JP2009148499A - Ultrasonic diagnostic equipment - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an ultrasonic diagnostic apparatus capable of automatically performing echo pattern classification from an obtained ultrasonic image.
An operation unit, a display monitor, a display processing unit that processes an image displayed on the display monitor, an ultrasonic image acquisition unit that acquires an ultrasonic image, and a two-dimensional tomographic image from the ultrasonic image A tomographic image obtaining unit for obtaining a luminance value at each pixel constituting the tomographic image, a binarizing unit for obtaining pixel information from the obtained luminance value, and a high per predetermined area A distribution density measuring unit for measuring a distribution density of luminance pixels; a distribution density classifying unit for acquiring distribution density information obtained by classifying the distribution density based on a predetermined threshold; and a boundary portion from the pixel information and the distribution density information. A boundary determining unit for defining; and an echo pattern classifying unit for classifying the tomographic image into echo patterns.
[Selection] Figure 1

Description

  The present invention relates to an ultrasonic diagnostic apparatus having a function of automatically performing echo pattern classification for a tumor or the like based on an ultrasonic image.

  In ultrasonic diagnosis using an ultrasonic diagnostic apparatus, it is necessary to measure the size of a tumor or the like observed in an ultrasonic image obtained from a soft tissue such as the uterus, liver, or breast. In order to eliminate the complexity of positioning the measurement location for each tumor to be measured in measuring the dimensions of such tumors, an automatic diagnosis is performed from the obtained ultrasonic diagnostic images. A technique is known in which the position of a tumor is grasped, the number thereof is counted, and the size is measured.

  For example, in the ultrasonic diagnostic apparatus described in Patent Document 1, the size of a tumor is measured by performing the processing shown in the flowchart in FIG. 9 on the obtained ultrasonic diagnostic image. Hereinafter, in the description of FIG. 9, each step is indicated as (S50 *).

  First, the latest image frame is acquired (S501), and necessary preprocessing is performed (S502). Here, the preprocessing includes compression of the entire image, definition of a search area, filter processing for noise removal, and the like.

  Next, the search area of the image for which preprocessing has been completed is binarized based on the size of the pixel value indicating luminance (S503). Then, a structure smaller than a predetermined area is removed from the binarized image (S504). Thereafter, the number of continuous objects is counted and the area is recorded (S505).

  Here, a filtering process is performed to exclude an excessively large region or an excessively small region (S506), the center of mass of the remaining object is obtained (S507), and the major axis of the structure is obtained from the obtained center of mass. Measure the short axis (S508).

Finally, the center of mass, the size of the major axis and minor axis, and the estimated area are displayed for the tumor identified in the above process (S509), and a series of processing is completed.
JP 2002-45358 A

  However, in the above-described conventional ultrasonic diagnostic apparatus, although it is possible to automatically identify the position of a tumor and measure their dimensions, not only the dimensions of the tumor, but also the pattern of the configuration, for example, Needless to say, it is more preferable.

  For example, for ovaries with a wide variety of tumors, the Japan Society of Ultrasound Medicine classifies the echo patterns of ovarian tumors into the six types shown in FIG. 2, and each echo pattern may be a malignant tumor or a borderline malignant tumor. (Committee on diagnostic criteria of the Japanese Society of Ultrasound: Echo pattern classification (draft) announcement of ovarian tumors. Ultrasound Medicine 21 (2): iii-v, 1993). In such a case, if not only the size of the tumor but also the echo pattern classification can be automated, both improvement of patient throughput and improvement of consistency of measurement accuracy can be realized at the same time.

  The present invention is for solving the problems of such a conventional ultrasonic diagnostic apparatus, and provides an ultrasonic diagnostic apparatus capable of automatically performing echo pattern classification from the obtained ultrasonic image. The purpose is to do.

  In order to solve the above problems, an ultrasonic diagnostic apparatus of the present invention includes an operation unit, a display monitor, a display processing unit that processes an image displayed on the display monitor, and an ultrasonic image acquisition that acquires an ultrasonic image. A tomographic image acquisition unit that obtains a two-dimensional tomographic image from the ultrasonic image, a luminance value acquisition unit that acquires a luminance value in each pixel constituting the tomographic image, and the acquired luminance value as a predetermined threshold value A binarization unit for binarizing the pixel to obtain pixel information obtained by classifying the pixel into two, a high luminance pixel and a low luminance pixel, and a distribution for measuring the distribution density of the high luminance pixel per predetermined area A density measuring unit, a distribution density classifying unit for acquiring distribution density information obtained by classifying the distribution density into a low density unit and a high density unit based on a predetermined threshold, and a boundary portion from the pixel information and the distribution density information. A boundary determining unit that constant, the shape of the boundary portion, and the pixel information, on the basis of said distribution density information, and having an echo pattern classifying unit for classifying the tomographic image in the echo pattern.

  With this configuration, it is possible to automatically classify an echo pattern such as a tumor, and to assist in identifying the echo pattern in a doctor's diagnosis.

  In the ultrasonic diagnostic apparatus of the present invention, the echo pattern classification unit converts the tomographic image obtained from the ultrasonic diagnostic image of the subject's ovary into six echo patterns of the ovarian tumor created by the Japanese Society of Ultrasonic Medicine. It has a configuration to classify.

  With this configuration, classification according to the echo pattern created by the Japanese Society of Ultrasound Medicine can be automatically performed.

