JP2021186208A - Ultrasonic diagnostic apparatus and image processing device - Google Patents

Abstract

To improve accuracy in measurement using an ultrasonic image.SOLUTION: An ultrasonic diagnostic apparatus includes a detection unit, an estimation unit and an output unit. The detection unit detects a first rectangle including a measurement part from an ultrasonic image. The estimation unit estimates a measurement point for measuring the measurement part on the basis of positional information of the first rectangle. The output unit outputs information relating to the measurement point.SELECTED DRAWING: Figure 1

Description

The embodiments disclosed in the present specification and drawings relate to an ultrasonic diagnostic apparatus and an image processing apparatus.

Ultrasound images are used to confirm fetal development. For example, an ultrasonic diagnostic apparatus uses an ultrasonic image to obtain a large lateral diameter of the fetal head (BPD: biparietal diameter), a head circumference (HC: head circumference), and an abdominal circumference (AC: abdominal circumference). , Femur length (FL: femur length), humerus length (HL: humerus length) and other parameters can be measured.

Here, when measuring parameters such as BPD, HC, AC, FL, and HL, there is known a method of estimating a measurement point for measuring a measurement site by image processing based on luminance. However, in such a method, if there is a portion of the ultrasonic image whose brightness is higher than the contour of the actual measurement portion, there is a possibility that the measurement point is estimated by the portion having the higher brightness.

Japanese Unexamined Patent Publication No. 2019-115559

One of the problems to be solved by the embodiments disclosed in the present specification and the drawings is to improve the accuracy of measurement using ultrasonic images. However, the problems solved by the embodiments disclosed in the present specification and the drawings are not limited to the above problems. The problem corresponding to each effect by each configuration shown in the embodiment described later can be positioned as another problem.

The ultrasonic diagnostic apparatus according to the present embodiment includes a detection unit, an estimation unit, and an output unit. The detection unit detects the first rectangle including the measurement site from the ultrasonic image. The estimation unit estimates a measurement point for measuring the measurement site based on the position information of the first rectangle. The output unit outputs information about the measurement point.

FIG. 1 is a block diagram showing an example of the configuration of the ultrasonic diagnostic apparatus according to the present embodiment. FIG. 2 is a diagram for explaining a problem when measuring a measurement site. FIG. 3 is a diagram for explaining processing by the image processing circuit of the ultrasonic diagnostic apparatus according to the present embodiment. FIG. 4 is a diagram for explaining processing by the image processing circuit of the ultrasonic diagnostic apparatus according to the present embodiment. FIG. 5 is a diagram for explaining processing by the image processing circuit of the ultrasonic diagnostic apparatus according to the present embodiment. FIG. 6 is a diagram for explaining processing by the image processing circuit of the ultrasonic diagnostic apparatus according to the present embodiment. FIG. 7 is a diagram for explaining processing by the image processing circuit of the ultrasonic diagnostic apparatus according to the present embodiment. FIG. 8 is a flowchart showing a processing procedure by the ultrasonic diagnostic apparatus according to the present embodiment. FIG. 9 is a diagram for explaining processing by the image processing circuit of the ultrasonic diagnostic apparatus according to the present embodiment. FIG. 10 is a diagram for explaining processing by the image processing circuit of the ultrasonic diagnostic apparatus according to the present embodiment. FIG. 11 is a diagram for explaining processing by the image processing circuit of the ultrasonic diagnostic apparatus according to the present embodiment. FIG. 12 is a diagram for explaining processing by the image processing circuit of the ultrasonic diagnostic apparatus according to the present embodiment. FIG. 13 is a block diagram showing a configuration example of the trained model generator according to the present embodiment.

Hereinafter, the ultrasonic diagnostic apparatus and the image processing apparatus according to the embodiment will be described with reference to the attached drawings. The embodiment is not limited to the following embodiments. Further, in principle, the contents described in one embodiment are similarly applied to other embodiments.

FIG. 1 is a block diagram showing a configuration example of the ultrasonic diagnostic apparatus 1 according to the present embodiment. As shown in FIG. 1, the ultrasonic diagnostic apparatus 1 according to the present embodiment includes an apparatus main body 100, an ultrasonic probe 101, an input device 102, and a display 103. The ultrasonic probe 101, the input device 102, and the display 103 are each connected to the device main body 100.

The ultrasonic probe 101 executes transmission / reception of ultrasonic waves (ultrasonic scan). For example, the ultrasonic probe 101 is in contact with the body surface of subject P (eg, the abdomen of a pregnant woman) and performs transmission and reception of ultrasonic waves to a region including at least a part of a foetation in the uterus of the pregnant woman. The ultrasonic probe 101 has a plurality of piezoelectric vibrators. The plurality of piezoelectric vibrators are piezoelectric elements having a piezoelectric effect of mutually converting an electric signal (pulse voltage) and mechanical vibration (vibration due to sound), and can be used as a drive signal (electric signal) supplied from the device main body 100. Based on this, an ultrasonic wave is generated. The generated ultrasonic waves are reflected by the mismatched surface of the acoustic impedance in the subject P, and are received by a plurality of piezoelectric vibrators as reflected wave signals (electrical signals) including components scattered by scatterers in the tissue. Will be done. The ultrasonic probe 101 sends the reflected wave signal received by the plurality of piezoelectric vibrators to the apparatus main body 100.

In the present embodiment, the ultrasonic probe 101 is a 1D array probe having a plurality of piezoelectric vibrators arranged in a predetermined direction in one dimension, or a 2D in which a plurality of piezoelectric vibrators are arranged two-dimensionally in a grid pattern. Any form of ultrasonic probe may be used, such as an array probe or a mechanical 4D probe that scans a three-dimensional region by mechanically swinging a plurality of three-dimensionally arranged piezoelectric vibrators.

The input device 102 has a mouse, a keyboard, a button, a panel switch, a touch command screen, a foot switch, a wheel, a trackball, a joystick, and the like, and receives various setting requests from the operator of the ultrasonic diagnostic device 1 and receives various setting requests from the device main body. The various setting requests received for 100 are transferred.

The display 103 displays a GUI (Graphical User Interface) for the operator of the ultrasonic diagnostic apparatus 1 to input various setting requests using the input device 102, ultrasonic image data generated in the apparatus main body 100, and the like. Or display. Further, the display 103 displays various messages in order to notify the operator of the processing status of the apparatus main body 100. The display 103 is an example of a “display unit”.

The device main body 100 is a device that generates ultrasonic image data based on the reflected wave signal received by the ultrasonic probe 101. The ultrasonic image data generated by the apparatus main body 100 may be two-dimensional ultrasonic image data generated based on a two-dimensional reflected wave signal, or may be generated based on a three-dimensional reflected wave signal. It may be three-dimensional ultrasonic image data.

As shown in FIG. 1, the apparatus main body 100 includes, for example, a transmission / reception circuit 110, a B mode processing circuit 120, a Doppler processing circuit 130, an image processing circuit 140, an image memory 150, a storage circuit 160, and a control circuit. It has 170 and. The transmission / reception circuit 110, the B-mode processing circuit 120, the Doppler processing circuit 130, the image processing circuit 140, the image memory 150, the storage circuit 160, and the control circuit 170 are communicably connected to each other. Further, the apparatus main body 100 is connected to the in-hospital network 2.

