JP2019115559A - Ultrasound diagnostic apparatus and information processing program - Google Patents

Abstract

To reduce troublesomeness in an operation to measure a structure in an image.SOLUTION: An ultrasound diagnostic apparatus according to the embodiment includes an image generation unit, an estimation unit, a display control unit, and input unit. The image generation unit generates, based on data collected by ultrasound scan on a subject, an ultrasound image corresponding to a region which includes a site of an unborn child. The estimation unit estimates a first shape which is applied to the site on the basis of the ultrasound image. The display control unit causes the ultrasound image to be displayed on a display unit and causes a first marker corresponding to the first shape to be displayed on the ultrasound image. The input unit receives an input which specifies a position on the ultrasound image. The estimation unit, when the input is received after the first marker is displayed, estimates a second shape, of the same type as the first shape, which is applied to the site on the basis of the ultrasound image and the position specified by the input. The display control unit causes a second marker corresponding to the second shape to be displayed on the ultrasound image.SELECTED DRAWING: Figure 1

Description

  Embodiments of the present invention relate to an ultrasonic diagnostic apparatus and an image processing program.

  The ultrasonic diagnostic apparatus radiates an ultrasonic pulse generated from an ultrasonic transducer built in an ultrasonic probe into the subject, receives a reflected wave from the tissue of the subject by the ultrasonic transducer, and generates image data etc. To generate and display the Conventionally, the size of a tissue shape on an ultrasound image, in particular, the fetal parietal diameter (BPD), fetal head circumference (HC), abdominal circumference (AC: abdominal circumference) in the obstetrics area There is known an ultrasonic diagnostic apparatus having a function of measuring a femur length (FL), a humerus length (HL) and the like.

  In such an ultrasonic diagnostic apparatus, it is generally possible to manually measure the size of the tissue shape on the image using a caliper, but in recent years, a technology for automatically or semi-automatically estimating the size has become available. It is disclosed. For example, in measurement of BPD, it is assumed that the fetal head is an ellipse, the shape of the fetal head on the image is estimated by an ellipse, and the length of the short axis of the estimated ellipse is measured as BPD.

U.S. Pat. No. 8,845,539

  The problem to be solved by the present invention is to reduce the complexity of the operation when measuring a structure in an image.

  The ultrasound diagnostic apparatus according to the embodiment includes an image generation unit, an estimation unit, a display control unit, and an input unit. The image generation unit generates an ultrasonic image corresponding to a region including a region of a fetus based on data acquired by an ultrasonic scan on a subject. The estimation unit estimates, based on the ultrasound image, a first figure applicable to the region. The display control unit causes the display unit to display the ultrasonic image, and displays a first marker corresponding to the first graphic on the ultrasonic image. The input unit receives an input for specifying a position on the ultrasound image. When the input unit receives the input after the display control unit displays the first marker, the estimation unit is based on the ultrasonic image and the position specified by the input. A second figure of the same type as the first figure, which is applicable to the part, is estimated. The display control unit causes a second marker corresponding to the second graphic to be displayed on the ultrasound image.

FIG. 1 is a block diagram showing a configuration example of an ultrasonic diagnostic apparatus according to the first embodiment. FIG. 2 is a diagram showing an example of estimation of a first figure by the estimation function according to the first embodiment. FIG. 3 is a diagram for explaining re-estimation of a figure by the estimation function according to the first embodiment. FIG. 4 is a diagram for explaining re-estimation of a figure by the estimation function according to the first embodiment. FIG. 5A is a diagram for explaining an example of parameters of an ellipse according to the first embodiment. FIG. 5B is a diagram for explaining an example of parameters of an ellipse according to the first embodiment. FIG. 5C is a diagram for explaining an example of parameters of an ellipse according to the first embodiment. FIG. 6 is a view showing an example of display by the control function according to the first embodiment. FIG. 7 is a flowchart showing the processing procedure of the ultrasonic diagnostic apparatus according to the first embodiment. FIG. 8 is a flowchart showing the processing procedure of the ultrasonic diagnostic apparatus according to the first embodiment. FIG. 9 is a diagram for explaining an example of estimation of a figure by the estimation function according to the second embodiment. FIG. 10 is a flowchart showing the processing procedure of the ultrasonic diagnostic apparatus according to the second embodiment. FIG. 11 is a diagram illustrating an example of estimation of a rectangle by the estimation function according to the third embodiment. FIG. 12 is a flowchart showing the processing procedure of the ultrasonic diagnostic apparatus according to the third embodiment. FIG. 13 is a diagram for explaining an example of processing by the estimation function according to the third embodiment.

  An ultrasonic diagnostic apparatus and an image processing program according to the embodiment will be described below with reference to the drawings. Note that the embodiment described below is an example, and the ultrasonic diagnostic apparatus and the image processing program according to the present embodiment are not limited to the following description.

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

  The ultrasonic probe 101 has a plurality of piezoelectric vibrators, and the plurality of piezoelectric vibrators generate ultrasonic waves based on drive signals supplied from the transmission / reception circuit 110 of the apparatus main body 100. In addition, the ultrasonic probe 101 receives a reflected wave from the subject P and converts it into an electric signal. That is, the ultrasound probe 101 performs ultrasound scanning on the subject P, and receives a reflected wave from the subject P. In addition, the ultrasonic probe 101 has a matching layer provided in the piezoelectric vibrator, a backing material that prevents the propagation of ultrasonic waves from the piezoelectric vibrator to the rear, and the like. The ultrasonic probe 101 is detachably connected to the apparatus main body 100.

  When an ultrasonic wave is transmitted from the ultrasonic probe 101 to the subject P, the transmitted ultrasonic wave is reflected one after another by the discontinuous surface of the acoustic impedance in the body tissue of the subject P, and the ultrasonic probe as a reflected wave signal A plurality of piezoelectric vibrators 101 are received. The amplitude of the received reflected wave signal depends on the difference in acoustic impedance at the discontinuity where the ultrasound is reflected. Note that the reflected wave signal when the transmitted ultrasonic pulse is reflected by the moving blood flow, the surface of the heart wall or the like depends on the velocity component of the moving body in the ultrasonic transmission direction by the Doppler effect. Receive a frequency shift.

  In this embodiment, the ultrasonic probe 101 may be a 1D array probe that scans an object in two dimensions, or a three-dimensional probe that scans an object in three dimensions, that is, a mechanical 4D probe or a 2D array probe. It is applicable. In obstetrics ultrasound, mechanical 4D probes are often used because of the requirement for visualizing the fetus in three dimensions. When using a three-dimensional probe, the display image on the display 103 includes a specific tomogram or multi planar reconstruction (MPR).

  The input interface 102 contacts the trackball, the switch button, the mouse, the keyboard, and the operation surface for setting a predetermined position (for example, the position of the tissue shape, the region of interest, the region other than the region of interest, etc.). A touch pad for performing an input operation, a touch command screen in which a display screen and a touch pad are integrated, a non-contact input circuit using an optical sensor, an audio input circuit, and the like are realized. The input interface 102 is connected to a processing circuit 150 described later, converts an input operation received from an operator (user) into an electric signal, and outputs the electric signal to the processing circuit 150. In the present specification, the input interface 102 is not limited to one having physical operation components such as a mouse and a keyboard. For example, an electrical signal processing circuit that receives an electrical signal corresponding to an input operation from an external input device provided separately from the device and outputs the electrical signal to the control circuit is also included in the example of the input interface. The input interface 102 is an example of an input unit.

  The display 103 displays a graphical user interface (GUI) for the operator (user) of the ultrasonic diagnostic apparatus 1 to input various setting requests using the input interface 102, or an ultrasonic wave generated in the apparatus main body 100 Display image data etc. Further, the display 103 displays various messages and display information in order to notify the operator of the processing status and processing result of the apparatus main body 100. The display 103 also has a speaker and can output audio.

  The device body 100 is a device that generates ultrasound image data based on the reflected wave signal received by the ultrasound probe 101. An apparatus main body 100 shown in FIG. 1 is an apparatus capable of generating two-dimensional ultrasound image data based on two-dimensional reflected wave data (echo data) received by the ultrasound probe 101. The apparatus main body 100 shown in FIG. 1 is an apparatus capable of generating three-dimensional ultrasound image data (volume data) based on the three-dimensional reflected wave data received by the ultrasound probe 101.

  As shown in FIG. 1, the device body 100 includes a transmission / reception circuit 110, a B-mode processing circuit 120, a Doppler processing circuit 130, a storage circuit 140, a processing circuit 150, and a communication interface 160. The transmission / reception circuit 110, the B mode processing circuit 120, the Doppler processing circuit 130, the storage circuit 140, the processing circuit 150, and the communication interface 160 are communicably connected to each other. In addition, the device body 100 is connected to the network 2.

