Ultrasound diagnostic device and method for controlling the ultrasound diagnostic device

Abstract

To provide an ultrasonic diagnostic device which can highly accurately determine an inspection portion regardless of the level of skill of an inspector and a control method of the ultrasonic diagnostic device.SOLUTION: An ultrasonic diagnostic device comprises: an image acquisition unit (41) which receives an input of an ultrasonic image of a subject by performing an ultrasonic inspection to the subject by an inspector; and a portion determination unit (25) which determines an inspection portion imaged in the ultrasonic image on the basis of posture information of the inspector and the subject acquired by analyzing a reflection signal when a range finder (42) transmits a detection signal to the inspector and the subject and the ultrasonic image acquired by the image acquisition unit (41).SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to an ultrasonic diagnostic apparatus for identifying an examination position on a subject and a method for controlling the ultrasonic diagnostic apparatus. [Background technology]

[0002] Conventionally, ultrasound images representing cross-sectional images of the inside of a subject have been taken using so-called ultrasound diagnostic devices. Typically, an examiner often identifies the examination region of the subject currently being imaged by checking the ultrasound image. However, because the appearance of the ultrasound image varies depending on various factors, such as differences in the shape of the region of the subject and differences in the scanned cross-sectional plane, an examiner, particularly one with low skill, may erroneously identify the examination region by simply checking the ultrasound image.

[0003] In order to prevent such erroneous site identification, techniques have been developed for automatically identifying the site to be examined by analyzing ultrasound images, as disclosed in Patent Documents 1 and 2, for example. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] International Publication No. 2017 / 145540 [Patent Document 2] International Publication No. 2018 / 142954 Summary of the Invention [Problem to be solved by the invention]

[0005] According to the techniques disclosed in Patent Documents 1 and 2, the examination area is automatically identified regardless of the examiner's level of proficiency, but there are cases where the analysis of the ultrasound image is not performed normally for some reason, and there is room for improvement in the accuracy of identifying the examination area.

[0006] The present invention has been made to solve these conventional problems, and an object of the present invention is to provide an ultrasound diagnostic apparatus and a control method for an ultrasound diagnostic apparatus that can identify the examination area with high accuracy regardless of the skill level of the examiner. [Means for solving the problem]

[0007] The above object can be achieved by the following configuration. [1] an image acquisition unit that inputs an ultrasound image of a subject by an examiner performing an ultrasound examination on the subject; a region discrimination unit that discriminates the region to be examined that appears in the ultrasound image based on posture information of the examiner and the subject that is acquired by analyzing the reflected signals when a detection signal is transmitted from the distance measuring device to the examiner and the subject, and based on the ultrasound image acquired by the image acquisition unit; An ultrasound diagnostic device comprising: [2] The ultrasound diagnostic device described in [1], wherein the part discrimination unit determines the examination part based on posture information and ultrasound images using a learning model that has learned the relationship between the posture of the examiner and the subject, and the ultrasound images taken in the posture of the examiner and the subject, and the examination part of the subject. [3] The learning model is The system is configured with a plurality of secondary learning models that correspond to a plurality of predetermined sections of the human body and that have learned the relationship between the ultrasound image of the subject and the examination site, selecting one sub-learning model from the plurality of sub-learning models based on the posture information; An ultrasound diagnostic device according to [2], which uses one secondary learning model based on an ultrasound image to identify the examination area in the corresponding section. [4] The learning model is having a plurality of candidate regions for the examination region; selecting at least one candidate region from the plurality of candidate regions based on the posture information; The ultrasound diagnostic device according to [3], which outputs one of at least one candidate region as an examination region based on an ultrasound image. [5] The ultrasound diagnostic device according to any one of [1] to [4], further comprising an information memory that stores posture information and ultrasound images in association with each other. [6] The image acquisition unit is an ultrasound probe; an image generating unit that generates an ultrasound image of the subject by transmitting and receiving ultrasound beams using an ultrasound probe; The ultrasonic diagnostic device according to any one of [1] to [5], [7] Acquire an ultrasound image of the subject; The examination area shown in the ultrasound image is identified based on posture information of the examiner and the subject, which is acquired by analyzing the reflected signals when the distance measuring device transmits a detection signal to the examiner and the subject, and the ultrasound image. A method for controlling an ultrasound diagnostic device. [Effects of the Invention]

