Ultrasound diagnostic system and method for controlling the ultrasound diagnostic system

The ultrasound diagnostic system addresses artifact management by using a trained model to detect and notify artifact location and cause, improving user capability to reduce and diagnose effectively.

JP7848020B2Active Publication Date: 2026-04-20FUJIFILM CORP
View PDF 11 Cites 0 Cited by

Patent Information

Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
FUJIFILM CORP
Filing Date
2022-03-24
Publication Date
2026-04-20

AI Technical Summary

Technical Problem

Existing ultrasound diagnostic systems struggle to effectively identify and manage artifacts, which can interfere with anatomical structure observation and diagnosis, particularly for users lacking expertise in artifact causes and appropriate reduction methods.

Method used

An ultrasound diagnostic system equipped with an image input unit, determination unit, and notification unit, utilizing a trained model to detect artifacts and notify their location and cause, along with methods for reduction, regardless of user skill level.

Benefits of technology

Enables users to easily and accurately identify and manage artifacts, facilitating effective diagnosis by providing location, cause, and reduction methods, enhancing user proficiency regardless of expertise.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 0007848020000001
    Figure 0007848020000001
  • Figure 0007848020000002
    Figure 0007848020000002
  • Figure 0007848020000003
    Figure 0007848020000003
Patent Text Reader

Abstract

To provide an ultrasonic diagnostic system which can properly deal with a case where an artifact occurs regardless of a level of skill of a user, and a control method of the ultrasonic diagnostic system.SOLUTION: An ultrasonic diagnostic system comprises: an image input unit (11) which inputs an ultrasonic image; a determination unit (16) which determines the presence / absence of the occurrence of an artifact in an ultrasonic image input to the image input unit by using a learned model learned with learning data in which the plurality of ultrasonic images capturing artifacts are associated with the occurrence cause of each artifact; and a notification unit (17) which notifies of the occurrence spot and occurrence cause of an artifact in the ultrasonic image when the determination unit (16) determines that an artifact occurs.SELECTED DRAWING: Figure 1
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to an ultrasonic diagnostic system for discriminating artifacts and a control method for an ultrasonic diagnostic system.

Background Art

[0002] Conventionally, an ultrasonic diagnostic system that obtains an ultrasonic image by transmitting ultrasonic waves from a so-called ultrasonic probe into a subject and receiving ultrasonic echoes from within the subject is known. Artifacts, which are so-called images, may be captured in the ultrasonic image. It is known that artifacts are generated by various factors. For example, an artifact may be generated when an ultrasonic beam called a side lobe, which is radiated radially from an oscillator array composed of a plurality of ultrasonic oscillators, is reflected by a reflector within the subject.

[0003] Such artifacts may interfere with the observation of the anatomical structure of the subject shown in the ultrasonic image. In this case, reduction of artifacts in the ultrasonic image is desired. However, since artifacts have various generation factors depending on their types, there are also various countermeasures for reducing artifacts. Therefore, for example, as disclosed in Patent Documents 1 and 2, techniques for specifying an artifact in an ultrasonic image as one of a plurality of defined types have been invented. Patent Document 1 discloses specifying an artifact in an ultrasonic image as one of a plurality of types, such as whether it represents a shadow of an anatomical structure within the subject or represents gas accumulated within the subject. Patent Document 2 discloses specifying an artifact in an ultrasonic image as one of a plurality of types, such as whether it is caused by so-called multiple reflections or represents a shadow of an anatomical structure.

Prior Art Documents

Patent Documents

[0004]

Patent Document 1

[0005] Artifacts can sometimes interfere with the observation of anatomical structures of a subject in ultrasound images, but on the other hand, they can also provide useful information for diagnosing the subject's medical condition. Furthermore, in order to reduce artifacts through appropriate operations such as changing the orientation and tilt of the ultrasound probe, and to utilize information about the type of artifact in the diagnosis of a subject, it was necessary for users, such as physicians, to be familiar with the causes of artifacts. Patent documents 1 and 2 identify artifacts in ultrasound images as one of several defined types, but even after confirming the identified type of artifact, it was sometimes difficult for users to grasp, for example, the detailed cause of the artifact. In particular, it was difficult for inexperienced users to take appropriate measures to reduce artifacts and to effectively utilize artifacts for diagnosis.

[0006] This invention was made to solve the problems of the past, and aims to provide an ultrasound diagnostic system and a control method for the ultrasound diagnostic system that can appropriately deal with artifacts when they occur, regardless of the user's skill level. [Means for solving the problem]

[0007] To achieve the above objective, the ultrasound diagnostic system according to the present invention is characterized by comprising: an image input unit for inputting ultrasound images; a determination unit for determining whether or not artifacts have occurred in the ultrasound images input to the image input unit by using a trained model trained with training data that links multiple ultrasound images in which artifacts are captured with the causes of each artifact; and a notification unit for notifying the location and cause of the artifact in the ultrasound image when the determination unit determines that an artifact has occurred.

[0008] The ultrasound diagnostic system includes a data storage unit that stores the principle of artifact generation and methods for resolving artifacts based on that principle. The notification unit can also notify the cause of the artifact, along with the artifact resolving method stored in the data storage unit. The data storage unit stores instances where artifacts were effectively utilized in diagnosis, and the notification unit, when notifying the cause of an artifact, can also notify the instances where artifacts stored in the data storage unit were effectively utilized in diagnosis.

[0009] The ultrasound diagnostic system comprises a diagnostic device including an image input unit, a judgment unit, and a notification unit, and the data storage unit can be located within the diagnostic device. Furthermore, the ultrasound diagnostic system includes a diagnostic device that includes an image input unit, a judgment unit, and a notification unit, and a server connected to the diagnostic device via a network, and the data storage unit can also be located on the server. Furthermore, the ultrasound diagnostic system comprises a diagnostic device including a notification unit, and a server connected to the diagnostic device via a network, which includes an image input unit and a judgment unit, and the data storage unit may be located on the server.

