Ultrasound diagnostic system, ultrasound diagnostic apparatus, ultrasound diagnostic method, and program

Abstract

To effectively display multiple diagnostic results to the user, generated by several pre-trained models with different characteristics targeting the same disease. [Solution] An ultrasound diagnostic system comprising an ultrasound probe and a first ultrasound diagnostic device connected to the ultrasound probe, wherein the first ultrasound diagnostic device comprises an ultrasound image generation unit that generates an ultrasound image based on a probe signal received from the ultrasound probe, a first storage unit that stores a plurality of trained models with different characteristics targeting the same disease used in the diagnostic processing of a subject, a first diagnostic processing unit that executes a plurality of diagnostic processes based on the ultrasound image in parallel using the plurality of trained models, and a display control unit that switches between a first mode in which all of the plurality of diagnostic results obtained by the plurality of diagnostic processes are displayed on the display unit and a second mode in which one or more of the plurality of diagnostic results are not displayed on the display unit.

Description

Technical Field

[0001] The present invention relates to an ultrasonic diagnostic system, an ultrasonic diagnostic apparatus, an ultrasonic diagnostic method, and a program.

Background Art

[0002] Conventionally, a system for automating the diagnosis of patients using AI (Artificial Intelligence) has been known. For example, Patent Document 1 proposes a medical information processing system that estimates a disease or symptom of a diagnostic target by inputting medical examination data of the diagnostic target into a learned model of AI (Patent Document 1).

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, the conventional medical information processing system has been unable to operate a plurality of diagnostic processes using a plurality of learned models with different characteristics for the same disease in parallel. For this reason, in the conventional medical information processing system, there have been cases where a plurality of diagnostic results obtained by these plurality of learned models cannot be effectively displayed to the user.

[0005] The present invention has been made in consideration of such circumstances, and one of its objects is to provide an ultrasonic diagnostic system, an ultrasonic diagnostic apparatus, an ultrasonic diagnostic method, and a program that can effectively display a plurality of diagnostic results obtained by a plurality of learned models with different characteristics for the same disease to the user.

Means for Solving the Problems

[0006] One aspect of the present invention is an ultrasound diagnostic system comprising: an ultrasound probe that transmits ultrasound to a subject and generates a probe signal based on the reflected wave from the subject; and a first ultrasound diagnostic device connected to the ultrasound probe, wherein the first ultrasound diagnostic device comprises: an ultrasound image generation unit that generates an ultrasound image based on the probe signal received from the ultrasound probe; a first storage unit that stores a plurality of trained models with different characteristics targeting the same disease, which are used for the diagnostic processing of the subject; a first diagnostic processing unit that executes a plurality of diagnostic processes based on the ultrasound image in parallel using the plurality of trained models; and a display control unit that switches between a first mode in which all of the plurality of diagnostic results obtained by the plurality of diagnostic processes are displayed on the display unit, and a second mode in which one or more of the plurality of diagnostic results are not displayed on the display unit. [Effects of the Invention]

[0007] According to one aspect of the present invention, it is possible to provide an ultrasound diagnostic system, ultrasound diagnostic apparatus, ultrasound diagnostic method, and program that can effectively display to a user multiple diagnostic results from multiple trained models with different characteristics targeting the same disease. [Brief explanation of the drawing]

[0008] [Figure 1] This is a diagram showing an example of an ultrasound diagnostic system 10. [Figure 2] This is a block diagram showing the configuration of the first ultrasound diagnostic device 100. [Figure 3] This is a block diagram showing the configuration of the second ultrasound diagnostic device 200. [Figure 4] This figure shows an example of the diagnostic process flow using the first ultrasound diagnostic device 100. [Figure 5] This figure shows an example of the diagnostic process flow using the second ultrasound diagnostic device 200. [Figure 6] This figure shows an example of user information 191. [Figure 7]This figure shows an example of model information 192. [Figure 8] This figure shows an example of the diagnostic results screen S1 in the first mode. [Figure 9] This figure shows an example of the diagnostic results screen S2 in the second mode. [Figure 10] This flowchart shows an example of a process performed by the first ultrasound diagnostic device 100. [Figure 11] This flowchart shows an example of a diagnostic process performed by the first ultrasound diagnostic device 100. [Modes for carrying out the invention]

[0009] Hereinafter, embodiments of the ultrasound diagnostic system, ultrasound diagnostic apparatus, ultrasound diagnostic method, and program of the present invention will be described with reference to the drawings.

[0010] [Ultrasound diagnostic system] Figure 1 shows an example of an ultrasound diagnostic system 10. The ultrasound diagnostic system 10 comprises an ultrasound probe 50, a first ultrasound diagnostic device 100, and a second ultrasound diagnostic device 200. The ultrasound probe 50 is communicated with the first ultrasound diagnostic device 100 by wire or wireless connection. The first ultrasound diagnostic device 100 is communicated with the second ultrasound diagnostic device 200 via a network NW. The network NW includes, for example, the Internet, a LAN (Local Area Network), a wireless base station, provider equipment, etc.

[0011] The ultrasound probe 50 is a device used for ultrasound (echo) examinations. The ultrasound probe 50 is, for example, a one-dimensional array linear probe in which multiple ultrasound transducers are arranged along a predetermined direction. The ultrasound probe 50 performs an ultrasound scan on a scan area within the biological body P, which is the subject, according to control from the first ultrasound diagnostic device 100. During the ultrasound scan, the ultrasound probe 50 transmits ultrasound to the biological body P and generates a probe signal based on the reflected waves from the subject. The ultrasound probe 50 transmits the generated probe signal to the first ultrasound diagnostic device 100.