[0008] According to the present invention, the ultrasound diagnostic device is equipped with an image acquisition unit that inputs ultrasound images of the subject when the examiner performs an ultrasound examination on the subject, and a part discrimination unit that discriminates the examination part shown in the ultrasound image based on posture information of the examiner and the subject obtained by analyzing the reflected signal when a detection signal is transmitted from a distance measuring device to the examiner and the subject, and the ultrasound image acquired by the image acquisition unit, thereby making it possible to discriminate the examination part with high accuracy regardless of the examiner's level of skill. [Brief explanation of the drawings]

[0009] [Figure 1] 1 is a block diagram showing the configuration of an ultrasound diagnostic apparatus according to an embodiment of the present invention; [Figure 2] 1 is a block diagram showing a configuration of a transmission / reception circuit according to an embodiment of the present invention; [Figure 3] FIG. 2 is a block diagram showing a configuration of an image generating unit according to the embodiment of the present invention. [Figure 4] 1 is a diagram schematically illustrating an example of the positional relationship between a distance measuring sensor unit, a subject, and an examiner according to an embodiment of the present invention. [Figure 5]4 is a flowchart showing the operation of the ultrasound diagnostic apparatus according to the embodiment of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0010] Hereinafter, an embodiment of the present invention will be described with reference to the accompanying drawings. The following description of the components will be given based on a representative embodiment of the present invention, but the present invention is not limited to such an embodiment. In this specification, a numerical range expressed using "to" means a range that includes the numerical values ​​before and after "to" as the lower and upper limits. In this specification, the terms "same" and "identical" include a margin of error generally accepted in the technical field.

[0011] Embodiment The configuration of an ultrasound diagnostic device according to an embodiment of the present invention is shown in Figure 1. The ultrasound diagnostic device includes an ultrasound probe 1, a diagnostic device 2 connected to the ultrasound probe 1, and a distance measurement sensor unit 3 connected to the diagnostic device 2. The ultrasonic probe 1 includes a transducer array 11 and a transmission / reception circuit 12 connected to the transducer array 11. The distance measurement sensor unit 3 includes a transmission unit 31 and a reception unit 32.

[0012] The diagnostic device 2 is connected to the ultrasound probe 1 and displays ultrasound images captured by the ultrasound probe 1. The diagnostic device 2 is used, for example, by an examiner to check the ultrasound images captured by the ultrasound probe 1 in real time.

[0013] The diagnostic device 2 includes an image generation unit 21 connected to the transmission / reception circuit 12 of the ultrasound probe 1, and a display control unit 22 and a monitor 23 are connected to the image generation unit 21, in turn. The image generation unit 21 and the ultrasound probe 1 form an image acquisition unit 41. The diagnostic device 2 also includes a signal analysis unit 24 connected to the receiving unit 32 of the distance measurement sensor unit 3. A part discrimination unit 25 is connected to the image generation unit 21 and the signal analysis unit 24. The part discrimination unit 25 is connected to the display control unit 22. An information memory 26 is also connected to the image generation unit 21 and the signal analysis unit 24. A device control unit 27 is also connected to the transmission / reception circuit 12, the display control unit 22, the signal analysis unit 24, the part discrimination unit 25, and the information memory 26. An input device 28 is connected to the device control unit 27.

[0014] Furthermore, the display control unit 22, the signal analysis unit 24, the part discrimination unit 25, and the device control unit 27 constitute a processor 29 for the diagnostic device 2. Furthermore, the signal analysis unit 24 and the distance measurement sensor unit 3 of the diagnostic device 2 constitute a distance measurement device 42.

[0015] The transducer array 11 of the ultrasonic probe 1 has a plurality of ultrasonic transducers arranged one-dimensionally or two-dimensionally. These ultrasonic transducers transmit ultrasonic waves in accordance with drive signals supplied from the transmission / reception circuit 12, receive ultrasonic echoes from the subject, and output signals based on the ultrasonic echoes. Each ultrasonic transducer is configured by forming electrodes on both ends of a piezoelectric element made of, for example, a piezoelectric ceramic typified by PZT (Lead Zirconate Titanate), a polymer piezoelectric element typified by PVDF (Poly Vinylidene Di Fluoride), or a piezoelectric single crystal typified by PMN-PT (Lead Magnesium Niobate-Lead Titanate).