[0010] The ultrasound diagnostic system includes an input device for specifying a region of interest based on the ultrasound image input to the image input unit, and a determination unit can determine whether or not artifacts occur in the region of interest. The image input unit may include an ultrasonic probe having a transducer array, and an image acquisition unit that transmits and receives ultrasonic beams from the transducer array to a subject and acquires an ultrasonic image based on the received signal output from the transducer array. An ultrasound diagnostic system may include a probe detection unit that detects the orientation and tilt of the ultrasound probe, and a guide unit that guides the change in the orientation and tilt of the ultrasound probe to reduce artifacts based on the orientation and tilt of the ultrasound probe detected by the probe detection unit.

[0011] The probe detection unit can consist of a probe sensor placed on the ultrasonic probe. Furthermore, the probe detection unit may also include an optical camera that captures an optical image of the ultrasonic probe, and an optical image analysis unit that detects the orientation and tilt of the ultrasonic probe by analyzing the optical image acquired by the optical camera.

[0012] The control method for an ultrasound diagnostic system according to the present invention is characterized by inputting an ultrasound image, using a trained model that has been trained on training data linking multiple ultrasound images in which artifacts are captured with the causes of each artifact, determining whether or not artifacts are present in the input ultrasound image, and if it is determined that artifacts are present, notifying the location and cause of the artifacts in the ultrasound image. [Effects of the Invention]

[0013] According to the present invention, since an ultrasonic diagnostic system includes an image input unit that inputs ultrasonic images, a determination unit that determines the presence or absence of artifacts in the ultrasonic images input to the image input unit by using a learned model learned from learning data in which a plurality of ultrasonic images with artifacts incorporated therein and the causes of the respective artifacts are associated with each other, and a notification unit that notifies the location and cause of the artifacts in the ultrasonic images when the determination unit determines that an artifact has occurred, it is possible to appropriately respond when an artifact occurs regardless of the user's proficiency level.

Brief Description of the Drawings

[0014] [Figure 1] It is a block diagram showing the configuration of the diagnostic apparatus in Embodiment 1 of the present invention. [Figure 2] It is a flowchart showing the operation of the diagnostic apparatus in Embodiment 1 of the present invention. [Figure 3] It is a block diagram showing the configuration of the ultrasonic diagnostic system according to Embodiment 2 of the present invention. [Figure 4] It is a block diagram showing the configuration of the transmission / reception circuit in Embodiment 2 of the present invention. [Figure 5] It is a block diagram showing the configuration of the image generation unit in Embodiment 2 of the present invention. [Figure 6] It is a block diagram showing the configuration of the ultrasonic diagnostic system according to Embodiment 3 of the present invention. [Figure 7] It is a block diagram showing the configuration of the ultrasonic diagnostic system according to Embodiment 4 of the present invention. [Figure 8] It is a block diagram showing the configuration of the ultrasonic diagnostic system according to Embodiment 5 of the present invention. [Figure 9] It is a block diagram showing the configuration of the ultrasonic diagnostic system according to Embodiment 6 of the present invention.

Modes for Carrying Out the Invention

[0015] Hereinafter, embodiments of this invention will be described based on the accompanying drawings. The description of the constituent elements described below is based on representative embodiments of the present invention, but the present invention is not limited to such embodiments. In this specification, a numerical range represented by "~" means a range including the numerical values described before and after "~" as the lower limit value and the upper limit value. In this specification, "identical" and "the same" shall include the error ranges generally acceptable in the technical field.

[0016] Embodiment 1 Fig. 1 shows the configuration of an ultrasonic diagnostic system according to Embodiment 1 of the present invention. The ultrasonic diagnostic system of Embodiment 1 is constituted by a diagnostic device 1. The diagnostic device 1 displays ultrasonic images obtained from an external device (not shown) such as a so-called ultrasonic probe or a so-called ultrasonic diagnostic device, and an external memory (not shown). The diagnostic device 1 is used, for example, for a user such as an examiner to confirm an ultrasonic image taken in real time by an ultrasonic probe, or for a user such as a doctor to observe the ultrasonic image and diagnose a subject.

[0017] The diagnostic device 1 includes an image input unit 11, to which a display control unit 12 and a monitor 13 are sequentially connected. An image memory 14 is also connected to the image input unit 11. The image memory 14 is connected to the display control unit 12. The diagnostic device 1 also includes a data storage unit 15. A determination unit 16 is connected to the image memory 14 and the data storage unit 15. A notification unit 17 is connected to the determination unit 16. The notification unit 17 is connected to the display control unit 12.

[0018] In addition, a device control unit 18 is connected to the display control unit 12, the image memory 14, the data storage unit 15, the determination unit 16, and the notification unit 17. An input device 19 is connected to the device control unit 18. Further, the display control unit 12, the determination unit 16, the notification unit 17, and the device control unit 18 constitute a processor 20 for the diagnostic device 1.

[0019] The image input unit 11 inputs ultrasound images to the diagnostic device 1 from an external device (not shown), such as an external ultrasound probe or ultrasound diagnostic device, or from an external memory (not shown). The image input unit 11 includes, for example, connection terminals for wired connection via a communication cable (not shown) to an external device (not shown), such as an ultrasound probe or ultrasound diagnostic device, or to an external recording medium, or an antenna for wireless connection to an ultrasound probe, an external device, or an external recording medium.

[0020] Examples of external memory connected to the image input unit 11 include recording media such as flash memory, HDD (Hard Disk Drive), SSD (Solid State Drive), FD (Flexible Disk), MO disk (Magneto-Optical disk), MT (Magnetic Tape), RAM (Random Access Memory), CD (Compact Disc), DVD (Digital Versatile Disc), SD card (Secure Digital card), or USB memory (Universal Serial Bus memory).

[0021] The display control unit 12, under the control of the device control unit 18, performs predetermined processing on the ultrasound image or the like input by the image input unit 11 and displays it on the monitor 13. The monitor 13 displays various information under the control of the display control unit 12. The monitor 13 may include, for example, a display device such as an LCD (Liquid Crystal Display) or an organic EL display (Organic Electroluminescence Display).

[0022] The image memory 14 is a memory that stores ultrasound images input by the image input unit 11 under the control of the device control unit 18. The ultrasound images stored in the image memory 14 are read out under the control of the device control unit 18 and sent to the determination unit 16. Alternatively, the ultrasound images stored in the image memory 14 can be read out under the control of the device control unit 18 and sent to the display control unit 12 for display on the monitor 13. For example, the image memory 14 can be a recording medium such as flash memory, HDD, SSD, FD, MO disk, MT, RAM, CD, DVD, SD card, or USB memory.