The transmission / reception circuit 110 controls transmission of ultrasonic waves by the ultrasonic probe 101. For example, the transmission / reception circuit 110 applies the above-mentioned drive signal (drive pulse) to the ultrasonic probe 101 at a timing when a predetermined transmission delay time is given to each oscillator based on the instruction of the control circuit 170. As a result, the transmission / reception circuit 110 causes the ultrasonic probe 101 to transmit an ultrasonic beam in which ultrasonic waves are focused in a beam shape.

Further, the transmission / reception circuit 110 controls reception of the reflected wave signal by the ultrasonic probe 101. As described above, the reflected wave signal is a signal in which the ultrasonic wave transmitted from the ultrasonic probe 101 is reflected by the internal tissue of the subject P. For example, the transmission / reception circuit 110 performs addition processing by giving a predetermined delay time to the reflected wave signal received by the ultrasonic probe 101 based on the instruction of the control circuit 170. As a result, the reflected component from the direction corresponding to the reception directivity of the reflected wave signal is emphasized. Then, the transmission / reception circuit 110 converts the reflected wave signal after the addition processing into a baseband band in-phase signal (I signal, I: In-phase) and an orthogonal signal (Q signal, Q: Quadrature-phase). Then, the transmission / reception circuit 110 sends the I signal and the Q signal (hereinafter referred to as IQ signal) as reflected wave data to the B mode processing circuit 120 and the Doppler processing circuit 130. The transmission / reception circuit 110 may convert the reflected wave signal after the addition processing into an RF (Radio Frequency) signal and then send it to the B mode processing circuit 120 and the Doppler processing circuit 130. The IQ signal and the RF signal are signals (reflected wave data) including phase information.

The B-mode processing circuit 120 performs various signal processing on the reflected wave data generated by the transmission / reception circuit 110 from the reflected wave signal. The B-mode processing circuit 120 performs logarithmic amplification, envelope detection processing, etc. on the reflected wave data received from the transmission / reception circuit 110, and the signal strength at each sample point (observation point) is expressed by the brightness of the brightness. Data (B mode data) is generated. The B-mode processing circuit 120 sends the generated B-mode data to the image processing circuit 140.

Further, the B mode processing circuit 120 executes signal processing for performing harmonic imaging for visualizing harmonic components. As harmonic imaging, contrast harmonic imaging (CHI: Contrast Harmonic Imaging) and tissue harmonic imaging (THI: Tissue Harmonic Imaging) are known. For contrast harmonic imaging and tissue harmonic imaging, the scan methods include amplitude modulation (AM), phase modulation (PM) called "Pulse Subtraction method" and "Pulse Inversion method", and AM. AMPM and the like are known in which both the effect of AM and the effect of PM can be obtained by combining and PM.

The Doppler processing circuit 130 generates data as Doppler data obtained by extracting motion information based on the Doppler effect of a moving body at each sample point in the scanning region from the reflected wave data generated by the transmission / reception circuit 110 from the reflected wave signal. Here, the motion information of the moving body is information such as the average velocity, the dispersion value, and the power value of the moving body, and the moving body is, for example, blood flow, tissues such as the heart wall, and a contrast medium. The Doppler processing circuit 130 sends the generated Doppler data to the image processing circuit 140.

For example, when the moving body is blood flow, the motion information of blood flow is information (blood flow information) such as average velocity, dispersion value, and power of blood flow. Blood flow information is obtained, for example, by the color Doppler method.

In the color Doppler method, first, ultrasonic waves are transmitted and received multiple times on the same scanning line, and then a data string of reflected wave data at the same position (same sample point) is used using an MTI (Moving Target Indicator) filter. A signal in a specific frequency band is passed through the signal representing the above, and a signal in other frequency bands is attenuated. That is, it suppresses a signal (clutter component) derived from a stationary tissue or a slow-moving tissue. As a result, the blood flow signal related to the blood flow is extracted from the signal representing the data string of the reflected wave data. Then, in the color Doppler method, blood flow information such as average velocity, dispersion value, and power of blood flow is estimated from the extracted blood flow signal, and the estimated blood flow information is generated as Doppler data.

The image processing circuit 140 performs image data (ultrasonic image data) generation processing, various image processing on the image data, and the like. For example, the image processing circuit 140 generates two-dimensional B-mode image data in which the intensity of the reflected wave is represented by luminance from the two-dimensional B-mode data generated by the B-mode processing circuit 120. Further, the image processing circuit 140 generates two-dimensional Doppler image data in which blood flow information is visualized from the two-dimensional Doppler data generated by the Doppler processing circuit 130. The two-dimensional Doppler image data is velocity image data representing the average velocity of blood flow, distributed image data representing the dispersion value of blood flow, power image data representing the power of blood flow, or image data obtained by combining these. The image processing circuit 140 generates color Doppler image data in which blood flow information such as average velocity, dispersion value, and power of blood flow is displayed in color as Doppler image data, and one blood flow information is in gray scale. Generate the displayed Doppler image data.

Here, the image processing circuit 140 generally converts (scan-converts) a scanning line signal string of ultrasonic scanning into a scanning line signal string of a video format typified by a television or the like, and ultrasonic waves for display. Generate image data. Specifically, the image processing circuit 140 generates ultrasonic image data for display by performing coordinate conversion according to the scanning form of ultrasonic waves by the ultrasonic probe 101. In addition to the scan conversion, the image processing circuit 140 also performs various image processing such as image processing (smoothing processing) for regenerating an average value image of brightness by using a plurality of image frames after scan conversion. , Image processing (edge enhancement processing) using a differential filter in the image is performed. Further, the image processing circuit 140 synthesizes character information, scales, body marks, etc. of various parameters with the ultrasonic image data.

That is, the B mode data and the Doppler data are ultrasonic image data before the scan conversion process, and the data generated by the image processing circuit 140 is the ultrasonic image data for display after the scan conversion process. The B-mode data and Doppler data are also referred to as raw data (Raw Data). The image processing circuit 140 generates two-dimensional ultrasonic image data for display from the two-dimensional ultrasonic image data before the scan conversion process.

Further, the image processing circuit 140 generates three-dimensional B-mode image data by performing coordinate conversion on the three-dimensional B-mode data generated by the B-mode processing circuit 120. Further, the image processing circuit 140 generates 3D Doppler image data by performing coordinate conversion on the 3D Doppler data generated by the Doppler processing circuit 130.

Further, the image processing circuit 140 performs rendering processing on the volume image data in order to generate various two-dimensional image data for displaying the volume image data on the display 103. The rendering process performed by the image processing circuit 140 includes, for example, a process of performing a multi-section reconstruction method (MPR: Multi Planer Reconstruction) to generate MPR image data from volume image data. Further, as the rendering process performed by the image processing circuit 140, for example, there is a volume rendering (VR) process for generating two-dimensional image data reflecting the information of the three-dimensional image. Further, as the rendering process performed by the image processing circuit 140, for example, there is a surface rendering (SR: Surface Rendering) process for generating two-dimensional image data by extracting only the surface information of the three-dimensional image.

The image processing circuit 140 stores the generated image data and the image data subjected to various image processing in the image memory 150. The image processing circuit 140 also generates information indicating the display position of each image data, various information for assisting the operation of the ultrasonic diagnostic apparatus 1, and incidental information related to diagnosis such as patient information, together with the image data. It may be stored in the memory 150.