  Furthermore, the ultrasonic diagnostic apparatus of the present invention has a configuration in which the display processing unit displays the type of echo pattern classified by the echo pattern classification unit on the display monitor simultaneously with the ultrasonic image.

  With this configuration, when a clear classification standard is set for the echo pattern, the operator can grasp the classification result automatically performed at a glance.

  The ultrasonic diagnostic apparatus of the present invention further includes a color image acquisition unit that obtains a color mode image from the ultrasonic diagnostic image, and a blood flow information determination unit that determines blood flow information from the color mode image. The echo pattern classification unit classifies the echo pattern using the blood flow information.

  With such a configuration, more accurate echo pattern classification can be performed based on color image information.

  Further, the ultrasonic diagnostic apparatus of the present invention includes a tomographic image memory for recording the tomographic image, a color image memory for recording the color image, the tomographic image recorded in the tomographic image memory, or the color A memory image calling unit that sequentially calls images designated by the operator from the operation unit from the color image recorded in the image memory, and the echo pattern classification unit is called by the memory image calling unit It has a configuration for sequentially classifying echo patterns on an image.

  With such a configuration, it is possible to classify the echo pattern based on a plurality of images obtained from the acquired ultrasonic image, and it is possible to improve the accuracy of the echo pattern classification.

  Further, in the ultrasonic diagnostic apparatus of the present invention, the ultrasonic image acquisition unit acquires a three-dimensional ultrasonic image, and based on the three-dimensional ultrasonic slice image, two-dimensional parallel to three axes that are orthogonal to each other A two-dimensional image acquisition unit that acquires a first ultrasonic cross-sectional image, a second ultrasonic cross-sectional image, and a third ultrasonic cross-sectional image, which are ultrasonic images, and display on the monitor unit by the display processing unit Using the one of the first ultrasonic cross-sectional image, the second ultrasonic cross-sectional image, and the third ultrasonic cross-sectional image, the region designated by the operator from the operation unit is used. A two-dimensional image calling unit that sequentially calls a plurality of two-dimensional ultrasound images included, and the echo pattern classifying unit is added to the plurality of two-dimensional ultrasonic images called by the two-dimensional image calling unit. A structure that sequentially classifies echo patterns. The has.

  Further, in the markedly obtained ultrasonic diagnostic apparatus of the present invention, the ultrasonic image acquisition unit acquires a three-dimensional ultrasonic slice image, and a plurality of two-dimensional images belonging to planes parallel to each other based on the three-dimensional ultrasonic image. The image processing apparatus further includes a multi-slice image acquisition unit that acquires a multi-slice image that is an ultrasonic image, and the display processing unit displays a plurality of the multi-slice images side by side on the display monitor and is displayed on the display monitor. The echo pattern classification unit classifies the echo pattern with respect to a two-dimensional ultrasonic image designated by the operator from the operation unit from among the plurality of multi-slice images.

  By having such a configuration, the operator can more visually specify the echo pattern classification part based on the three-dimensional ultrasonic image and a large number of two-dimensional ultrasonic images acquired from the three-dimensional ultrasonic image. More accurate echo pattern classification can be performed.

  Furthermore, in the ultrasonic diagnostic apparatus of the present invention, the display processing unit is classified into six types of echo patterns of ovarian tumors created by the Japanese Society of Ultrasonic Medicine classified by the echo pattern classification unit, the ultrasonic image, A schematic diagram of six echo patterns of the ovarian tumor is displayed on the display monitor.

  With such a configuration, the classified echo pattern and the classification standard can be compared, and the classification accuracy can be easily confirmed.

  In the ultrasonic diagnostic apparatus of the present invention, the display processing unit displays the boundary portion specified by the boundary determination unit on the display monitor so as to overlap the ultrasonic image.

  By doing in this way, the operator or doctor can visually distinguish the tumor in the ultrasonic image more easily.

  According to the ultrasonic diagnostic apparatus of the present invention, since an echo pattern can be automatically classified from an ultrasonic image, it is possible to simultaneously improve patient throughput and measurement result uniformity. .

  The best mode for carrying out the present invention will be described below with reference to the drawings.

(Embodiment 1)
A first embodiment of an ultrasonic diagnostic apparatus according to the present invention will be described below.

  The ultrasonic diagnostic apparatus according to the present embodiment can automatically classify an echo pattern of a tumor or the like from an acquired ultrasonic image, and in particular, echoes of six types of ovarian tumors indicated by the Japanese Society of Ultrasonic Medicine. It has a function of classifying into patterns.

  FIG. 1 is a block diagram showing a functional configuration of the ultrasonic diagnostic apparatus of the present embodiment. As shown in FIG. 1, the ultrasonic diagnostic apparatus according to the present embodiment includes an ultrasonic image acquisition unit 9, DSC 5, display processing unit 6, display monitor 7, operation unit 8, and control system circuit unit 10.

  Here, the ultrasonic image acquisition unit 9 includes an ultrasonic probe 1, a transmission circuit unit 2, a reception circuit unit 3, and a reception signal processing unit 4. The DSC 5 also has a function of a tomographic image acquisition unit 31 that acquires a tomographic image to be subjected to echo pattern classification. Further, the control system circuit unit 10 includes a central control unit 11 having a luminance value acquisition unit 21, a binarization unit 22, a distribution density measurement unit 23, a distribution density classification unit 24, a boundary determination unit 25, and an echo pattern classification unit 26. , A graphic controller 12 and a graphic memory 13.