[0016] The transmission / reception circuit 12, under the control of the device control unit 27, transmits ultrasonic waves from the transducer array 11 and generates sound ray signals based on reception signals acquired by the transducer array 11. As shown in Fig. 2, the transmission / reception circuit 12 has a pulser 51 connected to the transducer array 11, an amplifier unit 52, an AD (Analog to Digital) converter unit 53, and a beamformer 64, which are connected in series from the transducer array 11 in this order.

[0017] The pulser 51 includes, for example, a plurality of pulse generators, and adjusts the delay amount of each drive signal to the plurality of ultrasonic transducers of the transducer array 11 so that the ultrasonic waves transmitted from the plurality of ultrasonic transducers form an ultrasonic beam based on a transmission delay pattern selected in response to a control signal from the device control unit 27. In this way, when a pulsed or continuous wave voltage is applied to the electrodes of the ultrasonic transducers of the transducer array 11, the piezoelectric material expands and contracts, and pulsed or continuous wave ultrasonic waves are generated from each ultrasonic transducer, and an ultrasonic beam is formed from a composite wave of these ultrasonic waves.

[0018] The transmitted ultrasonic beam is reflected by an object such as a part of the subject, and propagates toward the transducer array 11 of the ultrasonic probe 1. The ultrasonic echo propagating toward the transducer array 11 in this manner is received by each ultrasonic transducer constituting the transducer array 11. At this time, each ultrasonic transducer constituting the transducer array 11 expands and contracts upon receiving the propagating ultrasonic echo, generating a received signal which is an electrical signal, and outputs this received signal to the amplifier unit 52.

[0019] The amplifier 52 amplifies the signals input from each ultrasonic transducer constituting the transducer array 11 and transmits the amplified signals to the AD converter 53. The AD converter 53 converts the signals transmitted from the amplifier 52 into digital reception data. The beamformer 64 performs so-called reception focusing processing by delaying and adding each piece of reception data received from the AD converter 53. This reception focusing processing causes the reception data converted by the AD converter 53 to be phased and added, and a sound ray signal in which the focus of the ultrasonic echo is narrowed is acquired.

[0020] As shown in FIG. 6, the image generating unit 21 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.

[0021] The signal processing unit 55 corrects the sound ray signals received from the transmission / reception circuit 12 for attenuation due to distance in accordance with the depth of the ultrasonic reflection position using the sound velocity value set by the device control unit 27, and then performs envelope detection processing to generate a B-mode image signal, which is tomographic image information regarding the tissue within the subject.

[0022] The DSC 56 converts (raster converts) the B-mode image signal generated by the signal processing unit 55 into an image signal that conforms to the scanning method of a normal television signal. 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 22, the region discrimination unit 25, and the information memory 26. The B-mode image signal thus subjected to image processing by the image processing unit 57 is called an ultrasound image.

[0023] Under the control of the device control unit 27, the display control unit 22 performs predetermined processing on the ultrasound image etc. generated by the image generation unit 21 and displays it on the monitor . The monitor 23 performs various displays under the control of the device control unit 27. The monitor 23 may include a display device such as an LCD (Liquid Crystal Display) or an organic EL display (Organic Electroluminescence Display).

[0024] The distance measurement sensor unit 3 is placed near an examiner J who performs an examination on the subject K using an ultrasonic probe 1 and the subject K, as shown in Fig. 4, for example, and transmits detection signals to the examiner J and the subject K, and receives reflected signals from them. The example in Fig. 4 shows the subject K lying on an examination table T, and the examiner J examining the arm of the subject K with the ultrasonic probe 1.

[0025] The transmitter 31 of the distance measuring sensor unit 3 transmits a detection signal to the examiner J and the subject K. The transmitter 31 is a so-called wireless transmitter of electromagnetic waves, and includes, for example, an antenna for transmitting the electromagnetic waves, a signal source such as an oscillator circuit, a modulation circuit for modulating the signal, and an amplifier for amplifying the signal. The receiving unit 32 includes an antenna for receiving electromagnetic waves and receives reflected signals from the examiner J and the subject K.

[0026] The distance measurement sensor unit 3 can be configured with a radar that transmits and receives detection signals of the so-called Wi-Fi (registered trademark) standard, which are made up of electromagnetic waves having a center frequency of 2.4 GHz or 5 GHz, or a radar that transmits and receives wideband detection signals having a center frequency of 1.78 GHz.The distance measurement sensor unit 3 can also be configured with a so-called LIDAR (Light Detection and Ranging, or Laser Imaging Detection and Ranging) sensor that transmits short-wavelength electromagnetic waves such as ultraviolet, visible light, or infrared light as detection signals.