[0012] The first ultrasound diagnostic device 100 is, for example, a portable computer such as a smartphone or tablet, but it may also be a notebook computer or a desktop computer. The first ultrasound diagnostic device 100 is a computer located at the edge of the network. The first ultrasound diagnostic device 100 is used, for example, by a doctor in a hospital. The first ultrasound diagnostic device 100 generates an ultrasound image (echo image) based on the probe signal received from the ultrasound probe 50. The ultrasound image may be a still image or a video. The first ultrasound diagnostic device 100 also performs diagnostic processing using AI (Artificial Intelligence) based on the ultrasound image. The diagnostic processing is for diagnosing the state of the living body P and the presence or absence of disease.

[0013] The second ultrasound diagnostic device 200 is a server computer with higher specifications than the first ultrasound diagnostic device 100. The second ultrasound diagnostic device 200 performs AI-based diagnostic processing in response to requests from the first ultrasound diagnostic device 100. In the example shown in Figure 1, for the sake of simplicity, one first ultrasound diagnostic device 100 is connected to the second ultrasound diagnostic device 200, but multiple first ultrasound diagnostic devices 100 may be connected to the second ultrasound diagnostic device 200.

[0014] [First Ultrasound Diagnostic Device] FIG. 2 is a block diagram showing the configuration of the first ultrasonic diagnostic apparatus 100. The first ultrasonic diagnostic apparatus 100 includes, for example, a first communication unit 110, an ultrasonic image generation unit 120, a first diagnostic processing unit 130, a determination unit 140, a decision unit 150, a display control unit 160, an input unit 170, a display unit 180, and a first storage unit 190.

[0015] The first communication unit 110 includes a communication module for communicating with the second ultrasonic diagnostic apparatus 200 via the network NW. The first communication unit 110 also includes a communication interface for communicating with the ultrasonic probe 50 by wire. Note that the first communication unit 110 may include a communication module for wirelessly communicating with the ultrasonic probe 50.

[0016] The ultrasonic image generation unit 120, the first diagnostic processing unit 130, the determination unit 140, the decision unit 150, and the display control unit 160 are realized, for example, by a hardware processor such as a CPU (Central Processing Unit) executing a program (software). Some or all of these components may be realized by hardware such as LSI (Large Scale Integration), ASIC (Application Specific Integrated Circuit), FPGA (Field-Programmable Gate Array), GPU (Graphics Processing Unit), or may be realized by cooperation of software and hardware. The program may be stored in advance in a storage device (a storage device having a non-transitory storage medium) such as an HDD (Hard Disk Drive) or a flash memory, or may be stored in a removable storage medium (a non-transitory storage medium) such as a DVD or a CD-ROM, and may be installed in the storage device by mounting the storage medium in a drive device.

[0017] The input unit 170 and the display unit 180 are realized by, for example, a touch panel display. Note that the configurations of the input unit 170 and the display unit 180 are not limited to this. For example, the input unit 170 may include a keyboard and a mouse, and the display unit 180 may be a display device such as a CRT (Cathode Ray Tube) display, a liquid crystal display, or an organic EL (Electro-Luminescence) display.

[0018] The first storage unit 190 is, for example, an HDD, a flash memory, a RAM (Random Access Memory), or the like. The first storage unit 190 may be a NAS (Network Attached Storage) device that can be accessed by the first ultrasonic diagnostic apparatus 100 via the network NW. The first storage unit 190 stores information such as user information 191, model information 192, diagnostic result information 193, and first learned models 194-1 to Nth learned models 194-N. N is a natural number of 2 or more. Each of the first learned models 194-1 to Nth learned models 194-N is a model generated by previously performing machine learning on teacher data and is information used when diagnostic processing is executed.

[0019] [Second Ultrasonic Diagnostic Apparatus] FIG. 3 is a block diagram showing the configuration of the second ultrasonic diagnostic apparatus 200. The second ultrasonic diagnostic apparatus 200 includes, for example, a second communication unit 210, a second diagnostic processing unit 230, and a second storage unit 290.

[0020] The second communication unit 210 is a communication interface for communicating with the first ultrasonic diagnostic apparatus 100 via the network NW. The second communication unit 210 is, for example, a network interface card.

[0021] The second diagnostic processing unit 230 is implemented, for example, by a hardware processor such as a CPU executing a program (software). Some or all of these components may be implemented by hardware such as an LSI, ASIC, FPGA, or GPU, or by the cooperation of software and hardware. The program may be stored in advance in a storage device such as an HDD or flash memory (a storage device equipped with a non-transient storage medium), or it may be stored in a removable storage medium such as a DVD or CD-ROM (a non-transient storage medium) and installed in the storage device when the storage medium is inserted into a drive device.

[0022] The second storage unit 290 is an HDD, flash memory, RAM, etc. The second storage unit 290 may also be a NAS device accessible by the second ultrasound diagnostic device 200 via a network NW. The second storage unit 290 stores information such as the first trained model 294-1 to the Nth trained model 294-N. The first trained model 294-1 to the Nth trained model 294-N stored in the second storage unit 290 are the same models as the first trained model 194-1 to the Nth trained model 194-N stored in the first storage unit 190.