  In FIG. 1, the luminance value acquisition unit 21, binarization unit 22, distribution density measurement unit 23, distribution density classification unit 24, boundary determination unit 25, and echo pattern classification unit 26 are described as independent functional blocks. . However, in the present embodiment, these blocks are functionally realized by the central control unit 11 operating according to predetermined programs (operating system and application program).

  The ultrasonic probe 1 includes a piezoelectric vibrator at one end thereof, and transmits and receives ultrasonic waves.

  The transmission circuit unit 2 generates drive voltage pulses. This drive voltage pulse is supplied to the transducer of the ultrasonic probe 1, and an ultrasonic pulse is transmitted from the transducer. While this ultrasonic pulse propagates through the subject, part of it reflects off the boundary surface where the acoustic impedance is different to form an echo signal, and part of the echo signal is received by the transducer, Converted.

  The receiving circuit unit 3 amplifies the voltage signal received by the ultrasonic probe 1 and performs delay control and addition.

  The received signal processing unit 4 performs processes such as logarithmic amplification, detection, A / D conversion, and the like on the voltage signal output from the receiving circuit unit 3 to generate a digitized ultrasonic image. In this manner, an ultrasonic image is obtained by the ultrasonic image acquisition unit 9 having the ultrasonic probe 1, the transmission circuit unit 2, the reception circuit unit 3, and the reception signal processing unit 4.

  The DSC 5 converts the ultrasonic image, which is an ultrasonic scanning signal, into a standard scanning echo signal that is the same as a normal TV signal by converting the scanning method. The echo image signal is temporarily stored in the frame memory, read out at an appropriate frame timing, and output to the display processing unit 6. Note that the DSC 5 converts the scanning method into the standard scanning method, so that an ultrasonic image can be grasped as a collection of luminance signals in minute pixels called pixels. The process of automatically performing echo pattern classification from an ultrasound image, which is a feature of the ultrasound diagnostic apparatus according to the present invention, is performed by decomposing an ultrasound image into pixels and processing based on the luminance value, as will be described later. Therefore, the image signal after being converted by the DSC 5 is a target signal for echo pattern classification. In this specification, an image signal that is a target of this echo pattern classification is referred to as a tomographic image. The DSC 5 also has a function as a tomographic image acquisition unit 31 that acquires a tomographic image for echo pattern classification from an ultrasonic image.

  The display processing unit 6 combines the echo image signal and the graphic image signal sent from the control system circuit unit 10 to generate a display image to be displayed on the display monitor 7.

  The display monitor 7 is an image display device such as a CRT or LCD, and displays the display image sent from the display processing unit 6.

  The operation unit 8 is an interface unit between the ultrasonic diagnostic apparatus and the operator, and includes a keyboard and the operator can directly input necessary data. In addition, a touch pen, a mouse, and the like are provided, and when the operator designates a desired portion of the display image displayed on the display monitor 7, the position can be recognized as data.

  The control system circuit unit 10 responds to an instruction from the operator input from the operation unit 8, and controls the driving timing of the entire ultrasonic diagnostic apparatus, control of data transmission / reception, various measurements, and generation of drawing graphic data for measurement. The circuit unit is responsible for overall control of measurement result graph display processing, measurement result storage, and the like.

  Various processes in the control system circuit unit 10 are performed by the central control unit 11. The central control unit 11 is an arithmetic circuit including a CPU and a work memory. According to an instruction signal input from the operation unit 8, acquisition of an ultrasonic image by the ultrasonic image acquisition unit 9 and synthesis with an echo image signal are performed. Then, an instruction is given to each part constituting the ultrasonic diagnostic apparatus, such as an instruction for a graphic image signal displayed on the display monitor 7. In order to give these instructions, the output of the central control unit 11 is input to the transmission circuit unit 2, the reception circuit unit 3, the reception signal processing unit 4, the DSC 5, the image composition unit 6, and the graphic control unit 12.

  Further, the central control unit 11 performs luminance pattern acquisition unit 21, binarization unit 22, distribution density measurement unit 23, distribution density classification unit 24 for performing echo pattern classification on the tomographic image acquired by DSC 5. A boundary determination unit 25 and an echo pattern classification unit 26. The specific functions of these units will be described later together with the processing content added to the echo pattern.

  The graphic control unit 12 generates a graphic image signal displayed on the display monitor 7 based on the signal from the central control unit 11.

  The graphic memory 13 temporarily records the graphic image signal generated by the graphic control unit 12 and outputs the graphic image signal to the display processing unit 6 in accordance with the timing at which the echo image signal is output from the DSC 5.

  The operation of the ultrasonic diagnostic apparatus according to the present embodiment configured as described above will be described by taking as an example the case of being used for ovarian tumor diagnosis.

  First, the ultrasonic probe 1 is placed at a position where the subject's ovary is observed. An ultrasonic pulse propagates from the ultrasonic probe 1 to the ovary in the subject and its surroundings, and the reflected wave passes through the ultrasonic probe 1, the receiving circuit unit 3, and the received signal processing unit 4 as an ultrasonic image. Sent to DSC5.