[0023] Incidentally, ultrasound images can sometimes contain what are called artifacts. Artifacts are known to occur due to various factors. For example, artifacts can occur when the ultrasound beam, known as a side lobe, which is transmitted radially from a transducer array composed of multiple ultrasound transducers, is reflected by a reflector within the subject.

[0024] Furthermore, so-called linear scans and sector scans are generally known as ultrasound scanning methods. Artifacts generated by side lobes are known to have different shapes depending on the scanning method. For example, when a linear scan is performed, artifacts generated by side lobes often have a shape that curves toward the deeper part at both ends of the ultrasound image in the lateral direction. For example, when a sector scan is performed, artifacts generated by side lobes often have a shape that curves toward the shallower part at both ends of the ultrasound image in the lateral direction. Here, the lateral direction of the ultrasound image refers to the direction perpendicular to the depth direction in the ultrasound image.

[0025] Such artifacts can interfere with the observation of the anatomical structures of the subject in ultrasound images. In this case, reducing artifacts in ultrasound images requires appropriate measures depending on the location and cause of the artifact. For example, if an artifact is caused by the reflection of a side lobe from a reflector within the subject, the artifact can sometimes be reduced by changing at least one of the orientation and tilt of the ultrasound probe in contact with the subject so that the side lobe does not reflect from the reflector causing the artifact.

[0026] Here, changing the orientation of the ultrasound probe means rotating the ultrasound probe so as to rotate the tomographic plane of the subject being scanned, while keeping the position of the so-called acoustic lens of the ultrasound probe constant on the subject's body surface. Changing the tilt of the ultrasound probe means tilting the ultrasound probe so as to tilt the tomographic plane of the subject being scanned, using the position of the acoustic lens of the ultrasound probe on the subject's body surface as a pivot point.

[0027] Furthermore, artifacts can sometimes provide useful information for diagnosing the patient's medical condition. For example, if an ultrasound image of a patient's lung clearly shows an artifact known as an A-line, caused by multiple reflections between the pleura and the ultrasound probe, pneumothorax is suspected as the patient's medical condition. Similarly, if an ultrasound image of a patient's lung shows a linear artifact extending roughly along the depth direction, pneumonia or pulmonary edema is suspected as the patient's medical condition. In addition, if an ultrasound image of a patient's liver shows a linear artifact extending roughly along the depth direction, cirrhosis or fatty liver disease is suspected as the patient's medical condition. Thus, by examining artifacts in ultrasound images, users such as physicians can accurately diagnose the patient's medical condition. However, since linear artifacts can also be caused by wrinkles in the patient's skin, for example, users usually need to be familiar with the location and cause of artifacts in order to make an accurate diagnosis.

[0028] The data storage unit 15 is a memory that pre-stores the generation principle of each artifact, a method for resolving the artifact based on the generation principle, and examples of when the artifact was effectively utilized for diagnosis, for multiple different types of artifacts. The generation principle of the artifact and the method for resolving the artifact stored in the data storage unit 15 are read under the control of the device control unit 18 and sent to the determination unit 16. Here, the data storage unit 15 can be, for example, a flash memory, HDD, SSD, FD, MO disk, MT, RAM, CD, DVD, SD card, or recording media such as a USB memory.

[0029] The determination unit 16 determines whether or not artifacts are present in the ultrasound image input to the image input unit 11 by using a trained model that has been trained on training data that links multiple ultrasound images in which artifacts are captured with the cause of each artifact.

[0030] The determination unit 16 can use pre-trained models that follow algorithms such as ResNet (Residual Neural Network), DenseNet (Dense Convolutional Network), AlexNet, Baseline, Batch Normalization, Dropout Regularization, NetWidth Search, or NetDepth Search. The determination unit 16 can also use models that follow these algorithms in appropriate combinations.

[0031] Furthermore, the determination unit 16 estimates the location and cause of artifacts occurring in the ultrasound image by using a trained model. For example, the determination unit 16 estimates that an artifact having a shape in which both ends in the lateral direction of the ultrasound image are curved toward the depth is an artifact caused by the side lobes reflecting off a reflector when a linear scan is performed, and can estimate the location of its occurrence, i.e., the position of the reflector to which the side lobes are reflected.

[0032] The determination unit 16 sends the estimated location and cause of the artifact to the notification unit 17. The determination unit 16 also reads the artifact generation principle and artifact elimination method corresponding to the estimated cause of the artifact from the data storage unit 15 and sends them to the notification unit 17.

[0033] If the determination unit 16 determines that an artifact has occurred, the notification unit 17 notifies the user of the location and cause of the artifact estimated by the determination unit 16. The notification unit 17 can notify the user, for example, by displaying a message on the monitor 13 indicating the location and cause of the artifact. The notification unit 17 can display the message on the monitor 13 using text, still images, videos, or a combination thereof.

[0034] Furthermore, when the notification unit 17 notifies the user of the cause of the artifact, it can also notify the user of methods for resolving the artifact based on the artifact generation principle stored in the data storage unit 15. In addition, when the notification unit 17 notifies the user of the cause of the artifact, it can also notify the user of examples stored in the data storage unit 15 in which the artifact has been effectively utilized for diagnosis.

[0035] The input device 19 receives input operations from the user and sends the input information to the device control unit 18. The input device 19 is composed of, for example, a keyboard, mouse, trackball, touchpad, and touch panel, or other devices for the inspector to perform input operations. The device control unit 18 controls each part of the diagnostic device according to a pre-recorded program or the like.

[0036] The processor 20, which is composed of the display control unit 12, determination unit 16, notification unit 17, and device control unit 18 of the diagnostic device 1, consists of a CPU (Central Processing Unit) and a control program for causing the CPU to perform various processes. However, it may also be composed of an FPGA (Field Programmable Gate Array), a DSP (Digital Signal Processor), an ASIC (Application Specific Integrated Circuit), a GPU (Graphics Processing Unit), or other ICs (Integrated Circuits), or a combination thereof.

[0037] Furthermore, the display control unit 12, determination unit 16, notification unit 17, and device control unit 18 of the processor 20 can be partially or entirely integrated into a single CPU or the like.