[0027] The signal analysis unit 24 of the diagnostic device 2 analyzes the reflected signal received by the distance measurement sensor unit 3 to obtain posture information of the examiner J and the subject K. The posture information of the examiner J and the subject K includes information on the positions of each part of the examiner J and the subject K, such as the head, shoulders, arms, waist, and legs of the examiner J and the subject K.

[0028] The signal analysis unit 24 can acquire posture information of the examiner J and the subject K using a machine learning model that has learned the reflected signals when the distance measurement sensor unit 3 transmits a detection signal to the human body. Specifically, the signal analysis unit 24 uses, for example, “ZHAO, Mingmin, et al. Through-wall human pose estimation using radio signals. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018. p. 7356-7365.”, “VASILEIADIS, Manolis; BOUGANIS, Christos-Savvas; estimation from 3D cloud data using 3D convolutional neural networks. Computer Vision and Image Understanding, 2019, 185: 12-23.", "JIANG, Wenjun, et al. Towards 3D human pose construction using WiFi. In: Proceedings of the 26th Annual International Conference on Mobile Computing and Networking. 2020. p. 1-14.", or "WANG, Fei, et al. Person-in-WiFi: Pose information can be obtained using the method described in "Fine-grained person perception using WiFi. In: Proceedings of the IEEE / CVF International Conference on Computer Vision. 2019. pp. 5452-5461."

[0029] Furthermore, the signal analysis unit 24 sets a coordinate system with the position of one part of the subject K as the origin, and can acquire three-dimensional coordinates of the positions of each part of the subject K as posture information of the subject K. The signal analysis unit 24 can set the three-dimensional coordinate system by, for example, setting the position of the neck of the subject K as the origin of the coordinate system, an axis along a line passing through the left and right shoulders of the subject as the first axis, an axis orthogonal to the first axis and along a line passing through the head and torso of the subject K as the second axis, and an axis orthogonal to both the first and second axes as the third axis. As a result, even if the positional relationship between the distance measurement sensor unit 3 and the subject K varies for each examination, the positions of each part of the subject K can be represented in the same three-dimensional coordinate system.

[0030] Here, for example, the position on the subject K where the tip of the arm of the examiner J is located can be identified as the position on the subject K where the examiner J is in contact with the ultrasound probe 1. Therefore, when the human body is divided into multiple sections, it is possible to identify the section on the subject K that is currently being examined based on the posture information of the subject K and the examiner J.

[0031] Furthermore, it is possible to identify the part of subject K that appears in an ultrasound image by using so-called machine learning or deep learning, which learns the relationship between the features of tissue structures that appear in an ultrasound image and the names of the parts of subject K that correspond to those tissue structures, or by using image analysis such as so-called template matching. However, when attempting to identify the part to be examined based solely on an ultrasound image, the part to be examined may be incorrectly identified due to various reasons, such as the shape and size of anatomical structures differing depending on the subject, or the examiner J not being able to obtain a clear ultrasound image due to low proficiency.

[0032] Therefore, in order to improve the accuracy of the examination region discrimination, the region discrimination unit 25 discriminates the examination region shown in the ultrasound image based on both the posture information of the subject K and the examiner J acquired by the signal analysis unit 24 and the ultrasound image of the subject K generated by the image generation unit 21. As a result, when discriminating the examination region based on the ultrasound image, the body parts of the subject K identified from the posture information of the subject K and the examiner J are taken into consideration, so that the examination region can be discriminated with high accuracy.

[0033] At this time, the part discrimination unit 25 can discriminate the current examination part of the subject based on the posture information of the subject K and the examiner J acquired by the signal analysis unit 24 and the ultrasound image generated by the image generation unit 21, using, for example, a learning model that has learned the relationship between the postures of the subject K and the examiner J, and the ultrasound image taken of the subject K and the examiner J in that posture, and the examination part of the subject.

[0034] More specifically, the learning model of part discrimination unit 25 has a plurality of candidate parts predetermined as candidates for the examination part, and can calculate the probability that the examination part shown in the ultrasound image is each of the plurality of candidate parts. In this case, the learning model can weight the probability of at least one candidate part corresponding to a body part of the subject identified from posture information of subject K and examiner J, for example. Of the plurality of candidate part probabilities calculated in this way, the learning model can discriminate the candidate part corresponding to the largest probability as the examination part.