  In the DSC 5, the ultrasonic image is sent to the display processing unit 6 as an echo image signal whose scanning method is converted from ultrasonic scanning to standard scanning. Information such as the hospital name, ultrasound transmission conditions, and reception conditions generated by the central control unit 11 is sent to the display processing unit 6 via the graphic control unit 12 and the graphic memory 13 to be displayed. A display image is generated by being synthesized with the echo image signal in the unit 6 and displayed on the display monitor 7.

  The operator diagnoses the ovary and its surroundings based on the display image displayed on the display monitor 7. At this time, the tomographic image obtained from the ultrasonic image by the DSC 5 is processed by the central control unit 11 and classified into the echo patterns of the six types of ovarian tumors shown by the Japanese Society of Ultrasonic Medicine shown in FIG. Is done.

  Hereinafter, a specific method for classifying echo patterns will be described with reference to the flowchart shown in FIG. In the flowchart of FIG. 3 and the description thereof, each step is displayed as (S1 **) (* represents a number).

  The echo pattern classification process according to the present embodiment shown in FIG. 3 starts from a state in which a tomographic image is input to the central control unit 11.

  As described above, the tomographic image can be grasped as a collection of luminance signals for individual pixels constituting the image. The luminance value acquisition unit 21 acquires the luminance value for each pixel (S101).

  The binarization unit 22 determines whether the acquired brightness value of each pixel is higher or lower than the value A, using the brightness value given as the predetermined value A as a threshold value. Then, pixel information classified into high luminance pixels having a luminance value higher than the predetermined value A and low luminance pixels having a luminance value lower than the predetermined value A for all pixels to be determined in the tomographic image. Obtain (S102).

  Next, the distribution density measuring unit 23 measures the density, which is the ratio of the high-luminance pixels to the area given as the predetermined value B, with respect to the determination target region in the tomographic image to obtain the distribution density ( S103). As described above, since each point on the tomographic image is replaced with a pixel, the area on the tomographic image can be directly grasped as the number of pixels. Accordingly, obtaining the distribution density is synonymous with obtaining the degree of distribution of the number of high-luminance pixels per unit pixel.

  Based on the obtained distribution density value, the distribution density classifying unit 24 uses a given value C as a reference value as a reference value, and a high-density portion having a distribution density higher than the value C and a distribution density lower than the value C. The distribution density information is obtained by classifying the low density portion (S104).

  By performing the processing up to S104, pixel information obtained by classifying each pixel into a high luminance pixel and a low luminance pixel from the tomographic image based on the three specified values A, B, and C, and a predetermined area By paying attention to the density of the high-luminance portion, the distribution density information classified into the high-density high-luminance portion or the low-density high-luminance portion is obtained.

  Next, the boundary determination part 25 determines a boundary part from pixel information and distribution density information (S105). Specifically, first, a low-luminance pixel area in the pixel information and a low-density high-luminance area in the distribution density information are set as a first group, and a high-density high-luminance area is determined from the distribution density information. Let it be the second group. And the boundary of these 1st groups and 2nd groups is calculated | required, and it determines with a boundary part. In other words, the boundary between the low-brightness and low-density region (which may be a plurality of locations) and the high-brightness and high-density region (which may be a plurality of locations) within the determination target region in the tomographic image is determined as the boundary portion. . Further, when the width of the high-density high-luminance part is narrower than the value E given as a predetermined value, a part having a width narrower than the value E is also determined as the boundary part. In the subsequent procedure, a high-density high-intensity part having a width narrower than the value E is handled only as a boundary part, and is not handled as a high-density high-luminance part.

  In this way, from the pixel information, distribution density information, and boundary portion information obtained up to step S105, the echo pattern classification unit 26 performs specific echo pattern classification according to the steps after step S106. Note that in the following echo pattern classification, the display area end of the tomographic image to be classified, that is, the boundary of the display area, is not handled as the boundary obtained by the boundary determination unit 25. .

  First, as a cystic part detection process, in a part forming a closed region, a part composed of a low luminance part or a low density high luminance part that is grasped as a cystic part is identified ( S106). And it is determined whether the cystic site | part exists in the area | region where the boundary part was closed, or multiple (S107).

Next, as an internal echo determination process, when one or a plurality of cystic sites are present, it is determined whether or not a low-intensity high-luminance part is included as the cystic site. As a result, when there is no group having a low-density high-intensity part, the cystic site is classified as a type I tumor (S108).

When there are a plurality of cystic sites, if at least one high-density part with low density is included, it is not classified as a type I tumor. If it is determined that a low-density high-intensity part is included, it is determined whether or not a high-density high-intensity part exists as a solidity detection process. Classifies the cystic site as a type II tumor (S109).

  If there is a high-density high-intensity part in the cystic part, there is a closed boundary composed of high-density high-intensity inside or adjacent to the cystic part If there is a high-density high-luminance part, the circumference of the high-density high-density part is measured as a circumference measurement process (S111). Then, as an area measurement process, the area of the high-density high-luminance part is measured (S112).

  Next, as the edge smoothness determination process, the ratio of the circumference obtained in the circumference measurement process (S111) to the area obtained in the area measurement process (S112) is calculated, and the obtained ratio is a value D. If it is smaller than the predetermined value D given as follows, it is classified as a type III tumor on the assumption that the target high-density high-intensity part is composed of smooth edges (S113).

Here, only when there are a plurality of high-density high-luminance portions and the ratio of the perimeter to the entire area is smaller than the value D, the tumor is classified as a type III tumor. If at least one edge is larger than the value D, it is classified as a type IV tumor.