[0038] Next, an example of the operation of the diagnostic device 1 in Embodiment 1 will be explained using the flowchart in Figure 2.

[0039] First, in step S1, an ultrasound image is input to the image input unit 11 from an external ultrasound probe (not shown), an external device (not shown), or an external memory (not shown). The input ultrasound image is displayed on the monitor 13 via the display control unit 12. The input ultrasound image is also stored in the image memory 14.

[0040] Next, in step S2, the determination unit 16 reads the ultrasound image stored in the image memory 14 based on the user's input operation via the input device 19, or automatically, and performs a process to determine whether or not an artifact has occurred in the ultrasound image. At this time, the determination unit 16 performs a process to determine whether or not an artifact has occurred using a trained model that has been trained on training data, which is linked to multiple ultrasound images in which artifacts have been captured and the cause of each artifact.

[0041] In step S3, the determination unit 16 outputs a determination result indicating whether or not artifacts have occurred in the ultrasound image. If the determination result indicates that no artifacts have occurred, the process returns to step S1. When an ultrasound image is input to the image input unit 11, the processing in steps S1 to S3 is performed again.

[0042] If the determination result in step S3 indicates that an artifact has occurred, the process proceeds to step S4. At this point, the determination unit 16 uses the trained model to estimate the location and cause of the artifact captured in the ultrasound image.

[0043] Normally, for a user to identify an artifact and estimate its location and cause, the user needs to be familiar with artifacts. However, according to the determination unit 16, the location and cause of the artifact can be easily and automatically estimated regardless of the user's level of expertise.

[0044] In step S4, the notification unit 17 notifies the user of the location and cause of the artifact determined in step S3 by displaying a message on the monitor 13. This allows the user, regardless of their skill level, to easily and accurately understand the location and cause of the artifact. Once the process in step S4 is completed, the operation of the diagnostic device 1 according to the flowchart in Figure 2 is finished.

[0045] As described above, according to the diagnostic device 1 in Embodiment 1, the determination unit 16 determines whether or not artifacts occur in the ultrasound image input to the image input unit 11 by using a trained model, estimates the location and cause of the artifact, and the notification unit 17 notifies the user of the location and cause of the artifact. Therefore, regardless of the user's skill level, they can easily and accurately grasp the location and cause of the artifact and take appropriate measures such as reducing the artifact or diagnosing the patient's condition based on the artifact.

[0046] Furthermore, if the determination result in step S3 indicates that an artifact has occurred, the determination unit 16 can read a method for resolving the artifact corresponding to the cause of the artifact from the data storage unit 15 and send it to the notification unit 17. In this case, in step S4, the notification unit 17 can inform the user of the cause of the artifact along with the method for resolving the artifact. For example, if an external ultrasound probe (not shown) is connected to the image input unit 11, the user can resolve the artifact by changing the orientation or tilt of the ultrasound probe, etc., by referring to the method for resolving the artifact notified by the notification unit 17.

[0047] Furthermore, if the determination result in step S3 indicates that an artifact has occurred, the determination unit 16 can read from the data storage unit 15 examples of cases where the artifact was effectively utilized in diagnosis, corresponding to the cause of the artifact, and send them to the notification unit 17. In this case, in step S4, the notification unit 17 can inform the user of the cause of the artifact, along with the examples of cases where the artifact was effectively utilized in diagnosis. Users such as doctors can then refer to the examples notified by the notification unit 17 to accurately diagnose the patient's condition.

[0048] Furthermore, while it is explained that the notification unit 17 notifies the user of the location and cause of the artifact by displaying a message on the monitor 13, the method of notification to the user by the notification unit 17 is not particularly limited. For example, if the diagnostic device 1 is equipped with a speaker (not shown), the notification unit 17 can notify the user by emitting sound through the speaker.

[0049] Furthermore, while it has been explained that the determination unit 16 determines whether or not artifacts occur in the entire ultrasound image, the determination unit 16 can also determine whether or not artifacts occur in a region of interest specified within the ultrasound image, for example, through user input via the input device 19. By determining whether or not artifacts occur in a region of interest, the determination unit 16 can reduce the computational load and determine whether or not artifacts occur more quickly than when determining whether or not artifacts occur from the entire ultrasound image.

[0050] Embodiment 2 The ultrasound diagnostic system of the present invention may also include an ultrasound probe connected to the diagnostic device 1.

[0051] Figure 3 shows the configuration of an ultrasound diagnostic system according to Embodiment 2 of the present invention. The ultrasound diagnostic system of Embodiment 2 is an ultrasound diagnostic system configured with the diagnostic device 1 shown in Figure 1, but with a diagnostic device 1A instead of the diagnostic device 1, and an ultrasound probe 3A connected to the diagnostic device 1A added.

[0052] The ultrasonic probe 3A includes a transducer array 31 and a transmitting / receiving circuit 32 connected to the transducer array 31.

[0053] Diagnostic device 1A is the same as diagnostic device 1 in embodiment 1, but with an image generation unit 41 instead of an image input unit 11, and a device control unit 18A instead of a device control unit 18. In diagnostic device 1A, the image generation unit 41 is connected to the transmit / receive circuit 32 of the ultrasound probe 3A. Here, the ultrasound probe 3A and the image generation unit 41 constitute the image input unit 11A. The transmit / receive circuit 32 and the image generation unit 41 constitute the image acquisition unit 42. The image generation unit 41 is also connected to the display control unit 12, the image memory 14, and the device control unit 18A. The device control unit 18A is also connected to the transmit / receive circuit 32 of the ultrasound probe 3A. The image generation unit 41, the display control unit 12, the determination unit 16, the notification unit 17, and the device control unit 18A constitute the processor 20A for diagnostic device 1A.

[0054] The transducer array 31 of the ultrasonic probe 3A has a plurality of ultrasonic transducers arranged in one or two dimensions. Each of these ultrasonic transducers transmits ultrasound according to a drive signal supplied from the transmitting / receiving circuit 32, and also receives ultrasonic echoes from the subject and outputs a signal based on the ultrasonic echoes. Each ultrasonic transducer is constructed by forming electrodes at both ends of a piezoelectric body made of, for example, a piezoelectric ceramic represented by PZT (Lead Zirconate Titanate), a polymer piezoelectric element represented by PVDF (Poly Vinylidene Di Fluoride), or a piezoelectric single crystal represented by PMN-PT (Lead Magnesium Niobate-Lead Titanate).