[0023] The first ultrasound diagnostic device 100 and the second ultrasound diagnostic device 200 each have the function of performing diagnostic processing based on ultrasound images (echo images). When determining the trained model to be used for disease diagnosis, adjusting the parameters to reduce false detection of diseases increases the number of missed detections. On the other hand, adjusting the parameters to reduce missed detections of diseases increases the number of false detections. For this reason, it is desirable to use multiple trained models with different characteristics targeting the same disease and to perform multiple diagnostic processes in parallel. However, since the first ultrasound diagnostic device 100 is often a smartphone or tablet, if the first ultrasound diagnostic device 100 is to perform all of the multiple diagnostic processes, the processing load on the first ultrasound diagnostic device 100 becomes excessive, leading to high battery consumption. For this reason, when performing multiple diagnostic processes using multiple trained models, it is desirable to distribute the multiple diagnostic processes between the first ultrasound diagnostic device 100 and the second ultrasound diagnostic device 200. However, when performing diagnostic processing with the second ultrasound diagnostic device 200, communication is required via a network NW, which may cause delays in the first ultrasound diagnostic device 100 receiving diagnostic results from the second ultrasound diagnostic device 200. For this reason, it is desirable to perform only high-priority diagnostic processing with the first ultrasound diagnostic device 100. Therefore, the ultrasound diagnostic system of this embodiment appropriately determines whether to perform diagnostic processing with the first ultrasound diagnostic device 100 or the second ultrasound diagnostic device 200. The diagnostic processing by the first ultrasound diagnostic device and the diagnostic processing by the second ultrasound diagnostic device will be described below.

[0024] [Diagnostic processing using the first ultrasound diagnostic device] Figure 4 shows an example of the diagnostic process flow by the first ultrasound diagnostic device 100. The example shown in Figure 4 illustrates the process flow when the determination unit 140 determines that the first ultrasound diagnostic device 100 should perform the diagnostic process.

[0025] First, the ultrasound probe 50 transmits ultrasound waves to the biological body P, which is the subject, and generates a probe signal based on the reflected waves from the biological body P. Then, the ultrasound probe 50 transmits the probe signal to the first ultrasound diagnostic device 100.

[0026] The ultrasound image generation unit 120 of the first ultrasound diagnostic device 100 generates an ultrasound image (echo image) based on the probe signal received from the ultrasound probe 50. For example, the ultrasound image generation unit 120 generates a two-dimensional ultrasound image composed of pixels by performing a coordinate transformation according to the ultrasound scanning pattern of the ultrasound probe 50. The ultrasound image generation unit 120 outputs the generated ultrasound image to the determination unit 140.

[0027] Meanwhile, the decision unit 150 determines which diagnostic process to execute. For example, a physician examining the living organism P may input information about the disease using the input unit 170, and the decision unit 150 may determine which diagnostic process to execute based on the information about the disease input by the physician. For example, the decision unit 150 may display multiple options related to the disease on the display unit 180, and determine which diagnostic process to execute according to the option selected by the physician using the input unit 170. For example, if the site to be diagnosed is the heart, the decision unit may display options such as cardiomyopathy, valvular heart disease, and myocardial infarction on the display unit 180. Also, for example, if cardiomyopathy is selected by the physician, the decision unit may determine that a diagnostic process targeting cardiomyopathy is the diagnostic process to be executed. The decision unit 150 outputs a diagnostic ID corresponding to the determined diagnostic process to the judgment unit 140. The diagnostic ID is identification information for identifying the diagnostic process.

[0028] Next, the determination unit 140 determines whether to perform the diagnostic process using the first ultrasound diagnostic device 100 or the second ultrasound diagnostic device 200. Details of the determination process by the determination unit 140 will be described later. If the determination unit 140 determines that the diagnostic process should be performed using the first ultrasound diagnostic device 100, it outputs the ultrasound image (echo image) generated by the ultrasound image generation unit 120 and the diagnostic ID for identifying the diagnostic process determined by the decision unit 150 to the first diagnostic processing unit 130.

[0029] Next, the first diagnostic processing unit 130 performs diagnostic processing using one of the first trained models 194-1 to the Nth trained model 194-N based on the ultrasound image (echo image). For example, the first diagnostic processing unit 130 reads the trained model corresponding to the diagnostic ID output from the determination unit 150 from the first storage unit 190, and inputs the ultrasound image to the read trained model to obtain a diagnostic result. To give a specific example, if the ultrasound image is an image of the heart of living organism P, and the diagnostic ID output from the determination unit 150 indicates a diagnosis of cardiomyopathy, the first diagnostic processing unit 130 reads the trained model corresponding to the diagnosis of cardiomyopathy from the first storage unit 190, and inputs the ultrasound image to the read trained model to obtain a diagnostic result regarding whether or not living organism P has developed cardiomyopathy. After that, the first diagnostic processing unit 130 outputs the diagnostic result to the display control unit 160.

[0030] The display control unit 160 displays the diagnostic results output from the first diagnostic processing unit 130 on the display unit 180. By checking the diagnostic results displayed on the display unit 180, the physician can understand the state of the biological P or the disease that the biological P is suffering from.

[0031] As shown in the processing flow in Figure 4, the first ultrasound diagnostic device 100 performs the diagnostic processing, allowing the diagnostic results to be displayed without being affected by delays caused by communication via the network NW. However, as mentioned above, when it is necessary to perform multiple diagnostic processes, it is not desirable to perform all of them on the first ultrasound diagnostic device 100. This is because the processing load on the first ultrasound diagnostic device 100 becomes excessive, leading to rapid battery consumption. For this reason, in this embodiment, the diagnostic processes with lower priority are performed on the second ultrasound diagnostic device 200. The diagnostic processing performed by the second ultrasound diagnostic device 200 will be described below.

[0032] [Diagnostic processing using the second ultrasound diagnostic device] Figure 5 shows an example of the diagnostic processing flow by the second ultrasound diagnostic device 200. The example shown in Figure 5 shows the processing flow when the determination unit 140 determines that the second ultrasound diagnostic device 200 should perform diagnostic processing. Note that the operation of the ultrasound probe 50, ultrasound image generation unit 120, and decision unit 150 is the same as in Figure 4, so the explanation is omitted.