  The transmission / reception circuit 110 includes a pulse generator, a transmission delay unit, a pulsar, and the like, and supplies a drive signal to the ultrasonic probe 101. The pulse generator repeatedly generates rate pulses for forming transmission ultrasonic waves at a predetermined rate frequency. In addition, the transmission delay unit focuses the ultrasonic waves generated from the ultrasonic probe 101 in a beam shape, and the pulse generator generates a delay time for each piezoelectric transducer necessary to determine transmission directivity. Give for each rate pulse. The pulser also applies a drive signal (drive pulse) to the ultrasonic probe 101 at a timing based on the rate pulse. That is, the transmission delay unit arbitrarily adjusts the transmission direction of the ultrasonic wave transmitted from the surface of the piezoelectric transducer by changing the delay time given to each rate pulse.

  The transmission / reception circuit 110 has a function capable of instantaneously changing the transmission frequency, the transmission drive voltage, and the like in order to execute a predetermined scan sequence based on an instruction from the processing circuit 150 described later. In particular, the change of the transmission drive voltage is realized by a linear amplifier type transmission circuit whose value can be switched instantaneously or a mechanism for electrically switching a plurality of power supply units.

  The transmission / reception circuit 110 also has a preamplifier, an A / D (Analog / Digital) converter, a reception delay unit, an adder, etc. Generate wave data. The preamplifier amplifies the reflected wave signal for each channel. The A / D converter A / D converts the amplified reflected wave signal. The reception delay unit provides a delay time necessary to determine reception directivity. The adder performs addition processing of the reflected wave signals processed by the reception delay unit to generate reflected wave data. By the addition processing of the adder, the reflection component from the direction according to the reception directivity of the reflected wave signal is emphasized, and a comprehensive beam of ultrasonic transmission and reception is formed by the reception directivity and the transmission directivity.

  The transmitting / receiving circuit 110 causes the ultrasonic probe 101 to transmit a two-dimensional ultrasonic beam when scanning the subject P two-dimensionally. Then, the transmission and reception circuit 110 generates two-dimensional reflected wave data from the two-dimensional reflected wave signal received by the ultrasonic probe 101. In addition, when the subject P is three-dimensionally scanned, the transmission and reception circuit 110 according to the present embodiment causes the ultrasonic probe 101 to transmit a three-dimensional ultrasonic beam. Then, the transmission / reception circuit 110 generates three-dimensional reflected wave data from the three-dimensional reflected wave signal received by the ultrasonic probe 101.

  Here, the form of the output signal from the transmission / reception circuit 110 is various forms, such as when it is a signal including phase information called RF (Radio Frequency) signal or when it is amplitude information after envelope detection processing. It is selectable.

  The B mode processing circuit 120 receives the reflected wave data from the transmission / reception circuit 110, performs logarithmic amplification, envelope detection processing, etc., and generates data (B mode data) in which the signal intensity is represented by the brightness of luminance. .

  The Doppler processing circuit 130 performs frequency analysis of velocity information from the reflected wave data received from the transmission / reception circuit 110, extracts blood flow, tissue, and contrast agent echo component due to the Doppler effect, and mobile information such as velocity, dispersion, and power. Generate data (Doppler data) extracted for many points. Specifically, the Doppler processing circuit 130 generates Doppler data at each of a plurality of sample points, such as an average velocity, an average dispersion value, an average power value, and the like, as motion information of the moving object. Here, the moving body is, for example, blood flow, tissue such as heart wall, or contrast agent. The Doppler processing circuit 130 estimates, as motion information (blood flow information) of the blood flow, information obtained by estimating the average velocity of the blood flow, the average dispersion value of the blood flow, the average power value of the blood flow, etc. at each of a plurality of sample points. Generate

  The Doppler processing circuit 130 has an MTI filter and a blood flow information generation unit, and executes, for example, a color Doppler method to calculate blood flow information. In the color Doppler method, transmission and reception of ultrasonic waves are performed a plurality of times on the same scanning line, and a moving target indicator (MTI) filter is applied to a data string at the same position to obtain stationary tissue or movement. The signal derived from the slow tissue (clutter signal) is suppressed to extract the signal derived from the blood flow. Then, in the color Doppler method, blood flow information such as blood flow velocity, blood flow dispersion, and blood flow power is estimated from the blood flow signal.

  The MTI filter uses a filter matrix to output a data sequence in which a clutter component is suppressed and a blood flow signal derived from a blood flow is extracted from a continuous data stream of reflected wave data at the same position (same sample point) Do. The blood flow information generation unit performs calculation such as autocorrelation calculation using data output from the MTI filter, estimates blood flow information, and outputs the estimated blood flow information as Doppler data. As the MTI filter, for example, a Butterworth-type IIR (Infinite Impulse Response) filter, a filter with fixed coefficients such as a polynomial regression filter (Polynomial Regression Filter), or a coefficient according to the input signal using an eigenvector or the like It is possible to apply an adaptive filter that changes.

  The B-mode processing circuit 120 and the Doppler processing circuit 130 illustrated in FIG. 1 can process both two-dimensional reflected wave data and three-dimensional reflected wave data. That is, the B-mode processing circuit 120 generates two-dimensional B-mode data from the two-dimensional reflected wave data, and generates three-dimensional B-mode data from the three-dimensional reflected wave data. Also, the Doppler processing circuit 130 generates two-dimensional Doppler data from two-dimensional reflected wave data, and generates three-dimensional Doppler data from three-dimensional reflected wave data.

  The storage circuit 140 is a memory for storing display image data generated by the processing circuit 150. The storage circuit 140 can also store data generated by the B-mode processing circuit 120 and the Doppler processing circuit 130. The B mode data and the Doppler data stored in the storage circuit 140 can be called by the operator after diagnosis, for example, and become ultrasound image data for display via the processing circuit 150.

  In addition, the memory circuit 140 may be a control program for performing ultrasonic wave transmission / reception, image processing and display processing, diagnostic information (for example, patient ID, doctor's findings, etc.) and various data such as a diagnostic protocol and various body marks. Remember. Further, data stored in the storage circuit 140 can be transferred to an external device via an interface (not shown). The external apparatus 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. Also, the form of storage in the storage circuit 140 may be temporary storage of live information, or storage for long-term recording due to the evidence of acquired fetal information.

  The processing circuit 150 controls the entire processing of the ultrasonic diagnostic apparatus 1. Specifically, the processing circuit 150 transmits and receives the transmission / reception circuit 110 and the B-mode processing circuit based on various setting requests input from the operator via the input interface 102 and various control programs and various data read from the storage circuit 140. At 120, the processing of the Doppler processing circuit 130 is controlled. The processing circuit 150 also controls the display ultrasonic image data stored in the storage circuit 140 to be displayed on the display 103 or a touch command screen or the like in the input interface 102. Hereinafter, the ultrasonic image data displayed on the display 103 or the touch command screen is also described as an ultrasonic image.

  The processing circuit 150 executes a control function 151, an image generation function 152, an estimation function 153, and a measurement function 154. The control function 151 is an example of a display control unit. The image generation function 152 is an example of an image generation unit. The estimation function 153 is an example of an estimation unit. The measurement function 154 is an example of a measurement unit.

  Here, for example, each processing function executed by the control function 151, the image generation function 152, the estimation function 153, and the measurement function 154, which are components of the processing circuit 150 shown in FIG. It is stored in memory circuit 140 in a form. The processing circuit 150 is a processor that realizes the function corresponding to each program by reading each program from the storage circuit 140 and executing it. In other words, the processing circuit 150 in the state where each program is read out has the respective functions shown in the processing circuit 150 of FIG.

  The communication interface 160 is an interface for communicating with various external devices via the network 2. The processing circuit 150 communicates with an external device through the communication interface 160. For example, the processing circuit 150 can exchange various data with an external device other than the ultrasonic diagnostic apparatus 1 through the communication interface 160.

  The overall configuration of the ultrasound diagnostic apparatus 1 according to the first embodiment has been described above. Based on this configuration, the ultrasonic diagnostic apparatus 1 according to the present embodiment can increase the accuracy of estimation and reduce the complexity of operation in semi-automatic measurement based on estimation of tissue shape. Specifically, when measuring the tissue in the ultrasonic image, the ultrasonic diagnostic apparatus 1 according to the first embodiment determines the position of the tissue designated on the ultrasonic image when the estimation of the tissue shape fails. Improve the accuracy of shape estimation by re-estimating the tissue shape based on it. As a result, the ultrasonic diagnostic apparatus 1 according to the first embodiment can reduce the time and labor of the manual designation operation of the tissue shape by the operator, and can reduce the complexity of the operation. Hereinafter, detailed processing in the ultrasonic diagnostic apparatus 1 will be described.