[0055] The transmitting and receiving circuit 32 transmits ultrasonic waves from the transducer array 31 and generates a sound line signal based on the received signal acquired by the transducer array 31, under the control of the device control unit 18A. As shown in Figure 4, the transmitting and receiving circuit 32 has a pulser 51 connected to the transducer array 31, and an amplifier 52, an AD (Analog to Digital) converter 53, and a beamformer 54 that are sequentially connected in series from the transducer array 31.

[0056] The pulser 51 includes, for example, multiple pulse generators, and based on a transmission delay pattern selected according to a control signal from the device control unit 18A, it supplies each drive signal to the multiple ultrasonic transducers of the transducer array 31, adjusting the delay amount, so that the ultrasonic waves transmitted from the transducers form an ultrasonic beam. In this way, when a pulsed or continuous wave voltage is applied to the electrodes of the ultrasonic transducers of the transducer array 31, the piezoelectric material expands and contracts, generating pulsed or continuous wave ultrasonic waves from each ultrasonic transducer, and an ultrasonic beam is formed from the combined wave of these ultrasonic waves.

[0057] The transmitted ultrasonic beam is reflected from a target, such as a part of the subject, and propagates toward the transducer array 31 of the ultrasonic probe 3A. The ultrasonic echo propagating toward the transducer array 31 is received by each ultrasonic transducer that makes up the transducer array 31. At this time, each ultrasonic transducer that makes up the transducer array 31 expands and contracts upon receiving the propagating ultrasonic echo, generating a received signal which is an electrical signal, and outputs these received signals to the amplification unit 52.

[0058] The amplification unit 52 amplifies the signals input from each ultrasonic transducer constituting the transducer array 31 and transmits the amplified signals to the AD conversion unit 53. The AD conversion unit 53 converts the signals transmitted from the amplification unit 52 into digital received data. The beamformer 54 performs so-called receive focus processing by adding each received data received from the AD conversion unit 53 with a corresponding delay. Through this receive focus processing, each received data converted by the AD conversion unit 53 is phase-corrected and added together, and a sound ray signal with a focused ultrasonic echo is obtained.

[0059] As shown in Figure 5, the image generation unit 41 has a configuration in which a signal processing unit 55, a DSC (Digital Scan Converter) 56, and an image processing unit 57 are connected in series in sequence.

[0060] The signal processing unit 55 receives the sound line signal from the transmitting / receiving circuit 32, applies a sound velocity value set by the device control unit 18A to correct for attenuation due to distance according to the depth of the ultrasonic reflection position, and then performs envelope detection processing to generate a B-mode image signal, which is tomographic image information of the tissue within the subject.

[0061] The DSC56 converts the B-mode image signal generated by the signal processing unit 55 into an image signal that follows the scanning method of a normal television signal (raster conversion). The image processing unit 57 performs various necessary image processing, such as gradation processing, on the B-mode image signal input from the DSC 56, and then sends the B-mode image signal to the display control unit 12 and the image memory 14. Hereafter, the B-mode image signal processed by the image processing unit 57 will be referred to as an ultrasonic image.

[0062] The ultrasound images of multiple frames continuously generated by the image generation unit 41 are sequentially displayed on the monitor 13 and stored in the image memory 14. The determination unit 16 reads the ultrasound images from the image memory 14 and uses a trained model to determine whether or not artifacts have occurred. If it is determined that artifacts have occurred, the determination unit 16 uses the trained model to estimate the location and cause of the artifacts. The notification unit 17 notifies the user of the location and cause of the artifacts estimated by the determination unit 16, for example, by displaying a message on the monitor 13.

[0063] Thus, according to the ultrasound diagnostic system of Embodiment 2 of the present invention, the user can easily change the orientation and tilt of the ultrasound probe 3A, for example, to eliminate artifacts in the ultrasound image by confirming the location and cause of the artifacts reported by the notification unit 17. Furthermore, by confirming the location and cause of the artifacts reported by the notification unit 17, the user can also easily and effectively utilize the artifact information to diagnose the subject.

[0064] Furthermore, the notification unit 17 can also notify the user of artifact generation principles and methods for eliminating artifacts based on those principles, or examples of cases where artifacts were effectively utilized in diagnosis, which are pre-stored in the data storage unit 15. This allows the user to more easily change the orientation and tilt of the ultrasound probe 3A to eliminate artifacts, and to more easily and effectively utilize artifact information while diagnosing the subject.

[0065] Although the image generation unit 41 is described as being provided in the diagnostic device 1A, it can also be provided in the ultrasound probe 3A instead. In this case, for example, the diagnostic device 1A is equipped with an image input unit 11, as in the diagnostic device 1 in Embodiment 1 shown in Figure 1, and the ultrasound image generated by the ultrasound probe 3A can be input to the image input unit 11.

[0066] Furthermore, if the determination unit 16 estimates that the reflection of side lobes from reflectors within the subject is the cause of the artifact, the device control unit 18A can, for example, change the beamforming conditions by controlling the transmitting / receiving circuit 32, thereby changing the tomographic plane of the subject being imaged, and thus transmit the ultrasonic beam from the transducer array 31 in a way that prevents the side lobes from reflecting from reflectors within the subject. The device control unit 18A can perform such processing based on instructions from the user via the input device 19, for example, or it can be done automatically. In this way, by having the device control unit 18A transmit the ultrasonic beam from the transducer array 31 in a way that prevents the side lobes from reflecting from reflectors within the subject, the user can easily reduce artifacts.

[0067] Embodiment 3 In embodiments 1 and 2, the user determines at least one of the orientation and tilt of the ultrasound probe to eliminate artifacts, but the ultrasound diagnostic system of the present invention can automatically guide the user to determine at least one of the orientation and tilt of the ultrasound probe to eliminate artifacts.

[0068] Figure 6 shows the configuration of an ultrasound diagnostic system according to Embodiment 3 of the present invention. The ultrasound diagnostic system of Embodiment 3 is the same as the ultrasound diagnostic system of Embodiment 2 shown in Figure 3, but with an ultrasound probe 3B instead of ultrasound probe 3A and a diagnostic device 1B instead of diagnostic device 1A.