[0033] The determination unit 140 determines whether to perform the diagnostic process using the first ultrasound diagnostic device 100 or the second ultrasound diagnostic device 200. Details of the determination process by the determination unit 140 will be described later. If the determination unit 140 determines that the diagnostic process should be performed using the second ultrasound diagnostic device 200, it outputs the ultrasound image (echo image) generated by the ultrasound image generation unit 120 and the diagnostic ID for identifying the diagnostic process determined by the decision unit 150 to the first communication unit 110.

[0034] The first communication unit 110 transmits ultrasound images (echo images) and a diagnostic ID to the second ultrasound diagnostic device 200 via the network NW. When transmitting information via the network NW, there is a possibility that the information may be leaked to the outside. For this reason, the determination unit 140 may encrypt the information to be transmitted (ultrasound images and diagnostic ID) in a predetermined manner between the first ultrasound diagnostic device 100 and the second ultrasound diagnostic device 200, and the first communication unit 110 may transmit the encrypted information. This prevents information leakage.

[0035] Next, the second communication unit 210 of the second ultrasound diagnostic device 200 receives the ultrasound image (echo image) and diagnostic ID from the first ultrasound diagnostic device 100 via the network NW. Subsequently, the second communication unit 210 outputs the ultrasound image (echo image) and diagnostic ID to the second diagnostic processing unit 230.

[0036] Next, the second diagnostic processing unit 230 performs diagnostic processing using one of the first trained models 294-1 to the Nth trained model 294-N based on the ultrasound image (echo image). For example, the second diagnostic processing unit 230 reads the trained model corresponding to the diagnostic ID output from the second communication unit 210 from the second storage unit 290, and obtains a diagnostic result by inputting the ultrasound image to the read trained model. After that, the second diagnostic processing unit 230 outputs the diagnostic result to the second communication unit 210.

[0037] The second communication unit 210 transmits the diagnostic results to the first ultrasound diagnostic device 100 via the network NW. When transmitting information via the network NW, there is a possibility that the information may be leaked to the outside. For this reason, the second diagnostic processing unit 230 may encrypt the information to be transmitted (diagnostic results) in a predetermined manner between the first ultrasound diagnostic device 100 and the second ultrasound diagnostic device 200, and the second communication unit 210 may transmit the encrypted information. This makes it possible to more reliably prevent information leakage.

[0038] Next, the first communication unit 110 of the first ultrasound diagnostic device 100 receives the diagnostic results from the second ultrasound diagnostic device 200 via the network NW. Subsequently, the first communication unit 110 outputs the diagnostic results to the display control unit 160.

[0039] The display control unit 160 displays the diagnostic results output from the first communication unit 110 on the display unit 180. By checking the diagnostic results displayed on the display unit 180, the doctor can understand the state of the living organism P or the disease that living organism P is suffering from.

[0040] The cases in which the first ultrasound diagnostic device 100 performs the diagnostic process (Figure 4) and the second ultrasound diagnostic device 200 performs the diagnostic process (Figure 5) have been described above. As mentioned above, the determination unit 140 determines whether to perform the diagnostic process using the first ultrasound diagnostic device 100 or the second ultrasound diagnostic device 200. The user information 191 and model information 192 used in the determination process by the determination unit 140 will be described below.

[0041] [User Information] Figure 6 shows an example of user information 191. User information 191 is information about a user (such as a doctor) who uses the ultrasound diagnostic system 10, and is stored in the first storage unit 190. As shown in Figure 6, user information 191 is a table that associates user ID, name, learning level, proficiency, information about certified physicians, and information about specialty. User ID is identification information for identifying the user. Name is information indicating the user's name. Learning level is information indicating the user's learning progress regarding diagnosis using ultrasound images. Specifically, the user may take an educational program regarding diagnosis using ultrasound images, and the learning level may be a value (for example, a value from 0 to 10) indicating the progress of the educational program. Proficiency is information indicating the user's proficiency with the ultrasound diagnostic system 10. For example, proficiency may be a value (for example, a value from 0 to 10) corresponding to the time or number of times the user has used the ultrasound diagnostic system 10. Information about certified physicians may be information indicating whether or not the user is a certified physician. A certified physician is a physician who has passed the examination set by a designated academic society and has been certified as meeting the standards for relevant clinical knowledge and experience. Information regarding specialty fields indicates the user's area of ​​expertise as a physician. This information may include, for example, orthopedic surgery, cardiac surgery, respiratory surgery, and neurosurgery, indicating the user's medical specialty.

[0042] [Model Information] Figure 7 shows an example of model information 192. Model information 192 is information about multiple learning models used in multiple diagnostic processes and is stored in the first storage unit 190. As shown in Figure 7, model information 192 is a table that associates model ID, diagnostic ID, target disease, and priority. Model ID is identification information for identifying a trained model. Diagnostic ID is identification information for identifying a diagnostic process. Target disease is information indicating the disease to be diagnosed. Target disease may be information indicating, for example, cardiomyopathy, valvular heart disease, and myocardial infarction. Priority is a value (for example, a value from 0 to 10) indicating the priority of the diagnostic process to be executed using the trained model. As will be described in detail later, diagnostic processes with high priority will be executed by the first ultrasound diagnostic device 100, and diagnostic processes with low priority will be executed by the second ultrasound diagnostic device 200.