  The control function 151 controls the entire ultrasonic diagnostic apparatus 1. For example, the control function 151 controls the transmission / reception circuit 110, the B mode processing circuit 120, and the Doppler processing circuit 130 to control collection of reflected wave data and generation of B mode data and Doppler data. That is, the control function 151 causes the ultrasound probe 101 to execute a two-dimensional ultrasound scan and a three-dimensional ultrasound scan on the subject. Further, the control function 151 controls the display 103 to display an ultrasound image generated by the image generation function 152, a processing result by the estimation function 153, the measurement function 154, and the like.

  The image generation function 152 generates ultrasound image data from the data generated by the B-mode processing circuit 120 and the Doppler processing circuit 130. That is, the image generation function 152 generates two-dimensional B-mode image data representing the intensity of the reflected wave as luminance from the two-dimensional B-mode data generated by the B-mode processing circuit 120. Further, the image generation function 152 generates two-dimensional Doppler image data representing moving body information from the two-dimensional Doppler data generated by the Doppler processing circuit 130. The two-dimensional Doppler image data is a velocity image, a variance image, a power image, or an image combining these. The image generation function 152 can also generate M mode image data from time series data of B mode data on one scanning line generated by the B mode processing circuit 120. The image generation function 152 can also generate a Doppler waveform in which velocity information of blood flow and tissue is plotted in time series from the Doppler data generated by the Doppler processing circuit 130.

  Here, the image generation function 152 generally converts (scan converts) a scanning line signal row of ultrasonic scanning into a scanning line signal row of a video format represented by a television etc., and uses the ultrasonic wave for display. Generate an image. Specifically, the image generation function 152 generates an ultrasonic image for display by performing coordinate conversion in accordance with the scan form of the ultrasonic wave by the ultrasonic probe 101. Further, the image generation function 152 performs, as various image processing other than scan conversion, for example, image processing (smoothing processing) for regenerating an average value image of luminance using a plurality of image frames after scan conversion, Image processing (edge enhancement processing) using a differential filter is performed in the image. In addition, the image generation function 152 combines character information of various parameters, a scale, a body mark, various markers, and the like on an ultrasonic image.

  That is, the B mode data and the Doppler data are ultrasound image data before scan conversion processing, and the data generated by the image generation function 152 is a display ultrasound image after scan conversion processing. The B mode data and the Doppler data are also referred to as raw data. The image generation function 152 generates “two-dimensional B-mode image or two-dimensional ultrasound image for display” from “two-dimensional B-mode data or two-dimensional Doppler data” which is two-dimensional ultrasound image data before scan conversion processing. Generate a "two-dimensional Doppler image".

  Furthermore, the image generation function 152 performs coordinate conversion on the three-dimensional B-mode data generated by the B-mode processing circuit 120 to generate three-dimensional B-mode image data. In addition, the image generation function 152 performs coordinate conversion on the three-dimensional Doppler data generated by the Doppler processing circuit 130 to generate three-dimensional Doppler image data. That is, the image generation function 152 generates “three-dimensional B-mode image data and three-dimensional Doppler image data” as “three-dimensional ultrasound image data (volume data)”. Further, the image generation function 152 generates an MPR image by performing multi-section conversion on three-dimensional B-mode data and three-dimensional Doppler data.

  As described above, the image generation function 152 performs coordinate conversion on the B mode data and the Doppler data to generate various display images. Here, the image generation function 152 according to the first embodiment generates an ultrasound image corresponding to a region including a part of a fetus. For example, the image generation function 152 generates an ultrasound image including bones of the fetal head, abdomen, legs, arms and the like.

  The estimation function 153 estimates a figure that fits the fetal site based on the ultrasound image. Here, when the estimation function 153 according to the first embodiment estimates a figure applicable to a part of a fetus included in an ultrasound image, and receives a correction instruction for the estimated figure, the estimation function 153 according to the correction instruction is received. Reestimate the figure that applies to the site. The details of the estimation by the estimation function 153 will be described later.

  The measurement function 154 measures the area of the fetus based on the figure estimated by the estimation function 153. For example, based on the figure estimated by the estimation function 153, the measurement function 154 measures the fetal head circumference (HC), the fetal head large lateral diameter (BPD), the abdominal circumference (AC), and the femur length (FL). ), Humeral length (HL) etc. are measured. The control function 151 controls the display 103 to display the estimation result by the estimation function 153 and the measurement result by the measurement function 154.

  Hereinafter, details of processing from estimation of a part by the estimation function 153 to re-estimation will be described. The estimation function 153 according to the first embodiment estimates, based on the ultrasound image, a first figure that fits the fetal site. Specifically, the estimation function 153 estimates a first figure applicable to bones such as the head, abdomen, legs and arms of the fetus included in the ultrasound image generated by the image generation function 152. FIG. 2 is a diagram showing an example of estimation of a first figure by the estimation function 153 according to the first embodiment. Here, in FIG. 2, a tomogram of the head of a fetus is shown, and an example of estimating an ellipse that fits the head is shown.

  As shown in FIG. 2, for example, the estimation function 153 estimates the ellipse 302 as a figure that fits to the fetal head 301 shown in the ultrasound image. The details of ellipse estimation by the estimation function 153 will be described later. As shown in FIG. 2, when the estimation function 153 estimates an ellipse 302 that fits to the head 301, the measurement function 154 determines the fetal head circumference (HC) and the size of the fetal head based on the estimated ellipse 302. Measure the diameter (BPD). That is, the measurement function 154 measures the circumference of the ellipse 302 and the short axis length. Also, as shown in FIG. 2, when the estimation function 153 estimates the ellipse 302 that fits the head 301, the control function 151 displays the ellipse 302, the constituent points 303 of the ellipse 302, etc. as marks on the ultrasound image. Let

  Here, as shown in FIG. 2, when the estimation function 153 estimates the ellipse 302 as an ellipse that fits the head 301 and the estimated ellipse 302 is displayed on the ultrasound image, the operator is It is determined that the ellipse applicable to the part 301 has been successfully estimated, and the fetal head circumference (HC) measured by the measurement function 154, the fetal head large lateral diameter (BPD), and the like can be used for diagnosis.

  On the other hand, the estimation by the estimation function 153 is not always successful, and may fail to estimate an ellipse that fits the head 301. For example, the estimation function 153 may fail to estimate an ellipse due to another tissue or an artifact (eg, high brightness near the body surface). The ultrasound diagnostic apparatus 1 according to the first embodiment reestimates the figure in such a situation. Here, the estimation function 153 uses the position on the ultrasound image input through the input interface 102 to re-estimate the figure. Hereinafter, re-estimation of a figure will be described with reference to FIGS. 3 and 4. FIG. 3 and FIG. 4 are diagrams for explaining re-estimation of figures by the estimation function 153 according to the first embodiment.

  For example, as shown in FIG. 3, when the estimation function 153 estimates the ellipse 304 as a figure applicable to the fetal head 301 shown in the ultrasound image, and the estimated ellipse 304 is displayed on the ultrasound image The operator can determine that the estimation of the ellipse that fits the head 301 has failed. Therefore, the control function 151 causes the display 103 to display an ultrasound image, and causes the ultrasound image to display a first marker corresponding to the figure (first figure) estimated by the estimation function 153 first. Here, the marker corresponding to the figure is display information indicating the figure, and includes information on the shape indicating the figure itself and component parts constituting the figure.

  For example, as shown in the upper diagram of FIG. 4, the control function 151 displays the ellipse 304 estimated by the estimation function 153 and the constituent points 305 of the ellipse 304 on the ultrasound image. Here, the configuration point 305 in the ellipse 304 may be a case where a configuration point of a predetermined position is displayed, or a configuration point of a position designated by the operator may be displayed. As an example, the control function 151 causes one point on the short axis of the ellipse estimated by the estimation function 153 to be displayed.

  As shown in the upper part of FIG. 4, when the control function 151 causes the first marker to be displayed on the ultrasound image, the input interface 102 receives an input for specifying the position on the ultrasound image. Specifically, the input interface 102 receives an input for specifying a position indicating a region of a fetus in an ultrasound image. For example, as shown in the lower part of FIG. 4, the input interface 102 receives an input for specifying the point 305 a on the contour of the head 301 by moving the constituent point 305 to the point 305 a.