[0035] The part discrimination unit 25 can use, as a learning model, a model that follows an algorithm such as ResNet (Residual Neural Network), DenseNet (Dense Convolutional Network), AlexNet, Baseline, Batch Normalization, Dropout Regularization, NetWidth Search, or NetDepth Search. The part discrimination unit 25 can also use models that follow these algorithms in appropriate combination with each other.

[0036] In this way, the part discrimination unit 25 determines the current examination part not only using the ultrasound image of the subject K but also supplementary information on the posture of the subject K and the examiner J. Therefore, the examination part can be discriminated with high accuracy regardless of the skill level of the examiner J. Furthermore, for example, the examination part can be determined more accurately than when the examination part is determined based only on the ultrasound image.

[0037] The learning model of the part discrimination unit 25 can be composed of multiple secondary learning models that correspond to multiple predetermined parts of the human body and that have learned the relationship between the ultrasound image of the subject K and the examination part. In this case, the learning model selects one of the multiple secondary learning models that corresponds to the body part of the subject K identified from the posture information, and inputs the ultrasound image into the selected secondary learning model, thereby discriminating the examination part in the corresponding part. More specifically, the learning model is composed of secondary learning models for, for example, the abdomen, the chest, and the upper limbs, and discriminates one of the candidate parts located in the abdomen, such as the liver and kidneys, as the examination part when the body part identified from the posture information of the subject K and the examiner J is the abdomen.

[0038] The learning model may also be configured as a single learning model, which selects at least one candidate site from multiple candidate sites that is included in a section of the human body identified based on posture information of the subject K and the examiner J, and outputs one of the selected candidate sites as an examination site based on an ultrasound image. For example, if the multiple candidate sites are the liver, kidneys, heart, lungs, and diaphragm, and the abdomen of the subject K is identified based on posture information of the subject K and the examiner J, the learning model may select the liver and kidneys corresponding to the abdomen as candidate sites from the multiple candidate sites. In this case, the learning model may calculate, for example, the probability that the liver is the examination site and the probability that the kidney is the examination site, and determine the site with the highest probability as the examination site. In this case, for example, the process of calculating the probability is performed only for at least one candidate site from the multiple candidate sites, thereby reducing the computational load on the site identification unit 25.

[0039] Furthermore, the learning model can calculate probabilities for each of multiple candidate regions based on ultrasound images, and then select at least one candidate region from the multiple candidate regions based on posture information of subject K and examiner J. For example, if the multiple candidate regions determined by the learning model are the liver, kidneys, heart, lungs, and diaphragm, and subject K's abdomen is identified based on posture information of subject K and examiner J, the learning model can select the liver and kidneys as candidate regions from the liver, kidneys, heart, lungs, and diaphragm for which probabilities have been calculated. In this case, the learning model determines, as the examination region, the region with the highest probability between the probability that the liver is the examination region and the probability that the kidney is the examination region. For example, even if, for some reason, the probability that the liver corresponds to the heart, lungs, or diaphragm becomes higher than the probability that the liver and kidney correspond to the heart, lungs, or diaphragm, the liver and kidneys are selected as candidate regions based on posture information, thereby enabling accurate identification of the examination region.

[0040] Furthermore, part discrimination unit 25 can also discriminate the examination part without using a learning model. For example, part discrimination unit 25 has template data representing a typical shape or the like for each of a plurality of candidate parts, and can calculate the probability that the examination part is each of a plurality of candidate parts by a so-called template matching method or the like, which compares the anatomical structure shown in the ultrasound image with the plurality of template data, and can discriminate the examination part based on the calculated probability.

[0041] In this case, the part discrimination section 25 can weight the probability of at least one part corresponding to a body part identified from the posture information of the subject K and the examiner J. Furthermore, the part discrimination section 25 can also select at least one part corresponding to a body part identified from the posture information of the subject K and the examiner J from among a plurality of predetermined candidate parts, and then discriminate the examination part.

[0042] Furthermore, the region discriminator 25 can display on the monitor 23 the name of the discriminated examination region of the subject, etc.