Further, the image processing circuit 140 according to the present embodiment executes the image generation function 141, the detection function 142, the estimation function 143, and the display control function 144. The detection function 142 is an example of a detection unit. The estimation function 143 is an example of an estimation unit. The display control function 144 is an example of an output unit.

Here, each processing function executed by the image generation function 141, the detection function 142, the estimation function 143, and the display control function 144, which are the components of the image processing circuit 140 shown in FIG. 1, is, for example, a program that can be executed by a computer. It is recorded in the storage circuit 160 in the form. The image processing circuit 140 is a processor that realizes a function corresponding to each program by reading each program from the storage circuit 160 and executing the program. In other words, the image processing circuit 140 in the state where each program is read out has each function shown in the image processing circuit 140 of FIG. The processing contents of the image generation function 141, the detection function 142, the estimation function 143, and the display control function 144 executed by the image processing circuit 140 will be described later.

In FIG. 1, it is assumed that each processing function performed by the image generation function 141, the detection function 142, the estimation function 143, and the display control function 144 is realized in the single image processing circuit 140. A processing circuit may be configured by combining a plurality of independent processors, and the function may be realized by each processor executing a program.

The word "processor" used in the above description is, for example, a CPU (Central Processing Unit), a GPU (Graphics Processing Unit), an integrated circuit for a specific application (Application Specific Integrated Circuit (ASIC)), or a programmable logic device (for example, a simple one). It means a circuit such as a programmable logic device (Simple Programmable Logic Device: SPLD), a complex programmable logic device (CPLD), and a field programmable gate array (FPGA). When the processor is, for example, a CPU, the processor realizes the function by reading and executing the program stored in the storage circuit 60. On the other hand, when the processor is, for example, an ASIC, the program is directly incorporated in the circuit of the processor instead of storing the program in the storage circuit 60. It should be noted that each processor of the present embodiment is not limited to the case where each processor is configured as a single circuit, and a plurality of independent circuits may be combined to form one processor to realize its function. good. Further, a plurality of components in FIG. 1 may be integrated into one processor to realize the function.

The image memory 150 and the storage circuit 160 are, for example, semiconductor memory elements such as RAM (Random Access Memory) and flash memory (Flash Memory), or storage devices such as hard disk and optical disk.

The image memory 150 is a memory that stores image data such as B-mode image data and Doppler image data generated by the image processing circuit 140 as ultrasonic image data. Further, the image memory 150 can also store image data such as B mode data generated by the B mode processing circuit 120 and Doppler data generated by the Doppler processing circuit 130 as ultrasonic image data. The ultrasonic image data stored in the image memory 150 can be called by an operator after diagnosis, for example, and becomes the ultrasonic image data for display via the image processing circuit 140.

The storage circuit 160 stores control programs for ultrasonic transmission / reception, image processing, and display processing, diagnostic information (for example, patient ID, doctor's findings, etc.), and various data such as diagnostic protocols and various body marks. .. Further, the data stored in the storage circuit 160 can be transferred to an external device via an interface unit (not shown). The external device is, for example, a PC (Personal Computer) used by a doctor who performs image diagnosis, a storage medium such as a CD or a DVD, a printer, or the like. Further, the storage circuit 160 may not be built in the ultrasonic diagnostic device 1 as long as the ultrasonic diagnostic device 1 is accessible on the network 2.

Further, the storage circuit 160 stores the trained model 400. The trained model 400 is a model generated by training using ultrasonic image data when an ultrasonic scan was performed in the past and training data representing a region including a measurement site in the ultrasonic image data. .. Examples of the learning include learning using AI (Artificial Intelligence) based on a neural network, machine learning, and the like. By the training, the trained model 400 receives the input of the ultrasonic image data which is the input data, and has a function to output the output data showing the result of detecting the region including the measurement site in the ultrasonic image data. Has been done. Here, examples of the measurement site include the head, abdomen, thigh, and upper arm of the foetation. The use and generation of the trained model 400 will be described later.

The control circuit 170 controls the entire processing of the ultrasonic diagnostic apparatus 1. Specifically, the control circuit 170 is a transmission / reception circuit 110 and a B mode processing circuit based on various setting requests input from the operator via the input device 102, various control programs read from the storage circuit 160, and various data. It controls the processing of 120, the Doppler processing circuit 130, the image processing circuit 140, and the like.

The transmission / reception circuit 110, the B mode processing circuit 120, the Doppler processing circuit 130, the image processing circuit 140, the control circuit 170, and the like built in the apparatus main body 100 include a processor (CPU (Central Processing Unit)) and an MPU (Micro-Processing). It may be composed of hardware such as Unit), integrated circuit, etc., but it may also be composed of software-modularized programs.

In the ultrasonic diagnostic apparatus 1 configured as described above, for example, the ultrasonic probe 101 includes a part (measurement site) of the fetus in the womb of the pregnant woman for the purpose of confirming the growth of the fetal in the womb of the pregnant woman. Transmission and reception of ultrasonic waves (ultrasonic scan) is executed for the region, and the image processing circuit 140 generates an ultrasonic image in which the region including the measurement site is imaged based on the scan result. For example, in the ultrasonic diagnostic apparatus 1, instead of manual measurement using a caliper, measurement sites such as the head and abdomen of the fetal are automatically detected from ultrasonic images, and the large lateral diameter of the fetal head (BPD). ), Peripheral length of the baby's head (HC), Peripheral abdomen (AC), Femoral bone length (FL), humeral bone length (HL), and other parameters are estimated. Further, in the ultrasonic diagnostic apparatus 1, the estimated fetal weight (EFW) can be calculated by using the parameters measured using the above measurement points.

The overall configuration of the ultrasonic diagnostic apparatus 1 according to the present embodiment has been described above. Under such a configuration, the ultrasonic diagnostic apparatus 1 according to the present embodiment can improve the accuracy of measurement using an ultrasonic image.

For example, when measuring parameters such as BPD, HC, AC, FL, and HL, there is known a method of estimating a measurement point for measuring a measurement site by image processing based on luminance. Specifically, when measuring parameters such as BPD, HC, and AC from an ultrasonic image, the contour of the measured part such as the head and abdomen is approximated by an ellipse, and the ultrasonic image is based on the brightness value. By detecting the elliptical high-luminance region, the measurement point for measuring the measurement site is estimated. In such a case, the measurement point is the end point of the long axis of the ellipse or the end point of the short axis. Similarly, when measuring parameters such as FL and HL from an ultrasonic image, a rod-shaped region corresponding to a measurement site such as a femur or a humerus is detected in the ultrasonic image based on a brightness value. Estimate the measurement point for measuring the measurement site. In such a case, the measurement points are the points at both ends of the rod-shaped region. However, when this method is applied, there are the following problems.

FIG. 2 is a diagram for explaining a problem when measuring a measurement site. For example, when measuring HC from an ultrasonic image, as shown in FIG. 2, a measurement point P101 for measuring the measurement site by detecting an elliptical HC100 that approximates the contour of the measurement site using luminance. ~ P103 is estimated. However, if there is a portion of the ultrasonic image whose brightness is higher than the contour of the actual measurement portion represented by the ellipse HC100, the measurement point may be estimated by the portion having the higher brightness. For example, as shown in FIG. 2, when there is a portion having a brightness higher than the contour represented by the ellipse HC100 and the ellipse HC200 is detected so as to include the portion, the point P201 located outside the measurement portion is the measurement point. Estimated as. In this way, when the measurement part is detected based on the brightness, the correct measurement point may not be estimated due to the high brightness part other than the measurement part. Therefore, parameters such as BPD, HC, AC, FL, and HL may be used. In some cases, it was not possible to measure accurately.