[0043] [Diagnosis Results Screen] In this embodiment, the display control unit 160 displays the location where a disease may be occurring and the degree of certainty of the disease, which is the diagnostic result, on the display unit 180, superimposed on the ultrasound image. The display control unit 160 switches between a first mode and a second mode based on user information 191, which is information about the user (such as a doctor) using the ultrasound diagnostic system 10. The first mode is a mode in which all of the multiple diagnostic results obtained by multiple diagnostic processes are displayed on the display unit 180. On the other hand, the second mode is a mode in which one or more of the multiple diagnostic results are not displayed on the display unit 180. The details of the diagnostic result screen S1 in the first mode and the diagnostic result screen S2 in the second mode will be described below.

[0044] (1) Diagnostic results screen for Mode 1 Figure 8 shows an example of the diagnostic results screen S1 in the first mode. In the example shown in Figure 8, it is assumed that the diagnostic process was performed using three pre-trained models (M001, M002, M003) with different characteristics targeting the same disease (e.g., cardiomyopathy). The diagnostic results screen S1 in the first mode includes an ultrasound image IM and multiple diagnostic results. The ultrasound image IM is an image (echo image) generated by the ultrasound image generation unit 120. Each of the multiple diagnostic results includes the name of the pre-trained model used in the diagnostic process (M001, M002, M003), the disease name (e.g., cardiomyopathy, valvular heart disease, etc.), and the degree of certainty of the disease (e.g., a percentage). In addition, circles are placed at locations where the disease may be present. Specifically, the diagnostic results screen S1 in the first mode displays the diagnostic results of the three pre-trained models (M001, M002, M003) overlaid on the ultrasound image IM. In other words, in the first mode, the display control unit 160 displays all of the multiple diagnostic results obtained by the multiple diagnostic processes on the display unit 180.

[0045] When inexperienced users in the medical field being diagnosed perform examinations based on ultrasound images, they may miss diseases. Therefore, for inexperienced users in the medical field being diagnosed, the display control unit 160 displays all of the multiple diagnostic results obtained by performing multiple diagnostic processes on the display unit 180, as shown in Figure 8. Generally, trained models that have few false positives tend to miss many diseases. On the other hand, trained models that have few missed diseases tend to have many false positives. Therefore, in the first mode, the display control unit 160 displays all of the multiple diagnostic results obtained using multiple trained models with such different characteristics on the display unit 180. This prevents inexperienced users in the medical field being diagnosed from missing diseases when performing examinations based on ultrasound images.

[0046] (2) Diagnostic results screen for the second mode Figure 9 shows an example of the diagnostic results screen S2 in the second mode. In the example shown in Figure 9, it is assumed that the diagnostic process was performed using three trained models (M001, M002, M003) with different characteristics that target the same disease (e.g., cardiomyopathy). Unlike the diagnostic results screen S1 in the first mode shown in Figure 8, the diagnostic results screen S2 in the second mode shown in Figure 9 displays only the ultrasound image IM and the diagnostic result of one trained model (M001), and does not display the diagnostic results of the other trained models (M002, M003). In other words, in the second mode, the display control unit 160 prevents one or more of the multiple diagnostic results from being displayed on the display unit 180.

[0047] For example, the display control unit 160 may obtain the priority of multiple trained models associated with the diagnostic ID output from the determination unit from the model information 192, and display the diagnostic results using trained models with a priority of a predetermined value or higher in the second mode, while not displaying the diagnostic results using trained models with a priority of less than the predetermined value in the second mode. As a result, in the second mode, only the diagnostic results using trained models with a priority of a predetermined value or higher will be displayed on the diagnostic results screen S2.

[0048] When an experienced user in the medical field being diagnosed performs an examination based on ultrasound images, their diagnostic ability is high, making it less likely that they will miss a disease. On the other hand, for experienced users, displaying all of the multiple diagnostic results on the display unit 180, as in the first mode, is undesirable because it would make the diagnostic results screen difficult to read, as diagnostic results that frequently detect diseases would also be displayed on the display unit 180. Furthermore, displaying all of the multiple diagnostic results on the display unit 180 would make it difficult to see the ultrasound image IM, which is also undesirable. Therefore, in the second mode, the display control unit 160, for experienced users in the medical field being diagnosed, prevents the display unit 180 from displaying one or more of the multiple diagnostic results obtained by performing multiple diagnostic processes, as shown in Figure 9. This improves the visibility of the diagnostic results screen, even when an experienced user in the medical field being diagnosed performs an examination based on ultrasound images.

[0049] [Mode switching process] The display control unit 160 switches between the first mode and the second mode based on user information 191, which is information about the user using the ultrasound diagnostic system 10. At this time, the display control unit 160 determines, based on the user information 191, whether the user (such as a doctor) using the ultrasound diagnostic system 10 is an inexperienced or experienced user in the medical field being diagnosed. As mentioned above, the user information 191 is a table that associates user ID, name, learning level, proficiency level, information about certified physicians, and information about specialty fields.

[0050] For example, a user (such as a doctor) using the ultrasound diagnostic system 10 may input a user ID using the input unit 170. The display control unit 160 may also acquire the user ID entered by the user and obtain user information 191 associated with the acquired user ID (for example, learning level, proficiency level, information on certified physicians, information on specialty, etc.).

[0051] Specifically, the display control unit 160 may obtain the learning level associated with the user ID from the user information 191. As mentioned above, the learning level is information indicating the user's learning progress regarding diagnosis using ultrasound images (for example, a value indicating the user's progress in an educational program). The display control unit 160 may set the first mode if the user's learning level is less than the first threshold TH1, and set the second mode if the user's learning level is equal to or greater than the first threshold. For example, if the first threshold TH1 is 8, the display control unit 160 may set the first mode if the user's learning level is less than 8, and set the second mode if the user's learning level is 8 or greater. Therefore, for users with a learning level of less than 8, setting the first mode can prevent missing a disease, and for users with a learning level of 8 or greater, setting the second mode can improve the visibility of the diagnostic result screen. As a result, the ultrasound diagnostic system 10 of this embodiment can effectively display to the user multiple diagnostic results from multiple trained models with different characteristics targeting the same disease.