[0043] The information memory 26, under the control of the device control unit 27, stores posture information of the subject K and the examiner J acquired by the signal analysis unit 24 and the ultrasound image generated by the image generation unit 21 corresponding to the posture information, in association with each other. The information memory 26 can associate the posture information and the ultrasound image with each other, for example, by describing the examination position in the so-called header information of the ultrasound image under the control of the device control unit 27. The information memory 26 can also associate the posture information and the ultrasound image with each other, for example, using a so-called timestamp or DICOM (Digital Imaging and Communications in Medicine) under the control of the device control unit 27. The posture information of the subject K and the examiner J and the ultrasound image stored in the information memory 26 can be read out and sent to the region discrimination unit 25, for example, by an input operation by the examiner J via the input device 28. This allows the region discrimination unit 25 to accurately determine the examination region shown in the ultrasound image, regardless of the examiner J's level of proficiency, even after the examination is completed.

[0044] Examples of the information memory 26 that can be used 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).

[0045] The device control section 27 controls each section of the diagnostic device 2 according to a pre-recorded program or the like. The input device 28 accepts input operations by the examiner J or the like, and sends the input information to the device control unit 27. The input device 28 is configured by devices such as a keyboard, a mouse, a trackball, a touchpad, and a touch panel that allow the examiner to perform input operations.

[0046] The processor 29 having the display control unit 22, the signal analysis unit 24, the part discrimination unit 25, and the device control unit 27 of the diagnostic device 2 is composed of a CPU (Central Processing Unit) and a control program for causing the CPU to perform various processes, but 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 may be composed of a combination of these.

[0047] Furthermore, the display control unit 22, signal analysis unit 24, part discrimination unit 25 and device control unit 27 of the processor 29 can be partially or entirely integrated into a single CPU or the like.

[0048] Next, an example of the operation of the ultrasound diagnostic apparatus according to the embodiment will be described with reference to the flowchart of FIG. First, in step S1, the distance measurement sensor unit 3 starts to continuously transmit detection signals to the subject K and the examiner J and continuously receive reflected signals from the subject K and the examiner J. At this time, the examiner J brings the ultrasound probe 1 into contact with the body surface of the subject K.

[0049] Next, in step S2, the signal analysis unit 24 detects the subject K and the examiner J by analyzing the reflected signal received by the distance measurement sensor unit 3 in step S1.

[0050] In the following step S3, the signal analysis unit 24 analyzes the reflected signal received by the distance measurement sensor unit 3 in step S1 to acquire posture information of the subject K and the examiner J detected in step S2. At this time, the signal analysis unit 24 also sets a coordinate system with one part of the subject K as the origin, and can acquire three-dimensional coordinates of the positions of each part of the subject K as posture information of the subject K. The signal analysis unit 24 can set the three-dimensional coordinate system, for example, by setting the position of the subject K's neck as the origin of the coordinate system, an axis along a line passing through the subject's left and right shoulders as the first axis, an axis perpendicular to the first axis and along a line passing through the subject's head and torso as the second axis, and an axis perpendicular to both the first and second axes as the third axis. This allows the positions of each part of the subject K to be represented in the same three-dimensional coordinate system, even if the positional relationship between the distance measurement sensor unit 3 and the subject K varies from examination to examination.

[0051] The posture information of the subject K and the examiner J thus obtained in step S3 is sent to the part discrimination unit 25 and the information memory .

[0052] In step S4, with the ultrasonic probe 1 in contact with the body surface of the subject K, the inside of the subject K is scanned by the ultrasonic probe 1, and an ultrasonic image representing a tomographic image of the inside of the subject K is acquired. At this time, the transmission / reception circuit 12 performs so-called reception focus processing under the control of the device control unit 27 to generate sound ray signals. The sound ray signals generated by the transmission / reception circuit 12 are sent to the image generation unit 21. The image generation unit 21 generates an ultrasonic image using the sound ray signals sent from the transmission / reception circuit 12. The ultrasonic image acquired in this manner is sent to the part determination unit 25 and the information memory 26.

[0053] Here, the posture information of the subject K and the examiner J sent to the information memory 26 in step S3, and the ultrasound image sent to the information memory 26 in step S4 can be linked to each other and stored in the information memory 26 under the control of the device control unit 27.

[0054] In step S5, the part discrimination unit 25 discriminates the examination part shown in the ultrasound image based on both the posture information of the subject K and the examiner J acquired in step S3 and the ultrasound image generated by the image generation unit 21 in step S4. The part discrimination unit 25 has a learning model that has previously learned the relationship between the postures of the subject K and the examiner, the ultrasound image acquired corresponding to that posture, and the examination part shown in that ultrasound image, and can discriminate the examination part by inputting the posture information of the subject K and the examiner J and the ultrasound image into the learning model.