Therefore, in the ultrasonic diagnostic apparatus 1 according to the present embodiment, the detection function 142 detects the first rectangle including the measurement site from the ultrasonic image. The estimation function 143 estimates a measurement point for measuring a measurement site based on the position information of the first rectangle. The display control function 144 outputs information about the measurement point.

Hereinafter, each function of the image generation function 141, the detection function 142, the estimation function 143, and the display control function 144 will be described with reference to FIGS. 3 to 8.

3 to 7 are diagrams for explaining the processing by the image processing circuit 140 of the ultrasonic diagnostic apparatus 1 according to the present embodiment. 3 to 7 are explanatory views when, for example, the ultrasonic diagnostic apparatus 1 measures the abdominal circumference (AC) of a foetation by using an ultrasonic image. In this case, the measurement site is the abdomen of the foetation. FIG. 8 is a flowchart showing a processing procedure by the ultrasonic diagnostic apparatus 1 according to the present embodiment. FIG. 8 shows a flowchart explaining the operation (image processing method) of the entire ultrasonic diagnostic apparatus 1, and describes which step of the flowchart each component corresponds to.

Step S101 in FIG. 8 is a step performed by the ultrasonic probe 101. In step S101, the ultrasonic probe 101 performs an ultrasonic scan. Specifically, the ultrasonic probe 101 is in contact with the body surface of the subject P (the abdomen of the pregnant woman), and an ultrasonic scan is performed on the region including a part (measurement site) of the foetation in the womb of the pregnant woman. Then, as a result of the ultrasonic scan, the reflected wave signal in the above region is collected.

Step S102 of FIG. 8 is a step in which the image processing circuit 140 calls a program corresponding to the image generation function 141 from the storage circuit 160 and is executed. In step S102, the image generation function 141 generates an ultrasonic image.

Specifically, the image generation function 141 generates an ultrasonic image 200 as shown in FIG. 3 based on the reflected wave signal obtained by the ultrasonic probe 101. The ultrasonic image 200 is ultrasonic image data in which a region including a measurement site is imaged. Here, the image generation function 141 may generate the ultrasonic image 200 by generating B-mode image data using the B-mode data generated by the B-mode processing circuit 120, or the image memory 150. The ultrasonic image 200 may be generated by using the ultrasonic image data stored in.

Step S103 of FIG. 8 is a step in which the image processing circuit 140 calls a program corresponding to the detection function 142 from the storage circuit 160 and is executed. In step S103, the detection function 142 detects the first bounding box including the measurement site from the ultrasonic image 200.

Specifically, first, the detection function 142 detects the measurement site from the ultrasonic image 200 by using the learned model 400 read from the storage circuit 160. The trained model 400 receives the input of the ultrasonic image data which is the input data, and outputs the output data which is the result of detecting the measurement site in the ultrasonic image data. For example, the trained model 400 outputs a rectangle including an ellipse that approximates the contour of the abdomen, which is a measurement site, as output data. Such a rectangle is also called a bounding box (boundary rectangle). The detection function 142 indicates the position and size of the abdomen of the foetation whose contour is approximated by an ellipse by inputting the ultrasonic image 200 into the trained model 400, and as a bounding box containing the abdomen of the fetal, FIG. The first bounding box 210 as shown in is detected. The first bounding box 210 is an example of a "first rectangle".

Further, the detection function 142 detects a predetermined structure from the ultrasonic image 200 by using the trained model 400. The trained model 400 receives the input of the ultrasonic image data which is the input data, and outputs the output data which is the result of detecting the predetermined structure in the ultrasonic image data. If the measurement site is the abdomen of the foetation, the predetermined structure is the spine of the foetation. For example, as shown in FIG. 4, the detection function 142 detects the spine 202 by inputting the ultrasonic image 200 into the trained model 400, and outputs the spine 202 as output data.

Here, the estimation function 143 estimates a temporary measurement point for measuring the abdomen of the foetation based on the position information of the first bounding box 210. For example, as shown in FIG. 4, the estimation function 143 estimates points 211 to 213 inscribed in the first bounding box 210 by an ellipse that approximates the contour of the abdomen of the foetation as temporary measurement points. The measurement points 211 to 213 are the end points of the long axis and the short axis of the ellipse inscribed in the first bounding box 210, and are the midpoints of the long side and the short side of the first bounding box 210.

Step S104 of FIG. 8 is a step in which the image processing circuit 140 calls a program corresponding to the detection function 142 from the storage circuit 160 and is executed. In step S104, the detection function 142 detects the orientation of the measurement site based on the position information of the first bounding box 210 and the position information of a predetermined structure.

Specifically, first, as shown in FIG. 4, the detection function 142 connects the center C210 of the first bounding box 210 and the center of the fetal spine 202, which is a predetermined structure, in the ultrasonic image 200. The line segment L210 is detected. Next, the detection function 142 detects the direction of the line segment L210 as the direction of the abdomen of the foetation, which is the measurement site. In the example shown in FIG. 4, the direction of the line segment L210 is tilted clockwise or counterclockwise by an angle θ with respect to the vertical direction or the horizontal direction of the screen on which the ultrasonic image 200 is displayed. Represents. The vertical direction and the horizontal direction of the screen on which the ultrasonic image 200 is displayed correspond to the column direction and the row direction of the pixels of the ultrasonic image 200, respectively. For example, as shown in FIG. 4, the direction of the line segment L210 is tilted counterclockwise by an angle θ with respect to the vertical direction of the screen on which the ultrasonic image 200 is displayed.

Step S105 in FIG. 8 is a step in which the image processing circuit 140 calls a program corresponding to the detection function 142 from the storage circuit 160 and is executed. In step S105, the detection function 142 performs a process of determining whether or not the measurement portion detected in step S104 is tilted.

As described above, the direction of the line segment L210 detected by the detection function 142 can be regarded as the direction of the abdomen of the foetation, which is the measurement site. For example, the abdomen depicted in the ultrasonic image 200 can be considered to be tilted counterclockwise by an angle θ with respect to the vertical direction of the screen on which the ultrasonic image 200 is displayed. In this case, in the determination process of step S105, the detection function 142 determines that the measurement site detected in step S104 is tilted (step S105; Yes).

Step S106 of FIG. 8 is a step in which the image processing circuit 140 calls a program corresponding to the detection function 142 from the storage circuit 160 and is executed. In step S106, the detection function 142 performs rotation processing on the ultrasonic image 200 based on the orientation of the measurement site detected in step S104. Specifically, the detection function 142 performs rotation processing so that the direction of the line segment L210 is the vertical direction or the horizontal direction of the screen on which the ultrasonic image 200 is displayed.