  The estimation function 153 applies to the region based on the ultrasound image and the position designated by the input when the input interface 102 receives an input after the control function 151 displays the first marker. Estimate a second figure of the same type as the figure of. Specifically, the estimation function 153 estimates a second figure including, as a component part of the figure, a position indicating a part designated by the input. For example, the estimation function 153 estimates, as an ellipse corresponding to the head 301, an ellipse including the point 305a on the contour of the head 301 as a constituent point.

  As described above, when the initial figure estimation fails, the estimation function 153 reestimates the figure so as to include the position indicating the fetal site input through the input interface 102. Here, the estimation function 153 according to the first embodiment estimates an ellipse that fits the fetal site by selecting an ellipse that best fits among the ellipse candidate group for each parameter of the ellipse. Specifically, the estimation function 153 calculates the cost when each of a plurality of second figure candidates including the position designated by the input as a component of the figure is applied to the ultrasound image, and the calculated cost is minimum. The second graphic candidate to be is estimated as a second graphic.

For example, the estimation function 153 estimates an ellipse based on the following equation (1) defined by the cost function. Here, “C (f _oval (p))” in the equation (1) is a cost function with “p” as a parameter of an ellipse, and is designed, for example, as shown in the following equation (2). Note that “I (x, y)” in the equation (2) indicates a luminance value, and “N _{f (p) = 1} ” indicates the number of pixels on the elliptical circumference.

  That is, as shown in Expression (1), the estimation function 153 estimates the elliptical parameter with the smallest cost among the plurality of costs calculated by the cost function while variously changing the parameter of the elliptical. Here, as shown in equation (2), the cost function is designed so that the cost becomes smaller as the arithmetic mean of the luminance values of the pixels on the elliptical circumference is larger. This is designed under the assumption that "bones have high pixel brightness values in ultrasound images". That is, when an ellipse is arranged on the ultrasound image, the arithmetic mean of the luminance values of the pixels at the position corresponding to the ellipse becomes larger as the ellipse overlaps with the bone of the head. Therefore, it indicates that the ellipse with the lowest cost overlaps the bone of the head most.

  As described above, the estimation function 153 estimates an ellipse that fits the fetal site (head) by extracting an elliptical parameter with the lowest cost among costs calculated by variously changing the parameters of the ellipse. . Here, as described above, in the re-estimation in the present embodiment, an ellipse including the position designated by the input as a component of the figure is estimated. That is, at the time of re-estimation, the estimation function 153 can estimate an ellipse under the condition that the number of parameters of the ellipse decreases, and can improve the accuracy of estimation of the ellipse.

Hereinafter, examples of parameters for ellipse estimation will be described using FIGS. 5A to 5C. 5A to 5C are diagrams for explaining an example of the parameters of the ellipse according to the first embodiment. For example, as shown in FIG. 5A, assuming that the center coordinates of the ellipse are “(x _c , y _c )”, the major axis is “a”, the minor axis is “b”, and the element of rotation is excluded, the ellipse is It shows by Formula (3).

In other words, the ellipse, as shown in equation (3), indicated by "a", "b", "x _c", four parameters "y _c". In addition, the type and number of parameters of the ellipse are not limited to those shown in the equation (3), and instead of using the minor axis and the major axis, a combination of one diameter and an aspect ratio may be used. In such a case, the ellipse is represented by the following equation (4). Incidentally, "b" in equation (4) indicates one of the diameter "R" represents the aspect ratio, "(x _c, y _c)" indicates the center coordinate. Here, the aspect ratio "R" is suitable for constraining the range of parameters, as it does not change much with many fetuses.

As described above, the estimation function 153 estimates the ellipse with the smallest cost while changing various parameters included in the equation of the ellipse represented by the equation (3) or the equation (4). Here, in the re-estimation of the ellipse in the present embodiment, the number of parameters can be reduced by estimating the ellipse including the position designated by the input as a component of the figure. For example, as shown in FIG. 5B, when “(x ₁ , y ₁ )” is designated by the operator's input, the estimation function 153 estimates an ellipse passing the point “(x ₁ , y ₁ )”. It will be. That is, when an ellipse passes through the point “(x ₁ , y ₁ )”, the equation (4) can be transformed into the following equation (5), and one diameter “b” of the ellipse is the other parameter Can be expressed by

  Therefore, the number of parameters can be reduced by substituting equation (5) for "b" in equation (4). As a result, it is not necessary to change "b", the number of ellipse candidates used for estimation can be reduced, and the accuracy of ellipse estimation can be improved. For example, in the first ellipse estimation, the estimation function 153 calculates costs for each of the ellipse candidates in which four parameters including “b” are variously changed, and extracts an ellipse with the lowest cost, but re-estimates. In this case, it is sufficient to calculate costs for each of the ellipse candidates obtained by variously changing the three parameters for which “b” is reduced, and it is possible to improve the accuracy of the ellipse estimation.

  The parameter to be reduced is not limited to “b”, and other parameters may be reduced. However, it is desirable to set a wider range of change as the target of reduction. For example, since the aspect ratio "R" of an ellipse does not differ much between fetuses, the range of change is originally narrow. That is, the number of ellipse candidates obtained by changing the parameter “R” is small. Therefore, the estimation function 153 gives priority to the type of parameter to be reduced, which has a wider range of change.

Here, in the above-described example, the case where the operator designates one point is described, but two or more points may be designated. For example, as shown in FIG. 5C, when “(x ₁ , y ₁ )” and “(x ₂ , y ₂ )” are designated by the operator's input, the estimation function 153 sets the point “(x ₁ , Ellipses passing through y ₁ ) and “(x ₂ , y ₂ )” will be estimated. For example, if an ellipse passes the points “(x ₁ , y ₁ )” and “(x ₂ , y ₂ )”, equation (4) can be transformed into equation (6) below, and the parameter “ It becomes possible to express y _c "by other parameters.

Therefore, the number of parameters can be reduced by substituting equation (6) for "y _c " in equation (4). As a result, it is not necessary to change "y _c ", the number of ellipse candidates used for estimation can be further reduced, and the accuracy of ellipse estimation can be improved.

  As described above, the estimation function 153 according to the first embodiment can improve the accuracy of the ellipse estimation by reducing the parameters of the ellipse using the position designated on the ultrasound image. Furthermore, the estimation function 153 can further improve the accuracy of figure estimation by restricting the range in which the parameter is changed as much as possible. That is, in addition to the reduction of the parameters described above, by narrowing the range in which the parameters are changed, the number of graphic candidates can be further reduced, and the accuracy of graphic estimation can be further improved.

  Specifically, the estimation function 153 estimates the second figure so as to further satisfy the constraints set based on the information on the fetus. As an example, the estimation function 153 estimates a second figure using a constraint based on a past measurement result of a fetus, a current measurement result, a measurement result of one of a plurality of twins etc., and the like.

  For example, in the case of using the past measurement result of the fetus, the estimation function 153 estimates the second figure using the constraint set based on the relationship between the number of weeks of the fetus and the measurement value. The measurements of fetal BPD, AC, FL, HL, etc. are closely related to the number of fetal weeks. Therefore, the estimation function 153 estimates the present measurement value from the past measurement result, and narrows the range in which the parameter is changed from the estimated measurement value. For example, the estimation function 153 estimates current HC and BPD values from past HC and BPD measurement results, and determines a range in which the aspect ratio “R” of the ellipse is changed from the estimated values. That is, the estimation function 153 calculates the costs of a plurality of ellipse candidates, each of which is changed by changing “R” within a range that is highly likely to be taken as the aspect ratio “R” of the current ellipse, Extract.

  Also, for example, even when using the current measurement result, the estimation function 153 can use the relationship between the number of weeks of the fetus and the measurement value. For example, if FL is already measured and then BPD is measured, if it is the same fetus, the central value for changing the ellipse diameter “b” from the past FL measurement value is the number of weeks and FL · BPD The range of changing the ellipse diameter "b" is narrowed.

  Further, for example, when using one measurement result of a plurality of twins and a plurality of fetuses, the estimation function 153 estimates the measurement value of the other fetus from the measurement result of one fetus, and changes the parameter from the estimated measurement value Narrow down.

  In the example described above, the head of the fetus has been described as an example, but the embodiment is not limited to this, and the embodiment may be applied to measurement of the abdomen, legs, arms, etc. of the fetus. Good. In such a case, for example, the estimation function 153 estimates an ellipse as a figure that fits the tomogram of the abdomen. Here, the estimation function 153 also performs estimation similar to that of the above-described head when estimating an ellipse of the abdomen. That is, the estimation function 153 reduces the parameters of the ellipse by estimating the ellipse including the position designated on the ultrasound image as a component. Furthermore, the estimation function 153 narrows the range of change of the parameters by estimating an ellipse so as to further satisfy the constraints set based on the information on the fetus.