  In the solidity detection process (S110), there is a high-density high-intensity part, but it is closed inside the cystic part or adjacent to the cystic part. If it is determined that the boundary does not exist, as a solidity dominant process, whether there is a cystic site obtained by the cystic detection process inside a closed boundary composed of high-density high-intensity parts. Determination is made (S115).

If there is a cystic site in the solidity dominant process, classify it as a type VI tumor. On the other hand, if there is no cystic site within a closed boundary composed of high-density high-intensity parts, it cannot be classified into any of the I-type to VI-type tumor patterns.

  Further, when it is determined in the cystic part detection process (S107) that there is no cystic part, as the solid pattern detection process, one or more parts having a closed boundary composed of high-density high-intensity parts are provided. It is determined whether there are a plurality (S114).

In the solid pattern detection process, if there is at least one region with a closed boundary composed of high-intensity and high-intensity parts, it is classified as a type VI tumor. On the other hand, if there is no site having a closed boundary composed of high-density and high-luminance parts, it cannot be classified into any tumor pattern from type I to VI.

  In this manner, the echo pattern classification unit 26 can automatically perform the echo pattern classification of the six types of ovarian tumors indicated by the Japanese Society of Ultrasonic Medicine based on the pixel information, the distribution density information, and the shape of the boundary.

  Note that the binarization unit 22 according to the present embodiment has a configuration in which the luminance value is determined in one step with respect to the threshold value, and the luminance value is determined with respect to the threshold value in a multi-step configuration. Also good. The values A, B, C, D, and E used in the ovarian tumor pattern determination flow in the present embodiment are appropriately set according to empirical rules and the like. Further, the ultrasonic diagnostic apparatus may automatically optimize these values based on information such as the overall brightness of the tomographic image to be displayed and the depth of field of the displayed tomographic image. Furthermore, a predetermined value may be set by the operator from the operation unit 8.

Based on the data from the central control unit 11, the result of the classified echo pattern is created as character information indicating that the graphic control unit 12 is any type from I type to VI type or that classification is impossible. It is superimposed on the echo image signal by the display processing unit 6 via the memory 13 and displayed on the display monitor 7. An example of the display image at this time is shown in FIG.

As shown in FIG. 4, as a pattern result of the ovarian tumor obtained as an ultrasonic diagnosis result, in this case, it is V type as character information 401 and superimposed on an echo image signal as a display image. Yes.

  In addition, when the operator operates from the operation unit 8, the classification result can be stored as a report together with the acquired ultrasonic image data, the comment of the diagnosis result, etc., or displayed on the screen. It can also be recorded in an external device (not shown).

  Furthermore, the operator designates the start and end of the echo pattern classification of the ovarian tumor by the operation from the operation unit 8. By doing so, the echo pattern classification of the ovarian tumor may be performed during the display of the so-called freeze image acquired from the ultrasound image, or during the display of the live image, not during the display of the freeze image. The echo pattern classification of the ovarian tumor may be started in real time, and the result of classification for each frame may be updated and displayed. When performing echo pattern classification in real time, the latest echo pattern classification result in one frame may be displayed, or the echo pattern classification results obtained sequentially after the echo pattern classification is started. It may be displayed like a majority vote display.

(Embodiment 2)
Next, a second embodiment of the ultrasonic diagnostic apparatus according to the present invention will be described with reference to FIG.

  FIG. 5 is a block diagram showing a functional configuration of the ultrasonic diagnostic apparatus according to the present embodiment. As shown in FIG. 5, the ultrasonic diagnostic apparatus according to the present embodiment has basically the same configuration as the ultrasonic diagnostic apparatus of the first embodiment shown in FIG. 9, DSC 5, display processing unit 6, display monitor 7, operation unit 8, and control system circuit unit 10. In the ultrasonic diagnostic apparatus according to this embodiment, the DSC 5 has a color image acquisition unit, the control system circuit unit 10 has a tomographic image memory 14 and a color image memory 15, and the central control unit 11 has a blood flow. The point which has the information discrimination | determination part 27 and the memory image calling part 28 differs from the ultrasound diagnosing device concerning 1st Embodiment shown in FIG.

  In the ultrasonic diagnostic apparatus of this embodiment, the configuration as shown in FIG. 5 can improve the efficiency of echo pattern classification by effectively using a color mode image in the echo pattern classification of a tomographic image.

  In the example shown in FIG. 3, the color images obtained from the ultrasonic diagnostic images by DSC 5 are classified into the echo patterns of the six types of ovarian tumors shown by the Japanese Society of Ultrasonic Medicine. Used for distribution density classification (S104). Specifically, the blood flow information discriminating unit 27 grasps whether or not color image information exists and its position. In the distribution density information used in the subsequent steps, the position where the color image exists as information is handled as a high-density high-luminance part.

  In this way, when a color image is acquired, it is compared with the case where distribution density classification is performed based only on a black and white tomographic image by treating the part where the color image information exists as a high-density high-luminance part. Thus, it is possible to obtain distribution density information with higher accuracy, and improve the classification accuracy of echo patterns of six types of ovarian tumors.

  In the ultrasonic diagnostic apparatus according to the present embodiment, the control system circuit unit 10 further includes a tomographic image memory 14 for recording a tomographic image acquired by the DSC 5 and a color image memory 15 for recording a color image. It has in the circuit part 10.