[0069] The ultrasonic probe 3B is an ultrasonic probe 3A in Embodiment 2 with the addition of a probe sensor 33. Furthermore, the diagnostic device 1B is an ultrasonic probe 1A in Embodiment 2 with the addition of a guide unit 43 and a device control unit 18B instead of a device control unit 18A.

[0070] In the diagnostic device 1B, the guide unit 43 is connected to the determination unit 16. The guide unit 43 is connected to the probe sensor 33 of the ultrasonic probe 3B. The guide unit 43 is also connected to the display control unit 12 and the device control unit 18B. Furthermore, the image generation unit 41, display control unit 12, determination unit 16, notification unit 17, device control unit 18B, and guide unit 43 of the diagnostic device 1B constitute the processor 20B for the diagnostic device 1B.

[0071] The probe sensor 33 is a sensor device positioned on the ultrasonic probe 3B and detecting the orientation and tilt of the ultrasonic probe 3B. The probe sensor 33 can be configured to include, for example, a sensor device such as an acceleration sensor, a gyroscope, or a magnetic sensor.

[0072] The guide unit 43 guides the user to change at least one of the orientation and tilt of the ultrasonic probe 3B in order to reduce artifacts, based on the orientation and tilt of the ultrasonic probe 3B detected by the probe sensor 33 and the location and cause of the artifacts estimated by the determination unit 16. The guide unit 43 can guide the user to change at least one of the orientation and tilt of the ultrasonic probe 3B by displaying a message on the monitor 13, for example, such as "You may be able to reduce this artifact by rotating the probe orientation by 90 degrees and scanning."

[0073] Thus, according to the ultrasound diagnostic system of Embodiment 3 of the present invention, the guide unit 43 guides the user to change at least one of the orientation and inclination of the ultrasound probe 3B to reduce artifacts, based on the orientation and inclination of the ultrasound probe 3B detected by the probe sensor 33 and the location and cause of artifact occurrence estimated by the determination unit 16. Therefore, regardless of their skill level, the user can easily reduce artifacts by appropriately changing at least one of the orientation and inclination of the ultrasound probe 3B.

[0074] Although it has been explained that the guide unit 43 guides the user by displaying messages on the monitor 13, the method of guidance is not particularly limited. For example, if the diagnostic device 1B is equipped with a speaker (not shown), the guide unit 43 can guide the user by emitting sound through the speaker.

[0075] Embodiment 4 In Embodiment 3, a probe sensor 33 is provided as a probe detection unit for detecting the orientation and tilt of the ultrasonic probe 3B, but the configuration of the probe detection unit is not limited to this. The probe detection unit can also be configured to detect the orientation and tilt of the ultrasonic probe 3B by, for example, capturing an optical image of the ultrasonic probe 3B and analyzing the captured optical image.

[0076] Figure 7 shows the configuration of an ultrasound diagnostic system according to Embodiment 4 of the present invention. The ultrasound diagnostic system of Embodiment 4 is the same as the ultrasound diagnostic system of Embodiment 2 shown in Figure 3, but with a diagnostic device 1C instead of diagnostic device 1A and an optical camera 61 added.

[0077] The diagnostic device 1C is the same as the diagnostic device 1A in Embodiment 2, but with the addition of a guide unit 43 and an optical image analysis unit 44, and with a device control unit 18C instead of a device control unit 18A. The guide unit 43 in Embodiment 4 is the same as the guide unit 43 in Embodiment 3 shown in Figure 6.

[0078] In the diagnostic device 1C, the optical image analysis unit 44 is connected to the optical camera 61. The optical camera 61 and the optical image analysis unit 44 constitute the probe detection unit 45. The optical image analysis unit 44 is also connected to the device control unit 18C and the guide unit 43. Furthermore, the image generation unit 41, display control unit 12, determination unit 16, notification unit 17, device control unit 18C, guide unit 43, and optical image analysis unit 44 constitute the processor 20C for the diagnostic device 1C.

[0079] The probe detection unit 45, which consists of an optical camera 61 and an optical image analysis unit 44, detects the orientation and tilt of the ultrasonic probe 3A. The optical camera 61 includes an image sensor such as a so-called CCD (Charge Coupled Device) image sensor or a so-called CMOS (Complementary Metal-Oxide-Semiconductor) image sensor, and captures an image of the ultrasonic probe 3A to acquire an optical image of the ultrasonic probe 3A. The optical camera 61 sends the acquired optical image to the optical image analysis unit 44.

[0080] The optical image analysis unit 44 detects the orientation and tilt of the ultrasonic probe by analyzing the optical image acquired by the optical camera 61. For example, the optical image analysis unit 44 stores multiple template images of the ultrasonic probe 3A taken from various angles, and can search within the optical image using a so-called template matching method with these multiple template images to detect the ultrasonic probe 3A, and then detect the orientation and tilt of the detected ultrasonic probe 3A.

[0081] Furthermore, the optical image analysis unit 44 can also detect the orientation and tilt of the ultrasound probe 3A by using a trained model that has been trained using multiple template images of the ultrasound probe 3A taken from various angles as so-called training data. As this trained model, for example, a model that follows algorithms such as ResNet, DenseNet, AlexNet, Baseline, batch normalization, dropout regularization, NetWidth search, or NetDepth search can be used. The optical image analysis unit 44 can also use models that follow these algorithms in appropriate combinations.

[0082] The optical image analysis unit 44 transmits the orientation and tilt of the ultrasonic probe 3A, which it has detected in this manner, to the guide unit 43.

[0083] The guide unit 43 guides the user to change at least one of the orientation and inclination of the ultrasonic probe 3A to reduce artifacts, based on the orientation and inclination of the ultrasonic probe 3A detected by the optical image analysis unit 44 and the location and cause of artifact occurrence estimated by the determination unit 16.