  Here, the estimation function 153 may set the aspect ratio as “1: 1” when estimating an ellipse that fits the tomogram of the abdomen of the fetus. That is, the estimation function 153 may apply a true circle when estimating an ellipse that fits the tomogram of the abdomen of the fetus. Thereby, the number of parameters can be reduced, and the estimation accuracy can be further improved.

  Also, for example, when measuring bones or the like of legs or arms, the estimation function 153 estimates a quadrangle or a line segment as a figure corresponding to each bone. In one example, the estimation function 153 applies a square or a line to the femur, tibia, calcaneus, humerus, ulna or calcaneus. For example, the estimation function 153 estimates a quadrangle surrounding a target bone or a line segment overlapping in the longitudinal direction of the bone. Here, also in the case of applying a figure to these bones, the estimation function 153 must estimate a quadrangle or line segment including a position designated on the ultrasound image as a component, as in the estimation of the above-described ellipse. , Reduce the parameters of the rectangle or line segment. Furthermore, the estimation function 153 narrows the range of change of the parameters by estimating a square or a line segment so as to further satisfy the constraints set based on the information on the fetus.

  Here, in the case of estimating a figure applicable to the bones of the legs and arms, it is possible to restrict the measurement of one bone by using the measurement result of one bone with respect to bone whose length does not change much. For example, in the case where one is an ulna and the other is a rib or one is a tibia and the other is a rib, the estimation function 153 uses the measurement result of one of the bones, and uses the measurement result of one of the bones Narrow the range of

  As described above, the estimation function 153 can improve the accuracy of the ellipse estimation by reducing the parameters of the ellipse using the position designated on the ultrasound image. Here, by setting the position designated on the ultrasound image to a predetermined position, it is possible to further reduce the number of graphic candidates. For example, when the position designated on the ultrasound image is determined to be one point on the minor axis of the ellipse, the estimation function 153 passes the designated point and the designated point is on the minor axis. Only an ellipse that is one point of can be a candidate.

  As described above, when the estimation function 153 re-estimates the figure, the measurement function 154 performs various measurements based on the re-estimated figure. Then, the control function 151 displays the re-estimation result and the measurement result on the ultrasound image. FIG. 6 is a view showing an example of display by the control function 151 according to the first embodiment. For example, as shown in FIG. 6, the control function 151 causes the re-estimated ellipse 304a of the head 301 and the constituent points 305a and 305b of the ellipse 304a to be displayed on the ultrasound image. Furthermore, as shown in FIG. 6, the control function 151 displays the measurement result of BPD based on the re-estimated ellipse 304a. The operator can determine that the measurement result is correct by referring to the re-estimation result and the measurement result shown in FIG.

  Next, the procedure of processing by the ultrasonic diagnostic apparatus 1 according to the first embodiment will be described. 7 and 8 are flowcharts showing the processing procedure of the ultrasound diagnostic apparatus 1 according to the first embodiment. Here, the process in FIG. 8 corresponds to the process of step S107 in FIG. The process shown in FIG. 8 is also performed in the estimation of the figure in step S105. Further, FIG. 8 shows processing in the case of estimating an ellipse.

  Steps S101 to S104, S106, S108, and S110 in FIG. 7 are realized, for example, by the processing circuit 150 reading out a program corresponding to the control function 151 from the storage circuit 140 and executing it. In addition, steps S105 and S107 are realized, for example, by the processing circuit 150 reading out a program corresponding to the control function 151 and a program corresponding to the estimation function 153 from the storage circuit 140 and executing the program. Step S109 is realized, for example, by the processing circuit 150 reading out a program corresponding to the measurement function 154 from the storage circuit 140 and executing it.

  In the ultrasonic diagnostic apparatus 1 according to the present embodiment, the processing circuit 150 first generates an ultrasonic image based on echo data received by the ultrasonic probe 101 as shown in FIG. It is displayed (step S101). Next, the processing circuit 150 determines whether or not the freeze button has been pressed (step S102). Here, when the freeze button is pressed (Yes at step S102), the processing circuit 150 displays the cross section when the freeze button is pressed (step S103). The processing circuit 150 continues the display of the ultrasound image in real time until the freeze button is pressed (No at step S102).

  Next, the processing circuit 150 determines whether the measurement button is pressed and the measurement item is selected (step S104). Here, when the measurement button is pressed and a measurement item is selected (Yes at step S104), the processing circuit 150 estimates a figure applicable to the part and displays the figure on the ultrasound image (step S105). The processing circuit 150 is in a standby state until the measurement button is pressed and a measurement item is selected (No at step S104). Although not shown, the processing circuit 150 performs various measurements when the estimation of the figure is completed.

  Then, the processing circuit 150 determines whether or not the constituent point of the figure has been moved (step S106). Here, if the constituent point of the figure has been moved (Yes at Step S106), the processing circuit 150 estimates the figure including the constituent point after movement and displays the figure on the ultrasound image (Step S107). On the other hand, when the constituent point of the figure is not moved (No at Step S106), the processing circuit 150 ends the processing.

  When the figure re-estimated in step S107 is displayed, the processing circuit 150 determines again whether the constituent point of the figure has been moved (step S108). Here, when the constituent point of the figure is moved (Yes at Step S108), the processing circuit 150 returns to Step S107, estimates the figure including the constituent point after movement, and displays it on the ultrasound image ( Step S107). On the other hand, when the constituent point of the figure is not moved (No at Step S108), the processing circuit 150 performs measurement based on the estimated figure (Step S109), and displays the measurement result together with the figure on the ultrasound image. (Step S110).

  Further, in the ultrasound diagnostic apparatus 1 according to the present embodiment, as shown in FIG. 8, the processing circuit 150 extracts an ellipse candidate group including constituent points after movement, and an ellipse parameter is selected from among the extracted ellipse candidate groups. Is selected (step S1071), and the cost of the ellipse is calculated (step S1072). Then, the processing circuit 150 determines whether the calculated cost is minimum (step S1073).

  Here, if the cost is the minimum (Step S1073: Yes), the processing circuit 150 updates the parameters for the minimum cost and the minimum cost (Step S1074), and calculates the costs for all the candidates. Is determined (step S1075). On the other hand, if the cost is not the minimum (No at Step S1073), the processing circuit 150 determines whether the cost has been calculated for all the candidates (Step S1075).

  In step S1075, when the cost has not been calculated for all the candidates (No in step S1075), the processing circuit 150 returns to step S1071 and selects an ellipse parameter from among the ellipse candidate group. On the other hand, if the costs have been calculated for all the candidates (Yes at step S1075), the processing circuit 150 displays an ellipse of the parameter with the lowest cost on the ultrasound image (step S1076).

  As described above, according to the first embodiment, the image generation function 152 generates an ultrasound image corresponding to a region including a region of a fetus based on data collected by ultrasound scanning on a subject . An estimation function 153 estimates a first figure that fits the site based on the ultrasound image. The control function 151 causes an ultrasound image to be displayed on the display unit, and causes the ultrasound image to display a first marker corresponding to the first graphic. The input interface 102 receives an input for specifying a position on the ultrasound image. The estimation function 153 applies to the region based on the ultrasound image and the position designated by the input when the input interface 102 receives an input after the control function 151 displays the first marker. Estimate a second figure of the same type as the figure of. The control function 151 causes the second marker corresponding to the second graphic to be displayed on the ultrasound image. Therefore, the ultrasonic diagnostic apparatus 1 according to the first embodiment can reduce the number of parameters indicating a figure by using the designated position, and the accuracy of estimation in semi-automatic measurement by estimation of tissue shape. To reduce the complexity of the operation.

  For example, when designating a figure by manual operation after failing in the first figure estimation, the operator moves a plurality of constituent points of the figure in accordance with the shape of the part while referring to the ultrasound image, Operation becomes complicated. For example, in the case of manually designating an ellipse, the operator designates at least two points of the short diameter and one point of the long diameter, or one point of the short diameter and two points of the long diameter. Furthermore, after designation, the operator operates to execute measurement on the figure after designation again. As described above, when designating a figure by manual operation after failing in the first figure estimation, the operation becomes complicated.

  The ultrasonic diagnostic apparatus 1 according to the first embodiment can perform high-accuracy re-estimation only by designating one of the constituent points of the figure before performing such a manual operation. Therefore, the situation in which the operator manually operates can be reduced, and the complexity of the operation can be reduced.

