movement.

[0049] Furthermore, processor 17 can repeat the contraction of muscle 16 multiple times, and automatically return all designated points A2 and B2 to their original positions at the point when muscle 16 returns to its original shape in step S45. When all designated points A2 and B2 remain stationary for a predetermined time, processor 17 determines that muscle 16 has returned to its original shape.

[0050] Then, in step S50 following step S40, processor 17 stores the processing results and analysis results of steps S20, S30, and S40 in auxiliary memory 19, displays them on display device 22, and outputs them to external device 13. Processor 17 also stores a large amount of data including the processing results and analysis results of step S40 in auxiliary memory 19, and stores in auxiliary memory 19 a trained model generated by machine learning.

[0051] (Example effect) According to the ultrasound image analysis system 10, the user can visually check the amount of movement of the muscle 16 by looking at the screen 31 of the display device 22. Furthermore, when the scale 31A is displayed on the screen 31, the user can more reliably visually check the amount of movement of the muscle 16. Furthermore, both the ultrasound image 32 and the graph 40 may be displayed side by side on the screen 31.

[0052] Using the ultrasound image analysis system 10, it is possible to determine in which direction and to what extent (how much) the muscle 16 has moved within the two-dimensional ultrasound image 32. This has the effect of making it easier to analyze the movement of the muscle 16. It can also contribute to estimating the hardness and softness of the muscle 16. In other words, it can contribute to estimating the stiffness (rigidity) of the muscle 16, i.e., how much movement (stretching, compression) occurs when a certain amount of load is applied to the muscle 16.

[0053] (Other use cases) Another use example that partially changes the use example of FIG. 2 is shown in FIG. 5. As shown in FIG. 5, the user can input part of the auxiliary information by operating the operation device 21 in step S60 before executing steps S10, S20, S30, and S40. Also, the user can input part of the auxiliary information before setting the region of interest in step S20. For example, for the acquired ultrasound image 32, the position of the superficial layer 16A and the position of the deep layer 16B, Whether or not the muscle 16 is subjected to an external force, and the direction of the external force if the muscle 16 is subjected to an external forceand the value of the external force. The auxiliary information input in step S20 and step S60 is stored in the auxiliary memory 19. In step S42 following step S41, the processor 17 can delete a designated point whose movement amount, relative to the designated point displayed in the previous ultrasound image 32 in the time series, is equal to or greater than a threshold value.

[0054] Specifically, in step S46, processor 17 determines whether or not there is an external force being applied to the outer surface of arm 15. If processor 17 determines Yes in step S46, it proceeds to step S47 and selects, as a first threshold value to be used when processing the amount of movement of designated point A2 in region of interest A1, a value that exceeds the second threshold value to be used when processing the amount of movement of designated point B2 in region of interest B1.

[0055] On the other hand, if processor 17 determines No in step S46, it proceeds to step S48 and sets the first threshold used when processing the amount of movement of designated point A2 in region of interest A1 and the second threshold used when processing the amount of movement of designated point B2 in region of interest B1 to the same value. The first threshold and second threshold used by processor 17 to process the amount of movement of the designated points are each stored in advance in auxiliary memory 19. Note that a reference threshold may be stored in auxiliary memory 19, and processor 17 may determine the first threshold and the second threshold by correcting the reference threshold.

[0056] Processor 17 can also set the first threshold used in step S47 to be larger than the first threshold used in step S48, and set the second threshold used in step S47 to be larger than the second threshold used in step S48. Furthermore, when determining the amount of movement of muscle 16 without distinguishing between superficial layer 16A and deep layer 16B of muscle 16, processor 17 can set the threshold used in step S48 to be smaller than the threshold used in step S47.

[0057] (Other use cases) When the processor 17 executes the above process, it can determine the amount of movement of the superficial layer 16A, which is susceptible to the influence of external force, and the amount of movement of the deep layer 16B, which is less susceptible to the influence of external force, depending on the state of application of the external force. Furthermore, under the following conditions: the type and identification number of the subject are the same, the same body part, the same cross-sectional direction of the muscle, the presence or absence of external force applied to the muscle, and the same direction and value of the external force if an external force is applied, the processor 17 can use the ultrasound image analysis system 10 to generate ultrasound images 32 for a predetermined period, for example, every month, and determine the amount of movement of the muscle 16. Therefore, it is possible to estimate the change over time in the state of the muscle 16 in response to the applied external force. The predetermined period is not limited to one month, but can be set by the user as desired, such as one week, one year, etc.