[0084] Thus, according to the ultrasound diagnostic system of Embodiment 4 of the present invention, the optical image analysis unit 44 detects the orientation and tilt of the ultrasound probe 3A based on the optical image of the ultrasound probe 3A acquired by the optical camera 61, and the guide unit 43 guides the user to change at least one of the orientation and tilt of the ultrasound probe 3A so as to reduce artifacts, based on the orientation and tilt of the ultrasound probe 3A detected by the optical image analysis unit 44 and the location and cause of artifact occurrence estimated by the determination unit 16. In this way, similar to the ultrasound diagnostic system of Embodiment 3, the user can easily reduce artifacts by appropriately changing at least one of the orientation and tilt of the ultrasound probe 3A, regardless of their skill level.

[0085] Embodiment 5 In Embodiment 1, the diagnostic device 1 is equipped with a data storage unit 15, but the data storage unit 15 can also be equipped in, for example, a so-called server.

[0086] Figure 8 shows the configuration of an ultrasound diagnostic system according to Embodiment 5 of the present invention. The ultrasound diagnostic system of Embodiment 5 is an ultrasound diagnostic system configured with the diagnostic device 1 shown in Figure 1, but with a diagnostic device 1D instead of the diagnostic device 1, and an additional server 71 connected to the diagnostic device 1D via a network NW.

[0087] Diagnostic device 1D is the same as diagnostic device 1 in embodiment 1, but with the addition of a communication unit 46, a device control unit 18D instead of the device control unit 18, and the removal of the data storage unit 15. The communication unit 46 is connected to the server 71 via a network NW. The communication unit 46 is also connected to the determination unit 16 and the device control unit 18D. The display control unit 12, determination unit 16, notification unit 17, device control unit 18D, and communication unit 46 constitute the processor 20D for diagnostic device 1D.

[0088] The server 71 is, for example, a computer that can connect to a network NW and is located at a distance from the diagnostic device 1D. The server 71 includes a data storage unit 72.

[0089] The data storage unit 72, similar to the data storage unit 15 in Embodiment 1, is a memory that pre-stores, for multiple different types of artifacts, the generation principle of each artifact, a method for resolving the artifact based on the generation principle, and examples of when the artifact was effectively utilized for diagnosis. The artifact resolving methods and examples of effective artifact utilization stored in the data storage unit 72 are transmitted to the communication unit 46 via the network NW. For the data storage unit 72, for example, a flash memory, HDD, SSD, FD, MO disk, MT, RAM, CD, DVD, SD card, or recording media such as a USB memory can be used.

[0090] The communication unit 46 connects to the server 71 via a network NW and transmits and receives information between the diagnostic device 1D and the server 71. The communication unit 46 includes, for example, a connection terminal for wired connection to the network NW via a communication cable (not shown), or an antenna for wireless connection to the network NW.

[0091] The determination unit 16 sends to the notification unit 17 the method for resolving the artifact and the example of effective use of the artifact, which were sent from the server 71 to the communication unit 46, corresponding to the estimated cause of the artifact. The notification unit 17 informs the user of methods for resolving artifacts or examples of effective utilization of artifacts transmitted from the determination unit 16.

[0092] Thus, even when the data storage unit 72 is included in the server 71, as in the ultrasound diagnostic system of Embodiment 5 of the present invention, the notification unit 17 notifies the user of methods for eliminating artifacts or examples of effective use of artifacts, just as in the case where the data storage unit 15 is included in the diagnostic device 1 as in Embodiment 1. As a result, the user can easily reduce artifacts and effectively utilize them in the diagnosis of the subject.

[0093] Although the aspects of Embodiment 5 are described as being applicable to Embodiment 1, they can also be applied to Embodiments 2 to 4. That is, a server 71 can be provided in the ultrasound diagnostic systems of Embodiments 2 to 4 in the same manner as in the ultrasound diagnostic system of Embodiment 5.

[0094] Embodiment 6 In Embodiment 5, the image input unit 11 and the determination unit 16 are provided in the diagnostic device 1D, but the image input unit 11 and the determination unit 16 may be provided in the server 71.

[0095] Figure 9 shows the configuration of the ultrasound diagnostic system according to Embodiment 6. The ultrasound diagnostic system of Embodiment 6 is the same as the ultrasound diagnostic system of Embodiment 5 shown in Figure 8, but with a server 71E instead of server 71 and a diagnostic device 1E instead of diagnostic device 1D. The diagnostic device 1E and server 71E are connected to each other via a network NW.

[0096] Diagnostic device 1E is the same as diagnostic device 1D in Embodiment 5, but with the image input unit 11 and determination unit 16 removed, and a device control unit 18E installed instead of the device control unit 18D. The display control unit 12, notification unit 17, device control unit 18E, and communication unit 46 constitute the processor 20E for diagnostic device 1E.

[0097] Server 71E is an addition to Server 71 in Embodiment 5, with the addition of an image input unit 73, a determination unit 74, and a server control unit 75. In Server 71E, the determination unit 74 is connected to the data storage unit 72 and the image input unit 73. Furthermore, the server control unit 75 is connected to the data storage unit 72, the image input unit 73, and the determination unit 74. The determination unit 74 and the server control unit 75 constitute a processor 76 for Server 71E.

[0098] The image input unit 73 of the server 71E is the same as the image input unit 11 of the diagnostic device 1D in Embodiment 5, and the determination unit 74 is the same as the determination unit 16 of the diagnostic device 1D in Embodiment 5. The server control unit 75 controls each part of the server 71E according to a pre-recorded program or the like.

[0099] Furthermore, the processor 76, which is composed of the determination unit 74 and the server control unit 75 of the server 71E, consists of a CPU and a control program for causing the CPU to perform various processes, but it may be composed using an FPGA, DSP, ASIC, GPU, or other IC, or a combination thereof. Furthermore, the determination unit 74 and the server control unit 75 of the processor 76 can be partially or entirely integrated into a single CPU or the like.

[0100] In the ultrasound diagnostic system of Embodiment 6, an ultrasound image is input to the image input unit 73 of the server 71E from an external device or recording medium (not shown). The image input unit 73 sends the ultrasound image input from the external device or recording medium to the determination unit 74.

[0101] The determination unit 74 uses a trained model to determine whether or not artifacts occur in the ultrasound image transmitted from the image input unit 73. The determination unit 74 also uses the trained model to estimate the location and cause of the artifacts occurring in the ultrasound image.