[0052] Furthermore, the display control unit 160 may obtain the proficiency level associated with the user ID from the user information 191. As mentioned above, the proficiency level is information indicating the user's proficiency with respect to the ultrasound diagnostic system 10 (for example, a value corresponding to the time and number of times the user has used the ultrasound diagnostic system 10). The display control unit 160 may set the first mode if the user's proficiency level is less than the second threshold TH2, and set the second mode if the user's proficiency level is equal to or greater than the second threshold TH2. For example, if the second threshold TH2 is 8, the display control unit 160 may set the first mode if the user's proficiency level is less than 8, and set the second mode if the user's proficiency level is 8 or greater. Therefore, by setting the first mode for users with a proficiency level of less than 8, it is possible to prevent missing a disease, and by setting the second mode for users with a proficiency level of 8 or greater, it is possible to improve the visibility of the diagnostic result screen. As a result, the ultrasound diagnostic system 10 of this embodiment can effectively display to the user multiple diagnostic results from multiple trained models with different characteristics targeting the same disease.

[0053] Furthermore, the display control unit 160 may obtain information about certified physicians associated with the user ID from the user information 191. As mentioned above, the information about certified physicians may be information indicating whether or not the user is a certified physician. The display control unit 160 may set the first mode if the user is not a certified physician, and set the second mode if the user is a certified physician. Therefore, by setting the first mode for users who are not certified physicians, it is possible to prevent them from missing a disease, and by setting the second mode for users who are certified physicians, it is possible to improve the visibility of the diagnostic results screen. As a result, the ultrasound diagnostic system 10 of this embodiment can effectively display to the user multiple diagnostic results from multiple trained models with different characteristics targeting the same disease.

[0054] Furthermore, the display control unit 160 may obtain information regarding the user's specialty, which is associated with the user ID, from the user information 191. As mentioned above, the information regarding the specialty indicates the user's specialty as a physician. The information regarding the specialty may be, for example, information indicating the user's medical specialty, such as orthopedics, cardiac surgery, respiratory surgery, and neurosurgery. The display control unit 160 may set a first mode if the disease targeted by multiple diagnostic processes (e.g., cardiomyopathy) is not a disease related to the user's specialty, and set a second mode if the disease targeted by multiple diagnostic processes (e.g., cardiomyopathy) is a disease related to the user's specialty. Therefore, for users whose specialty is not the target disease, setting the first mode can prevent them from missing a disease, and for users whose specialty is the target disease, setting the second mode can improve the visibility of the diagnostic results screen. As a result, the ultrasound diagnostic system 10 of this embodiment can effectively display to the user multiple diagnostic results from multiple trained models with different characteristics targeting the same disease.

[0055] The display control unit 160 may calculate a score based on at least two of the following pieces of information: the user's learning level, proficiency, information about certified physicians, and information about their specialty. Based on the calculated score, the display control unit 160 may set either the first or second mode. For example, the display control unit 160 may calculate a first score such that the higher the user's learning level, the higher the value. The display control unit 160 may also calculate a second score such that the higher the user's proficiency, the higher the value. The display control unit 160 may also calculate a third score such that the value is higher if the user is a certified physician. The display control unit 160 may also calculate a fourth score such that the value is higher if the diseases targeted by multiple diagnostic processes are diseases related to the user's specialty. The display control unit 160 may also calculate a total score by summing at least two of the first to fourth scores. Furthermore, the display control unit 160 may set the first mode if the total score is less than a predetermined value, and set the second mode if the total score is equal to or greater than the predetermined value. As a result, the ultrasound diagnostic system 10 of this embodiment can effectively display to the user multiple diagnostic results from multiple trained models with different characteristics targeting the same disease.

[0056] [flowchart] Figure 10 is a flowchart showing an example of the process performed by the first ultrasound diagnostic device 100. First, the ultrasound image generation unit 120 generates an ultrasound image (echo image) based on the probe signal received from the ultrasound probe 50 (S101).

[0057] Next, the decision unit 150 determines the diagnostic process to be executed (S102). For example, the decision unit 150 may determine the diagnostic process to be executed based on the disease information entered by the user (such as a doctor) using the input unit 170.

[0058] Next, the first diagnostic processing unit 130 performs diagnostic processing (S103). In the diagnostic processing in S103, multiple diagnostic processes are executed using multiple trained models with different characteristics that target the same disease. The detailed flow of the diagnostic processing will be described later in Figure 11.

[0059] Next, the display control unit 160 determines whether to set the first mode or the second mode (S104). For example, the display control unit 160 may determine whether to set the first mode or the second mode based on user information 191, which is information about the user using the ultrasound diagnostic system 10. As mentioned above, the display control unit 160 may determine to set the first mode if the user using the ultrasound diagnostic system 10 is a user with little experience in the medical field being diagnosed. On the other hand, the display control unit 160 may determine to set the second mode if the user using the ultrasound diagnostic system 10 is a user with extensive experience in the medical field being diagnosed.

[0060] Next, if the display control unit 160 determines that the first mode should be set, it displays all of the multiple diagnostic results obtained by the multiple diagnostic processes on the display unit 180, as shown in Figure 8 (S105). This prevents the disease from being missed, even when a user with little experience in the medical field being diagnosed performs an examination based on ultrasound images.