[0058] Furthermore, the user can repeat the usage example of Figure 5 multiple times at predetermined intervals using the same identification number, the same subject, and the same conditions. When processor 17 executes the process shown in Figure 5 for the second or subsequent time, processor 17 can perform the second or subsequent processing, analysis, and judgment based on the learned data generated by the previous process of Figure 5. For example, processor 17 may automatically set regions of interest A1 and B1 on screen 31 without the user having to operate operation device 21 in step S20. When processor 17 performs this process, the user's operation is simplified.

[0059] Furthermore, when extracting designated points A2 and B2 in step S30, processor 17 may choose not to extract designated points that were previously deleted by executing the example of use in Fig. 5. If processor 17 performs this process, the process of excluding either designated point A2 or B2 in step S42 can be simplified.

[0060] (supplementary explanation) An example of the technical meaning of the matters disclosed in this embodiment is as follows: The ultrasound image analysis device 12 is an example of an ultrasound image analysis device and a computer. The ultrasound probe 11 is an example of an ultrasound probe. The transmission / reception device 20 is an example of a transmission / reception device. The processor 17 is an example of a processor. Step S10 is an example of a first process. Step S20 is an example of a second process. Step S30 is an example of a third process. Step S40 is an example of a fourth process. Step S20 and step S60 are examples of a fifth process. Step 60 is an example of a sixth process.

[0061] Arm 15 is an example of a subject. Muscle 16 is an example of a muscle. Superficial layer 16A is an example of a superficial layer of a muscle. Deep layer 16B is an example of a deep layer of a muscle. Region of interest A1 is an example of a first region of interest. Region of interest B1 is an example of a second region of interest. Designated point A2 is an example of a first designated point. Designated point B2 is an example of a second designated point. Representative designated points A3 and B3 are examples of representative designated points. The outer shape of the region of interest is not limited to a rectangle, but may be an ellipse, a circle, a triangle, a pentagon, a hexagon, etc. The subject is not limited to a human arm, but may be a human leg, torso, etc. The subject may also be an animal other than a human.

[0062] This embodiment describes the following features. For example, the present invention describes an ultrasound image analysis method executed by a computer connected to an ultrasound probe that irradiates an object with ultrasound, converts reflected waves generated by the ultrasound probe into signals, and processes signals acquired from the ultrasound probe to generate two-dimensional ultrasound images. The ultrasound image analysis method includes the following steps: a first step of generating multiple ultrasound images showing the movement of the object's muscles; a second step of setting a region of interest in a single ultrasound image selected from the multiple ultrasound images; a third step of extracting designated points within the region of interest; and a fourth step of automatically tracking the designated points in each of the ultrasound images other than the selected ultrasound image to determine the amount of movement of the muscle. The ultrasound image analysis method is disclosed based on the flowcharts of FIGS. 2 and 5.

[0063] Also disclosed is a storage medium having stored therein an ultrasound image analysis program that causes a computer connected to an ultrasound probe that converts reflected waves generated by irradiating an object with ultrasound waves into signals and outputs the signals, and that processes signals acquired from the ultrasound probe to generate two-dimensional ultrasound images, the program causing the computer to execute a first process of generating multiple ultrasound images showing the movement of the object's muscles, a second process of setting a region of interest in a single ultrasound image selected from the multiple ultrasound images, a third process of extracting designated points within the region of interest, and a fourth process of determining the amount of movement of the muscle by automatically tracking each of the designated points for the ultrasound images other than the selected ultrasound image. Note that the storage medium can also be understood as a program product in which a program is stored. [Industrial Applicability]

[0064] This embodiment can be used as an ultrasound image analysis device and an ultrasound image analysis program for analyzing ultrasound images of muscles obtained by irradiating a subject with ultrasound. [Explanation of symbols]

[0065] 11...ultrasound probe, 12...ultrasound image analyzer, 15...arm, 16...muscle, 16A...surface layer, 16B...deep layer, 17...processor, 20...transmitting / receiving device, A1, B1...region of interest, A2, B2...designated point