  Further, according to the first embodiment, the measurement function 154 acquires a first measurement value by measurement based on a first figure, and acquires a second measurement value by measurement based on a second figure. The control function 151 displays the first measurement value with the first marker, and displays the second measurement value with the second marker. Therefore, the ultrasound diagnostic apparatus 1 according to the first embodiment can perform measurement based on a figure obtained by highly accurate estimation, and can obtain more accurate measurement values.

  Further, according to the first embodiment, the first graphic and the second graphic are an ellipse, a square, or a line segment. Therefore, the ultrasonic diagnostic apparatus 1 according to the first embodiment makes it possible to improve the measurement accuracy of the fetus.

  Further, according to the first embodiment, the input interface 102 receives an input for specifying a position indicating a region in an ultrasound image. The estimation function 153 estimates a second figure including, as a component part of the figure, a position indicating a part designated by the input. Therefore, the ultrasound diagnosis apparatus 1 according to the first embodiment can reduce the number of parameters of the figure to improve the estimation accuracy.

  Further, according to the first embodiment, the estimation function 153 calculates the cost when applying a plurality of second figure candidates including the position designated by the input as a part of the figure to the ultrasound image. The second figure candidate for which the calculated cost is minimum is estimated as a second figure. Therefore, the ultrasound diagnostic apparatus 1 according to the first embodiment makes it possible to estimate an ellipse accurately.

  Further, according to the first embodiment, the estimation function 153 estimates the second figure so as to further satisfy the constraints set based on the information on the fetus. Therefore, the ultrasound diagnostic apparatus 1 according to the first embodiment can narrow the range in which the parameters of the figure are changed, and can further improve the estimation accuracy.

  Further, according to the first embodiment, the measurement function 154 measures the fetal head circumference, the fetal head large lateral diameter, or the abdominal circumference based on the ellipse estimated by the estimation function 153. The measurement function 154 also measures the length of the femur, tibia, calcaneus, humerus, ulna or calcaneus based on the quadrangle or line segment estimated by the estimation function 153. Therefore, the ultrasonic diagnostic apparatus 1 according to the first embodiment makes it possible to perform various measurements of the fetus with high accuracy.

Second Embodiment
In the embodiment described above, the case of estimating the figure by selecting the figure with the lowest cost among the plurality of figure candidates has been described. In the second embodiment, the case of estimating a figure by performing edge detection of a part will be described. In addition, about the structure similar to 1st Embodiment, the same code | symbol may be attached hereafter and description may be abbreviate | omitted.

  The estimation function 153 according to the second embodiment detects a point sequence indicating an edge in an ultrasound image, approximates the detected point sequence, and includes a figure including the position designated by the input as a constituent part of the figure. Estimated as the second figure. FIG. 9 is a diagram for explaining an example of estimation of a figure by the estimation function 153 according to the second embodiment. In addition, in FIG. 9, the case where an ellipse is estimated is shown.

  For example, the estimation function 153 first detects an edge of the head 401 from an ultrasound image including the head 401 of the fetus. Here, the estimation function 153 detects an edge from an ultrasound image by, for example, the following three methods. (1) A threshold value of luminance is set on the skull of the fetus, and the luminance of a predetermined level or more is used as an edge. (2) Smooth the input image with a Gaussian filter, calculate the derivative of the smoothed image to find the magnitude and direction of the gradient, emphasize only the components along the direction, and then take the threshold of the image Get an edge. (3) The relationship between the past image and the edge is learned in advance by a neural network or the like, and each parameter of the learning process is determined, and then the edge is obtained by the input image and each parameter of the learning process.

  As described above, when an edge is detected, the estimation function 153 extracts the edge point string 402 as shown in the upper part of FIG. 9 by performing processing such as thinning on the edge of the image. Then, the estimation function 153 performs ellipse fitting on the extracted edge point sequence 402 to extract an ellipse. Here, the estimation function 153 estimates the ellipse so as to include the position designated through the input interface 102 as a component of the ellipse. That is, when extracting the ellipse 404 by performing fitting on the point sequence 402 of the edge as shown in the lower diagram of FIG. 9, the estimation function 153 passes the composing points of the ellipse specified by the input. As such, the fitting of the ellipse 404 is performed.

  As the fitting method, methods such as the least squares method and the maximum likelihood estimation method can be used. Also, an algorithm such as RANSAC (Random Sample Consensus) may be used in combination to remove outliers of the point sequence.

  Also, in the above process, instead of fitting the ellipse, directly obtain the parameters of the ellipse by the Hough transform, or obtain the parameters of the circle tangent to or tangent to the ellipse, and then obtain the parameters of the ellipse indirectly. You may Even in the estimation of an ellipse by the above method, using the equation of the ellipse and the parameters of the ellipse is the same as in the first embodiment, and therefore the reduction of the ellipse parameter by manual specification of the point on the ellipse and the range where the ellipse parameter can be taken Since the accuracy of the ellipse estimation can be improved by the restriction of (1), the complexity of the operation can be reduced as in the first embodiment.

  Further, in the case where machine learning is used in edge detection, re-learning may be performed using the result of the operator manually correcting the position of the ellipse. More specifically, not only learning dictionary data but also a set of past images and edges are stored in the device itself or in a processing system connected to the device and a network, and the operator calculates the point on the ellipse Make weights heavier than other edge points.

  Next, the procedure of processing by the ultrasonic diagnostic apparatus 1 according to the second embodiment will be described. FIG. 10 is a flowchart showing the processing procedure of the ultrasonic diagnostic apparatus 1 according to the second embodiment. Note that FIG. 10 corresponds to the process of step S107 in FIG. The process shown in FIG. 10 is also performed in the estimation of the figure in step S105. Further, FIG. 10 shows processing in the case of estimating an ellipse.

  In the ultrasound diagnostic apparatus 1 according to the present embodiment, as shown in FIG. 10, the processing circuit 150 first extracts an edge from the image (step S2071), and extracts a point sequence of the edge (step S2072). Next, the processing circuit 150 fits the ellipse so as to include the designated constituent points (step S 2073), and extracts each parameter of the ellipse (step S 2074). Then, the processing circuit 150 causes the ellipse of the extracted parameter to be displayed on the ultrasonic image (step S2075).

  As described above, according to the second embodiment, the estimation function 153 detects a point sequence indicating an edge in an ultrasound image, approximates the detected point sequence, and graphically indicates the position designated by the input. The figure included as a component part of is estimated as a second figure. Therefore, the ultrasonic diagnostic apparatus 1 according to the second embodiment makes it possible to improve the estimation accuracy even in the estimation of figures by edge detection.

Third Embodiment
In the embodiment described above, the case where the range of the parameter of the figure is restricted is described based on the past measurement result of the fetus, the current measurement result, the measurement result of one of the twin and the like fetuses, and the like. In the third embodiment, in different parts of the same fetus in the same image, in the same part in different images of the same fetus, and in the same part in a plurality of fetuses such as twins, the other based on the measurement results of one part The case where restriction is applied to the estimation of the part of That is, in the third embodiment, not the estimation by the parameter but the measurement result of one part is used to improve the estimation accuracy of the other part. In addition, about the structure similar to 1st Embodiment, the same code | symbol may be attached hereafter and description may be abbreviate | omitted.

  When applied to different parts of the same fetus in the same image, the image generation function 152 according to the third embodiment is based on the data acquired by the ultrasound scan on the subject, the first part of the fetus and An ultrasound image corresponding to a region including the second region is generated. For example, the image generation function 152 generates an ultrasound image including an ulna and a rib, an ultrasound image including a tibia and a rib, and the like.

  Then, the estimation function 153 according to the third embodiment is based on the ultrasound image and the first measurement value obtained by measurement based on the first figure or the first figure applicable to the first region. Then, a second figure that fits to the second part is estimated. For example, the estimation function 153 estimates a figure applicable to the other bone based on the measurement result of either the ulna or the calcaneus. Here, the estimation function 153 estimates a square or a line segment as a figure applicable to a bone.

  FIG. 11 is a diagram illustrating an example of estimation of a quadrilateral by the estimation function 153 according to the third embodiment. For example, as illustrated in FIG. 11, the estimation function 153 estimates a quadrangle 502 circumscribing the bone 501. Here, the estimation function 153 according to the third embodiment restricts the estimation of the other part using the measurement result of the measured part among the plurality of parts. As an example, the estimation function 153 extracts the target bone area from the area corresponding to the bone extracted from the ultrasound image, using the measurement result of the measured part. For example, the estimation function 153 estimates the size of the target bone from the size of the bone that has been measured, and extracts a region corresponding to the estimated size.