[0061] On the other hand, if the display control unit 160 determines that the second mode should be set, it will not display one or more of the multiple diagnostic results obtained by the multiple diagnostic processes on the display unit 180, as shown in Figure 9 (S106). This improves the visibility of the diagnostic results screen, even when an experienced user in the medical field being diagnosed performs an examination based on ultrasound images.

[0062] Figure 11 is a flowchart showing an example of a diagnostic process performed by the first ultrasound diagnostic device 100. The diagnostic process shown in Figure 11 is a detailed description of S103 in Figure 10. First, the determination unit 140 identifies multiple diagnostic processes to be executed based on the diagnostic ID output from the determination unit (S201). For example, in Figure 7 above, if the diagnostic ID output from the determination unit is D001, the determination unit 140 identifies the diagnostic processes using three trained models (M001, M002, M003) as multiple diagnostic processes to be executed.

[0063] Next, the determination unit 140 determines whether or not to execute each of the identified diagnostic processes on the first ultrasound diagnostic device 100 (S202). For example, the determination unit 140 obtains the priority of each of the identified trained models (M001, M002, M003) from the model information 192. The determination unit 140 also determines that diagnostic processes performed by trained models with an acquired priority of a predetermined value or higher will be executed on the first ultrasound diagnostic device, and that diagnostic processes performed by trained models with an acquired priority of less than the predetermined value will be executed on the second ultrasound diagnostic device.

[0064] In this way, the determination unit 140 determines whether each of the multiple diagnostic processes should be executed on the first ultrasound diagnostic device 100 or the second ultrasound diagnostic device 200. Specifically, the determination unit 140 determines that the diagnostic processes for obtaining diagnostic results displayed in the second mode (diagnostic processes with a priority of a predetermined value or higher) should be executed on the first ultrasound diagnostic device 100, and the diagnostic processes for obtaining diagnostic results that are not displayed in the second mode (diagnostic processes with a priority of less than a predetermined value) should be executed on the second ultrasound diagnostic device 200. By distributing the multiple diagnostic processes between the first ultrasound diagnostic device 100 and the second ultrasound diagnostic device 200 in this way, it is possible to prevent the processing load on the first ultrasound diagnostic device 100 from becoming excessive and causing rapid battery consumption.

[0065] If it is determined in S202 that the first ultrasound diagnostic device 100 should perform a diagnostic process, the first diagnostic processing unit 130 performs the diagnostic process (S203). Subsequently, the first diagnostic processing unit 130 outputs the diagnostic result to the display control unit 160 and proceeds to S104 in Figure 10.

[0066] On the other hand, if it is not determined in S202 that the first ultrasound diagnostic device 100 should perform the diagnostic process, the determination unit 140 requests the second ultrasound diagnostic device 200 to perform the diagnostic process (S204). Specifically, the determination unit 140 controls the first communication unit 110 to send the diagnostic process request to the second ultrasound diagnostic device 200. The diagnostic process request includes the model ID of the trained model used to perform the diagnostic process and the ultrasound image. The second diagnostic processing unit 230 of the second ultrasound diagnostic device 200 performs multiple diagnostic processes in parallel based on the ultrasound image using multiple trained models stored in the second storage unit 290, in response to the diagnostic process request received from the first ultrasound diagnostic device 100. The second diagnostic processing unit 230 also controls the second communication unit 210 to send the diagnostic result to the first ultrasound diagnostic device 100. Subsequently, the first communication unit 110 of the first ultrasound diagnostic device 100 outputs the diagnostic results received from the second ultrasound diagnostic device 200 to the display control unit 160, and the process proceeds to S104 in Figure 10.

[0067] As described above, the ultrasound diagnostic system 10 comprises an ultrasound probe 50 and a first ultrasound diagnostic device 100. The ultrasound probe 50 transmits ultrasound to a subject (living body P) and generates a probe signal based on the reflected wave from the subject. The first ultrasound diagnostic device 100 is connected to the ultrasound probe 50. The first ultrasound diagnostic device 100 comprises an ultrasound image generation unit 120, a first storage unit 190, a first diagnostic processing unit 130, and a display control unit 160. The ultrasound image generation unit 120 generates an ultrasound image based on the probe signal received from the ultrasound probe 50. The first storage unit 190 stores multiple trained models with different characteristics targeting the same disease, which are used for the diagnostic processing of the subject (living body P). The first diagnostic processing unit 130 uses the multiple trained models to execute multiple diagnostic processes based on ultrasound images in parallel. The display control unit 160 switches between a first mode in which all of the multiple diagnostic results obtained from multiple diagnostic processes are displayed on the display unit 180, and a second mode in which one or more of the multiple diagnostic results are not displayed on the display unit 180. As a result, the ultrasound diagnostic system 10 of this embodiment can effectively display to the user multiple diagnostic results from multiple trained models with different characteristics that target the same disease.