Claims

1. a transmitting / receiving device connected to an ultrasonic probe that converts reflected waves generated by irradiating an object with ultrasonic waves into signals and outputs the signals; a processor that processes signals acquired from the ultrasound probe to generate a two-dimensional ultrasound image; An ultrasound image analysis device having: The processor: a first process for generating a plurality of ultrasound images of the subject's muscles in motion; a second process of setting a region of interest in a single selected ultrasound image from among the plurality of ultrasound images; a third process of extracting a designated point within the region of interest; a fourth process of automatically tracking the designated points on the ultrasound images other than the selected ultrasound image to determine the amount of movement of the muscle; This is a configuration that runs an operating device is further provided that allows a user to input the position of the superficial layer and the position of the deep layer of the muscle in the ultrasound image and to input whether or not the muscle is subjected to an external force; The processor: a fifth process for determining the positions of the superficial layer and the deep layer of the muscle in the ultrasound image before executing the second process; a sixth process of determining whether or not the muscle is subjected to an external force before executing the second process; Further execute the second processing executed by the processor includes a process of setting a first region of interest in a superficial layer of the muscle in the ultrasound image and a process of setting a second region of interest in a deep layer of the muscle; the third process executed by the processor includes a process of extracting a first designated point in the first region of interest and a process of extracting a second designated point in the second region of interest; The fourth process executed by the processor is a process of excluding a movement amount of a first specified point in a first region of interest that is equal to or greater than a first threshold value and determining a movement amount of the muscle in the superficial layer; a process of excluding a movement amount of a second specified point in a second region of interest that is equal to or greater than a second threshold value and determining a movement amount of the muscle in the deep layer; Including, when it is determined in the sixth process that the muscle is subjected to an external force, the processor executes the fourth process using the first threshold value that exceeds the second threshold value; An ultrasound image analysis device, wherein when the processor determines in the fifth process that the muscle is not subjected to an external force, it executes the fourth process using the first threshold value and the second threshold value that are the same magnitude.

2. 2. The ultrasonic image analysis device according to claim 1, A fourth process executed by the processor includes: An ultrasound image analysis device configured to exclude from the tracking targets those of the specified points that have relatively large amounts of movement, and to determine the amount of movement of the muscle based on the amount of movement of the remaining specified points.

3. 2. The ultrasonic image analysis device according to claim 1, A fourth process executed by the processor includes: An ultrasound image analysis device configured to determine the amount of movement of the muscle based on an average value of the amounts of movement of the plurality of specified points.

4. 2. The ultrasonic image analysis device according to claim 1, A fourth process executed by the processor includes: An ultrasound image analysis device configured to determine the amount of movement of the muscle by automatically tracking a representative designated point located at the center of the region of interest.

5. 2. The ultrasonic image analysis device according to claim 1, an operating device is further provided that can be operated by a user to input whether or not the muscle is subjected to an external force; The processor determines whether the muscle is subjected to an external force before executing the second process; the fourth process executed by the processor is a process of determining a movement amount of the muscle by excluding a movement amount of the specified point if the movement amount of the specified point is equal to or greater than a threshold value; When the processor determines that the muscle is subjected to an external force, the processor executes the fourth process using a first threshold value; When the processor determines that the muscle is not subjected to an external force, the processor executes the fourth process using a second threshold value that is less than the first threshold value. Ultrasound image analysis device.

6. An ultrasound image analysis program that causes a computer to execute processing, the computer being connected to an ultrasound probe that irradiates an object with ultrasound, converts reflected waves generated by the ultrasound into signals, and outputs the signals, and that processes signals acquired from the ultrasound probe to generate two-dimensional ultrasound images, The computer, a first process for generating a plurality of ultrasound images of the subject's muscles in motion; a second process of setting a region of interest in a single selected ultrasound image from among the plurality of ultrasound images; a third process of extracting a designated point within the region of interest; a fourth process of automatically tracking the designated points on the ultrasound images other than the selected ultrasound image to determine the amount of movement of the muscle; Execute The computer further includes an operation device that allows a user to input the positions of the superficial layer and the deep layer of the muscle in the ultrasound image and to input whether or not the muscle is subjected to an external force, The computer, a fifth process for determining the positions of the superficial layer and the deep layer of the muscle in the ultrasound image before executing the second process; a sixth process of determining whether or not the muscle is subjected to an external force before executing the second process; Further execute the second processing executed by the computer includes processing of setting a first region of interest in a superficial layer of the muscle in the ultrasound image and setting a second region of interest in a deep layer of the muscle; the third process executed by the computer includes a process of extracting a first designated point in the first region of interest and a process of extracting a second designated point in the second region of interest; The fourth process executed by the computer is a process of excluding a movement amount of a first specified point in a first region of interest that is equal to or greater than a first threshold value and determining a movement amount of the muscle in the superficial layer; a process of excluding a movement amount of a second specified point in a second region of interest that is equal to or greater than a second threshold value and determining a movement amount of the muscle in the deep layer; Including, when it is determined in the sixth process that the muscle is subjected to an external force, the computer executes the fourth process using the first threshold value that exceeds the second threshold value; An ultrasound image analysis program, wherein when the fifth process determines that the muscle is not subjected to an external force, the computer executes the fourth process using the first threshold value and the second threshold value that are the same magnitude.

Images