  In addition, when applied to a plurality of regions in different images of the same fetus, the image generation function 152 according to the third embodiment is a first region of the fetus based on data collected by an ultrasound scan on a subject. And a second ultrasound image corresponding to a second region including the second region of the fetus.

  Then, the estimation function 153 according to the third embodiment includes: a second ultrasound image; and a first measurement value acquired by measurement based on a first figure or the first figure applicable to the first region. , To estimate a second figure that applies to the second part. For example, the estimation function 153 estimates a figure applicable to the ulna in the current image based on the measurement result of the ulna in the past image. Alternatively, for example, the estimation function 153 estimates a figure applicable to the ribs in the current image based on the measurement result of the ulna in the current image. Also in this case, as in the above, the estimation function 153 estimates the size of the target bone from the measured size of bone, and extracts a region corresponding to the estimated size of the bone.

  In addition, when applied to the same site in a plurality of fetuses such as twins, the image generation function 152 according to the third embodiment determines the number of the first fetus based on the data acquired by the ultrasound scan on the subject. A first ultrasound image corresponding to a first region including one region and a second ultrasound image corresponding to a second region including a second region of a second fetus are generated.

  Then, the estimation function 153 according to the third embodiment includes: a second ultrasound image; and a first measurement value acquired by measurement based on a first figure or the first figure applicable to the first region. , To estimate a second figure that applies to the second part. For example, the estimation function 153 estimates a figure applicable to the ulna in the second fetus based on the measurement result of the ulna in the first fetus. Also in this case, as in the above, the estimation function 153 estimates the size of the target bone from the measured size, and extracts a bone equivalent region corresponding to the estimated size.

  As described above, when the estimation function 153 estimates a figure, the control function 151 causes the display 103 to display the estimation result. For example, the control function 151 causes an ultrasound image to be displayed, and causes the ultrasound image to display a first marker corresponding to the first graphic and a second marker corresponding to the second graphic. Also, for example, the control function 151 causes the first ultrasound image to be displayed, causes the first ultrasound image to display the first marker corresponding to the first figure, and causes the second ultrasound image to be displayed. The second marker corresponding to the second figure is displayed on the second ultrasound image.

  Next, the procedure of processing by the ultrasonic diagnostic apparatus 1 according to the third embodiment will be described. FIG. 12 is a flowchart showing the processing procedure of the ultrasonic diagnostic apparatus 1 according to the third embodiment. In addition, in FIG. 12, only the process of estimation of the figure by the estimation function 153 is shown.

  In the ultrasound diagnostic apparatus 1 according to the present embodiment, as shown in FIG. 12, the processing circuit 150 first constrains the detection area (step S301) and calculates a histogram of pixel values in the area (step S302). ). Then, the processing circuit 150 calculates a threshold from the histogram (step S303). For example, the processing circuit 150 sets a condition such that the top 5% of the luminance value of the image is obtained, and uses the luminance value which is the minimum under the condition as a threshold.

  Then, the processing circuit 150 binarizes the image using the calculated threshold (step S304). Here, since the obtained binary image has noise such as an excessive area or a hole, the processing circuit 150 executes the morphological processing to remove the noise (step S305). Specifically, the processing circuit 150 removes noise by opening and closing. By this processing, tissue shapes other than the target site are also extracted.

  Then, the processing circuit 150 assigns an ID to each of the extracted tissue shapes (step S306), and calculates the length of the area of each ID (step S307). Here, the area of each ID is a quadrangle circumscribed to the extracted tissue shape, and the length of the area can be determined by rotating calipers. The calculation of the length is not limited to the rotation caliper method. For example, using binary data and the center of gravity, first, the point A farthest from the center of gravity and the point B farthest from the point A are determined. The method of making distance into length etc. can be applied.

  Thereafter, the processing circuit 150 extracts a target tissue shape from the measured length of bone and the calculated length of each ID area (step S308). For example, the processing circuit 150 extracts the tissue shape included in the figure corresponding to the length of the target bone estimated from the measured length of the bone. Here, even if it is assumed that the target site is the longest tissue on the ultrasound image, the longest tissue is preferentially selected among the lengths calculated in step S307. Good.

  In addition, in step S301 in FIG. 12, the detection area is restricted. This restriction is to set the area for estimating the figure only to the area of interest selected by the operator, the area where tissue shape can not exist, or It includes the exclusion of an area that may not be necessary. Also, for example, there are those that are present close together on the same screen, such as the ulna and ribs, and the lengths do not change much. In this case, the processing circuit 150 either removes the measured area or makes the ID of the longest area and the second longest area when estimating the other length after one measurement is completed. Among them, exclude measured IDs. For example, the processing circuit 150 removes the measured ulna 601 in FIG. 13 from the ID and sets only the rib 602 as an estimation target. Thereby, it is possible to prevent the shape measured in the past from being selected again or selecting another part by mistake. FIG. 13 is a diagram for explaining an example of processing by the estimation function 153 according to the third embodiment.

  As described above, according to the third embodiment, the estimation function 153 is used in different parts of the same fetus in the same image, in the same part in different images of the same fetus, or in the same part in a plurality of fetuses such as twins. And constrain the estimation of the other part based on the measurement result of one part. Therefore, the ultrasound diagnostic apparatus 1 according to the third embodiment can estimate a figure using measured information, and can improve the estimation accuracy.

Fourth Embodiment
Now, the first to third embodiments have been described so far, but may be implemented in various different modes other than the first to third embodiments described above.

  In the embodiment described above, the case of estimating the figure that fits the part has been described. However, the embodiment is not limited to this, and for example, the figure to be estimated may not exactly correspond to the part.

  Further, in the embodiment described above, the case where the measurement item is selected by the user has been described, but the embodiment is not limited to this, and may be, for example, the case of automatic determination. In such a case, for example, the estimation function 153 determines the type of the part and the measurement based on the estimation result of the first part, and estimates the second figure based on the figure of the shape according to the determined type. . For example, the process of ellipse estimation in the measurement of BPD or AC includes the extraction of the feature value of the target tissue shape. Therefore, when the measurement button is pressed in a state where the target tissue shape is displayed, the estimation function 153 executes a function to determine whether it is the head or the abdomen of the fetus, and the target of measurement using the function. Automatic determination of site and type of measurement. This can reduce the operating procedure of the operator.

  The estimation function 153 can also estimate a figure based on dictionary data. Specifically, the estimation function 153 estimates the second graphic based on the dictionary data indicating the relationship between the part and the graphic parameter, which is generated as training data on the graphic data that is applicable to the part. That is, the estimation function 153 generates dictionary data as learning data on the relationship between the estimated part and the figure, and stores the dictionary data in the storage circuit 140. Here, the dictionary data is updated by the relationship between the part derived by re-estimation and the parameter of the figure.

  Moreover, in the embodiment described above, the case where the ultrasonic diagnostic apparatus 1 executes various processes has been described. However, the embodiment is not limited to this, and may be implemented by, for example, an information processing apparatus on a network. In such a case, for example, ultrasound image data collected by the ultrasound diagnostic apparatus 1 is transmitted to an external information processing apparatus via the network 2. Then, the processing circuit of the external information processing apparatus executes the same processing as the control function 151, the image generation function 152, the estimation function 153, and the measurement function 154 described above.

  Each component of each device illustrated in the embodiment described above is functionally conceptual, and does not necessarily have to be physically configured as illustrated. That is, the specific form of the dispersion and integration of each device is not limited to that shown in the drawings, and all or a part thereof is functionally or physically dispersed in any unit depending on various loads, usage conditions, etc. It can be integrated and configured. Furthermore, all or any part of each processing function performed in each device may be realized by a CPU and a program analyzed and executed by the CPU, or may be realized as wired logic hardware.

  Further, among the processes described in the above-described embodiment, all or part of the process described as being automatically performed may be manually performed, or the process described as being manually performed. All or part of can be performed automatically by known methods. In addition to the above, the processing procedures, control procedures, specific names, and information including various data and parameters shown in the above documents and drawings can be arbitrarily changed unless otherwise specified.

  Note that the word “processor” used in the above description refers to, for example, a central processing unit (CPU), a graphics processing unit (GPU), or an application specific integrated circuit (ASIC), a programmable logic device (ASIC). For example, it means circuits such as Simple Programmable Logic Device (SPLD), Complex Programmable Logic Device (CPLD), and Field Programmable Gate Array (FPGA). The processor implements a function by reading and executing a program stored in the memory circuit 140. Note that instead of storing the program in the memory circuit 140, the program may be directly incorporated in the circuit of the processor. In this case, the processor implements the function by reading and executing a program embedded in the circuit. Each processor according to the present embodiment is not limited to being configured as a single circuit for each processor, and may be configured as one processor by combining a plurality of independent circuits to realize the function. Good. Furthermore, multiple components in each figure may be integrated into one processor to realize its function.