[0068] Although embodiments for carrying out the present invention have been described above using examples, the present invention is not limited in any way to these embodiments, and various modifications and substitutions can be made without departing from the spirit of the present invention. [Explanation of symbols]

[0069] 10 Ultrasound diagnostic systems 50 Ultrasound probes 100 First Ultrasound Diagnostic Device 110 First Communications Department 120 Ultrasound Image Generation Unit 130 First Diagnostic Processing Unit 140 Judgment section 150 Decision Section 160 Display Control Unit 170 Input section 180 Display section 190 1st memory section 200 Second Ultrasound Diagnostic Device 210 Second Communications Department 230 Second Diagnostic Processing Unit 290 2nd memory section

Claims

1. An ultrasonic probe that transmits ultrasound to a subject and generates a probe signal based on the reflected wave from the subject, A first ultrasound diagnostic device connected to the aforementioned ultrasound probe, An ultrasound diagnostic system comprising, The first ultrasound diagnostic device is An ultrasonic image generation unit generates an ultrasonic image based on the probe signal received from the ultrasonic probe, A first storage unit that stores multiple trained models with different characteristics targeting the same disease, which are used for the diagnostic processing of the subject, A first diagnostic processing unit that uses the aforementioned multiple trained models to execute multiple diagnostic processes based on the ultrasound image in parallel, The system includes a display control unit that switches between a first mode in which all of the multiple diagnostic results obtained by the multiple diagnostic processes are displayed on the display unit, and a second mode in which one or more of the multiple diagnostic results are not displayed on the display unit. Ultrasound diagnostic system.

2. The display control unit switches between the first mode and the second mode based on user information, which is information about the user using the ultrasound diagnostic system. The ultrasound diagnostic system according to claim 1.

3. The user information includes a learning level indicating the user's learning progress regarding diagnosis using ultrasound images. The display control unit sets the first mode when the user's learning level is less than the first threshold, and sets the second mode when the user's learning level is equal to or greater than the first threshold. The ultrasound diagnostic system according to claim 2.

4. The user information includes the user's proficiency with respect to the ultrasound diagnostic system. The display control unit sets the first mode when the user's skill level is less than the second threshold, and sets the second mode when the user's skill level is equal to or greater than the second threshold. The ultrasound diagnostic system according to claim 2.

5. The user information includes information indicating whether or not the user is a certified physician. The display control unit sets the first mode if the user is a certified physician, and sets the second mode if the user is not a certified physician. The ultrasound diagnostic system according to claim 2.

6. The user information includes information indicating the user's area of ​​expertise as a physician, The display control unit sets the first mode if the disease targeted by the plurality of diagnostic processes is not a disease related to the specialty field, and sets the second mode if the disease targeted by the plurality of diagnostic processes is a disease related to the specialty field. The ultrasound diagnostic system according to claim 2.

7. The display control unit overlays the ultrasound image with the location where the disease is likely to occur and the degree of certainty of the disease, which is the accuracy, and displays these on the display unit as diagnostic results. The ultrasound diagnostic system according to claim 1.

8. The system further comprises a second ultrasound diagnostic device capable of communicating with the first ultrasound diagnostic device via a network, The first ultrasound diagnostic device is The device further comprises a first communication unit that transmits the aforementioned ultrasound image to the second ultrasound diagnostic device, The second ultrasound diagnostic device is A second communication unit that receives the ultrasound image from the first ultrasound diagnostic device, A second storage unit that stores the aforementioned multiple trained models, The system includes a second diagnostic processing unit that performs multiple diagnostic processes based on the ultrasound image in parallel using the multiple trained models. The ultrasound diagnostic system according to claim 1.

9. The first ultrasound diagnostic apparatus further includes a determination unit that determines whether to perform each of the plurality of diagnostic processes using the first ultrasound diagnostic apparatus or the second ultrasound diagnostic apparatus. The ultrasound diagnostic system according to claim 8.

10. The determination unit determines that, among the plurality of diagnostic processes, the diagnostic process for obtaining a diagnostic result displayed in the second mode will be performed by the first ultrasound diagnostic device, and the diagnostic process for obtaining a diagnostic result not displayed in the second mode will be performed by the second ultrasound diagnostic device. The ultrasound diagnostic system according to claim 9.

11. An ultrasound diagnostic apparatus connected to an ultrasound probe that transmits ultrasound waves to a subject and generates a probe signal based on the reflected waves from the subject, An ultrasonic image generation unit generates an ultrasonic image based on the probe signal received from the ultrasonic probe, A storage unit that stores multiple trained models with different characteristics targeting the same disease, which are used for the diagnostic processing of the subject, A diagnostic processing unit that uses the aforementioned multiple trained models to execute multiple diagnostic processes based on the ultrasound image in parallel, A display control unit that switches between a first mode in which all of the multiple diagnostic results obtained by the multiple diagnostic processes are displayed on the display unit, and a second mode in which one or more of the multiple diagnostic results are not displayed on the display unit. An ultrasound diagnostic device equipped with the following features.

12. An ultrasound diagnostic device connected to an ultrasound probe that transmits ultrasound waves to a subject and generates a probe signal based on the reflected waves from the subject, Based on the probe signal received from the ultrasound probe, an ultrasound image is generated. Multiple trained models with different characteristics targeting the same disease are stored in the memory unit for use in the diagnostic processing of the subject. Using the aforementioned multiple trained models, multiple diagnostic processes based on the ultrasound images are executed in parallel. A first mode in which all of the multiple diagnostic results obtained by the multiple diagnostic processes are displayed on the display unit, and a second mode in which one or more of the multiple diagnostic results are not displayed on the display unit, can be switched between. Ultrasound diagnostic methods.

13. An ultrasound diagnostic device connected to an ultrasound probe that transmits ultrasound waves to a subject and generates a probe signal based on the reflected waves from the subject, Based on the probe signal received from the aforementioned ultrasound probe, an ultrasound image is generated. The memory unit stores multiple trained models with different characteristics targeting the same disease, which are used in the diagnostic processing of the subject. Using the aforementioned multiple trained models, multiple diagnostic processes based on the ultrasound images are executed in parallel. A first mode in which all of the multiple diagnostic results obtained by the multiple diagnostic processes are displayed on the display unit, and a second mode in which one or more of the multiple diagnostic results are not displayed on the display unit, are to be switched between. program.

Images