[0102] The ultrasound image input to the image input unit 73, the determination result of the determination unit 74 regarding the presence or absence of artifacts, and the location and cause of the artifacts estimated by the determination unit 74 are transmitted to the communication unit 46 of the diagnostic device 1E via the network NW.

[0103] The communication unit 46 of the diagnostic device 1E sends the ultrasound image received from the server 71E via the network NW to the image memory 14. The ultrasound image is then stored in the image memory 14. The ultrasound image stored in the image memory 14 is then sent to the display control unit 12 under the control of the device control unit 18E and displayed on the monitor 13.

[0104] Furthermore, the communication unit 46 sends to the notification unit 17 the determination result regarding the presence or absence of artifacts received from the server 71E via the network NW, as well as the location and cause of the artifacts.

[0105] When the determination unit 74 determines that an artifact has occurred, the notification unit 17 notifies the user of the location and cause of the artifact estimated by the determination unit 74. In addition, when notifying the user of the cause of the artifact, the notification unit 17 can also notify the user of a method for resolving the artifact based on the artifact generation principle stored in the data storage unit 72. Furthermore, when notifying the user of the cause of the artifact, the notification unit 17 can also notify the user of examples stored in the data storage unit 72 in which artifacts have been effectively utilized for diagnosis.

[0106] From the above, even when the image input unit 73 and the determination unit 74 are included in the server, as in the ultrasound diagnostic system of Embodiment 6 of the present invention, the notification unit 17 notifies the user of methods for eliminating artifacts or examples of effective use of artifacts, similar to when the image input unit 11 and the determination unit 16 are included in the diagnostic device 1D, as in Embodiment 5. Therefore, the user can easily reduce artifacts and effectively utilize them in the diagnosis of the subject.

[0107] Furthermore, in the ultrasound diagnostic system of Embodiment 6, since the determination unit 74 is included in the server 71E, it is not necessary to determine the presence or absence of artifacts and to estimate the location and cause of artifact occurrence within the diagnostic device 1E, thereby reducing the computational load on the diagnostic device 1E. For example, when multiple diagnostic devices 1E are installed in different locations and users at each location use their respective diagnostic devices 1E to diagnose subjects, it is not necessary to install an expensive processor 20E with high computing power in each diagnostic device 1E. In this way, since it is not necessary to install an expensive processor 20E in the diagnostic device 1E, the introduction of the ultrasound diagnostic system is easy, especially when installing multiple diagnostic devices 1E. [Explanation of symbols]

[0108] 1,1A,1B,1C,1D,1E Diagnostic device, 3A,3B Ultrasonic probe, 11,11A,73 Image input unit, 12 Display control unit, 13 Monitor, 14 Image memory, 15,72 Data storage unit, 16,74 Judgment unit, 17 Notification unit, 18,18A,18B,18C,18D,18E Device control unit, 19 Input device, 20,20A,20B,20C,20D,20E,76 Processor, 31 Transducer array, 32 Transmit / receive circuit, 33 Probe sensor, 41 Image generation unit, 42 Image acquisition unit, 43 Guide unit, 44 Optical image analysis unit, 45 Probe detection unit, 46 Communication unit, 51 Pulsar, 52 Amplifier unit, 53 AD conversion unit, 54 Beamformer, 55 Signal processing unit, 56 DSC, 57 Image processing unit, 61 optical camera, 71, 71E server, 75 server control unit, NW network.

Claims

1. An image input unit for inputting ultrasound images, A determination unit determines whether or not artifacts are present in the ultrasound image input to the image input unit by using a trained model trained on training data that links multiple ultrasound images in which artifacts are captured with the cause of each artifact, A data storage unit containing examples of cases where artifacts were effectively utilized in diagnosis, An ultrasound diagnostic system that, when the determination unit determines that an artifact has occurred, notifies the location of the artifact in the ultrasound image, the cause of the artifact, and the case in which the artifact was effectively used for diagnosis.

2. The diagnostic device includes the image input unit, the determination unit, and the notification unit, The data storage unit is located in the diagnostic device, as described in claim 1 of the ultrasound diagnostic system.

3. A diagnostic device including the image input unit, the determination unit, and the notification unit, A server connected to the diagnostic device via the network Equipped with, The data storage unit is located in the server as described in claim 1 of the ultrasound diagnostic system.

4. A diagnostic device including the aforementioned notification unit, A server connected to the diagnostic device via a network, and including the image input unit and the determination unit. Equipped with, The data storage unit is located in the server as described in claim 1 of the ultrasound diagnostic system.

5. The image input unit is equipped with an input device for specifying a region of interest based on the ultrasound image input to the image input unit, through user input operations. The ultrasound diagnostic system according to any one of claims 1 to 4, wherein the determination unit determines whether or not artifacts occur in the region of interest.

6. The aforementioned image input unit is An ultrasonic probe having a transducer array, An image acquisition unit that transmits and receives ultrasonic beams from the transducer array to a subject and acquires an ultrasonic image based on the received signal output from the transducer array. An ultrasound diagnostic system according to any one of claims 1 to 5, including the following:

7. A probe detection unit that detects the orientation and tilt of the ultrasonic probe, A guide unit that guides at least one of the change in the orientation and tilt of the ultrasonic probe, which reduces the artifact, based on the orientation and tilt of the ultrasonic probe detected by the probe detection unit and the location and cause of the artifact. The ultrasound diagnostic system according to claim 6, comprising:

8. The ultrasound diagnostic system according to claim 7, wherein the probe detection unit comprises a probe sensor arranged on the ultrasound probe.

9. The probe detection unit is An optical camera that captures an optical image by photographing the aforementioned ultrasound probe, An optical image analysis unit detects the orientation and tilt of the ultrasonic probe by analyzing the optical image acquired by the optical camera. The ultrasound diagnostic system according to claim 7, including the following:

Citation Information

Patent Citations

  • Paint and dirt remover in abrasive application tools for hard surfaces

    JP2001501656A

  • Ultrasonic diagnostic apparatus

    JP2011110102A

  • Ultrasonic diagnostic apparatus and program

    JP2016010523A

  • Ultrasound clinical feature detection and related devices, systems, and methods

    JP2020512112A

  • Intelligent ultrasound system for detecting image artifacts

    JP2021501656A