  Further, the image processing method described in the above-described embodiment can be realized by executing a prepared image processing program on a computer such as a personal computer or a workstation. This image processing method can be distributed via a network such as the Internet. This image processing method can also be executed by being recorded on a computer-readable recording medium such as a hard disk, flexible disk (FD), CD-ROM, MO, DVD, etc. and reading from the recording medium by a computer. .

  According to at least one embodiment described above, the complexity of the operation when measuring a structure in an image can be reduced.

  While certain embodiments of the present invention have been described, these embodiments have been presented by way of example only, and are not intended to limit the scope of the invention. These embodiments can be implemented in other various forms, and various omissions, replacements, and modifications can be made without departing from the scope of the invention. These embodiments and modifications thereof are included in the invention described in the claims and the equivalents thereof as well as included in the scope and the gist of the invention.

Reference Signs List 1 ultrasonic diagnostic apparatus 102 input interface 150 processing circuit 151 control function 152 image generation function 153 estimation function 154 measurement function

Claims (20)

An image generation unit configured to generate an ultrasound image corresponding to a region including a region of a fetus based on data acquired by ultrasound scanning on a subject;
An estimation unit configured to estimate a first figure applicable to the region based on the ultrasound image;
A display control unit that causes the display unit to display the ultrasound image, and displays a first marker corresponding to the first graphic on the ultrasound image;
An input unit that receives an input for specifying a position on the ultrasound image;
Equipped with
When the input unit receives the input after the display control unit displays the first marker, the estimation unit is based on the ultrasonic image and the position specified by the input. Estimating a second figure of the same kind as the first figure, which applies to the part;
The ultrasonic diagnostic apparatus, wherein the display control unit displays a second marker corresponding to the second graphic on the ultrasonic image. It further comprises a measurement unit that acquires a first measurement value by measurement based on the first figure, and acquires a second measurement value by measurement based on the second figure,
The ultrasonic diagnostic apparatus according to claim 1, wherein the display control unit displays the first measurement value together with the first marker, and displays the second measurement value together with the second marker.   The ultrasonic diagnostic apparatus according to claim 1, wherein the first graphic and the second graphic are an ellipse, a square, or a line segment. The input unit receives an input for specifying a position indicating the site in the ultrasound image;
The ultrasound diagnostic apparatus according to any one of claims 1 to 3, wherein the estimation unit estimates the second graphic including the position indicating the part designated by the input as a component of the graphic.   The estimation unit calculates the cost when each of a plurality of second figure candidates including the position specified by the input as a component of the figure is applied to the ultrasound image, and the calculated cost is minimized. The ultrasound diagnostic apparatus according to any one of claims 1 to 4, wherein a second figure candidate is estimated as the second figure.   The estimation unit detects a point sequence indicating an edge in the ultrasound image, approximates the detected point sequence, and includes the second figure including the position designated by the input as a component of the figure. The ultrasound diagnostic apparatus according to any one of claims 1 to 4, which is estimated as a figure.   The ultrasound diagnostic apparatus according to any one of claims 1 to 6, wherein the estimation unit estimates the second figure so as to further satisfy a constraint set based on information on the fetus.   The ultrasonic diagnostic apparatus according to claim 2, wherein the measurement unit measures the fetal head peripheral length, the fetal head large lateral diameter, or the abdominal peripheral length based on the ellipse estimated by the estimation unit.   The ultrasonic diagnostic apparatus according to claim 2, wherein the measurement unit measures a length of a femur, a tibia, a calcaneus, a humerus, an ulna or a calcaneus on the basis of a square or a line segment estimated by the estimation unit. .   The estimation unit determines the type of the part and the measurement based on the estimation result of the first figure, and estimates the second figure based on a figure of a shape according to the determined type. The ultrasonic diagnostic device according to any one of to 9. An image generator configured to generate an ultrasound image corresponding to a region including a first portion and a second portion of a fetus based on data acquired by ultrasound scanning on a subject;
A second fitting to the second part based on the ultrasound image and a first measurement value obtained by measurement based on the first figure fitting to the first part or the first figure. An estimation unit that estimates the figure of
A display control unit that causes the display unit to display the ultrasound image, and displays a first marker corresponding to the first graphic and a second marker corresponding to the second graphic on the ultrasound image; ,
An ultrasonic diagnostic apparatus comprising:   The ultrasonic diagnostic apparatus according to claim 11, wherein one of the first part and the second part is an ulna and the other is a rib or one is a tibia and the other is a rib. A first ultrasound image corresponding to a first region including a first region of a fetus, and a second region including a second region of the fetus based on data acquired by ultrasound scanning on a subject; An image generator for generating a second ultrasound image corresponding to the area;
The second region is based on the second ultrasonic image and a first measurement value obtained by measurement based on the first figure or the first figure that applies to the first region. An estimation unit that estimates a second figure that is applicable;
The first ultrasonic image is displayed on a display unit, a first marker corresponding to the first graphic is displayed on the first ultrasonic image, and the second ultrasonic image is displayed. A display control unit which causes a second marker corresponding to the second graphic to be displayed on the second ultrasonic image.
An ultrasonic diagnostic apparatus comprising: A first ultrasound image corresponding to a first region including a first region of a first fetus and a second region of a second fetus based on data collected by ultrasound scanning on a subject An image generation unit generating a second ultrasound image corresponding to a second region including
The second region is based on the second ultrasonic image and a first measurement value obtained by measurement based on the first figure or the first figure that applies to the first region. An estimation unit that estimates a second figure that is applicable;
The first ultrasonic image is displayed on a display unit, a first marker corresponding to the first graphic is displayed on the first ultrasonic image, and the second ultrasonic image is displayed. A display control unit which causes a second marker corresponding to the second graphic to be displayed on the second ultrasonic image.
An ultrasonic diagnostic apparatus comprising:   The estimation unit estimates the second figure based on dictionary data indicating a relationship between the part and the parameter of the figure, which is generated as training data on a figure data applicable to the part. The ultrasonic diagnostic device as described in.   The ultrasonic diagnostic apparatus according to claim 15, wherein the dictionary data is updated based on the estimated second figure. Generating an ultrasound image corresponding to a region including a region of a fetus based on data acquired by ultrasound scanning on a subject;
Estimating a first figure applicable to the region based on the ultrasound image;
Displaying the ultrasound image on a display unit, and displaying a first marker corresponding to the first figure on the ultrasound image;
Accepting an input specifying the position on the ultrasound image;
After the display of the first marker, when the input is received, the same type as the first figure that conforms to the portion based on the ultrasound image and the position specified by the input Estimate the figure of 2,
An image processing program that causes a computer to execute processing for displaying a second marker corresponding to the second graphic on the ultrasound image. Generating an ultrasound image corresponding to a region including the first region and the second region of the fetus based on the data acquired by the ultrasound scan on the subject;
A second fitting to the second part based on the ultrasound image and a first measurement value obtained by measurement based on the first figure fitting to the first part or the first figure. Estimate the figure of
The display unit is configured to display the ultrasound image, and a first marker corresponding to the first graphic and a second marker corresponding to the second graphic are displayed on the ultrasound image.
An image processing program that causes a computer to execute each process. A first ultrasound image corresponding to a first region including a first region of a fetus, and a second region including a second region of the fetus based on data acquired by ultrasound scanning on a subject; Generating a second ultrasound image corresponding to the region;
The second region is based on the second ultrasonic image and a first measurement value obtained by measurement based on the first figure or the first figure that applies to the first region. Estimate the second figure that applies
The first ultrasonic image is displayed on a display unit, a first marker corresponding to the first graphic is displayed on the first ultrasonic image, and the second ultrasonic image is displayed. And a second marker corresponding to the second figure is displayed on the second ultrasound image.
An image processing program that causes a computer to execute each process. A first ultrasound image corresponding to a first region including a first region of a first fetus and a second region of a second fetus based on data collected by ultrasound scanning on a subject Generating a second ultrasound image corresponding to a second region including
The second region is based on the second ultrasonic image and a first measurement value obtained by measurement based on the first figure or the first figure that applies to the first region. Estimate the second figure that applies
The first ultrasonic image is displayed on a display unit, a first marker corresponding to the first graphic is displayed on the first ultrasonic image, and the second ultrasonic image is displayed. And a second marker corresponding to the second figure is displayed on the second ultrasound image.
An image processing program that causes a computer to execute each process.

Images