[0055] Here, the body part of the subject K from which the ultrasound image is taken can be identified based on the posture information of the subject K and the examiner J. Therefore, for example, when identifying the examination part based on the ultrasound image, the accuracy of identifying the examination part can be improved by taking into account the identified body part of the subject K.

[0056] The part discrimination unit 25 displays information about the examination part discriminated in this way on the monitor 23. By checking the information about the examination part displayed on the monitor 23, the examiner J can easily grasp the current examination part while proceeding with the examination of the subject.

[0057] In step S6, the device control unit 27 determines whether to end the test. For example, if the examiner J inputs instruction information to end the test via the input device 28, the device control unit 27 determines to end the current test. Also, for example, if the examiner J does not input instruction information to end the test via the input device 28, the device control unit 27 determines to continue the current test.

[0058] If it is determined in step S6 that the inspection should be continued, the process returns to step S3. In this way, the processes of steps S3 to S6 are repeated as long as it is determined in step S6 that the inspection should be continued.

[0059] Furthermore, if it is determined in step S6 that the examination should be ended, the device control unit 27 controls each unit of the ultrasonic diagnostic device to end the examination, and the operation of the ultrasonic diagnostic device according to the flowchart of FIG. 5 ends.

[0060] Here, after the examination is completed, the posture information and ultrasound image stored in association with each other can be read out from information memory 26 based on, for example, an input operation by examiner J or the like via input device 28. In this case, region discrimination unit 25 can discriminate the examination region appearing in the read ultrasound image based on the posture information of subject K and examiner J and the ultrasound image read out from information memory 26. As a result, for example, when a doctor or the like diagnoses the subject by checking the ultrasound image, he or she can accurately grasp the examination region appearing in the ultrasound image by checking the name of the examination region discriminated by region discrimination unit 25, thereby improving the accuracy of the diagnosis.

[0061] As described above, according to the ultrasound diagnostic apparatus of the embodiment of the present invention, the part discrimination unit 25 discriminates the part to be examined of the subject based on both the posture information of the subject K and the examiner J acquired by the signal analysis unit 24 and the ultrasound image generated by the image generation unit 21, and therefore the part to be examined can be discriminated with high accuracy regardless of the skill level of the examiner J. Furthermore, according to the ultrasound diagnostic apparatus of the embodiment of the present invention, the accuracy of discrimination of the part to be examined can be improved compared to when the part to be examined is determined based only on the ultrasound image.

[0062] Although the signal analysis unit 24 has been described as being provided in the diagnostic device 2, for example, the distance measurement sensor unit 3 and the signal analysis unit 24 can also form a distance measurement device 42 independent of the diagnostic device 2. In this case, the signal analysis unit 24 of the distance measurement device 42 acquires posture information of the subject K and the examiner J, and the acquired posture information is sent to the part determination unit 25 of the diagnostic device 2. Therefore, even in this case, as in the case where the diagnostic device 2 is provided with the signal analysis unit 24, the part determination unit 25 determines the examination part based on both the posture information of the subject K and the examiner J acquired by the signal analysis unit 24 and the ultrasound image generated by the image generation unit 21.

[0063] 2, the distance measuring sensor unit 3 is shown to be installed near the examiner J and the subject K, but the installation position of the distance measuring sensor unit 3 is not particularly limited as long as the detection signal transmitted from the distance measuring sensor unit 3 reaches the examiner J and the subject K. The distance measuring sensor unit 3 can also be installed, for example, on the ceiling of the room where the examiner J is inspecting the subject K.

[0064] Furthermore, although the signal analysis unit 24 has been described as setting a coordinate system having the position of one part of the subject K as the origin, the part identification unit 25 may instead of the signal analysis unit 24 set a coordinate system having the position of one part of the subject K as the origin. In this case, the signal analysis unit 24 can acquire three-dimensional coordinates of each part of the subject K having the origin at an arbitrary position, such as within a room in which the distance measurement sensor unit 3 is installed, based on, for example, a reflected signal transmitted from the receiving unit 32 of the distance measurement sensor unit 3. The part identification unit 25 converts the three-dimensional coordinates of each part of the subject K acquired by the signal analysis unit 24 into an expression in a three-dimensional coordinate system having the position of one part of the subject K as the origin. Even in this case, for example, even if the positional relationship between the distance measurement sensor unit 3 and the subject K varies from test to test, the positions of each part of the subject K can be expressed in the same three-dimensional coordinate system.