  Then, when the operator operates a plurality of images stored in the tomographic image memory 14 and the color image memory 15 from the operation unit 8, an image for starting echo pattern classification from the plurality of recorded images Determine the image to end. After that, when the operator gives an instruction to execute the echo pattern classification from the operation unit 8, the memory image calling unit 28 sequentially calls the images recorded in the tomographic image memory 13 and the color image memory 14, and the echo pattern is recorded. Perform the classification process.

  As described above, the tomographic image and the color image are stored in the respective recording means, and the echo pattern processing is performed on the stored plural images, so that the echo pattern can be classified with higher accuracy.

(Embodiment 3)
Next, regarding the ultrasonic diagnostic apparatus according to the present invention, a third embodiment, which is still another embodiment, will be described with reference to FIG.

  FIG. 6 is a block diagram illustrating a functional configuration of the ultrasonic diagnostic apparatus according to the present embodiment. As shown in FIG. 6, the ultrasonic diagnostic apparatus according to the present embodiment is basically the same in configuration as the ultrasonic diagnostic apparatus of the first embodiment shown in FIG. 9, DSC 5, display processing unit 6, display monitor 7, operation unit 8, and control system circuit unit 10. In the ultrasonic diagnostic apparatus according to the present embodiment, the ultrasonic image acquisition unit 9 has the swing control unit 16, the DSC 5 has the two-dimensional image acquisition unit 33 and the multi-slice image acquisition unit 34, and the central control unit 11. 1 is different from the ultrasonic diagnostic apparatus according to the first embodiment shown in FIG. In the present embodiment, the ultrasonic probe 1 is compatible with 3D for acquiring a three-dimensional image or 4D for acquiring three-dimensional images continuously.

  In the ultrasonic diagnostic apparatus according to the present embodiment, a configuration as shown in FIG. 6 enables acquisition of a three-dimensional image as an ultrasonic image, which is also useful from the viewpoint of diagnosis using an ultrasonic image. A diagnostic device can be obtained. Also, in the automatic classification of echo patterns, since processing using the obtained three-dimensional image can be performed, it is easy to grasp the echo pattern classification sensuously and can be performed with high accuracy.

  In the present embodiment, the three-dimensional ultrasonic probe 1 is used, and is controlled by the swing control unit 16 to swing, so that the information on the subject can be acquired as three-dimensional spatial information. In addition, a so-called 4D image that is displayed on the display monitor 7 while continuously acquiring and updating the image information of the subject in real time can be obtained.

  FIG. 7 shows an example of a display image on the display monitor 7 when three-dimensional image display is performed. As shown in FIG. 7, the display image is divided into four, and in the 3D image display area 504 at the lower right in FIG. 7, a three-dimensional three-dimensional image of the object to be measured is displayed. The A cross-section display area 501 has a first two-dimensional ultrasound image, the upper right B cross-section display area 502 has a second two-dimensional ultrasound image, and the lower left C-section display area 503 has a third one. These two-dimensional ultrasonic images are respectively displayed. Then, the first two-dimensional ultrasonic image, the second two-dimensional ultrasonic image, and the third two-dimensional ultrasonic image are respectively displayed with orthogonal three-dimensional axes (usually x, y, and z). 2), which is acquired by the two-dimensional image acquisition unit 33 of the DSC 5 from the three-dimensional ultrasonic image obtained by the ultrasonic image acquisition means 9.

  When the three-dimensional display image shown in FIG. 7 is displayed, the operator operates the operation unit 8 to specify the position where the echo pattern classification is started. Further, by operating the operation unit 8, a position to end the echo pattern classification is designated. In the example of FIG. 7, an echo pattern classification start position 505 and a classification end position 506 are displayed on the display image displayed on the display monitor 7 using the first two-dimensional ultrasonic image displayed in the A cross-section display area 501. Instruct.

  Upon receiving an instruction from the operator, the central control unit 11 sets an axis parallel to the first two-dimensional ultrasound image displayed in the A cross-section display area 501 between the designated echo pattern classification start position and classification end position. A two-dimensional image calling unit 29 reconstructs a second two-dimensional ultrasound image that is a two-dimensional image along an axis direction (for example, the x-axis) and a vertical axis (for example, the y-axis). get. Then, an echo pattern classification process is performed on the reconstructed plural two-dimensional ultrasonic images.

  In this way, by specifying a two-dimensional ultrasonic image for performing echo pattern classification from the three-dimensional ultrasonic image and performing echo pattern classification for the obtained two-dimensional ultrasonic images, the operator can obtain classification information. It is possible to accurately obtain the echo information of the portion that is desired to be obtained, and the echo pattern classification is performed for a plurality of two-dimensional ultrasonic images, so that the classification accuracy is also improved.

  In the present embodiment, as described above, the echo pattern classification process is performed on a plurality of two-dimensional ultrasonic images, so that the classification result may be obtained in a plurality of parts. In this case, a plurality of classification results can be displayed on the display monitor 7 and the results can be transmitted to the operator. For example, in the case of classifying into the echo patterns of six types of ovarian tumors shown by the Japanese Society of Ultrasound Medicine as shown in FIG. 3, as shown in the lower right of FIG. 7, the echo pattern classification result display unit 507 For example, the respective classification results S1 to S10 obtained from 10 two-dimensional ultrasonic images, and the representative value “V type” obtained as a majority decision thereof are shown.