By performing the rotation process, there is a high possibility that the anterior-posterior direction of the abdomen of the foetation, which is the measurement site, becomes the vertical direction or the horizontal direction of the screen, and the left-right direction becomes the horizontal direction or the vertical direction of the screen. That is, by performing the rotation process, there is a high possibility that the long axis or the short axis of the ellipse detected as the contour of the abdomen becomes the vertical direction or the horizontal direction of the screen on which the ultrasonic image 200 is displayed. Further, by performing such rotation processing, there is a high possibility that one side of the bounding box will be in the vertical direction or the horizontal direction of the screen on which the ultrasonic image 200 is displayed.

For example, as shown in FIG. 5, the detection function 142 performs rotation processing so that the direction of the line segment L210 is the vertical direction of the screen on which the ultrasonic image 200 is displayed. That is, since the direction of the line segment L210 is tilted counterclockwise by an angle θ with respect to the vertical direction of the screen on which the ultrasonic image 200 is displayed, the detection function 142 displays the ultrasonic image 200. Rotate clockwise by an angle θ.

Step S107 of FIG. 8 is a step in which the image processing circuit 140 calls a program corresponding to the detection function 142 from the storage circuit 160 and is executed. In step S107, the detection function 142 detects the second bounding box including the measurement site from the ultrasonic image 200 after the rotation process executed in step S106.

Specifically, the detection function 142 indicates the position and size of the fetal abdomen whose contour is approximated by an ellipse by inputting the ultrasonic image 200 after the rotation processing into the trained model 400, and indicates the position and size of the fetal abdomen. A second bounding box 220 as shown in FIG. 5 is detected as a bounding box containing the above. In this case, the bounding box is changed from the first bounding box 210 to the second bounding box 220. For example, the second bounding box 220 is an example of a "second rectangle".

Step S108 of FIG. 8 is a step in which the image processing circuit 140 calls a program corresponding to the estimation function 143 from the storage circuit 160 and is executed. In step S108, the estimation function 143 estimates a measurement point for measuring the abdomen of the foetation based on the position information of the second bounding box 220.

Specifically, as shown in FIG. 5, the estimation function 143 estimates points 221 to 223 inscribed in the second bounding box 220 by the ellipse 224 that approximates the contour of the abdomen of the foetation as measurement points. The points 221 to 223 are the end points of the long axis and the end points of the short axis of the ellipse 224, and are the midpoints of the long side and the short side of the second bounding box 220. In this case, the estimation function 143 uses measurement points 211 to 213 based on the position information of the first bounding box 210 as measurement points for measuring the abdomen of the foetation, and measurement points 221 based on the position information of the second bounding box 220. Update to ~ 223.

In the determination process of step S105, the ultrasonic image 200 displays the direction of the line segment L210 detected by the detection function 142 when the vertical direction or the horizontal direction of the screen on which the ultrasonic image 200 is displayed is used as a reference. When the screen is in the vertical or horizontal direction, the abdomen depicted in the ultrasonic image 200 can be regarded as not tilted. In this case, the detection function 142 determines that the measurement site detected in step S104 is not tilted (step S105; No), and step S108 is executed without executing steps S106 and S107. That is, the detection function 142 does not rotate the ultrasonic image 200, and in step S108, the estimation function 143 measures the measurement points 211 to 213 based on the position information of the first bounding box 210 and the abdomen of the foetation. It is a measurement point for this.

Step S109 of FIG. 8 is a step in which the image processing circuit 140 calls a program corresponding to the display control function 144 from the storage circuit 160 and is executed. In step S109, the display control function 144 outputs information on the measurement points 221 to 223 on the screen.

For example, the display control function 144 displays, as information on the measurement points 221 to 223, an image on the display 103 in which the mark indicating the position of the measurement points 221 to 223 is drawn on the ultrasonic image 200 before the rotation processing is performed. Let me. Specifically, first, as shown in FIG. 5, the display control function 144 draws a mark indicating the position of the measurement points 221 to 223 on the ultrasonic image 200 after the rotation process. Here, the ultrasonic image 200 on which the mark indicating the position of the measurement points 221 to 223 is drawn is an image obtained by rotating the ultrasonic image 200 shown in FIG. 4 clockwise by an angle θ. Therefore, as shown in FIG. 6, the display control function 144 rotates the ultrasonic image 200 on which the mark indicating the position of the measurement points 221 to 223 is drawn by an angle θ counterclockwise. At this time, as shown in FIG. 7, the display 103 displays an image in which the marks indicating the positions of the measurement points 221 to 223 are drawn on the ultrasonic image 200 before the rotation processing is performed. Further, on the display 103, an ellipse 224 in which the measurement points 221 to 223 serve as the end points of the long axis and the end points of the short axis is displayed superimposed on the image.

Here, the display control function 144 may notify the operator that the measurement points 221 to 223 have been estimated when the image shown in FIG. 7 is displayed on the display 103 as information regarding the measurement points 221 to 223. good. For example, the input device 102 or the display 103 is provided with a lamp such as an LED (Light Emitting Diode), and the display control function 144 indicates that the measurement points 221 to 223 are estimated by turning on the lamp. Then, the image shown in FIG. 7 may be displayed on the display 103. For example, the display control function 144 may display on the display 103 that the measurement points 221 to 223 have been estimated by a message, and then display the image shown in FIG. 7 on the display 103. For example, the display 103 may have a speaker (not shown), and the display control function 144 may output a predetermined sound such as a beep sound, and then display the image shown in FIG. 7 on the display 103.

The mark displayed on the image shown in FIG. 7 can be changed by the operator. For example, the operator can move the mark displayed on the image by operating the input device 102.

Thereby, the estimation function 143 can measure the abdominal circumference (AC) of the foetation by using the ultrasonic image 200 and the measurement points 221 to 223. For example, the estimation function 143 measures the length around the ellipse 224 formed by the measurement points 221 to 223 as AC in the ultrasonic image 200.

As described above, in the ultrasonic diagnostic apparatus 1 according to the present embodiment, the detection function 142 detects the first bounding box 210 including the measurement site from the ultrasonic image 200, and the estimation function 143 is the first bounding box. Based on the position information of 210, the measurement point for measuring the measurement site is estimated. Specifically, the detection function 142 detects a predetermined structure from the ultrasonic image 200 together with the first bounding box 210. Next, the detection function 142 performs rotation processing on the ultrasonic image 200 based on the position information of the predetermined structure and the position information of the first bounding box 210, and the rotation processing of the ultrasonic waves is performed. From the image 200, the second bounding box 220 including the measurement site is detected. Next, the estimation function 143 uses measurement points 211 to 213 based on the position information of the first bounding box 210 as measurement points for measuring the measurement site, and measurement points 221 to 221 based on the position information of the second bounding box 220. Update to 223. Then, the display control function 144 outputs information regarding the measurement points 221 to 223.

As a result, in the ultrasonic diagnostic apparatus 1 according to the present embodiment, the ellipse that fits the contour of the measurement site is detected based on the high-intensity region, and the measurement point is not estimated, but the bounding box that includes the entire measurement site is included. Is detected and the measurement point is estimated, so that the accuracy of measurement using the ultrasonic image 200 is improved. Further, in the ultrasonic diagnostic apparatus 1 according to the present embodiment, since the measurement points are estimated from the entire measurement site by using the bounding box, the measurement points are more efficiently estimated than the measurement points whose features are difficult to appear one by one. Can be estimated.