[0065] In the flowchart of FIG. 5, the process proceeds in the order of step S3 and step S4, but step S3 and step S4 can also be processed in parallel.

[0066] 5, an ultrasound image is generated in step S4 each time posture information is acquired in step S3, but it is also possible to acquire posture information once in step S3 each time a certain number of frames of ultrasound images are generated in step S4. It is also possible to generate one frame of ultrasound image in step S4 each time posture information is acquired multiple times in step S3.

[0067] Furthermore, although the image generating unit 21 has been described as being provided in the diagnostic device 2, it may also be provided in the ultrasound probe 1 instead of in the diagnostic device 2.

[0068] Furthermore, the diagnostic device 2 may be a so-called stationary type, a portable type, or a handheld type configured by a so-called smartphone or tablet computer, etc. In this way, the type of device that configures the diagnostic device 2 is not particularly limited. Furthermore, the ultrasound probe 1 and the diagnostic device 2 can be connected to each other by wire or wirelessly. [Explanation of symbols]

[0069] 1 Ultrasound probe, 2 Diagnostic device, 3 Distance measurement sensor unit, 11 Transducer array, 12 Transmitting and receiving circuit, 21 Image generation unit, 22 Display control unit, 23 Monitor, 24 Signal analysis unit, 25 Part discrimination unit, 26 Information memory, 27 Device control unit, 28 Input device, 29 Processor, 31 Transmitting unit, 32 Receiving unit, 41 Image acquisition unit, 42 Distance measurement device, 51 Pulser, 52 Amplifying unit, 53 AD conversion unit, 54 Beamformer, 55 Signal processing unit, 56 DSC, 57 Image processing unit, J Examiner, K Subject, T Examination table.

Claims

1. an image acquisition unit that inputs an ultrasound image of a subject by an examiner performing an ultrasound examination on the subject; a region discrimination unit that discriminates an examination region shown in the ultrasound image based on posture information of the examiner and the subject, which is acquired by analyzing a reflected signal when a detection signal is transmitted from a distance measuring device to the examiner and the subject, and the ultrasound image acquired by the image acquisition unit; Equipped with The part discrimination unit a plurality of candidate sites for the test site; Identifying a body part to be examined in the subject based on the posture information; selecting at least one candidate site corresponding to the identified section from the plurality of candidate sites; An ultrasound diagnostic device that determines one of the at least one candidate region as the region to be examined based on the ultrasound image.

2. 2. The ultrasound diagnostic device according to claim 1, wherein the part determination unit determines the examination part based on the posture information and the ultrasound image using a learning model that has learned the relationship between the postures of the examiner and the subject, and the relationship between the ultrasound image captured in the postures of the examiner and the subject and the examination part of the subject.

3. The learning model is The system is configured by a plurality of secondary learning models that correspond to a plurality of predetermined sections of the human body and that have learned the relationship between the ultrasound image of the subject and the examination region, selecting one of the plurality of secondary learning models based on the posture information; The ultrasound diagnostic apparatus according to claim 2 , wherein the examination region is identified in the corresponding section by the one secondary learning model based on the ultrasound image.

4. The learning model is the plurality of candidate regions for the examination region; selecting the at least one candidate region from the plurality of candidate regions based on the posture information; The ultrasonic diagnostic apparatus according to claim 3 , wherein one of the at least one candidate region is output as the region to be examined based on the ultrasonic image.

5. 5. The ultrasonic diagnostic apparatus according to claim 1, further comprising an information memory for storing the posture information and the ultrasonic image in association with each other.

6. The image acquisition unit an ultrasound probe; an image generating unit that generates the ultrasonic image of the subject by transmitting and receiving ultrasonic beams using the ultrasonic probe; The ultrasonic diagnostic apparatus according to any one of claims 1 to 4, comprising:

7. acquiring an ultrasound image of the subject; identifying a body part of the subject to be examined based on posture information of the examiner and the subject obtained by analyzing a reflected signal when a detection signal is transmitted from a distance measuring device to the examiner and the subject; selecting at least one candidate region corresponding to the identified section from a plurality of candidate regions for the examination region shown in the ultrasound image; determining one of the at least one candidate region as the examination region based on the ultrasound image; A method for controlling an ultrasound diagnostic device.

Images