  Needless to say, the display of the echo pattern classification results can be arbitrarily performed, and the number of two-dimensional ultrasonic images to be classified is not limited to ten. Furthermore, in the classification method of the echo pattern shown in the present embodiment, the classification region is defined using the first two-dimensional ultrasonic image displayed as the A section using FIG. However, the ultrasonic diagnostic apparatus according to the present invention is not limited to this, and the classification determined by using the first two-dimensional ultrasonic image is performed. The region may be classified using the third two-dimensional ultrasound image, and the second two-dimensional ultrasound image or the third two-dimensional image may be used to define the echo pattern classification region. It goes without saying that ultrasound images can be used.

  As described above, the three-dimensional structure is usually obtained by classifying the echo pattern from the two-dimensional ultrasonic image obtained from the three-dimensional ultrasonic image data as shown in the present embodiment. It is possible to more accurately diagnose and classify echo patterns for various tumors.

  Further, in the ultrasonic diagnostic apparatus according to the present embodiment, by using the fact that a three-dimensional ultrasonic image is obtained as described above, a two-dimensional ultrasonic wave that is the target of the echo pattern classification by the operator by another method. A method of specifying an image is also conceivable.

  In performing this method, as shown in FIG. 6, the DSC 5 includes a multi-slice image acquisition unit 34, and two-dimensional ultrasound images on a plurality of planes perpendicular to one axial direction are obtained for a diagnostic object. Obtain sequentially. Note that such an image is usually called a multi-slice image because it slices a target object into a plurality of slices.

  FIG. 8 shows a state in which a multi-slice image is displayed on the display monitor 7. As shown in FIG. 8, the image acquired by the multi-slice image acquisition unit 34 is processed by the central control unit 11 so that a plurality of images are displayed side by side in a continuous state. 12 is sent. Then, it is displayed on the display monitor 7 via the graphic memory 13 and the display processing unit 6.

  Here, the operator operates the operation unit 8 to specify the classification start position 601 and the classification end position 602 in order to specify an image to be subjected to echo pattern classification. The central control unit 11 performs echo pattern classification on the slice image between the designated classification start position and classification end position. Also in this case, since the echo pattern classification is performed on a plurality of two-dimensional ultrasonic images designated by the operator, a plurality of classification results may be obtained. Therefore, as in the case shown in FIG. 7, it is preferable to display a plurality of classification results themselves and a calculated value by majority vote for the echo pattern classification results by superimposing them on the multi-slice image.

  Also in FIG. 8, as an example in the case of classifying into the echo patterns of the six types of ovarian tumors shown by the Japanese Society of Ultrasonic Medicine shown in FIG. 3, as shown in the lower right of FIG. For example, the respective classification results S1 to S10 obtained from 10 two-dimensional ultrasonic images, and the representative value “V type” obtained as a majority decision thereof are shown.

  Also in this case, it goes without saying that the operator can arbitrarily determine the number of two-dimensional ultrasound images that are the echo pattern classification targets and the start / end positions thereof.

  As described above, when the ultrasonic image acquisition means 9 can acquire a three-dimensional ultrasonic image, the obtained two-dimensional ultrasonic images continuous in one axial direction are displayed as a multi-slice screen, and the operator By specifying this multi-slice screen and defining the start position and end position of echo pattern classification, it is possible to easily determine the target to be subjected to echo pattern classification visually, and more detailed tumors etc. And an echo pattern classification result with high accuracy can be obtained.

  In the ultrasonic diagnostic apparatus according to the present invention, when automatically classifying the echo pattern of the ovarian tumor created by the Japanese Society of Ultrasonic Medicine shown in each of the above embodiments, when displaying the classification result, You may make it display together the schematic diagram which modeled the echo pattern shown in FIG. In this way, the actual ultrasonic echo image and the classification result can be easily compared with the schematic diagram, and the accuracy of the classification result can be determined at a glance.

  Further, in the course of the ovarian tumor echo pattern classification process shown in FIG. 3, the boundary information in the echo pattern obtained in the boundary determination step (S105) is transmitted from the central control unit 11 to the graphic control unit 13 and the graphic. It is conceivable to display the image on the display monitor 7 through the memory 14 and the display processing unit 6 so as to be superimposed on the ultrasonic image subjected to the echo pattern classification. In this way, the status of the ovarian tumor that has been classified can be more clearly and visually grasped, and the convenience of the operator's operation and the accuracy of tumor diagnosis by the doctor can be improved. .

  In each of the above embodiments, a classification standard is established as an echo pattern classification method, and there is a strong need for an actual use of an ultrasonic diagnostic apparatus. Although the classification has been described, according to the present invention, pixel information, distribution density information, and boundary information can be obtained with high accuracy for an ultrasound image. It is possible to automatically perform echo pattern classification for various types of tumors and other subjects.

  As described above, since the ultrasonic diagnostic apparatus according to the present invention can automatically perform the echo pattern classification based on the image obtained by the ultrasonic image acquisition means, It can support diagnostic work and can be used industrially. In particular, it is useful for screening for ovarian tumors in gynecology.