Further, although not limited to the detection using the trained model 400, in the site detection, the site can be detected at a more accurate position when the posture of the site to be detected is not tilted. In the present embodiment, the measurement site is detected by the bounding box, a predetermined structure capable of estimating the posture of the measurement site is detected, and one side of the bounding box containing the measurement site is in the vertical or horizontal direction. Rotate the image to be detected. Then, in the present embodiment, by performing the bounding box detection process again from the image after the rotation process, the site can be detected at a more accurate position, and as a result, the estimation accuracy of the measurement point is also improved. be able to.

In the above-described embodiment, the case of measuring the abdominal circumference (AC) of the foetation has been described, but the present invention is not limited to this, and the fetal head circumference (BPD), fetal head circumference (HC), and femur are not limited thereto. This embodiment can also be applied when measuring parameters such as length (FL) and humerus length (HL).

First, a case of measuring parameters such as BPD and HC will be described. FIG. 9 is a diagram for explaining processing by the image processing circuit of the ultrasonic diagnostic apparatus according to the present embodiment, and is an explanatory diagram when measuring parameters such as BPD and HC.

For example, after steps S101 and S102 are executed, in step S103, the detection function 142 detects the first bounding box including the measurement site from the ultrasonic image. Specifically, the detection function 142 indicates the position and size of the fetal head whose contour is approximated by an ellipse by inputting the ultrasonic image 500 into the trained model 400, and includes the fetal head. As the bounding box to be used, the first bounding box 510 as shown in FIG. 9 is detected. Further, the detection function 142 detects a predetermined structure by inputting the ultrasonic image 500 into the trained model 400. For example, if the measurement site is the head of the foetation, the predetermined structure is the septum pellucidum 502 of the foetation. Here, the estimation function 143 estimates a temporary measurement point for measuring the head of the foetation based on the position information of the first bounding box 510. For example, as shown in FIG. 9, the estimation function 143 estimates points 511 to 514 inscribed in the first bounding box 510 by an ellipse that approximates the contour of the head of the foetation as temporary measurement points.

In step S104, the detection function 142 detects the orientation of the measurement site based on the position information of the first bounding box 510 and the position information of the predetermined structure. Specifically, first, as shown in FIG. 9, the detection function 142 performs the center C510 of the first bounding box 510 and the center of the transparent septum 502 of the foetation, which is a predetermined structure, in the ultrasonic image 500. The line segment L510 connecting the portions is detected. Next, the detection function 142 detects the direction of the line segment L510 as the direction of the head of the foetation, which is the measurement site. For example, when the vertical direction or the horizontal direction of the screen on which the ultrasonic image 500 is displayed is used as a reference, the direction of the line segment L510 is the horizontal direction of the screen on which the ultrasonic image 500 is displayed.

In step S105, the detection function 142 performs a process of determining whether or not the measurement portion detected in step S104 is tilted.

In the determination process of step S105, when the vertical direction or the horizontal direction of the screen on which the ultrasonic image 500 is displayed is used as a reference, the direction of the line segment L510 detected by the detection function 142 is the screen on which the ultrasonic image 500 is displayed. When it is in the vertical or horizontal direction, the head depicted in the ultrasonic image 500 can be regarded as not tilted. In this case, the detection function 142 determines that the measurement site detected in step S104 is not tilted (step S105; No), and the process of step S108 is executed without the process of steps S106 and S107 being executed. That is, the detection function 142 does not rotate the ultrasonic image 500, and in step S108, the estimation function 143 sets the measurement points 511 to 514 based on the position information of the first bounding box 310 to the head of the foetation. It is a measurement point for measurement.

In step S109, the display control function 144 causes the display 103 to display an image drawn on the ultrasonic image 500 by a mark indicating the position of the measurement points 511 to 514 as information regarding the measurement points 511 to 514.

As a result, the estimation function 143 can measure HC by using the ultrasonic image 500 and the measurement points 511 to 514. For example, the estimation function 143 measures the length around the ellipse formed by the measurement points 511 to 514 as HC in the ultrasonic image 500.

As a result, the estimation function 143 can measure HC by using the ultrasonic image 500 and the measurement points 511 to 514. For example, the estimation function 143 measures the length around the ellipse formed by the measurement points 511 to 514 as HC in the ultrasonic image 500.

Further, the estimation function 143 can measure the BPD by using the ultrasonic image 500 and the measurement points 513 and 514. For example, the estimation function 143 measures the length of the line segment connecting the measurement points 513 and the measurement points 514 as the BPD in the ultrasonic image 500.

When the detection function 142 determines in the determination process of step S105 that the measurement site detected in step S104 is tilted (step S105; Yes), the following processes of steps S106 to S109 are executed.

First, in step S106, the detection function 142 performs rotation processing on the ultrasonic image 500 based on the orientation of the measurement site detected in step S104. Specifically, the detection function 142 performs rotation processing so that the direction of the line segment L510 is the vertical direction or the horizontal direction of the screen on which the ultrasonic image 500 is displayed. Next, in step S107, the detection function 142 detects the second bounding box including the measurement site from the ultrasonic image 500 after the rotation process executed in step S106. Specifically, the detection function 142 indicates the position and size of the head of the foetation whose contour is approximated by an ellipse by inputting the ultrasonic image 500 after the rotation processing into the trained model 400. The second bounding box is detected as a bounding box containing the head.

Next, in step S108, the estimation function 143 estimates a measurement point for measuring the head of the foetation based on the position information of the second bounding box. Specifically, the estimation function 143 estimates a point inscribed in the second bounding box by an ellipse that approximates the contour of the head of the foetation as a measurement point. In this case, the estimation function 143 changes the measurement points 511 to 514 based on the position information of the first bounding box 510 to the measurement points based on the position information of the second bounding box as measurement points for measuring the head of the foetation. Update. Then, in step S109, the display control function 144 causes the display 103 to display the image drawn on the ultrasonic image 500 by the mark indicating the position of the updated measurement point as the information regarding the measurement point.

In step S103, for example, when the measurement site is the head of the foetation, the predetermined structure is the transparent septum 502 of the foetation, but the present invention is not limited to this.

For example, as shown in FIG. 10, when the measurement site is the head of a foetation, the predetermined structure may be the corpora quadrigem 503 of the foetation. In this case, in step S104, first, as shown in FIG. 10, the detection function 142 has the center C510 of the first bounding box 510 and the fetal quadrigem tank 503, which is a predetermined structure, in the ultrasonic image 500. The line segment L510 connecting to the central portion of the above is detected. Next, the detection function 142 detects the direction of the line segment L510 as the direction of the head of the foetation, which is the measurement site. After that, the processing after step S105 is performed. For example, when the measurement site is not tilted (step S105; No), the measurement points 511 to 514 are estimated from the position information of the first bounding box 310 without performing the rotation processing on the ultrasonic image 500 (step S108). ), Information about the measurement points 511 to 514 is displayed on the display 103 (step S109). On the other hand, the measurement site is tilted (step S105; Yes), rotation processing is performed on the ultrasonic image 500 (step S106), and the second bounding including the measurement site is taken from the ultrasonic image 500 after the rotation processing. The box is detected (step S107). Then, the measurement point is estimated from the position information of the second bounding box (step S108), and the information about the measurement point is displayed on the display 103 (step S109). In the example shown in FIG. 10, even when the predetermined structure is the corpora quadrigem 503 of the foetation, the orientation of the head of the foetation is detected as in the case where the predetermined structure is the septum pellucidum 502. be able to.