1 is a block diagram showing a configuration of an ultrasonic diagnostic apparatus according to a first embodiment of the present invention. Schematic diagram of echo patterns of ovarian tumors created by the Japanese Society of Ultrasound Medicine The flowchart which shows the determination process of the classification | category of an ovarian tumor pattern in the ultrasonic diagnostic apparatus concerning the 1st Embodiment of this invention Example of a display image that displays the results of ovarian tumor pattern determination The block diagram which shows the structure of the ultrasonic diagnosing device concerning the 2nd Embodiment of this invention. The block diagram which shows the structure of the ultrasonic diagnosing device concerning the 3rd Embodiment of this invention. Example of display image of ovarian tumor pattern classification in so-called three-dimensional image display Example of display image of ovarian tumor pattern classification in so-called multi-slice image display Flow chart showing automatic cyst detection and dimension measurement processing in a conventional ultrasonic diagnostic apparatus

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 Ultrasonic probe 2 Transmission circuit part 3 Reception circuit part 4 Reception signal processing part 5 DSC
DESCRIPTION OF SYMBOLS 6 Display processing part 7 Display monitor 8 Operation part 9 Ultrasonic image acquisition part 10 Control system circuit part 11 Central control part 12 Graphic control part 13 Graphic memory

Claims (9)

An operation unit;
A display monitor;
A display processing unit for processing an image to be displayed on the display monitor;
An ultrasound image acquisition unit for acquiring an ultrasound image;
A tomographic image acquisition unit for obtaining a two-dimensional tomographic image from the ultrasonic image;
A luminance value acquisition unit for acquiring a luminance value in each pixel constituting the tomographic image;
A binarization unit that binarizes the acquired luminance value based on a predetermined threshold, and acquires pixel information obtained by classifying the pixel into two of a high luminance pixel and a low luminance pixel;
A distribution density measuring unit for measuring the distribution density of the high-luminance pixels per predetermined area;
A distribution density classification unit for obtaining distribution density information obtained by classifying the distribution density into a low density part and a high density part based on a predetermined threshold;
A boundary determination unit that defines a boundary from the pixel information and the distribution density information;
An ultrasonic diagnostic apparatus, comprising: an echo pattern classification unit that classifies the tomographic image into echo patterns based on the shape of the boundary, the pixel information, and the distribution density information.   The ultrasonic diagnosis according to claim 1, wherein the echo pattern classification unit classifies the tomographic image obtained from an ultrasonic diagnostic image of a subject's ovary into six echo patterns of an ovarian tumor created by the Japanese Society of Ultrasonic Medicine. apparatus.   The ultrasonic diagnostic apparatus according to claim 1, wherein the display processing unit displays the type of echo pattern classified by the echo pattern classification unit on the display monitor simultaneously with the ultrasonic image. A color image acquisition unit for obtaining a color mode image from the ultrasonic diagnostic image;
A blood flow information discriminating unit for discriminating blood flow information from the color mode image;
The ultrasound diagnostic apparatus according to claim 1, wherein the echo pattern classification unit classifies an echo pattern using the blood flow information. A tomographic image memory for recording the tomographic image, and a color image memory for recording the color image;
A memory image calling unit that sequentially calls images specified by the operator from the operation unit from the tomographic image recorded in the tomographic image memory or the color image recorded in the color image memory;
The ultrasonic diagnostic apparatus according to any one of claims 1 to 4, wherein the echo pattern classification unit sequentially classifies echo patterns for images called by the memory image calling unit. The ultrasonic image acquisition unit acquires a three-dimensional ultrasonic image,
A first ultrasonic cross-sectional image, a second ultrasonic cross-sectional image, and a third ultrasonic wave, which are two-dimensional ultrasonic images parallel to three axes orthogonal to each other, based on the three-dimensional ultrasonic slice image. A two-dimensional image acquisition unit for acquiring a cross-sectional image;
An operation is performed using any one of the first ultrasonic cross-sectional image, the second ultrasonic cross-sectional image, and the third ultrasonic cross-sectional image displayed on the monitor unit by the display processing unit. A two-dimensional image calling unit that sequentially calls a plurality of two-dimensional ultrasound images included in the region designated by the operator from the operation unit;
The ultrasound according to any one of claims 1 to 4, wherein the echo pattern classification unit sequentially classifies echo patterns for the plurality of two-dimensional ultrasound images called by the two-dimensional image calling unit. Diagnostic device. The ultrasonic image acquisition unit acquires a three-dimensional supersonic image,
A multi-slice image acquisition unit that acquires a multi-slice image that is a plurality of two-dimensional ultrasonic images belonging to planes parallel to each other based on the three-dimensional ultrasonic image;
The display processing unit displays a plurality of the multi-slice images side by side on the display monitor,
The echo pattern classification unit classifies an echo pattern with respect to a two-dimensional ultrasonic image designated by an operator from the operation unit from among the plurality of multi-slice images displayed on the display monitor. The ultrasonic diagnostic apparatus of any one of -4.   The display processing unit is a schematic diagram of six types of echo patterns of the ovarian tumor created by the Japanese Society of Ultrasonic Medicine classified by the echo pattern classification unit, the ultrasonic image, and the six echo patterns of the ovarian tumor. The ultrasonic diagnostic apparatus according to claim 3, wherein the ultrasonic diagnostic apparatus displays on the display monitor.   The ultrasonic diagnostic apparatus according to claim 1, wherein the display processing unit displays the boundary portion specified by the boundary determination unit on the display monitor so as to overlap the ultrasonic image.

Images