Further, for example, as shown in FIG. 11, when the measurement site is the head of the foetation, the predetermined structures may be the fetal septum pellucidum 502 and the quadrigemular cistern 503. In this case, in step S104, first, as shown in FIG. 11, in the ultrasonic image 500, the detection function 142 has the center C510 of the first bounding box 510 and the transparent septum 502 of the foetation which is a predetermined structure. And the line segment L510 connecting the central part of the four hill body tank 503 is detected. Next, the detection function 142 detects the direction of the line segment L510 as the direction of the head of the foetation, which is the measurement site. After that, the processing after step S105 is performed. For example, when the measurement site is not tilted (step S105; No), the measurement points 511 to 514 are estimated from the position information of the first bounding box 310 without performing the rotation processing on the ultrasonic image 500 (step S108). ), Information about the measurement points 511 to 514 is displayed on the display 103 (step S109). On the other hand, the measurement site is tilted (step S105; Yes), rotation processing is performed on the ultrasonic image 500 (step S106), and the second bounding including the measurement site is taken from the ultrasonic image 500 after the rotation processing. The box is detected (step S107). Then, the measurement point is estimated from the position information of the second bounding box (step S108), and the information about the measurement point is displayed on the display 103 (step S109). In the example shown in FIG. 11, since the predetermined structure is the fetal transparent septum 502 and the quadrigemular cistern 503, the predetermined structure is either the transparent septum 502 or the quadrigemular cistern 503. The orientation of the fetal head can be detected more accurately than in the case.

Next, the case of measuring FL will be described. FIG. 12 is a diagram for explaining processing by the image processing circuit of the ultrasonic diagnostic apparatus according to the present embodiment, and is an explanatory diagram in the case of measuring FL.

For example, after steps S101 and S102 are executed, in step S103, the detection function 142 detects the first bounding box including the measurement site from the ultrasonic image. Specifically, when the ultrasonic image data is input, the trained model 400 outputs a bounding box circumscribing to the rod-shaped region corresponding to the femur, which is the measurement site, as output data. The detection function 142 indicates the position and size of the fetal thigh approximated to a rod-shaped region by inputting an ultrasonic image 600 into the trained model 400, and a bounding box containing the fetal thigh. As shown in FIG. 12, the first bounding box 610 is detected. Here, the detection function 142 does not execute steps S104 to S107 when the measurement site is the femur or the humerus.

In step S108, the estimation function 143 estimates a measurement point for measuring the thigh of the foetation based on the position information of the first bounding box 610. For example, as shown in FIG. 12, the estimation function 143 estimates points 611 and 612 inscribed in the first bounding box 610 as measurement points by the rod-shaped region corresponding to the thigh of the foetation. The measurement points 611 and 612 correspond to both ends of the femur.

In step S109, the display control function 144 causes the display 103 to display an image drawn on the ultrasonic image 600 by a mark indicating the position of the measurement points 611 and 612 as information regarding the measurement points 611 and 612.

As a result, the estimation function 143 can measure FL by using the ultrasonic image 600 and the measurement points 611 and 612. For example, the estimation function 143 measures the length of the line segment connecting the measurement points 611 and the measurement points 612 as FL in the ultrasonic image 600.

Similarly, in the case of measuring HL, for example, by executing steps S101 to S103, S108, and S109, the estimation function 143 determines the length of the line segment connecting the two measurement points in the ultrasonic image. Measure as HL.

Here, a process of generating a trained model 400 by machine learning will be described.

The trained model 400 is generated by, for example, a device different from the ultrasonic diagnostic device 1 (hereinafter, referred to as a trained model generator) and stored in the ultrasonic diagnostic device 1 (for example, a storage circuit). Stored in 160). Here, the trained model generator may be realized by the ultrasonic diagnostic apparatus 1, for example, the trained model 400 is generated by the ultrasonic diagnostic apparatus 1 (for example, the estimation function 143) and its storage circuit. It may be stored in 160. Hereinafter, a case where the trained model 400 is generated by the trained model generator and stored in the ultrasonic diagnostic apparatus 1 will be described as an example.

FIG. 13 is a block diagram showing a configuration example of the trained model generation device 300 in the present embodiment. As shown in FIG. 13, the trained model generation device 300 includes an input device 302, a display 303, an image processing circuit 340, and a storage circuit 360. The trained model generator 300 is used as a viewer for generating the trained model 400.

The input device 302 has a mouse, a keyboard, a button, a panel switch, a touch command screen, a foot switch, a wheel, a trackball, a joystick, and the like, and receives various setting requests from the operator of the trained model generation device 300 and receives an image. The various setting requests received are transferred to the processing circuit 340. The display 303 is a monitor referenced by the operator of the trained model generator 300.

The image processing circuit 340 controls the entire processing of the trained model generation device 300. For example, the image processing circuit 340 executes the learning data acquisition function 341 and the trained model generation function 342 as shown in FIG.

The storage circuit 360 is, for example, a semiconductor memory element such as a RAM or a flash memory, or a storage device such as a hard disk or an optical disk. Here, each processing function executed by the learning data acquisition function 341 and the trained model generation function 342, which are the components of the image processing circuit 340, is recorded in the storage circuit 360 in the form of a program that can be executed by a computer, for example. ing. The image processing circuit 340 is a processor that realizes a function corresponding to each program by reading each program from the storage circuit 360 and executing the program. Further, the storage circuit 360 stores a learning program as an algorithm of the neural network.

In the process of generating the trained model 400, first, the training data acquisition function 341 of the trained model generation device 300 acquires a plurality of data sets obtained when the ultrasonic scan is performed in the past. Each of the plurality of data sets includes ultrasonic image data collected when an ultrasonic scan was performed on the measurement site in the past, and training data representing a region including the measurement site in the ultrasonic image data. Since the neural network algorithm is learned from experience, the data set used for learning does not have to be the same subject.

The trained model generation function 342 of the trained model generation device 300 learns a pattern of training data from a plurality of data sets by using the learning program 502 read from the storage circuit 160. At this time, the trained model generation function 342 is equipped with a function to receive the input of the input data (ultrasonic image data) and output the output data indicating the result of detecting the region including the measurement site in the ultrasonic image data. Generate the trained model 400. For example, the generated trained model 400 is stored in the ultrasonic diagnostic apparatus 1 (stored in the storage circuit 160). The trained model 400 in the storage circuit 160 can be read out by, for example, the detection function 142 of the ultrasonic diagnostic apparatus 1.

In the process using the trained model 400, the detection function 142 of the ultrasonic diagnostic apparatus 1 inputs ultrasonic image data as input data. Then, the detection function 142 detects the region including the measurement site from the ultrasonic image 200, which is the ultrasonic image data, using the trained model 400 read from the storage circuit 160, and outputs the output data as a result of the detection. Output.

In the present embodiment, the case where the trained model 400 is used has been described, but the trained model 400 may not be used. For example, in the present embodiment, a measurement portion such as the abdomen may be detected by image processing using luminance, and then a bounding box including the measurement portion may be detected. In such a case, the present embodiment may detect the measurement part as a part surrounded by an arbitrary curve without detecting the measurement part as a figure applicable to the measurement part such as an ellipse. Further, in the present embodiment, a predetermined structure may also be detected by image processing using luminance without using the trained model 400.

(Other embodiments)
The embodiment is not limited to the above-described embodiment. For example, the image processing circuit 140 may be a workstation installed separately from the ultrasonic diagnostic apparatus 1. In this case, the workstation has a processing circuit similar to the image processing circuit 140 and performs the above-mentioned processing.

Further, each component of each device shown in the embodiment is functionally conceptual, and does not necessarily have to be physically configured as shown in the figure. That is, the specific form of distribution / integration of each device is not limited to the one shown in the figure, and all or part of them may be functionally or physically distributed / physically in arbitrary units according to various loads and usage conditions. Can be integrated and configured. Further, each processing function performed by each device may be realized by a CPU and a program analyzed and executed by the CPU, or may be realized as hardware by wired logic.

Further, the display method described in the above embodiment can be realized by executing an image processing program prepared in advance on a computer such as a personal computer or a workstation. This image processing program can be distributed via a network such as the Internet. Further, this image processing program is recorded on a non-temporary recording medium such as a hard disk, flexible disk (FD), CD-ROM, MO, or DVD that can be read by a computer, and is executed by being read from the recording medium by the computer. You can also do it.

According to at least one embodiment described above, the accuracy of measurement using an ultrasonic image can be improved.

Although some embodiments have been described, these embodiments are presented as examples and are not intended to limit the scope of the invention. These embodiments can be implemented in various other embodiments, and various omissions, replacements, changes, and combinations of embodiments can be made without departing from the gist of the invention. These embodiments and variations thereof are included in the scope of the invention described in the claims and the equivalent scope thereof, as are included in the scope and gist of the invention.

Regarding the above embodiments, the following appendices are disclosed as one aspect and selective features of the invention.
(Appendix 1)
A detector that detects the first rectangle containing the measurement site from the ultrasonic image,
An estimation unit that estimates a measurement point for measuring the measurement site based on the position information of the first rectangle, and an estimation unit.
An output unit that outputs information about the measurement point and
An ultrasonic diagnostic device equipped with.
(Appendix 2)
The detector is
A predetermined structure is detected from the ultrasonic image together with the first rectangle.
Based on the position information of the predetermined structure and the position information of the first rectangle, the ultrasonic image is rotated.
A second rectangle containing the measurement site is detected from the ultrasonic image subjected to the rotation processing, and the second rectangle is detected.
As the measurement point, the estimation unit updates the measurement point based on the position information of the first rectangle to the measurement point based on the position information of the second rectangle.
The output unit may output information about a measurement point based on the position information of the second rectangle.
(Appendix 3)
The detection unit performs the rotation process so that the direction of the line segment connecting the predetermined structure and the center of the first rectangle is the vertical direction or the horizontal direction of the screen on which the ultrasonic image is displayed. You may go.
(Appendix 4)
The detection unit may not perform the rotation process when the direction of the line segment is the vertical direction or the horizontal direction of the screen on which the ultrasonic image is displayed.
(Appendix 5)
When the contour of the measurement site is approximated by an ellipse, the detection unit may make the major axis or the minor axis of the ellipse the vertical or horizontal direction of the screen on which the ultrasonic image is displayed. Rotation processing may be performed.
(Appendix 6)
When the contour of the measurement site is approximated by a rectangle, the detection unit performs the rotation process so that one side of the rectangle is in the vertical or horizontal direction of the screen on which the ultrasonic image is displayed. You may.
(Appendix 7)
The output unit may display an image drawn on the ultrasonic image by a mark indicating the position of the measurement point on the display unit.
(Appendix 8)
The output unit may display an image in which the mark indicating the position of the measurement point is drawn on the ultrasonic image before the rotation process is performed on the display unit.
(Appendix 9)
When the measurement site is the abdomen of the foetation, the predetermined structure may be the spine of the foetation.
(Appendix 10)
When the measurement site is the head of a foetation, the predetermined structure may be at least one of the fetal septum pellucidum and the corpora quadrigem.
(Appendix 11)
A detector that detects the first rectangle containing the measurement site from the ultrasonic image,
An estimation unit that estimates a measurement point for measuring the measurement site based on the position information of the first rectangle, and an estimation unit.
An output unit that outputs information about the measurement point and
An image processing device comprising.

142 Detection function 143 Estimation function 144 Display control function 210 1st bounding box 221 to 223 Measurement point 510 1st bounding box 511 to 513 Measurement point 610 1st bounding box 611 to 613 Measurement point

Claims (11)

A detector that detects the first rectangle containing the measurement site from the ultrasonic image,
An estimation unit that estimates a measurement point for measuring the measurement site based on the position information of the first rectangle, and an estimation unit.
An output unit that outputs information about the measurement point and
An ultrasonic diagnostic device equipped with. The detector is
A predetermined structure is detected from the ultrasonic image together with the first rectangle.
Based on the position information of the predetermined structure and the position information of the first rectangle, the ultrasonic image is rotated.
A second rectangle containing the measurement site is detected from the ultrasonic image subjected to the rotation process.
The estimation unit updates the measurement point based on the position information of the first rectangle to the measurement point based on the position information of the second rectangle as the measurement point.
The output unit outputs information about a measurement point based on the position information of the second rectangle.
The ultrasonic diagnostic apparatus according to claim 1. The detection unit performs the rotation process so that the direction of the line segment connecting the predetermined structure and the center of the first rectangle is the vertical direction or the horizontal direction of the screen on which the ultrasonic image is displayed. conduct,
The ultrasonic diagnostic apparatus according to claim 2. The detection unit does not perform the rotation process when the direction of the line segment is the vertical direction or the horizontal direction of the screen on which the ultrasonic image is displayed.
The ultrasonic diagnostic apparatus according to claim 3. When the contour of the measurement site is approximated by an ellipse, the detection unit may make the major axis or the minor axis of the ellipse the vertical or horizontal direction of the screen on which the ultrasonic image is displayed. Perform rotation processing,
The ultrasonic diagnostic apparatus according to any one of claims 2 to 4. When the contour of the measurement portion is approximated by a rectangle, the detection unit performs the rotation process so that one side of the rectangle is in the vertical or horizontal direction of the screen on which the ultrasonic image is displayed. ,
The ultrasonic diagnostic apparatus according to any one of claims 2 to 4. In the output unit, the mark indicating the position of the measurement point causes the display unit to display the image drawn on the ultrasonic image.
The ultrasonic diagnostic apparatus according to any one of claims 1 to 6. In the output unit, the mark indicating the position of the measurement point causes the display unit to display an image drawn on the ultrasonic image before the rotation process is performed.
The ultrasonic diagnostic apparatus according to any one of claims 2 to 6. When the measurement site is the abdomen of the foetation, the predetermined structure is the spine of the foetation.
The ultrasonic diagnostic apparatus according to any one of claims 2 to 6 and 8. When the measurement site is the head of the foetation, the predetermined structure is at least one of the fetal septum pellucidum and the corporora quadrigem.
The ultrasonic diagnostic apparatus according to any one of claims 2 to 6 and 8. A detector that detects the first rectangle containing the measurement site from the ultrasonic image,
An estimation unit that estimates a measurement point for measuring the measurement site based on the position information of the first rectangle, and an estimation unit.
An output unit that outputs information about the measurement point and
An image processing device comprising.

Images